added test cases
This commit is contained in:
Florian Förster
parent
30fe71e80a
commit
fb28b8548b
1844
docs/lang_main/analysis/graphs.html
Normal file
1844
docs/lang_main/analysis/graphs.html
Normal file
File diff suppressed because it is too large
Load Diff
98
docs/lang_main/analysis/index.html
Normal file
98
docs/lang_main/analysis/index.html
Normal file
@ -0,0 +1,98 @@
|
|||||||
|
<!doctype html>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="utf-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1">
|
||||||
|
<meta name="generator" content="pdoc3 0.11.5">
|
||||||
|
<title>lang_main.analysis API documentation</title>
|
||||||
|
<meta name="description" content="">
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/sanitize.min.css" integrity="sha512-y1dtMcuvtTMJc1yPgEqF0ZjQbhnc/bFhyvIyVNb9Zk5mIGtqVaAB1Ttl28su8AvFMOY0EwRbAe+HCLqj6W7/KA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/typography.min.css" integrity="sha512-Y1DYSb995BAfxobCkKepB1BqJJTPrOp3zPL74AWFugHHmmdcvO+C48WLrUOlhGMc0QG7AE3f7gmvvcrmX2fDoA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/styles/default.min.css" crossorigin>
|
||||||
|
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:1.5em;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:2em 0 .50em 0}h3{font-size:1.4em;margin:1.6em 0 .7em 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .2s ease-in-out}a:visited{color:#503}a:hover{color:#b62}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900;font-weight:bold}pre code{font-size:.8em;line-height:1.4em;padding:1em;display:block}code{background:#f3f3f3;font-family:"DejaVu Sans Mono",monospace;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source > summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible;min-width:max-content}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em 1em;margin:1em 0}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
|
||||||
|
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul ul{padding-left:1em}.toc > ul > li{margin-top:.5em}}</style>
|
||||||
|
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
|
||||||
|
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/highlight.min.js" integrity="sha512-D9gUyxqja7hBtkWpPWGt9wfbfaMGVt9gnyCvYa+jojwwPHLCzUm5i8rpk7vD7wNee9bA35eYIjobYPaQuKS1MQ==" crossorigin></script>
|
||||||
|
<script>window.addEventListener('DOMContentLoaded', () => {
|
||||||
|
hljs.configure({languages: ['bash', 'css', 'diff', 'graphql', 'ini', 'javascript', 'json', 'plaintext', 'python', 'python-repl', 'rust', 'shell', 'sql', 'typescript', 'xml', 'yaml']});
|
||||||
|
hljs.highlightAll();
|
||||||
|
/* Collapse source docstrings */
|
||||||
|
setTimeout(() => {
|
||||||
|
[...document.querySelectorAll('.hljs.language-python > .hljs-string')]
|
||||||
|
.filter(el => el.innerHTML.length > 200 && ['"""', "'''"].includes(el.innerHTML.substring(0, 3)))
|
||||||
|
.forEach(el => {
|
||||||
|
let d = document.createElement('details');
|
||||||
|
d.classList.add('hljs-string');
|
||||||
|
d.innerHTML = '<summary>"""</summary>' + el.innerHTML.substring(3);
|
||||||
|
el.replaceWith(d);
|
||||||
|
});
|
||||||
|
}, 100);
|
||||||
|
})</script>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<main>
|
||||||
|
<article id="content">
|
||||||
|
<header>
|
||||||
|
<h1 class="title">Module <code>lang_main.analysis</code></h1>
|
||||||
|
</header>
|
||||||
|
<section id="section-intro">
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
<h2 class="section-title" id="header-submodules">Sub-modules</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code class="name"><a title="lang_main.analysis.graphs" href="graphs.html">lang_main.analysis.graphs</a></code></dt>
|
||||||
|
<dd>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt><code class="name"><a title="lang_main.analysis.preprocessing" href="preprocessing.html">lang_main.analysis.preprocessing</a></code></dt>
|
||||||
|
<dd>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt><code class="name"><a title="lang_main.analysis.shared" href="shared.html">lang_main.analysis.shared</a></code></dt>
|
||||||
|
<dd>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt><code class="name"><a title="lang_main.analysis.timeline" href="timeline.html">lang_main.analysis.timeline</a></code></dt>
|
||||||
|
<dd>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt><code class="name"><a title="lang_main.analysis.tokens" href="tokens.html">lang_main.analysis.tokens</a></code></dt>
|
||||||
|
<dd>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
</dl>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
</article>
|
||||||
|
<nav id="sidebar">
|
||||||
|
<div class="toc">
|
||||||
|
<ul></ul>
|
||||||
|
</div>
|
||||||
|
<ul id="index">
|
||||||
|
<li><h3>Super-module</h3>
|
||||||
|
<ul>
|
||||||
|
<li><code><a title="lang_main" href="../index.html">lang_main</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
<li><h3><a href="#header-submodules">Sub-modules</a></h3>
|
||||||
|
<ul>
|
||||||
|
<li><code><a title="lang_main.analysis.graphs" href="graphs.html">lang_main.analysis.graphs</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.preprocessing" href="preprocessing.html">lang_main.analysis.preprocessing</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.shared" href="shared.html">lang_main.analysis.shared</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.timeline" href="timeline.html">lang_main.analysis.timeline</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.tokens" href="tokens.html">lang_main.analysis.tokens</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
</ul>
|
||||||
|
</nav>
|
||||||
|
</main>
|
||||||
|
<footer id="footer">
|
||||||
|
<p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.11.5</a>.</p>
|
||||||
|
</footer>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
451
docs/lang_main/analysis/preprocessing.html
Normal file
451
docs/lang_main/analysis/preprocessing.html
Normal file
@ -0,0 +1,451 @@
|
|||||||
|
<!doctype html>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="utf-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1">
|
||||||
|
<meta name="generator" content="pdoc3 0.11.5">
|
||||||
|
<title>lang_main.analysis.preprocessing API documentation</title>
|
||||||
|
<meta name="description" content="">
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/sanitize.min.css" integrity="sha512-y1dtMcuvtTMJc1yPgEqF0ZjQbhnc/bFhyvIyVNb9Zk5mIGtqVaAB1Ttl28su8AvFMOY0EwRbAe+HCLqj6W7/KA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/typography.min.css" integrity="sha512-Y1DYSb995BAfxobCkKepB1BqJJTPrOp3zPL74AWFugHHmmdcvO+C48WLrUOlhGMc0QG7AE3f7gmvvcrmX2fDoA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/styles/default.min.css" crossorigin>
|
||||||
|
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:1.5em;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:2em 0 .50em 0}h3{font-size:1.4em;margin:1.6em 0 .7em 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .2s ease-in-out}a:visited{color:#503}a:hover{color:#b62}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900;font-weight:bold}pre code{font-size:.8em;line-height:1.4em;padding:1em;display:block}code{background:#f3f3f3;font-family:"DejaVu Sans Mono",monospace;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source > summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible;min-width:max-content}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em 1em;margin:1em 0}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
|
||||||
|
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul ul{padding-left:1em}.toc > ul > li{margin-top:.5em}}</style>
|
||||||
|
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
|
||||||
|
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/highlight.min.js" integrity="sha512-D9gUyxqja7hBtkWpPWGt9wfbfaMGVt9gnyCvYa+jojwwPHLCzUm5i8rpk7vD7wNee9bA35eYIjobYPaQuKS1MQ==" crossorigin></script>
|
||||||
|
<script>window.addEventListener('DOMContentLoaded', () => {
|
||||||
|
hljs.configure({languages: ['bash', 'css', 'diff', 'graphql', 'ini', 'javascript', 'json', 'plaintext', 'python', 'python-repl', 'rust', 'shell', 'sql', 'typescript', 'xml', 'yaml']});
|
||||||
|
hljs.highlightAll();
|
||||||
|
/* Collapse source docstrings */
|
||||||
|
setTimeout(() => {
|
||||||
|
[...document.querySelectorAll('.hljs.language-python > .hljs-string')]
|
||||||
|
.filter(el => el.innerHTML.length > 200 && ['"""', "'''"].includes(el.innerHTML.substring(0, 3)))
|
||||||
|
.forEach(el => {
|
||||||
|
let d = document.createElement('details');
|
||||||
|
d.classList.add('hljs-string');
|
||||||
|
d.innerHTML = '<summary>"""</summary>' + el.innerHTML.substring(3);
|
||||||
|
el.replaceWith(d);
|
||||||
|
});
|
||||||
|
}, 100);
|
||||||
|
})</script>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<main>
|
||||||
|
<article id="content">
|
||||||
|
<header>
|
||||||
|
<h1 class="title">Module <code>lang_main.analysis.preprocessing</code></h1>
|
||||||
|
</header>
|
||||||
|
<section id="section-intro">
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
<h2 class="section-title" id="header-functions">Functions</h2>
|
||||||
|
<dl>
|
||||||
|
<dt id="lang_main.analysis.preprocessing.analyse_feature"><code class="name flex">
|
||||||
|
<span>def <span class="ident">analyse_feature</span></span>(<span>data: DataFrame, target_feature: str) ‑> tuple[pandas.core.frame.DataFrame]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def analyse_feature(
|
||||||
|
data: DataFrame,
|
||||||
|
target_feature: str,
|
||||||
|
) -> tuple[DataFrame]:
|
||||||
|
# feature columns
|
||||||
|
feature_entries = data[target_feature]
|
||||||
|
logger.info(
|
||||||
|
'Number of entries for feature >>%s<<: %d', target_feature, len(feature_entries)
|
||||||
|
)
|
||||||
|
# obtain unique entries
|
||||||
|
unique_feature_entries = feature_entries.unique()
|
||||||
|
|
||||||
|
# prepare result DataFrame
|
||||||
|
cols = ['batched_idxs', 'entry', 'len', 'num_occur', 'assoc_obj_ids', 'num_assoc_obj_ids']
|
||||||
|
result_df = pd.DataFrame(columns=cols)
|
||||||
|
|
||||||
|
for entry in tqdm(unique_feature_entries, mininterval=1.0):
|
||||||
|
len_entry = len(entry)
|
||||||
|
filt = data[target_feature] == entry
|
||||||
|
temp = data[filt]
|
||||||
|
batched_idxs = temp.index.to_numpy()
|
||||||
|
assoc_obj_ids = temp['ObjektID'].unique()
|
||||||
|
assoc_obj_ids = np.sort(assoc_obj_ids, kind='stable')
|
||||||
|
num_assoc_obj_ids = len(assoc_obj_ids)
|
||||||
|
num_dupl = filt.sum()
|
||||||
|
|
||||||
|
conc_df = pd.DataFrame(
|
||||||
|
data=[
|
||||||
|
[batched_idxs, entry, len_entry, num_dupl, assoc_obj_ids, num_assoc_obj_ids]
|
||||||
|
],
|
||||||
|
columns=cols,
|
||||||
|
)
|
||||||
|
|
||||||
|
result_df = pd.concat([result_df, conc_df], ignore_index=True)
|
||||||
|
|
||||||
|
result_df = result_df.sort_values(
|
||||||
|
by=['num_occur', 'len'], ascending=[False, False]
|
||||||
|
).copy()
|
||||||
|
|
||||||
|
return (result_df,)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.analysis.preprocessing.load_raw_data"><code class="name flex">
|
||||||
|
<span>def <span class="ident">load_raw_data</span></span>(<span>path: Path,<br>date_cols: Collection[str] = ('VorgangsDatum', 'ErledigungsDatum', 'Arbeitsbeginn', 'ErstellungsDatum')) ‑> tuple[pandas.core.frame.DataFrame]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def load_raw_data(
|
||||||
|
path: Path,
|
||||||
|
date_cols: Collection[str] = (
|
||||||
|
'VorgangsDatum',
|
||||||
|
'ErledigungsDatum',
|
||||||
|
'Arbeitsbeginn',
|
||||||
|
'ErstellungsDatum',
|
||||||
|
),
|
||||||
|
) -> tuple[DataFrame]:
|
||||||
|
"""load IHM dataset with standard structure
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
path : str
|
||||||
|
path to dataset file, usually CSV file
|
||||||
|
date_cols : Collection[str], optional
|
||||||
|
columns which contain dates and are parsed as such,
|
||||||
|
by default (
|
||||||
|
'VorgangsDatum',
|
||||||
|
'ErledigungsDatum',
|
||||||
|
'Arbeitsbeginn',
|
||||||
|
'ErstellungsDatum',
|
||||||
|
)
|
||||||
|
|
||||||
|
Returns
|
||||||
|
-------
|
||||||
|
DataFrame
|
||||||
|
raw dataset as DataFrame
|
||||||
|
"""
|
||||||
|
# load dataset
|
||||||
|
date_cols = list(date_cols)
|
||||||
|
data = pd.read_csv(
|
||||||
|
filepath_or_buffer=path,
|
||||||
|
sep=';',
|
||||||
|
encoding='cp1252',
|
||||||
|
parse_dates=list(date_cols),
|
||||||
|
dayfirst=True,
|
||||||
|
)
|
||||||
|
logger.info('Loaded dataset successfully.')
|
||||||
|
logger.info(
|
||||||
|
(
|
||||||
|
f'Dataset properties: number of entries: {len(data)}, '
|
||||||
|
f'number of features {len(data.columns)}'
|
||||||
|
)
|
||||||
|
)
|
||||||
|
return (data,)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>load IHM dataset with standard structure</p>
|
||||||
|
<h2 id="parameters">Parameters</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><strong><code>path</code></strong> : <code>str</code></dt>
|
||||||
|
<dd>path to dataset file, usually CSV file</dd>
|
||||||
|
<dt><strong><code>date_cols</code></strong> : <code>Collection[str]</code>, optional</dt>
|
||||||
|
<dd>columns which contain dates and are parsed as such,
|
||||||
|
by default (
|
||||||
|
'VorgangsDatum',
|
||||||
|
'ErledigungsDatum',
|
||||||
|
'Arbeitsbeginn',
|
||||||
|
'ErstellungsDatum',
|
||||||
|
)</dd>
|
||||||
|
</dl>
|
||||||
|
<h2 id="returns">Returns</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code>DataFrame</code></dt>
|
||||||
|
<dd>raw dataset as DataFrame</dd>
|
||||||
|
</dl></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.analysis.preprocessing.merge_similarity_duplicates"><code class="name flex">
|
||||||
|
<span>def <span class="ident">merge_similarity_duplicates</span></span>(<span>data: DataFrame, model: SentenceTransformer, cos_sim_threshold: float) ‑> tuple[pandas.core.frame.DataFrame]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def merge_similarity_duplicates(
|
||||||
|
data: DataFrame,
|
||||||
|
model: SentenceTransformer,
|
||||||
|
cos_sim_threshold: float,
|
||||||
|
) -> tuple[DataFrame]:
|
||||||
|
logger.info('Start merging of similarity candidates...')
|
||||||
|
|
||||||
|
# data
|
||||||
|
merged_data = data.copy()
|
||||||
|
model_input = merged_data['entry']
|
||||||
|
candidates_idx = candidates_by_index(
|
||||||
|
data_model_input=model_input,
|
||||||
|
model=model,
|
||||||
|
cos_sim_threshold=cos_sim_threshold,
|
||||||
|
)
|
||||||
|
# graph of similar ids
|
||||||
|
similar_id_graph, _ = similar_index_connection_graph(candidates_idx)
|
||||||
|
|
||||||
|
for similar_id_group in similar_index_groups(similar_id_graph):
|
||||||
|
similar_id_group = list(similar_id_group)
|
||||||
|
similar_data = merged_data.loc[similar_id_group, :]
|
||||||
|
# keep first entry with max number occurrences, then number of
|
||||||
|
# associated objects, then length of entry
|
||||||
|
similar_data = similar_data.sort_values(
|
||||||
|
by=['num_occur', 'num_assoc_obj_ids', 'len'],
|
||||||
|
ascending=[False, False, False],
|
||||||
|
)
|
||||||
|
# merge information to first entry
|
||||||
|
data_idx = cast(PandasIndex, similar_data.index[0])
|
||||||
|
similar_data.at[data_idx, 'num_occur'] = similar_data['num_occur'].sum()
|
||||||
|
assoc_obj_ids = similar_data['assoc_obj_ids'].to_numpy()
|
||||||
|
assoc_obj_ids = np.concatenate(assoc_obj_ids)
|
||||||
|
assoc_obj_ids = np.unique(assoc_obj_ids)
|
||||||
|
similar_data.at[data_idx, 'assoc_obj_ids'] = assoc_obj_ids
|
||||||
|
similar_data.at[data_idx, 'num_assoc_obj_ids'] = len(assoc_obj_ids)
|
||||||
|
# remaining indices, should be removed
|
||||||
|
similar_id_group.remove(data_idx)
|
||||||
|
merged_similar_data = similar_data.drop(index=similar_id_group)
|
||||||
|
# update entry in main dataset, drop remaining entries
|
||||||
|
merged_data.update(merged_similar_data)
|
||||||
|
merged_data = merged_data.drop(index=similar_id_group)
|
||||||
|
|
||||||
|
logger.info('Similarity candidates merged successfully.')
|
||||||
|
|
||||||
|
return (merged_data,)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.analysis.preprocessing.numeric_pre_filter_feature"><code class="name flex">
|
||||||
|
<span>def <span class="ident">numeric_pre_filter_feature</span></span>(<span>data: DataFrame, feature: str, bound_lower: int | None, bound_upper: int | None) ‑> tuple[pandas.core.frame.DataFrame]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def numeric_pre_filter_feature(
|
||||||
|
data: DataFrame,
|
||||||
|
feature: str,
|
||||||
|
bound_lower: int | None,
|
||||||
|
bound_upper: int | None,
|
||||||
|
) -> tuple[DataFrame]:
|
||||||
|
"""filter DataFrame for a given numerical feature regarding their bounds
|
||||||
|
bounds are inclusive: entries (bound_lower <= entry <= bound_upper) are retained
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
data : DataFrame
|
||||||
|
DataFrame to filter
|
||||||
|
feature : str
|
||||||
|
feature name to filter
|
||||||
|
bound_lower : int | None
|
||||||
|
lower bound of values to retain
|
||||||
|
bound_upper : int | None
|
||||||
|
upper bound of values to retain
|
||||||
|
|
||||||
|
Returns
|
||||||
|
-------
|
||||||
|
tuple[DataFrame]
|
||||||
|
filtered DataFrame
|
||||||
|
|
||||||
|
Raises
|
||||||
|
------
|
||||||
|
ValueError
|
||||||
|
if no bounds are provided, at least one bound must be set
|
||||||
|
"""
|
||||||
|
if not any([bound_lower, bound_upper]):
|
||||||
|
raise ValueError('No bounds for filtering provided')
|
||||||
|
|
||||||
|
data = data.copy()
|
||||||
|
if bound_lower is None:
|
||||||
|
bound_lower = cast(int, data[feature].min())
|
||||||
|
if bound_upper is None:
|
||||||
|
bound_upper = cast(int, data[feature].max())
|
||||||
|
|
||||||
|
filter_lower = data[feature] >= bound_lower
|
||||||
|
filter_upper = data[feature] <= bound_upper
|
||||||
|
filter = filter_lower & filter_upper
|
||||||
|
|
||||||
|
data = data.loc[filter]
|
||||||
|
|
||||||
|
return (data,)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>filter DataFrame for a given numerical feature regarding their bounds
|
||||||
|
bounds are inclusive: entries (bound_lower <= entry <= bound_upper) are retained</p>
|
||||||
|
<h2 id="parameters">Parameters</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><strong><code>data</code></strong> : <code>DataFrame</code></dt>
|
||||||
|
<dd>DataFrame to filter</dd>
|
||||||
|
<dt><strong><code>feature</code></strong> : <code>str</code></dt>
|
||||||
|
<dd>feature name to filter</dd>
|
||||||
|
<dt><strong><code>bound_lower</code></strong> : <code>int | None</code></dt>
|
||||||
|
<dd>lower bound of values to retain</dd>
|
||||||
|
<dt><strong><code>bound_upper</code></strong> : <code>int | None</code></dt>
|
||||||
|
<dd>upper bound of values to retain</dd>
|
||||||
|
</dl>
|
||||||
|
<h2 id="returns">Returns</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code>tuple[DataFrame]</code></dt>
|
||||||
|
<dd>filtered DataFrame</dd>
|
||||||
|
</dl>
|
||||||
|
<h2 id="raises">Raises</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code>ValueError</code></dt>
|
||||||
|
<dd>if no bounds are provided, at least one bound must be set</dd>
|
||||||
|
</dl></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.analysis.preprocessing.remove_NA"><code class="name flex">
|
||||||
|
<span>def <span class="ident">remove_NA</span></span>(<span>data: DataFrame, target_features: Collection[str] = ('VorgangsBeschreibung',)) ‑> tuple[pandas.core.frame.DataFrame]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def remove_NA(
|
||||||
|
data: DataFrame,
|
||||||
|
target_features: Collection[str] = ('VorgangsBeschreibung',),
|
||||||
|
) -> tuple[DataFrame]:
|
||||||
|
"""function to drop NA entries based on a subset of features to be analysed
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
data : DataFrame
|
||||||
|
standard IHM dataset, perhaps pre-cleaned
|
||||||
|
target_features : Collection[str], optional
|
||||||
|
subset to analyse to define an NA entry, by default ('VorgangsBeschreibung',)
|
||||||
|
|
||||||
|
Returns
|
||||||
|
-------
|
||||||
|
DataFrame
|
||||||
|
dataset with removed NA entries for given subset of features
|
||||||
|
"""
|
||||||
|
target_features = list(target_features)
|
||||||
|
wo_NA = data.dropna(axis=0, subset=target_features, ignore_index=True).copy() # type: ignore
|
||||||
|
logger.info(
|
||||||
|
f'Removed NA entries for features >>{target_features}<< from dataset successfully.'
|
||||||
|
)
|
||||||
|
|
||||||
|
return (wo_NA,)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>function to drop NA entries based on a subset of features to be analysed</p>
|
||||||
|
<h2 id="parameters">Parameters</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><strong><code>data</code></strong> : <code>DataFrame</code></dt>
|
||||||
|
<dd>standard IHM dataset, perhaps pre-cleaned</dd>
|
||||||
|
<dt><strong><code>target_features</code></strong> : <code>Collection[str]</code>, optional</dt>
|
||||||
|
<dd>subset to analyse to define an NA entry, by default ('VorgangsBeschreibung',)</dd>
|
||||||
|
</dl>
|
||||||
|
<h2 id="returns">Returns</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code>DataFrame</code></dt>
|
||||||
|
<dd>dataset with removed NA entries for given subset of features</dd>
|
||||||
|
</dl></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.analysis.preprocessing.remove_duplicates"><code class="name flex">
|
||||||
|
<span>def <span class="ident">remove_duplicates</span></span>(<span>data: DataFrame) ‑> tuple[pandas.core.frame.DataFrame]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def remove_duplicates(
|
||||||
|
data: DataFrame,
|
||||||
|
) -> tuple[DataFrame]:
|
||||||
|
"""removes duplicated entries over all features in the given dataset
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
data : DataFrame
|
||||||
|
read data with standard structure
|
||||||
|
|
||||||
|
Returns
|
||||||
|
-------
|
||||||
|
DataFrame
|
||||||
|
dataset with removed duplicates over all features
|
||||||
|
"""
|
||||||
|
# obtain info about duplicates over all features
|
||||||
|
duplicates_filt = data.duplicated()
|
||||||
|
logger.info(f'Number of duplicates over all features: {duplicates_filt.sum()}')
|
||||||
|
# drop duplicates
|
||||||
|
wo_duplicates = data.drop_duplicates(ignore_index=True)
|
||||||
|
duplicates_subset: list[str] = [
|
||||||
|
'VorgangsID',
|
||||||
|
'ObjektID',
|
||||||
|
]
|
||||||
|
duplicates_subset_filt = wo_duplicates.duplicated(subset=duplicates_subset)
|
||||||
|
logger.info(
|
||||||
|
(
|
||||||
|
'Number of duplicates over subset '
|
||||||
|
f'>>{duplicates_subset}<<: {duplicates_subset_filt.sum()}'
|
||||||
|
)
|
||||||
|
)
|
||||||
|
wo_duplicates = wo_duplicates.drop_duplicates(
|
||||||
|
subset=duplicates_subset, ignore_index=True
|
||||||
|
).copy()
|
||||||
|
logger.info('Removed all duplicates from dataset successfully.')
|
||||||
|
logger.info(
|
||||||
|
'New Dataset properties: number of entries: %d, number of features %d',
|
||||||
|
len(wo_duplicates),
|
||||||
|
len(wo_duplicates.columns),
|
||||||
|
)
|
||||||
|
|
||||||
|
return (wo_duplicates,)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>removes duplicated entries over all features in the given dataset</p>
|
||||||
|
<h2 id="parameters">Parameters</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><strong><code>data</code></strong> : <code>DataFrame</code></dt>
|
||||||
|
<dd>read data with standard structure</dd>
|
||||||
|
</dl>
|
||||||
|
<h2 id="returns">Returns</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code>DataFrame</code></dt>
|
||||||
|
<dd>dataset with removed duplicates over all features</dd>
|
||||||
|
</dl></div>
|
||||||
|
</dd>
|
||||||
|
</dl>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
</article>
|
||||||
|
<nav id="sidebar">
|
||||||
|
<div class="toc">
|
||||||
|
<ul></ul>
|
||||||
|
</div>
|
||||||
|
<ul id="index">
|
||||||
|
<li><h3>Super-module</h3>
|
||||||
|
<ul>
|
||||||
|
<li><code><a title="lang_main.analysis" href="index.html">lang_main.analysis</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
<li><h3><a href="#header-functions">Functions</a></h3>
|
||||||
|
<ul class="">
|
||||||
|
<li><code><a title="lang_main.analysis.preprocessing.analyse_feature" href="#lang_main.analysis.preprocessing.analyse_feature">analyse_feature</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.preprocessing.load_raw_data" href="#lang_main.analysis.preprocessing.load_raw_data">load_raw_data</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.preprocessing.merge_similarity_duplicates" href="#lang_main.analysis.preprocessing.merge_similarity_duplicates">merge_similarity_duplicates</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.preprocessing.numeric_pre_filter_feature" href="#lang_main.analysis.preprocessing.numeric_pre_filter_feature">numeric_pre_filter_feature</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.preprocessing.remove_NA" href="#lang_main.analysis.preprocessing.remove_NA">remove_NA</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.preprocessing.remove_duplicates" href="#lang_main.analysis.preprocessing.remove_duplicates">remove_duplicates</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
</ul>
|
||||||
|
</nav>
|
||||||
|
</main>
|
||||||
|
<footer id="footer">
|
||||||
|
<p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.11.5</a>.</p>
|
||||||
|
</footer>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
273
docs/lang_main/analysis/shared.html
Normal file
273
docs/lang_main/analysis/shared.html
Normal file
@ -0,0 +1,273 @@
|
|||||||
|
<!doctype html>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="utf-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1">
|
||||||
|
<meta name="generator" content="pdoc3 0.11.5">
|
||||||
|
<title>lang_main.analysis.shared API documentation</title>
|
||||||
|
<meta name="description" content="">
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/sanitize.min.css" integrity="sha512-y1dtMcuvtTMJc1yPgEqF0ZjQbhnc/bFhyvIyVNb9Zk5mIGtqVaAB1Ttl28su8AvFMOY0EwRbAe+HCLqj6W7/KA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/typography.min.css" integrity="sha512-Y1DYSb995BAfxobCkKepB1BqJJTPrOp3zPL74AWFugHHmmdcvO+C48WLrUOlhGMc0QG7AE3f7gmvvcrmX2fDoA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/styles/default.min.css" crossorigin>
|
||||||
|
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:1.5em;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:2em 0 .50em 0}h3{font-size:1.4em;margin:1.6em 0 .7em 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .2s ease-in-out}a:visited{color:#503}a:hover{color:#b62}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900;font-weight:bold}pre code{font-size:.8em;line-height:1.4em;padding:1em;display:block}code{background:#f3f3f3;font-family:"DejaVu Sans Mono",monospace;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source > summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible;min-width:max-content}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em 1em;margin:1em 0}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
|
||||||
|
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul ul{padding-left:1em}.toc > ul > li{margin-top:.5em}}</style>
|
||||||
|
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
|
||||||
|
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/highlight.min.js" integrity="sha512-D9gUyxqja7hBtkWpPWGt9wfbfaMGVt9gnyCvYa+jojwwPHLCzUm5i8rpk7vD7wNee9bA35eYIjobYPaQuKS1MQ==" crossorigin></script>
|
||||||
|
<script>window.addEventListener('DOMContentLoaded', () => {
|
||||||
|
hljs.configure({languages: ['bash', 'css', 'diff', 'graphql', 'ini', 'javascript', 'json', 'plaintext', 'python', 'python-repl', 'rust', 'shell', 'sql', 'typescript', 'xml', 'yaml']});
|
||||||
|
hljs.highlightAll();
|
||||||
|
/* Collapse source docstrings */
|
||||||
|
setTimeout(() => {
|
||||||
|
[...document.querySelectorAll('.hljs.language-python > .hljs-string')]
|
||||||
|
.filter(el => el.innerHTML.length > 200 && ['"""', "'''"].includes(el.innerHTML.substring(0, 3)))
|
||||||
|
.forEach(el => {
|
||||||
|
let d = document.createElement('details');
|
||||||
|
d.classList.add('hljs-string');
|
||||||
|
d.innerHTML = '<summary>"""</summary>' + el.innerHTML.substring(3);
|
||||||
|
el.replaceWith(d);
|
||||||
|
});
|
||||||
|
}, 100);
|
||||||
|
})</script>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<main>
|
||||||
|
<article id="content">
|
||||||
|
<header>
|
||||||
|
<h1 class="title">Module <code>lang_main.analysis.shared</code></h1>
|
||||||
|
</header>
|
||||||
|
<section id="section-intro">
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
<h2 class="section-title" id="header-functions">Functions</h2>
|
||||||
|
<dl>
|
||||||
|
<dt id="lang_main.analysis.shared.candidates_by_index"><code class="name flex">
|
||||||
|
<span>def <span class="ident">candidates_by_index</span></span>(<span>data_model_input: pandas.core.series.Series,<br>model: sentence_transformers.SentenceTransformer.SentenceTransformer,<br>cos_sim_threshold: float = 0.5) ‑> Iterator[tuple[int | numpy.int64, int | numpy.int64]]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def candidates_by_index(
|
||||||
|
data_model_input: Series,
|
||||||
|
model: SentenceTransformer,
|
||||||
|
cos_sim_threshold: float = 0.5,
|
||||||
|
) -> Iterator[tuple[PandasIndex, PandasIndex]]:
|
||||||
|
"""function to filter candidate indices based on cosine similarity
|
||||||
|
using SentenceTransformer model in batch mode,
|
||||||
|
feed data as Series to retain information about indices of entries and
|
||||||
|
access them later in the original dataset
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
obj_id : ObjectID
|
||||||
|
_description_
|
||||||
|
data_model_input : Series
|
||||||
|
containing indices and text entries to process
|
||||||
|
model : SentenceTransformer
|
||||||
|
necessary SentenceTransformer model to encode text entries
|
||||||
|
cos_sim_threshold : float, optional
|
||||||
|
threshold for cosine similarity to filter candidates, by default 0.5
|
||||||
|
|
||||||
|
Yields
|
||||||
|
------
|
||||||
|
Iterator[tuple[PandasIndex, PandasIndex]]
|
||||||
|
tuple of index pairs which meet the cosine similarity threshold
|
||||||
|
"""
|
||||||
|
# embeddings
|
||||||
|
batch = cast(list[str], data_model_input.to_list())
|
||||||
|
embds = cast(
|
||||||
|
Tensor,
|
||||||
|
model.encode(
|
||||||
|
batch,
|
||||||
|
convert_to_numpy=False,
|
||||||
|
convert_to_tensor=True,
|
||||||
|
show_progress_bar=False,
|
||||||
|
),
|
||||||
|
)
|
||||||
|
# cosine similarity
|
||||||
|
cos_sim = cast(npt.NDArray, model.similarity(embds, embds).numpy())
|
||||||
|
np.fill_diagonal(cos_sim, 0.0)
|
||||||
|
cos_sim = np.triu(cos_sim)
|
||||||
|
cos_sim_idx = np.argwhere(cos_sim >= cos_sim_threshold)
|
||||||
|
|
||||||
|
for idx_array in cos_sim_idx:
|
||||||
|
idx_pair = cast(
|
||||||
|
tuple[np.int64, np.int64], tuple(data_model_input.index[idx] for idx in idx_array)
|
||||||
|
)
|
||||||
|
yield idx_pair</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>function to filter candidate indices based on cosine similarity
|
||||||
|
using SentenceTransformer model in batch mode,
|
||||||
|
feed data as Series to retain information about indices of entries and
|
||||||
|
access them later in the original dataset</p>
|
||||||
|
<h2 id="parameters">Parameters</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><strong><code>obj_id</code></strong> : <code>ObjectID</code></dt>
|
||||||
|
<dd><em>description</em></dd>
|
||||||
|
<dt><strong><code>data_model_input</code></strong> : <code>Series</code></dt>
|
||||||
|
<dd>containing indices and text entries to process</dd>
|
||||||
|
<dt><strong><code>model</code></strong> : <code>SentenceTransformer</code></dt>
|
||||||
|
<dd>necessary SentenceTransformer model to encode text entries</dd>
|
||||||
|
<dt><strong><code>cos_sim_threshold</code></strong> : <code>float</code>, optional</dt>
|
||||||
|
<dd>threshold for cosine similarity to filter candidates, by default 0.5</dd>
|
||||||
|
</dl>
|
||||||
|
<h2 id="yields">Yields</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code>Iterator[tuple[PandasIndex, PandasIndex]]</code></dt>
|
||||||
|
<dd>tuple of index pairs which meet the cosine similarity threshold</dd>
|
||||||
|
</dl></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.analysis.shared.clean_string_slim"><code class="name flex">
|
||||||
|
<span>def <span class="ident">clean_string_slim</span></span>(<span>string: str) ‑> str</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def clean_string_slim(string: str) -> str:
|
||||||
|
"""mapping function to clean single string entries in a series (feature-wise)
|
||||||
|
of the dataset, used to be applied element-wise for string features
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
string : str
|
||||||
|
dataset entry feature
|
||||||
|
|
||||||
|
Returns
|
||||||
|
-------
|
||||||
|
str
|
||||||
|
cleaned entry
|
||||||
|
"""
|
||||||
|
# remove special chars
|
||||||
|
# string = pattern_escape_newline.sub(' ', string)
|
||||||
|
string = pattern_escape_seq.sub(' ', string)
|
||||||
|
string = pattern_repeated_chars.sub('', string)
|
||||||
|
# string = pattern_dates.sub('', string)
|
||||||
|
# dates are used for context, should not be removed at this stage
|
||||||
|
string = pattern_whitespace.sub(' ', string)
|
||||||
|
# remove whitespaces at the beginning and the end
|
||||||
|
string = string.strip()
|
||||||
|
|
||||||
|
return string</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>mapping function to clean single string entries in a series (feature-wise)
|
||||||
|
of the dataset, used to be applied element-wise for string features</p>
|
||||||
|
<h2 id="parameters">Parameters</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><strong><code>string</code></strong> : <code>str</code></dt>
|
||||||
|
<dd>dataset entry feature</dd>
|
||||||
|
</dl>
|
||||||
|
<h2 id="returns">Returns</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code>str</code></dt>
|
||||||
|
<dd>cleaned entry</dd>
|
||||||
|
</dl></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.analysis.shared.entry_wise_cleansing"><code class="name flex">
|
||||||
|
<span>def <span class="ident">entry_wise_cleansing</span></span>(<span>data: pandas.core.frame.DataFrame,<br>target_features: Collection[str],<br>cleansing_func: Callable[[str], str] = <function clean_string_slim>) ‑> tuple[pandas.core.frame.DataFrame]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def entry_wise_cleansing(
|
||||||
|
data: DataFrame,
|
||||||
|
target_features: Collection[str],
|
||||||
|
cleansing_func: Callable[[str], str] = clean_string_slim,
|
||||||
|
) -> tuple[DataFrame]:
|
||||||
|
# apply given cleansing function to target feature
|
||||||
|
target_features = list(target_features)
|
||||||
|
data[target_features] = data[target_features].map(cleansing_func)
|
||||||
|
logger.info(
|
||||||
|
('Successfully applied entry-wise cleansing procedure >>%s<< for features >>%s<<'),
|
||||||
|
cleansing_func.__name__,
|
||||||
|
target_features,
|
||||||
|
)
|
||||||
|
return (data,)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.analysis.shared.similar_index_connection_graph"><code class="name flex">
|
||||||
|
<span>def <span class="ident">similar_index_connection_graph</span></span>(<span>similar_idx_pairs: Iterable[tuple[int | numpy.int64, int | numpy.int64]]) ‑> tuple[networkx.classes.graph.Graph, dict[str, float]]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def similar_index_connection_graph(
|
||||||
|
similar_idx_pairs: Iterable[tuple[PandasIndex, PandasIndex]],
|
||||||
|
) -> tuple[Graph, dict[str, float]]:
|
||||||
|
# build index graph to obtain graph of connected (similar) indices
|
||||||
|
# use this graph to get connected components (indices which belong together)
|
||||||
|
# retain semantic connection on whole dataset
|
||||||
|
similar_id_graph = nx.Graph()
|
||||||
|
# for idx1, idx2 in similar_idx_pairs:
|
||||||
|
# # inplace operation, parent/child do not really exist in undirected graph
|
||||||
|
# update_graph(graph=similar_id_graph, parent=idx1, child=idx2)
|
||||||
|
update_graph(graph=similar_id_graph, batch=similar_idx_pairs)
|
||||||
|
|
||||||
|
graph_info = get_graph_metadata(graph=similar_id_graph, logging=False)
|
||||||
|
|
||||||
|
return similar_id_graph, graph_info</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.analysis.shared.similar_index_groups"><code class="name flex">
|
||||||
|
<span>def <span class="ident">similar_index_groups</span></span>(<span>similar_id_graph: networkx.classes.graph.Graph) ‑> Iterator[tuple[int | numpy.int64, ...]]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def similar_index_groups(
|
||||||
|
similar_id_graph: Graph,
|
||||||
|
) -> Iterator[tuple[PandasIndex, ...]]:
|
||||||
|
# groups of connected indices
|
||||||
|
ids_groups = cast(Iterator[set[PandasIndex]], nx.connected_components(G=similar_id_graph))
|
||||||
|
|
||||||
|
for id_group in ids_groups:
|
||||||
|
yield tuple(id_group)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
</dl>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
</article>
|
||||||
|
<nav id="sidebar">
|
||||||
|
<div class="toc">
|
||||||
|
<ul></ul>
|
||||||
|
</div>
|
||||||
|
<ul id="index">
|
||||||
|
<li><h3>Super-module</h3>
|
||||||
|
<ul>
|
||||||
|
<li><code><a title="lang_main.analysis" href="index.html">lang_main.analysis</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
<li><h3><a href="#header-functions">Functions</a></h3>
|
||||||
|
<ul class="">
|
||||||
|
<li><code><a title="lang_main.analysis.shared.candidates_by_index" href="#lang_main.analysis.shared.candidates_by_index">candidates_by_index</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.shared.clean_string_slim" href="#lang_main.analysis.shared.clean_string_slim">clean_string_slim</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.shared.entry_wise_cleansing" href="#lang_main.analysis.shared.entry_wise_cleansing">entry_wise_cleansing</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.shared.similar_index_connection_graph" href="#lang_main.analysis.shared.similar_index_connection_graph">similar_index_connection_graph</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.shared.similar_index_groups" href="#lang_main.analysis.shared.similar_index_groups">similar_index_groups</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
</ul>
|
||||||
|
</nav>
|
||||||
|
</main>
|
||||||
|
<footer id="footer">
|
||||||
|
<p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.11.5</a>.</p>
|
||||||
|
</footer>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
333
docs/lang_main/analysis/timeline.html
Normal file
333
docs/lang_main/analysis/timeline.html
Normal file
@ -0,0 +1,333 @@
|
|||||||
|
<!doctype html>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="utf-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1">
|
||||||
|
<meta name="generator" content="pdoc3 0.11.5">
|
||||||
|
<title>lang_main.analysis.timeline API documentation</title>
|
||||||
|
<meta name="description" content="">
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/sanitize.min.css" integrity="sha512-y1dtMcuvtTMJc1yPgEqF0ZjQbhnc/bFhyvIyVNb9Zk5mIGtqVaAB1Ttl28su8AvFMOY0EwRbAe+HCLqj6W7/KA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/typography.min.css" integrity="sha512-Y1DYSb995BAfxobCkKepB1BqJJTPrOp3zPL74AWFugHHmmdcvO+C48WLrUOlhGMc0QG7AE3f7gmvvcrmX2fDoA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/styles/default.min.css" crossorigin>
|
||||||
|
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:1.5em;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:2em 0 .50em 0}h3{font-size:1.4em;margin:1.6em 0 .7em 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .2s ease-in-out}a:visited{color:#503}a:hover{color:#b62}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900;font-weight:bold}pre code{font-size:.8em;line-height:1.4em;padding:1em;display:block}code{background:#f3f3f3;font-family:"DejaVu Sans Mono",monospace;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source > summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible;min-width:max-content}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em 1em;margin:1em 0}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
|
||||||
|
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul ul{padding-left:1em}.toc > ul > li{margin-top:.5em}}</style>
|
||||||
|
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
|
||||||
|
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/highlight.min.js" integrity="sha512-D9gUyxqja7hBtkWpPWGt9wfbfaMGVt9gnyCvYa+jojwwPHLCzUm5i8rpk7vD7wNee9bA35eYIjobYPaQuKS1MQ==" crossorigin></script>
|
||||||
|
<script>window.addEventListener('DOMContentLoaded', () => {
|
||||||
|
hljs.configure({languages: ['bash', 'css', 'diff', 'graphql', 'ini', 'javascript', 'json', 'plaintext', 'python', 'python-repl', 'rust', 'shell', 'sql', 'typescript', 'xml', 'yaml']});
|
||||||
|
hljs.highlightAll();
|
||||||
|
/* Collapse source docstrings */
|
||||||
|
setTimeout(() => {
|
||||||
|
[...document.querySelectorAll('.hljs.language-python > .hljs-string')]
|
||||||
|
.filter(el => el.innerHTML.length > 200 && ['"""', "'''"].includes(el.innerHTML.substring(0, 3)))
|
||||||
|
.forEach(el => {
|
||||||
|
let d = document.createElement('details');
|
||||||
|
d.classList.add('hljs-string');
|
||||||
|
d.innerHTML = '<summary>"""</summary>' + el.innerHTML.substring(3);
|
||||||
|
el.replaceWith(d);
|
||||||
|
});
|
||||||
|
}, 100);
|
||||||
|
})</script>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<main>
|
||||||
|
<article id="content">
|
||||||
|
<header>
|
||||||
|
<h1 class="title">Module <code>lang_main.analysis.timeline</code></h1>
|
||||||
|
</header>
|
||||||
|
<section id="section-intro">
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
<h2 class="section-title" id="header-functions">Functions</h2>
|
||||||
|
<dl>
|
||||||
|
<dt id="lang_main.analysis.timeline.calc_delta_to_next_failure"><code class="name flex">
|
||||||
|
<span>def <span class="ident">calc_delta_to_next_failure</span></span>(<span>data: pandas.core.frame.DataFrame,<br>date_feature: str = 'ErstellungsDatum',<br>name_delta_feature: str = 'Zeitspanne bis zum nächsten Ereignis [Tage]',<br>convert_to_days: bool = True) ‑> pandas.core.frame.DataFrame</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def calc_delta_to_next_failure(
|
||||||
|
data: DataFrameTLFiltered,
|
||||||
|
date_feature: str = 'ErstellungsDatum',
|
||||||
|
name_delta_feature: str = NAME_DELTA_FEAT_TO_NEXT_FAILURE,
|
||||||
|
convert_to_days: bool = True,
|
||||||
|
) -> DataFrameTLFiltered:
|
||||||
|
data = data.copy()
|
||||||
|
last_val = data[date_feature].iat[-1]
|
||||||
|
shifted = data[date_feature].shift(-1, fill_value=last_val)
|
||||||
|
data[name_delta_feature] = shifted - data[date_feature]
|
||||||
|
data = data.sort_values(by=name_delta_feature, ascending=False)
|
||||||
|
|
||||||
|
if convert_to_days:
|
||||||
|
data[name_delta_feature] = data[name_delta_feature].dt.days
|
||||||
|
|
||||||
|
return data</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.analysis.timeline.calc_delta_to_repair"><code class="name flex">
|
||||||
|
<span>def <span class="ident">calc_delta_to_repair</span></span>(<span>data: pandas.core.frame.DataFrame,<br>date_feature_start: str = 'ErstellungsDatum',<br>date_feature_end: str = 'ErledigungsDatum',<br>name_delta_feature: str = 'Zeitspanne bis zur Behebung [Tage]',<br>convert_to_days: bool = True) ‑> tuple[pandas.core.frame.DataFrame]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def calc_delta_to_repair(
|
||||||
|
data: DataFrame,
|
||||||
|
date_feature_start: str = 'ErstellungsDatum',
|
||||||
|
date_feature_end: str = 'ErledigungsDatum',
|
||||||
|
name_delta_feature: str = NAME_DELTA_FEAT_TO_REPAIR,
|
||||||
|
convert_to_days: bool = True,
|
||||||
|
) -> tuple[DataFrame]:
|
||||||
|
logger.info('Calculating time differences between start and end of operations...')
|
||||||
|
data = data.copy()
|
||||||
|
data[name_delta_feature] = data[date_feature_end] - data[date_feature_start]
|
||||||
|
|
||||||
|
if convert_to_days:
|
||||||
|
data[name_delta_feature] = data[name_delta_feature].dt.days
|
||||||
|
|
||||||
|
logger.info('Calculation successful.')
|
||||||
|
|
||||||
|
return (data,)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.analysis.timeline.cleanup_descriptions"><code class="name flex">
|
||||||
|
<span>def <span class="ident">cleanup_descriptions</span></span>(<span>data: pandas.core.frame.DataFrame,<br>properties: Collection[str] = ('VorgangsBeschreibung', 'ErledigungsBeschreibung')) ‑> tuple[pandas.core.frame.DataFrame]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def cleanup_descriptions(
|
||||||
|
data: DataFrame,
|
||||||
|
properties: Collection[str] = (
|
||||||
|
'VorgangsBeschreibung',
|
||||||
|
'ErledigungsBeschreibung',
|
||||||
|
),
|
||||||
|
) -> tuple[DataFrame]:
|
||||||
|
logger.info('Cleaning necessary descriptions...')
|
||||||
|
data = data.copy()
|
||||||
|
features = list(properties)
|
||||||
|
data[features] = data[features].fillna('N.V.')
|
||||||
|
(data,) = entry_wise_cleansing(data, target_features=features)
|
||||||
|
logger.info('Cleansing successful.')
|
||||||
|
|
||||||
|
return (data.copy(),)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.analysis.timeline.filter_activities_per_obj_id"><code class="name flex">
|
||||||
|
<span>def <span class="ident">filter_activities_per_obj_id</span></span>(<span>data: pandas.core.frame.DataFrame,<br>activity_feature: str = 'VorgangsTypName',<br>relevant_activity_types: Iterable[str] = ('Reparaturauftrag (Portal)',),<br>feature_obj_id: str = 'ObjektID',<br>threshold_num_activities: int = 1) ‑> tuple[pandas.core.frame.DataFrame, pandas.core.series.Series]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def filter_activities_per_obj_id(
|
||||||
|
data: DataFrame,
|
||||||
|
activity_feature: str = 'VorgangsTypName',
|
||||||
|
relevant_activity_types: Iterable[str] = ('Reparaturauftrag (Portal)',),
|
||||||
|
feature_obj_id: str = 'ObjektID',
|
||||||
|
threshold_num_activities: int = 1,
|
||||||
|
) -> tuple[DataFrame, Series]:
|
||||||
|
data = data.copy()
|
||||||
|
# filter only relevant activities, count occurrences for each ObjectID
|
||||||
|
logger.info('Filtering activities per ObjectID...')
|
||||||
|
filt_rel_activities = data[activity_feature].isin(relevant_activity_types)
|
||||||
|
data_filter_activities = data.loc[filt_rel_activities].copy()
|
||||||
|
num_activities_per_obj_id = cast(
|
||||||
|
Series, data_filter_activities[feature_obj_id].value_counts(sort=True)
|
||||||
|
)
|
||||||
|
# filter for ObjectIDs with more than given number of activities
|
||||||
|
filt_below_thresh = num_activities_per_obj_id <= threshold_num_activities
|
||||||
|
# index of series contains ObjectIDs
|
||||||
|
obj_ids_below_thresh = num_activities_per_obj_id[filt_below_thresh].index
|
||||||
|
filt_entries_below_thresh = data_filter_activities[feature_obj_id].isin(
|
||||||
|
obj_ids_below_thresh
|
||||||
|
)
|
||||||
|
|
||||||
|
num_activities_per_obj_id = num_activities_per_obj_id.loc[~filt_below_thresh]
|
||||||
|
data_filter_activities = data_filter_activities.loc[~filt_entries_below_thresh]
|
||||||
|
logger.info('Activities per ObjectID filtered successfully.')
|
||||||
|
|
||||||
|
return data_filter_activities, num_activities_per_obj_id</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.analysis.timeline.filter_timeline_cands"><code class="name flex">
|
||||||
|
<span>def <span class="ident">filter_timeline_cands</span></span>(<span>data: pandas.core.frame.DataFrame,<br>cands: dict[int, tuple[tuple[int | numpy.int64, ...], ...]],<br>obj_id: int,<br>entry_idx: int,<br>sort_feature: str = 'ErstellungsDatum') ‑> pandas.core.frame.DataFrame</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def filter_timeline_cands(
|
||||||
|
data: DataFrame,
|
||||||
|
cands: TimelineCandidates,
|
||||||
|
obj_id: ObjectID,
|
||||||
|
entry_idx: int,
|
||||||
|
sort_feature: str = 'ErstellungsDatum',
|
||||||
|
) -> DataFrameTLFiltered:
|
||||||
|
data = data.copy()
|
||||||
|
cands_for_obj_id = cands[obj_id]
|
||||||
|
cands_choice = cands_for_obj_id[entry_idx]
|
||||||
|
data = data.loc[list(cands_choice)].sort_values(
|
||||||
|
by=sort_feature,
|
||||||
|
ascending=True,
|
||||||
|
)
|
||||||
|
|
||||||
|
return data</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.analysis.timeline.generate_model_input"><code class="name flex">
|
||||||
|
<span>def <span class="ident">generate_model_input</span></span>(<span>data: pandas.core.frame.DataFrame,<br>target_feature_name: str = 'nlp_model_input',<br>model_input_features: Iterable[str] = ('VorgangsTypName', 'VorgangsArtText', 'VorgangsBeschreibung')) ‑> tuple[pandas.core.frame.DataFrame]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def generate_model_input(
|
||||||
|
data: DataFrame,
|
||||||
|
target_feature_name: str = 'nlp_model_input',
|
||||||
|
model_input_features: Iterable[str] = (
|
||||||
|
'VorgangsTypName',
|
||||||
|
'VorgangsArtText',
|
||||||
|
'VorgangsBeschreibung',
|
||||||
|
),
|
||||||
|
) -> tuple[DataFrame]:
|
||||||
|
logger.info('Generating concatenation of model input features...')
|
||||||
|
data = data.copy()
|
||||||
|
model_input_features = list(model_input_features)
|
||||||
|
input_features = data[model_input_features].fillna('').astype(str)
|
||||||
|
data[target_feature_name] = input_features.apply(
|
||||||
|
lambda x: ' - '.join(x),
|
||||||
|
axis=1,
|
||||||
|
)
|
||||||
|
logger.info('Model input generated successfully.')
|
||||||
|
|
||||||
|
return (data,)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.analysis.timeline.get_timeline_candidates"><code class="name flex">
|
||||||
|
<span>def <span class="ident">get_timeline_candidates</span></span>(<span>data: pandas.core.frame.DataFrame,<br>num_activities_per_obj_id: pandas.core.series.Series,<br>*,<br>model: sentence_transformers.SentenceTransformer.SentenceTransformer,<br>cos_sim_threshold: float,<br>feature_obj_id: str = 'ObjektID',<br>feature_obj_text: str = 'HObjektText',<br>model_input_feature: str = 'nlp_model_input') ‑> tuple[dict[int, tuple[tuple[int | numpy.int64, ...], ...]], dict[int, str]]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def get_timeline_candidates(
|
||||||
|
data: DataFrame,
|
||||||
|
num_activities_per_obj_id: Series,
|
||||||
|
*,
|
||||||
|
model: SentenceTransformer,
|
||||||
|
cos_sim_threshold: float,
|
||||||
|
feature_obj_id: str = 'ObjektID',
|
||||||
|
feature_obj_text: str = 'HObjektText',
|
||||||
|
model_input_feature: str = 'nlp_model_input',
|
||||||
|
) -> tuple[TimelineCandidates, dict[ObjectID, str]]:
|
||||||
|
logger.info('Obtaining timeline candidates...')
|
||||||
|
candidates = _get_timeline_candidates_index(
|
||||||
|
data=data,
|
||||||
|
num_activities_per_obj_id=num_activities_per_obj_id,
|
||||||
|
model=model,
|
||||||
|
cos_sim_threshold=cos_sim_threshold,
|
||||||
|
feature_obj_id=feature_obj_id,
|
||||||
|
model_input_feature=model_input_feature,
|
||||||
|
)
|
||||||
|
tl_candidates = _transform_timeline_candidates(candidates)
|
||||||
|
logger.info('Timeline candidates obtained successfully.')
|
||||||
|
# text mapping to obtain object descriptors
|
||||||
|
logger.info('Mapping ObjectIDs to their respective text descriptor...')
|
||||||
|
map_obj_text = _map_obj_id_to_texts(
|
||||||
|
data=data,
|
||||||
|
feature_obj_id=feature_obj_id,
|
||||||
|
feature_obj_text=feature_obj_text,
|
||||||
|
)
|
||||||
|
logger.info('ObjectIDs successfully mapped to text descriptors.')
|
||||||
|
|
||||||
|
return tl_candidates, map_obj_text</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.analysis.timeline.remove_non_relevant_obj_ids"><code class="name flex">
|
||||||
|
<span>def <span class="ident">remove_non_relevant_obj_ids</span></span>(<span>data: pandas.core.frame.DataFrame,<br>thresh_unique_feat_per_id: int,<br>*,<br>feature_uniqueness: str = 'HObjektText',<br>feature_obj_id: str = 'ObjektID') ‑> tuple[pandas.core.frame.DataFrame]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def remove_non_relevant_obj_ids(
|
||||||
|
data: DataFrame,
|
||||||
|
thresh_unique_feat_per_id: int,
|
||||||
|
*,
|
||||||
|
feature_uniqueness: str = 'HObjektText',
|
||||||
|
feature_obj_id: str = 'ObjektID',
|
||||||
|
) -> tuple[DataFrame]:
|
||||||
|
logger.info('Removing non-relevant ObjectIDs from dataset...')
|
||||||
|
data = data.copy()
|
||||||
|
ids_to_ignore = _non_relevant_obj_ids(
|
||||||
|
data=data,
|
||||||
|
thresh_unique_feat_per_id=thresh_unique_feat_per_id,
|
||||||
|
feature_uniqueness=feature_uniqueness,
|
||||||
|
feature_obj_id=feature_obj_id,
|
||||||
|
)
|
||||||
|
# only retain entries with ObjectIDs not in IDs to ignore
|
||||||
|
data = data.loc[~(data[feature_obj_id].isin(ids_to_ignore))]
|
||||||
|
logger.debug('Ignored ObjectIDs: %s', ids_to_ignore)
|
||||||
|
logger.info('Non-relevant ObjectIDs removed successfully.')
|
||||||
|
|
||||||
|
return (data,)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
</dl>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
</article>
|
||||||
|
<nav id="sidebar">
|
||||||
|
<div class="toc">
|
||||||
|
<ul></ul>
|
||||||
|
</div>
|
||||||
|
<ul id="index">
|
||||||
|
<li><h3>Super-module</h3>
|
||||||
|
<ul>
|
||||||
|
<li><code><a title="lang_main.analysis" href="index.html">lang_main.analysis</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
<li><h3><a href="#header-functions">Functions</a></h3>
|
||||||
|
<ul class="">
|
||||||
|
<li><code><a title="lang_main.analysis.timeline.calc_delta_to_next_failure" href="#lang_main.analysis.timeline.calc_delta_to_next_failure">calc_delta_to_next_failure</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.timeline.calc_delta_to_repair" href="#lang_main.analysis.timeline.calc_delta_to_repair">calc_delta_to_repair</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.timeline.cleanup_descriptions" href="#lang_main.analysis.timeline.cleanup_descriptions">cleanup_descriptions</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.timeline.filter_activities_per_obj_id" href="#lang_main.analysis.timeline.filter_activities_per_obj_id">filter_activities_per_obj_id</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.timeline.filter_timeline_cands" href="#lang_main.analysis.timeline.filter_timeline_cands">filter_timeline_cands</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.timeline.generate_model_input" href="#lang_main.analysis.timeline.generate_model_input">generate_model_input</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.timeline.get_timeline_candidates" href="#lang_main.analysis.timeline.get_timeline_candidates">get_timeline_candidates</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.timeline.remove_non_relevant_obj_ids" href="#lang_main.analysis.timeline.remove_non_relevant_obj_ids">remove_non_relevant_obj_ids</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
</ul>
|
||||||
|
</nav>
|
||||||
|
</main>
|
||||||
|
<footer id="footer">
|
||||||
|
<p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.11.5</a>.</p>
|
||||||
|
</footer>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
320
docs/lang_main/analysis/tokens.html
Normal file
320
docs/lang_main/analysis/tokens.html
Normal file
@ -0,0 +1,320 @@
|
|||||||
|
<!doctype html>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="utf-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1">
|
||||||
|
<meta name="generator" content="pdoc3 0.11.5">
|
||||||
|
<title>lang_main.analysis.tokens API documentation</title>
|
||||||
|
<meta name="description" content="">
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/sanitize.min.css" integrity="sha512-y1dtMcuvtTMJc1yPgEqF0ZjQbhnc/bFhyvIyVNb9Zk5mIGtqVaAB1Ttl28su8AvFMOY0EwRbAe+HCLqj6W7/KA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/typography.min.css" integrity="sha512-Y1DYSb995BAfxobCkKepB1BqJJTPrOp3zPL74AWFugHHmmdcvO+C48WLrUOlhGMc0QG7AE3f7gmvvcrmX2fDoA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/styles/default.min.css" crossorigin>
|
||||||
|
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:1.5em;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:2em 0 .50em 0}h3{font-size:1.4em;margin:1.6em 0 .7em 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .2s ease-in-out}a:visited{color:#503}a:hover{color:#b62}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900;font-weight:bold}pre code{font-size:.8em;line-height:1.4em;padding:1em;display:block}code{background:#f3f3f3;font-family:"DejaVu Sans Mono",monospace;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source > summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible;min-width:max-content}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em 1em;margin:1em 0}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
|
||||||
|
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul ul{padding-left:1em}.toc > ul > li{margin-top:.5em}}</style>
|
||||||
|
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
|
||||||
|
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/highlight.min.js" integrity="sha512-D9gUyxqja7hBtkWpPWGt9wfbfaMGVt9gnyCvYa+jojwwPHLCzUm5i8rpk7vD7wNee9bA35eYIjobYPaQuKS1MQ==" crossorigin></script>
|
||||||
|
<script>window.addEventListener('DOMContentLoaded', () => {
|
||||||
|
hljs.configure({languages: ['bash', 'css', 'diff', 'graphql', 'ini', 'javascript', 'json', 'plaintext', 'python', 'python-repl', 'rust', 'shell', 'sql', 'typescript', 'xml', 'yaml']});
|
||||||
|
hljs.highlightAll();
|
||||||
|
/* Collapse source docstrings */
|
||||||
|
setTimeout(() => {
|
||||||
|
[...document.querySelectorAll('.hljs.language-python > .hljs-string')]
|
||||||
|
.filter(el => el.innerHTML.length > 200 && ['"""', "'''"].includes(el.innerHTML.substring(0, 3)))
|
||||||
|
.forEach(el => {
|
||||||
|
let d = document.createElement('details');
|
||||||
|
d.classList.add('hljs-string');
|
||||||
|
d.innerHTML = '<summary>"""</summary>' + el.innerHTML.substring(3);
|
||||||
|
el.replaceWith(d);
|
||||||
|
});
|
||||||
|
}, 100);
|
||||||
|
})</script>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<main>
|
||||||
|
<article id="content">
|
||||||
|
<header>
|
||||||
|
<h1 class="title">Module <code>lang_main.analysis.tokens</code></h1>
|
||||||
|
</header>
|
||||||
|
<section id="section-intro">
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
<h2 class="section-title" id="header-functions">Functions</h2>
|
||||||
|
<dl>
|
||||||
|
<dt id="lang_main.analysis.tokens.add_doc_info_to_graph"><code class="name flex">
|
||||||
|
<span>def <span class="ident">add_doc_info_to_graph</span></span>(<span>graph: <a title="lang_main.analysis.graphs.TokenGraph" href="graphs.html#lang_main.analysis.graphs.TokenGraph">TokenGraph</a>,<br>doc: spacy.tokens.doc.Doc,<br>weight: int | None) ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def add_doc_info_to_graph(
|
||||||
|
graph: TokenGraph,
|
||||||
|
doc: SpacyDoc,
|
||||||
|
weight: int | None,
|
||||||
|
) -> None:
|
||||||
|
# iterate over sentences
|
||||||
|
for sent in doc.sents:
|
||||||
|
# iterate over tokens in sentence
|
||||||
|
for token in sent:
|
||||||
|
# skip tokens which are not relevant
|
||||||
|
if not (token.pos_ in POS_OF_INTEREST or token.tag_ in TAG_OF_INTEREST):
|
||||||
|
continue
|
||||||
|
# skip token which are dates or times
|
||||||
|
if token.pos_ == 'NUM' and is_str_date(string=token.text):
|
||||||
|
continue
|
||||||
|
|
||||||
|
relevant_descendants = obtain_relevant_descendants(token=token)
|
||||||
|
# for non-AUX: add parent <--> descendant pair to graph
|
||||||
|
if token.pos_ not in POS_INDIRECT:
|
||||||
|
for descendant in relevant_descendants:
|
||||||
|
# add descendant and parent to graph
|
||||||
|
update_graph(
|
||||||
|
graph=graph,
|
||||||
|
parent=token.lemma_,
|
||||||
|
child=descendant.lemma_,
|
||||||
|
weight_connection=weight,
|
||||||
|
)
|
||||||
|
else:
|
||||||
|
# if indirect POS, make connection between all associated words
|
||||||
|
combs = combinations(relevant_descendants, r=2)
|
||||||
|
for comb in combs:
|
||||||
|
# !! parents and children do not really exist in this case,
|
||||||
|
# !! but only one connection is made
|
||||||
|
update_graph(
|
||||||
|
graph=graph,
|
||||||
|
parent=comb[0].lemma_,
|
||||||
|
child=comb[1].lemma_,
|
||||||
|
weight_connection=weight,
|
||||||
|
)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.analysis.tokens.build_token_graph"><code class="name flex">
|
||||||
|
<span>def <span class="ident">build_token_graph</span></span>(<span>data: pandas.core.frame.DataFrame,<br>model: spacy.language.Language,<br>*,<br>target_feature: str = 'entry',<br>weights_feature: str | None = None,<br>batch_idx_feature: str | None = 'batched_idxs',<br>build_map: bool = True,<br>batch_size_model: int = 50,<br>logging_graph: bool = True) ‑> tuple[<a title="lang_main.analysis.graphs.TokenGraph" href="graphs.html#lang_main.analysis.graphs.TokenGraph">TokenGraph</a>, dict[int | numpy.int64, spacy.tokens.doc.Doc] | None]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def build_token_graph(
|
||||||
|
data: DataFrame,
|
||||||
|
model: SpacyModel,
|
||||||
|
*,
|
||||||
|
target_feature: str = 'entry',
|
||||||
|
weights_feature: str | None = None,
|
||||||
|
batch_idx_feature: str | None = 'batched_idxs',
|
||||||
|
build_map: bool = True,
|
||||||
|
batch_size_model: int = 50,
|
||||||
|
logging_graph: bool = True,
|
||||||
|
) -> tuple[TokenGraph, dict[PandasIndex, SpacyDoc] | None]:
|
||||||
|
graph = TokenGraph(enable_logging=logging_graph)
|
||||||
|
model_input = cast(tuple[str], tuple(data[target_feature].to_list()))
|
||||||
|
if weights_feature is not None:
|
||||||
|
weights = cast(tuple[int], tuple(data[weights_feature].to_list()))
|
||||||
|
else:
|
||||||
|
weights = None
|
||||||
|
|
||||||
|
docs_mapping: dict[PandasIndex, SpacyDoc] | None
|
||||||
|
if build_map and batch_idx_feature is None:
|
||||||
|
raise ValueError('Can not build mapping if batched indices are unknown.')
|
||||||
|
elif build_map:
|
||||||
|
indices = cast(tuple[list[PandasIndex]], tuple(data[batch_idx_feature].to_list()))
|
||||||
|
docs_mapping = {}
|
||||||
|
else:
|
||||||
|
indices = None
|
||||||
|
docs_mapping = None
|
||||||
|
|
||||||
|
index: int = 0
|
||||||
|
|
||||||
|
for doc in tqdm(
|
||||||
|
model.pipe(model_input, batch_size=batch_size_model), total=len(model_input)
|
||||||
|
):
|
||||||
|
weight: int | None = None
|
||||||
|
if weights is not None:
|
||||||
|
weight = weights[index]
|
||||||
|
|
||||||
|
add_doc_info_to_graph(
|
||||||
|
graph=graph,
|
||||||
|
doc=doc,
|
||||||
|
weight=weight,
|
||||||
|
)
|
||||||
|
# build map if option chosen
|
||||||
|
if indices is not None and docs_mapping is not None:
|
||||||
|
corresponding_indices = indices[index]
|
||||||
|
for idx in corresponding_indices:
|
||||||
|
docs_mapping[idx] = doc
|
||||||
|
|
||||||
|
index += 1
|
||||||
|
|
||||||
|
# metadata
|
||||||
|
graph.update_metadata()
|
||||||
|
# convert to undirected
|
||||||
|
graph.to_undirected(logging=False)
|
||||||
|
graph.perform_static_analysis()
|
||||||
|
|
||||||
|
return graph, docs_mapping</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.analysis.tokens.is_str_date"><code class="name flex">
|
||||||
|
<span>def <span class="ident">is_str_date</span></span>(<span>string: str, fuzzy: bool = False) ‑> bool</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def is_str_date(
|
||||||
|
string: str,
|
||||||
|
fuzzy: bool = False,
|
||||||
|
) -> bool:
|
||||||
|
"""not stable function to test strings for dates, not 100 percent reliable
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
string : str
|
||||||
|
string to check for dates
|
||||||
|
fuzzy : bool, optional
|
||||||
|
whether to use dateutils.parser.pase fuzzy capability, by default False
|
||||||
|
|
||||||
|
Returns
|
||||||
|
-------
|
||||||
|
bool
|
||||||
|
indicates whether date was found or not
|
||||||
|
"""
|
||||||
|
try:
|
||||||
|
# check if string is a number
|
||||||
|
# if length is greater than 8, it is not a date
|
||||||
|
int(string)
|
||||||
|
if len(string) not in {2, 4}:
|
||||||
|
return False
|
||||||
|
except ValueError:
|
||||||
|
# not a number
|
||||||
|
pass
|
||||||
|
|
||||||
|
try:
|
||||||
|
parse(string, fuzzy=fuzzy, dayfirst=True, yearfirst=False)
|
||||||
|
return True
|
||||||
|
except ValueError:
|
||||||
|
date_found: bool = False
|
||||||
|
match = pattern_dates.search(string)
|
||||||
|
if match is None:
|
||||||
|
return date_found
|
||||||
|
date_found = any(match.groups())
|
||||||
|
return date_found</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>not stable function to test strings for dates, not 100 percent reliable</p>
|
||||||
|
<h2 id="parameters">Parameters</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><strong><code>string</code></strong> : <code>str</code></dt>
|
||||||
|
<dd>string to check for dates</dd>
|
||||||
|
<dt><strong><code>fuzzy</code></strong> : <code>bool</code>, optional</dt>
|
||||||
|
<dd>whether to use dateutils.parser.pase fuzzy capability, by default False</dd>
|
||||||
|
</dl>
|
||||||
|
<h2 id="returns">Returns</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code>bool</code></dt>
|
||||||
|
<dd>indicates whether date was found or not</dd>
|
||||||
|
</dl></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.analysis.tokens.obtain_relevant_descendants"><code class="name flex">
|
||||||
|
<span>def <span class="ident">obtain_relevant_descendants</span></span>(<span>token: spacy.tokens.token.Token) ‑> Iterator[spacy.tokens.token.Token]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def obtain_relevant_descendants(
|
||||||
|
token: SpacyToken,
|
||||||
|
) -> Iterator[SpacyToken]:
|
||||||
|
for descendant in token.subtree:
|
||||||
|
# subtrees contain the token itself
|
||||||
|
# if current element is token skip this element
|
||||||
|
if descendant == token:
|
||||||
|
continue
|
||||||
|
|
||||||
|
# if descendant is a date skip it)
|
||||||
|
if is_str_date(string=descendant.text):
|
||||||
|
continue
|
||||||
|
|
||||||
|
logger.debug(
|
||||||
|
'Token >>%s<<, POS >>%s<< | descendant >>%s<<, POS >>%s<<',
|
||||||
|
token,
|
||||||
|
token.pos_,
|
||||||
|
descendant,
|
||||||
|
descendant.pos_,
|
||||||
|
)
|
||||||
|
|
||||||
|
# eliminate cases of cross-references with verbs
|
||||||
|
if (token.pos_ == 'AUX' or token.pos_ == 'VERB') and (
|
||||||
|
descendant.pos_ == 'AUX' or descendant.pos_ == 'VERB'
|
||||||
|
):
|
||||||
|
continue
|
||||||
|
# skip cases in which descendant is indirect POS with others than verbs
|
||||||
|
elif descendant.pos_ in POS_INDIRECT:
|
||||||
|
continue
|
||||||
|
# skip cases in which child has no relevant POS or TAG
|
||||||
|
elif not (descendant.pos_ in POS_OF_INTEREST or descendant.tag_ in TAG_OF_INTEREST):
|
||||||
|
continue
|
||||||
|
|
||||||
|
yield descendant
|
||||||
|
|
||||||
|
# TODO look at results and fine-tune function accordingly</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.analysis.tokens.pre_clean_word"><code class="name flex">
|
||||||
|
<span>def <span class="ident">pre_clean_word</span></span>(<span>string: str) ‑> str</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def pre_clean_word(string: str) -> str:
|
||||||
|
pattern = r'[^A-Za-zäöüÄÖÜ]+'
|
||||||
|
string = re.sub(pattern, '', string)
|
||||||
|
|
||||||
|
return string</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
</dl>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
</article>
|
||||||
|
<nav id="sidebar">
|
||||||
|
<div class="toc">
|
||||||
|
<ul></ul>
|
||||||
|
</div>
|
||||||
|
<ul id="index">
|
||||||
|
<li><h3>Super-module</h3>
|
||||||
|
<ul>
|
||||||
|
<li><code><a title="lang_main.analysis" href="index.html">lang_main.analysis</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
<li><h3><a href="#header-functions">Functions</a></h3>
|
||||||
|
<ul class="">
|
||||||
|
<li><code><a title="lang_main.analysis.tokens.add_doc_info_to_graph" href="#lang_main.analysis.tokens.add_doc_info_to_graph">add_doc_info_to_graph</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.tokens.build_token_graph" href="#lang_main.analysis.tokens.build_token_graph">build_token_graph</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.tokens.is_str_date" href="#lang_main.analysis.tokens.is_str_date">is_str_date</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.tokens.obtain_relevant_descendants" href="#lang_main.analysis.tokens.obtain_relevant_descendants">obtain_relevant_descendants</a></code></li>
|
||||||
|
<li><code><a title="lang_main.analysis.tokens.pre_clean_word" href="#lang_main.analysis.tokens.pre_clean_word">pre_clean_word</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
</ul>
|
||||||
|
</nav>
|
||||||
|
</main>
|
||||||
|
<footer id="footer">
|
||||||
|
<p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.11.5</a>.</p>
|
||||||
|
</footer>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
206
docs/lang_main/config.html
Normal file
206
docs/lang_main/config.html
Normal file
@ -0,0 +1,206 @@
|
|||||||
|
<!doctype html>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="utf-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1">
|
||||||
|
<meta name="generator" content="pdoc3 0.11.5">
|
||||||
|
<title>lang_main.config API documentation</title>
|
||||||
|
<meta name="description" content="">
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/sanitize.min.css" integrity="sha512-y1dtMcuvtTMJc1yPgEqF0ZjQbhnc/bFhyvIyVNb9Zk5mIGtqVaAB1Ttl28su8AvFMOY0EwRbAe+HCLqj6W7/KA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/typography.min.css" integrity="sha512-Y1DYSb995BAfxobCkKepB1BqJJTPrOp3zPL74AWFugHHmmdcvO+C48WLrUOlhGMc0QG7AE3f7gmvvcrmX2fDoA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/styles/default.min.css" crossorigin>
|
||||||
|
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:1.5em;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:2em 0 .50em 0}h3{font-size:1.4em;margin:1.6em 0 .7em 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .2s ease-in-out}a:visited{color:#503}a:hover{color:#b62}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900;font-weight:bold}pre code{font-size:.8em;line-height:1.4em;padding:1em;display:block}code{background:#f3f3f3;font-family:"DejaVu Sans Mono",monospace;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source > summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible;min-width:max-content}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em 1em;margin:1em 0}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
|
||||||
|
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul ul{padding-left:1em}.toc > ul > li{margin-top:.5em}}</style>
|
||||||
|
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
|
||||||
|
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/highlight.min.js" integrity="sha512-D9gUyxqja7hBtkWpPWGt9wfbfaMGVt9gnyCvYa+jojwwPHLCzUm5i8rpk7vD7wNee9bA35eYIjobYPaQuKS1MQ==" crossorigin></script>
|
||||||
|
<script>window.addEventListener('DOMContentLoaded', () => {
|
||||||
|
hljs.configure({languages: ['bash', 'css', 'diff', 'graphql', 'ini', 'javascript', 'json', 'plaintext', 'python', 'python-repl', 'rust', 'shell', 'sql', 'typescript', 'xml', 'yaml']});
|
||||||
|
hljs.highlightAll();
|
||||||
|
/* Collapse source docstrings */
|
||||||
|
setTimeout(() => {
|
||||||
|
[...document.querySelectorAll('.hljs.language-python > .hljs-string')]
|
||||||
|
.filter(el => el.innerHTML.length > 200 && ['"""', "'''"].includes(el.innerHTML.substring(0, 3)))
|
||||||
|
.forEach(el => {
|
||||||
|
let d = document.createElement('details');
|
||||||
|
d.classList.add('hljs-string');
|
||||||
|
d.innerHTML = '<summary>"""</summary>' + el.innerHTML.substring(3);
|
||||||
|
el.replaceWith(d);
|
||||||
|
});
|
||||||
|
}, 100);
|
||||||
|
})</script>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<main>
|
||||||
|
<article id="content">
|
||||||
|
<header>
|
||||||
|
<h1 class="title">Module <code>lang_main.config</code></h1>
|
||||||
|
</header>
|
||||||
|
<section id="section-intro">
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
<h2 class="section-title" id="header-functions">Functions</h2>
|
||||||
|
<dl>
|
||||||
|
<dt id="lang_main.config.get_config_paths"><code class="name flex">
|
||||||
|
<span>def <span class="ident">get_config_paths</span></span>(<span>root_folder: Path, cfg_name: str, cyto_stylesheet_name: str) ‑> tuple[pathlib.Path, pathlib.Path]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def get_config_paths(
|
||||||
|
root_folder: Path,
|
||||||
|
cfg_name: str,
|
||||||
|
cyto_stylesheet_name: str,
|
||||||
|
) -> tuple[Path, Path]:
|
||||||
|
cfg_path_internal = (root_folder / cfg_name).resolve()
|
||||||
|
cyto_stylesheet_path = (root_folder / cyto_stylesheet_name).resolve()
|
||||||
|
|
||||||
|
return cfg_path_internal, cyto_stylesheet_path</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.config.load_cfg"><code class="name flex">
|
||||||
|
<span>def <span class="ident">load_cfg</span></span>(<span>starting_path: Path,<br>glob_pattern: str,<br>stop_folder_name: str | None,<br>lookup_cwd: bool = False) ‑> dict[str, typing.Any]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def load_cfg(
|
||||||
|
starting_path: Path,
|
||||||
|
glob_pattern: str,
|
||||||
|
stop_folder_name: str | None,
|
||||||
|
lookup_cwd: bool = False,
|
||||||
|
) -> dict[str, Any]:
|
||||||
|
"""Look for configuration file. Internal configs are not used any more because
|
||||||
|
the library behaviour is only guaranteed by external configurations.
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
starting_path : Path
|
||||||
|
path to start for the lookup
|
||||||
|
glob_pattern : str
|
||||||
|
pattern of the config file naming scheme
|
||||||
|
stop_folder_name : str | None
|
||||||
|
folder name at which the lookup should stop, the parent folder
|
||||||
|
is also searched, e.g.
|
||||||
|
if starting_path is path/to/start/folder and stop_folder_name is 'to',
|
||||||
|
then path/ is also searched
|
||||||
|
|
||||||
|
Returns
|
||||||
|
-------
|
||||||
|
dict[str, Any]
|
||||||
|
loaded config file
|
||||||
|
|
||||||
|
Raises
|
||||||
|
------
|
||||||
|
LangMainConfigNotFoundError
|
||||||
|
if no config file was found
|
||||||
|
"""
|
||||||
|
cfg_path: Path | None = None
|
||||||
|
if lookup_cwd:
|
||||||
|
print('Looking for cfg file in CWD.', flush=True)
|
||||||
|
cfg_path = search_cwd(glob_pattern)
|
||||||
|
|
||||||
|
if cfg_path is None:
|
||||||
|
print(
|
||||||
|
(
|
||||||
|
f'Looking iteratively for config file. Start: {starting_path}, '
|
||||||
|
f'stop folder: {stop_folder_name}'
|
||||||
|
),
|
||||||
|
flush=True,
|
||||||
|
)
|
||||||
|
cfg_path = search_iterative(
|
||||||
|
starting_path=starting_path,
|
||||||
|
glob_pattern=glob_pattern,
|
||||||
|
stop_folder_name=stop_folder_name,
|
||||||
|
)
|
||||||
|
|
||||||
|
if cfg_path is None:
|
||||||
|
raise LangMainConfigNotFoundError('Config file was not found.')
|
||||||
|
|
||||||
|
config = load_toml_config(path_to_toml=cfg_path)
|
||||||
|
print(f'Loaded config from: >>{cfg_path}<<')
|
||||||
|
|
||||||
|
return config.copy()</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Look for configuration file. Internal configs are not used any more because
|
||||||
|
the library behaviour is only guaranteed by external configurations.</p>
|
||||||
|
<h2 id="parameters">Parameters</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><strong><code>starting_path</code></strong> : <code>Path</code></dt>
|
||||||
|
<dd>path to start for the lookup</dd>
|
||||||
|
<dt><strong><code>glob_pattern</code></strong> : <code>str</code></dt>
|
||||||
|
<dd>pattern of the config file naming scheme</dd>
|
||||||
|
<dt><strong><code>stop_folder_name</code></strong> : <code>str | None</code></dt>
|
||||||
|
<dd>folder name at which the lookup should stop, the parent folder
|
||||||
|
is also searched, e.g.
|
||||||
|
if starting_path is path/to/start/folder and stop_folder_name is 'to',
|
||||||
|
then path/ is also searched</dd>
|
||||||
|
</dl>
|
||||||
|
<h2 id="returns">Returns</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code>dict[str, Any]</code></dt>
|
||||||
|
<dd>loaded config file</dd>
|
||||||
|
</dl>
|
||||||
|
<h2 id="raises">Raises</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code>LangMainConfigNotFoundError</code></dt>
|
||||||
|
<dd>if no config file was found</dd>
|
||||||
|
</dl></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.config.load_toml_config"><code class="name flex">
|
||||||
|
<span>def <span class="ident">load_toml_config</span></span>(<span>path_to_toml: str | Path) ‑> dict[str, typing.Any]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def load_toml_config(
|
||||||
|
path_to_toml: str | Path,
|
||||||
|
) -> dict[str, Any]:
|
||||||
|
with open(path_to_toml, 'rb') as f:
|
||||||
|
data = tomllib.load(f)
|
||||||
|
print('Loaded TOML config file successfully.', flush=True)
|
||||||
|
|
||||||
|
return data</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
</dl>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
</article>
|
||||||
|
<nav id="sidebar">
|
||||||
|
<div class="toc">
|
||||||
|
<ul></ul>
|
||||||
|
</div>
|
||||||
|
<ul id="index">
|
||||||
|
<li><h3>Super-module</h3>
|
||||||
|
<ul>
|
||||||
|
<li><code><a title="lang_main" href="index.html">lang_main</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
<li><h3><a href="#header-functions">Functions</a></h3>
|
||||||
|
<ul class="">
|
||||||
|
<li><code><a title="lang_main.config.get_config_paths" href="#lang_main.config.get_config_paths">get_config_paths</a></code></li>
|
||||||
|
<li><code><a title="lang_main.config.load_cfg" href="#lang_main.config.load_cfg">load_cfg</a></code></li>
|
||||||
|
<li><code><a title="lang_main.config.load_toml_config" href="#lang_main.config.load_toml_config">load_toml_config</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
</ul>
|
||||||
|
</nav>
|
||||||
|
</main>
|
||||||
|
<footer id="footer">
|
||||||
|
<p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.11.5</a>.</p>
|
||||||
|
</footer>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
66
docs/lang_main/constants.html
Normal file
66
docs/lang_main/constants.html
Normal file
@ -0,0 +1,66 @@
|
|||||||
|
<!doctype html>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="utf-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1">
|
||||||
|
<meta name="generator" content="pdoc3 0.11.5">
|
||||||
|
<title>lang_main.constants API documentation</title>
|
||||||
|
<meta name="description" content="">
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/sanitize.min.css" integrity="sha512-y1dtMcuvtTMJc1yPgEqF0ZjQbhnc/bFhyvIyVNb9Zk5mIGtqVaAB1Ttl28su8AvFMOY0EwRbAe+HCLqj6W7/KA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/typography.min.css" integrity="sha512-Y1DYSb995BAfxobCkKepB1BqJJTPrOp3zPL74AWFugHHmmdcvO+C48WLrUOlhGMc0QG7AE3f7gmvvcrmX2fDoA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/styles/default.min.css" crossorigin>
|
||||||
|
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:1.5em;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:2em 0 .50em 0}h3{font-size:1.4em;margin:1.6em 0 .7em 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .2s ease-in-out}a:visited{color:#503}a:hover{color:#b62}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900;font-weight:bold}pre code{font-size:.8em;line-height:1.4em;padding:1em;display:block}code{background:#f3f3f3;font-family:"DejaVu Sans Mono",monospace;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source > summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible;min-width:max-content}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em 1em;margin:1em 0}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
|
||||||
|
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul ul{padding-left:1em}.toc > ul > li{margin-top:.5em}}</style>
|
||||||
|
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
|
||||||
|
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/highlight.min.js" integrity="sha512-D9gUyxqja7hBtkWpPWGt9wfbfaMGVt9gnyCvYa+jojwwPHLCzUm5i8rpk7vD7wNee9bA35eYIjobYPaQuKS1MQ==" crossorigin></script>
|
||||||
|
<script>window.addEventListener('DOMContentLoaded', () => {
|
||||||
|
hljs.configure({languages: ['bash', 'css', 'diff', 'graphql', 'ini', 'javascript', 'json', 'plaintext', 'python', 'python-repl', 'rust', 'shell', 'sql', 'typescript', 'xml', 'yaml']});
|
||||||
|
hljs.highlightAll();
|
||||||
|
/* Collapse source docstrings */
|
||||||
|
setTimeout(() => {
|
||||||
|
[...document.querySelectorAll('.hljs.language-python > .hljs-string')]
|
||||||
|
.filter(el => el.innerHTML.length > 200 && ['"""', "'''"].includes(el.innerHTML.substring(0, 3)))
|
||||||
|
.forEach(el => {
|
||||||
|
let d = document.createElement('details');
|
||||||
|
d.classList.add('hljs-string');
|
||||||
|
d.innerHTML = '<summary>"""</summary>' + el.innerHTML.substring(3);
|
||||||
|
el.replaceWith(d);
|
||||||
|
});
|
||||||
|
}, 100);
|
||||||
|
})</script>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<main>
|
||||||
|
<article id="content">
|
||||||
|
<header>
|
||||||
|
<h1 class="title">Module <code>lang_main.constants</code></h1>
|
||||||
|
</header>
|
||||||
|
<section id="section-intro">
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
</article>
|
||||||
|
<nav id="sidebar">
|
||||||
|
<div class="toc">
|
||||||
|
<ul></ul>
|
||||||
|
</div>
|
||||||
|
<ul id="index">
|
||||||
|
<li><h3>Super-module</h3>
|
||||||
|
<ul>
|
||||||
|
<li><code><a title="lang_main" href="index.html">lang_main</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
</ul>
|
||||||
|
</nav>
|
||||||
|
</main>
|
||||||
|
<footer id="footer">
|
||||||
|
<p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.11.5</a>.</p>
|
||||||
|
</footer>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
330
docs/lang_main/errors.html
Normal file
330
docs/lang_main/errors.html
Normal file
@ -0,0 +1,330 @@
|
|||||||
|
<!doctype html>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="utf-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1">
|
||||||
|
<meta name="generator" content="pdoc3 0.11.5">
|
||||||
|
<title>lang_main.errors API documentation</title>
|
||||||
|
<meta name="description" content="">
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/sanitize.min.css" integrity="sha512-y1dtMcuvtTMJc1yPgEqF0ZjQbhnc/bFhyvIyVNb9Zk5mIGtqVaAB1Ttl28su8AvFMOY0EwRbAe+HCLqj6W7/KA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/typography.min.css" integrity="sha512-Y1DYSb995BAfxobCkKepB1BqJJTPrOp3zPL74AWFugHHmmdcvO+C48WLrUOlhGMc0QG7AE3f7gmvvcrmX2fDoA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/styles/default.min.css" crossorigin>
|
||||||
|
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:1.5em;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:2em 0 .50em 0}h3{font-size:1.4em;margin:1.6em 0 .7em 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .2s ease-in-out}a:visited{color:#503}a:hover{color:#b62}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900;font-weight:bold}pre code{font-size:.8em;line-height:1.4em;padding:1em;display:block}code{background:#f3f3f3;font-family:"DejaVu Sans Mono",monospace;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source > summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible;min-width:max-content}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em 1em;margin:1em 0}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
|
||||||
|
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul ul{padding-left:1em}.toc > ul > li{margin-top:.5em}}</style>
|
||||||
|
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
|
||||||
|
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/highlight.min.js" integrity="sha512-D9gUyxqja7hBtkWpPWGt9wfbfaMGVt9gnyCvYa+jojwwPHLCzUm5i8rpk7vD7wNee9bA35eYIjobYPaQuKS1MQ==" crossorigin></script>
|
||||||
|
<script>window.addEventListener('DOMContentLoaded', () => {
|
||||||
|
hljs.configure({languages: ['bash', 'css', 'diff', 'graphql', 'ini', 'javascript', 'json', 'plaintext', 'python', 'python-repl', 'rust', 'shell', 'sql', 'typescript', 'xml', 'yaml']});
|
||||||
|
hljs.highlightAll();
|
||||||
|
/* Collapse source docstrings */
|
||||||
|
setTimeout(() => {
|
||||||
|
[...document.querySelectorAll('.hljs.language-python > .hljs-string')]
|
||||||
|
.filter(el => el.innerHTML.length > 200 && ['"""', "'''"].includes(el.innerHTML.substring(0, 3)))
|
||||||
|
.forEach(el => {
|
||||||
|
let d = document.createElement('details');
|
||||||
|
d.classList.add('hljs-string');
|
||||||
|
d.innerHTML = '<summary>"""</summary>' + el.innerHTML.substring(3);
|
||||||
|
el.replaceWith(d);
|
||||||
|
});
|
||||||
|
}, 100);
|
||||||
|
})</script>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<main>
|
||||||
|
<article id="content">
|
||||||
|
<header>
|
||||||
|
<h1 class="title">Module <code>lang_main.errors</code></h1>
|
||||||
|
</header>
|
||||||
|
<section id="section-intro">
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
<h2 class="section-title" id="header-classes">Classes</h2>
|
||||||
|
<dl>
|
||||||
|
<dt id="lang_main.errors.DependencyMissingError"><code class="flex name class">
|
||||||
|
<span>class <span class="ident">DependencyMissingError</span></span>
|
||||||
|
<span>(</span><span>*args, **kwargs)</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">class DependencyMissingError(Exception):
|
||||||
|
"""Error raised if needed dependency could not be found"""</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Error raised if needed dependency could not be found</p></div>
|
||||||
|
<h3>Ancestors</h3>
|
||||||
|
<ul class="hlist">
|
||||||
|
<li>builtins.Exception</li>
|
||||||
|
<li>builtins.BaseException</li>
|
||||||
|
</ul>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.errors.EdgePropertyNotContainedError"><code class="flex name class">
|
||||||
|
<span>class <span class="ident">EdgePropertyNotContainedError</span></span>
|
||||||
|
<span>(</span><span>*args, **kwargs)</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">class EdgePropertyNotContainedError(Exception):
|
||||||
|
"""Error raised if a needed edge property is not contained in graph edges"""</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Error raised if a needed edge property is not contained in graph edges</p></div>
|
||||||
|
<h3>Ancestors</h3>
|
||||||
|
<ul class="hlist">
|
||||||
|
<li>builtins.Exception</li>
|
||||||
|
<li>builtins.BaseException</li>
|
||||||
|
</ul>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.errors.EmptyEdgesError"><code class="flex name class">
|
||||||
|
<span>class <span class="ident">EmptyEdgesError</span></span>
|
||||||
|
<span>(</span><span>*args, **kwargs)</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">class EmptyEdgesError(EmptyGraphError):
|
||||||
|
"""Error raised if action should be performed on a graph's edges, but
|
||||||
|
it does not contain any"""</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Error raised if action should be performed on a graph's edges, but
|
||||||
|
it does not contain any</p></div>
|
||||||
|
<h3>Ancestors</h3>
|
||||||
|
<ul class="hlist">
|
||||||
|
<li><a title="lang_main.errors.EmptyGraphError" href="#lang_main.errors.EmptyGraphError">EmptyGraphError</a></li>
|
||||||
|
<li>builtins.Exception</li>
|
||||||
|
<li>builtins.BaseException</li>
|
||||||
|
</ul>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.errors.EmptyGraphError"><code class="flex name class">
|
||||||
|
<span>class <span class="ident">EmptyGraphError</span></span>
|
||||||
|
<span>(</span><span>*args, **kwargs)</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">class EmptyGraphError(Exception):
|
||||||
|
"""Error raised if an operation should be performed on the graph,
|
||||||
|
but it does not contain any nodes or edges"""</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Error raised if an operation should be performed on the graph,
|
||||||
|
but it does not contain any nodes or edges</p></div>
|
||||||
|
<h3>Ancestors</h3>
|
||||||
|
<ul class="hlist">
|
||||||
|
<li>builtins.Exception</li>
|
||||||
|
<li>builtins.BaseException</li>
|
||||||
|
</ul>
|
||||||
|
<h3>Subclasses</h3>
|
||||||
|
<ul class="hlist">
|
||||||
|
<li><a title="lang_main.errors.EmptyEdgesError" href="#lang_main.errors.EmptyEdgesError">EmptyEdgesError</a></li>
|
||||||
|
</ul>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.errors.GraphRenderError"><code class="flex name class">
|
||||||
|
<span>class <span class="ident">GraphRenderError</span></span>
|
||||||
|
<span>(</span><span>*args, **kwargs)</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">class GraphRenderError(Exception):
|
||||||
|
"""Error raised if a graph object can not be rendered"""</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Error raised if a graph object can not be rendered</p></div>
|
||||||
|
<h3>Ancestors</h3>
|
||||||
|
<ul class="hlist">
|
||||||
|
<li>builtins.Exception</li>
|
||||||
|
<li>builtins.BaseException</li>
|
||||||
|
</ul>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.errors.LangMainConfigNotFoundError"><code class="flex name class">
|
||||||
|
<span>class <span class="ident">LangMainConfigNotFoundError</span></span>
|
||||||
|
<span>(</span><span>*args, **kwargs)</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">class LangMainConfigNotFoundError(Exception):
|
||||||
|
"""Error raised if a config file could not be found successfully"""</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Error raised if a config file could not be found successfully</p></div>
|
||||||
|
<h3>Ancestors</h3>
|
||||||
|
<ul class="hlist">
|
||||||
|
<li>builtins.Exception</li>
|
||||||
|
<li>builtins.BaseException</li>
|
||||||
|
</ul>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.errors.LanguageModelNotFoundError"><code class="flex name class">
|
||||||
|
<span>class <span class="ident">LanguageModelNotFoundError</span></span>
|
||||||
|
<span>(</span><span>*args, **kwargs)</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">class LanguageModelNotFoundError(Exception):
|
||||||
|
"""Error raised if a given language model could not be loaded successfully"""</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Error raised if a given language model could not be loaded successfully</p></div>
|
||||||
|
<h3>Ancestors</h3>
|
||||||
|
<ul class="hlist">
|
||||||
|
<li>builtins.Exception</li>
|
||||||
|
<li>builtins.BaseException</li>
|
||||||
|
</ul>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.errors.NoPerformableActionError"><code class="flex name class">
|
||||||
|
<span>class <span class="ident">NoPerformableActionError</span></span>
|
||||||
|
<span>(</span><span>*args, **kwargs)</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">class NoPerformableActionError(Exception):
|
||||||
|
"""Error describing that no action is available in the current pipeline"""</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Error describing that no action is available in the current pipeline</p></div>
|
||||||
|
<h3>Ancestors</h3>
|
||||||
|
<ul class="hlist">
|
||||||
|
<li>builtins.Exception</li>
|
||||||
|
<li>builtins.BaseException</li>
|
||||||
|
</ul>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.errors.NodePropertyNotContainedError"><code class="flex name class">
|
||||||
|
<span>class <span class="ident">NodePropertyNotContainedError</span></span>
|
||||||
|
<span>(</span><span>*args, **kwargs)</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">class NodePropertyNotContainedError(Exception):
|
||||||
|
"""Error raised if a needed node property is not contained in graph edges"""</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Error raised if a needed node property is not contained in graph edges</p></div>
|
||||||
|
<h3>Ancestors</h3>
|
||||||
|
<ul class="hlist">
|
||||||
|
<li>builtins.Exception</li>
|
||||||
|
<li>builtins.BaseException</li>
|
||||||
|
</ul>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.errors.OutputInPipelineContainerError"><code class="flex name class">
|
||||||
|
<span>class <span class="ident">OutputInPipelineContainerError</span></span>
|
||||||
|
<span>(</span><span>*args, **kwargs)</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">class OutputInPipelineContainerError(Exception):
|
||||||
|
"""Error raised if an output was detected by one of the performed
|
||||||
|
actions in a PipelineContainer. Each action in a PipelineContainer is itself a
|
||||||
|
procedure which does not have any parameters or return values and should therefore not
|
||||||
|
return any values."""</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Error raised if an output was detected by one of the performed
|
||||||
|
actions in a PipelineContainer. Each action in a PipelineContainer is itself a
|
||||||
|
procedure which does not have any parameters or return values and should therefore not
|
||||||
|
return any values.</p></div>
|
||||||
|
<h3>Ancestors</h3>
|
||||||
|
<ul class="hlist">
|
||||||
|
<li>builtins.Exception</li>
|
||||||
|
<li>builtins.BaseException</li>
|
||||||
|
</ul>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.errors.WrongActionTypeError"><code class="flex name class">
|
||||||
|
<span>class <span class="ident">WrongActionTypeError</span></span>
|
||||||
|
<span>(</span><span>*args, **kwargs)</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">class WrongActionTypeError(Exception):
|
||||||
|
"""Error raised if added action type is not supported by corresponding pipeline"""</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Error raised if added action type is not supported by corresponding pipeline</p></div>
|
||||||
|
<h3>Ancestors</h3>
|
||||||
|
<ul class="hlist">
|
||||||
|
<li>builtins.Exception</li>
|
||||||
|
<li>builtins.BaseException</li>
|
||||||
|
</ul>
|
||||||
|
</dd>
|
||||||
|
</dl>
|
||||||
|
</section>
|
||||||
|
</article>
|
||||||
|
<nav id="sidebar">
|
||||||
|
<div class="toc">
|
||||||
|
<ul></ul>
|
||||||
|
</div>
|
||||||
|
<ul id="index">
|
||||||
|
<li><h3>Super-module</h3>
|
||||||
|
<ul>
|
||||||
|
<li><code><a title="lang_main" href="index.html">lang_main</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
<li><h3><a href="#header-classes">Classes</a></h3>
|
||||||
|
<ul>
|
||||||
|
<li>
|
||||||
|
<h4><code><a title="lang_main.errors.DependencyMissingError" href="#lang_main.errors.DependencyMissingError">DependencyMissingError</a></code></h4>
|
||||||
|
</li>
|
||||||
|
<li>
|
||||||
|
<h4><code><a title="lang_main.errors.EdgePropertyNotContainedError" href="#lang_main.errors.EdgePropertyNotContainedError">EdgePropertyNotContainedError</a></code></h4>
|
||||||
|
</li>
|
||||||
|
<li>
|
||||||
|
<h4><code><a title="lang_main.errors.EmptyEdgesError" href="#lang_main.errors.EmptyEdgesError">EmptyEdgesError</a></code></h4>
|
||||||
|
</li>
|
||||||
|
<li>
|
||||||
|
<h4><code><a title="lang_main.errors.EmptyGraphError" href="#lang_main.errors.EmptyGraphError">EmptyGraphError</a></code></h4>
|
||||||
|
</li>
|
||||||
|
<li>
|
||||||
|
<h4><code><a title="lang_main.errors.GraphRenderError" href="#lang_main.errors.GraphRenderError">GraphRenderError</a></code></h4>
|
||||||
|
</li>
|
||||||
|
<li>
|
||||||
|
<h4><code><a title="lang_main.errors.LangMainConfigNotFoundError" href="#lang_main.errors.LangMainConfigNotFoundError">LangMainConfigNotFoundError</a></code></h4>
|
||||||
|
</li>
|
||||||
|
<li>
|
||||||
|
<h4><code><a title="lang_main.errors.LanguageModelNotFoundError" href="#lang_main.errors.LanguageModelNotFoundError">LanguageModelNotFoundError</a></code></h4>
|
||||||
|
</li>
|
||||||
|
<li>
|
||||||
|
<h4><code><a title="lang_main.errors.NoPerformableActionError" href="#lang_main.errors.NoPerformableActionError">NoPerformableActionError</a></code></h4>
|
||||||
|
</li>
|
||||||
|
<li>
|
||||||
|
<h4><code><a title="lang_main.errors.NodePropertyNotContainedError" href="#lang_main.errors.NodePropertyNotContainedError">NodePropertyNotContainedError</a></code></h4>
|
||||||
|
</li>
|
||||||
|
<li>
|
||||||
|
<h4><code><a title="lang_main.errors.OutputInPipelineContainerError" href="#lang_main.errors.OutputInPipelineContainerError">OutputInPipelineContainerError</a></code></h4>
|
||||||
|
</li>
|
||||||
|
<li>
|
||||||
|
<h4><code><a title="lang_main.errors.WrongActionTypeError" href="#lang_main.errors.WrongActionTypeError">WrongActionTypeError</a></code></h4>
|
||||||
|
</li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
</ul>
|
||||||
|
</nav>
|
||||||
|
</main>
|
||||||
|
<footer id="footer">
|
||||||
|
<p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.11.5</a>.</p>
|
||||||
|
</footer>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
123
docs/lang_main/index.html
Normal file
123
docs/lang_main/index.html
Normal file
@ -0,0 +1,123 @@
|
|||||||
|
<!doctype html>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="utf-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1">
|
||||||
|
<meta name="generator" content="pdoc3 0.11.5">
|
||||||
|
<title>lang_main API documentation</title>
|
||||||
|
<meta name="description" content="">
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/sanitize.min.css" integrity="sha512-y1dtMcuvtTMJc1yPgEqF0ZjQbhnc/bFhyvIyVNb9Zk5mIGtqVaAB1Ttl28su8AvFMOY0EwRbAe+HCLqj6W7/KA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/typography.min.css" integrity="sha512-Y1DYSb995BAfxobCkKepB1BqJJTPrOp3zPL74AWFugHHmmdcvO+C48WLrUOlhGMc0QG7AE3f7gmvvcrmX2fDoA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/styles/default.min.css" crossorigin>
|
||||||
|
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:1.5em;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:2em 0 .50em 0}h3{font-size:1.4em;margin:1.6em 0 .7em 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .2s ease-in-out}a:visited{color:#503}a:hover{color:#b62}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900;font-weight:bold}pre code{font-size:.8em;line-height:1.4em;padding:1em;display:block}code{background:#f3f3f3;font-family:"DejaVu Sans Mono",monospace;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source > summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible;min-width:max-content}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em 1em;margin:1em 0}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
|
||||||
|
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul ul{padding-left:1em}.toc > ul > li{margin-top:.5em}}</style>
|
||||||
|
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
|
||||||
|
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/highlight.min.js" integrity="sha512-D9gUyxqja7hBtkWpPWGt9wfbfaMGVt9gnyCvYa+jojwwPHLCzUm5i8rpk7vD7wNee9bA35eYIjobYPaQuKS1MQ==" crossorigin></script>
|
||||||
|
<script>window.addEventListener('DOMContentLoaded', () => {
|
||||||
|
hljs.configure({languages: ['bash', 'css', 'diff', 'graphql', 'ini', 'javascript', 'json', 'plaintext', 'python', 'python-repl', 'rust', 'shell', 'sql', 'typescript', 'xml', 'yaml']});
|
||||||
|
hljs.highlightAll();
|
||||||
|
/* Collapse source docstrings */
|
||||||
|
setTimeout(() => {
|
||||||
|
[...document.querySelectorAll('.hljs.language-python > .hljs-string')]
|
||||||
|
.filter(el => el.innerHTML.length > 200 && ['"""', "'''"].includes(el.innerHTML.substring(0, 3)))
|
||||||
|
.forEach(el => {
|
||||||
|
let d = document.createElement('details');
|
||||||
|
d.classList.add('hljs-string');
|
||||||
|
d.innerHTML = '<summary>"""</summary>' + el.innerHTML.substring(3);
|
||||||
|
el.replaceWith(d);
|
||||||
|
});
|
||||||
|
}, 100);
|
||||||
|
})</script>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<main>
|
||||||
|
<article id="content">
|
||||||
|
<header>
|
||||||
|
<h1 class="title">Package <code>lang_main</code></h1>
|
||||||
|
</header>
|
||||||
|
<section id="section-intro">
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
<h2 class="section-title" id="header-submodules">Sub-modules</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code class="name"><a title="lang_main.analysis" href="analysis/index.html">lang_main.analysis</a></code></dt>
|
||||||
|
<dd>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt><code class="name"><a title="lang_main.config" href="config.html">lang_main.config</a></code></dt>
|
||||||
|
<dd>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt><code class="name"><a title="lang_main.constants" href="constants.html">lang_main.constants</a></code></dt>
|
||||||
|
<dd>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt><code class="name"><a title="lang_main.errors" href="errors.html">lang_main.errors</a></code></dt>
|
||||||
|
<dd>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt><code class="name"><a title="lang_main.io" href="io.html">lang_main.io</a></code></dt>
|
||||||
|
<dd>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt><code class="name"><a title="lang_main.loggers" href="loggers.html">lang_main.loggers</a></code></dt>
|
||||||
|
<dd>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt><code class="name"><a title="lang_main.model_loader" href="model_loader.html">lang_main.model_loader</a></code></dt>
|
||||||
|
<dd>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt><code class="name"><a title="lang_main.pipelines" href="pipelines/index.html">lang_main.pipelines</a></code></dt>
|
||||||
|
<dd>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt><code class="name"><a title="lang_main.render" href="render/index.html">lang_main.render</a></code></dt>
|
||||||
|
<dd>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt><code class="name"><a title="lang_main.search" href="search.html">lang_main.search</a></code></dt>
|
||||||
|
<dd>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt><code class="name"><a title="lang_main.types" href="types.html">lang_main.types</a></code></dt>
|
||||||
|
<dd>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
</dl>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
</article>
|
||||||
|
<nav id="sidebar">
|
||||||
|
<div class="toc">
|
||||||
|
<ul></ul>
|
||||||
|
</div>
|
||||||
|
<ul id="index">
|
||||||
|
<li><h3><a href="#header-submodules">Sub-modules</a></h3>
|
||||||
|
<ul>
|
||||||
|
<li><code><a title="lang_main.analysis" href="analysis/index.html">lang_main.analysis</a></code></li>
|
||||||
|
<li><code><a title="lang_main.config" href="config.html">lang_main.config</a></code></li>
|
||||||
|
<li><code><a title="lang_main.constants" href="constants.html">lang_main.constants</a></code></li>
|
||||||
|
<li><code><a title="lang_main.errors" href="errors.html">lang_main.errors</a></code></li>
|
||||||
|
<li><code><a title="lang_main.io" href="io.html">lang_main.io</a></code></li>
|
||||||
|
<li><code><a title="lang_main.loggers" href="loggers.html">lang_main.loggers</a></code></li>
|
||||||
|
<li><code><a title="lang_main.model_loader" href="model_loader.html">lang_main.model_loader</a></code></li>
|
||||||
|
<li><code><a title="lang_main.pipelines" href="pipelines/index.html">lang_main.pipelines</a></code></li>
|
||||||
|
<li><code><a title="lang_main.render" href="render/index.html">lang_main.render</a></code></li>
|
||||||
|
<li><code><a title="lang_main.search" href="search.html">lang_main.search</a></code></li>
|
||||||
|
<li><code><a title="lang_main.types" href="types.html">lang_main.types</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
</ul>
|
||||||
|
</nav>
|
||||||
|
</main>
|
||||||
|
<footer id="footer">
|
||||||
|
<p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.11.5</a>.</p>
|
||||||
|
</footer>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
227
docs/lang_main/io.html
Normal file
227
docs/lang_main/io.html
Normal file
@ -0,0 +1,227 @@
|
|||||||
|
<!doctype html>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="utf-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1">
|
||||||
|
<meta name="generator" content="pdoc3 0.11.5">
|
||||||
|
<title>lang_main.io API documentation</title>
|
||||||
|
<meta name="description" content="">
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/sanitize.min.css" integrity="sha512-y1dtMcuvtTMJc1yPgEqF0ZjQbhnc/bFhyvIyVNb9Zk5mIGtqVaAB1Ttl28su8AvFMOY0EwRbAe+HCLqj6W7/KA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/typography.min.css" integrity="sha512-Y1DYSb995BAfxobCkKepB1BqJJTPrOp3zPL74AWFugHHmmdcvO+C48WLrUOlhGMc0QG7AE3f7gmvvcrmX2fDoA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/styles/default.min.css" crossorigin>
|
||||||
|
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:1.5em;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:2em 0 .50em 0}h3{font-size:1.4em;margin:1.6em 0 .7em 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .2s ease-in-out}a:visited{color:#503}a:hover{color:#b62}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900;font-weight:bold}pre code{font-size:.8em;line-height:1.4em;padding:1em;display:block}code{background:#f3f3f3;font-family:"DejaVu Sans Mono",monospace;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source > summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible;min-width:max-content}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em 1em;margin:1em 0}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
|
||||||
|
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul ul{padding-left:1em}.toc > ul > li{margin-top:.5em}}</style>
|
||||||
|
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
|
||||||
|
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/highlight.min.js" integrity="sha512-D9gUyxqja7hBtkWpPWGt9wfbfaMGVt9gnyCvYa+jojwwPHLCzUm5i8rpk7vD7wNee9bA35eYIjobYPaQuKS1MQ==" crossorigin></script>
|
||||||
|
<script>window.addEventListener('DOMContentLoaded', () => {
|
||||||
|
hljs.configure({languages: ['bash', 'css', 'diff', 'graphql', 'ini', 'javascript', 'json', 'plaintext', 'python', 'python-repl', 'rust', 'shell', 'sql', 'typescript', 'xml', 'yaml']});
|
||||||
|
hljs.highlightAll();
|
||||||
|
/* Collapse source docstrings */
|
||||||
|
setTimeout(() => {
|
||||||
|
[...document.querySelectorAll('.hljs.language-python > .hljs-string')]
|
||||||
|
.filter(el => el.innerHTML.length > 200 && ['"""', "'''"].includes(el.innerHTML.substring(0, 3)))
|
||||||
|
.forEach(el => {
|
||||||
|
let d = document.createElement('details');
|
||||||
|
d.classList.add('hljs-string');
|
||||||
|
d.innerHTML = '<summary>"""</summary>' + el.innerHTML.substring(3);
|
||||||
|
el.replaceWith(d);
|
||||||
|
});
|
||||||
|
}, 100);
|
||||||
|
})</script>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<main>
|
||||||
|
<article id="content">
|
||||||
|
<header>
|
||||||
|
<h1 class="title">Module <code>lang_main.io</code></h1>
|
||||||
|
</header>
|
||||||
|
<section id="section-intro">
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
<h2 class="section-title" id="header-functions">Functions</h2>
|
||||||
|
<dl>
|
||||||
|
<dt id="lang_main.io.create_saving_folder"><code class="name flex">
|
||||||
|
<span>def <span class="ident">create_saving_folder</span></span>(<span>saving_path_folder: str | pathlib.Path, overwrite_existing: bool = False) ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def create_saving_folder(
|
||||||
|
saving_path_folder: str | Path,
|
||||||
|
overwrite_existing: bool = False,
|
||||||
|
) -> None:
|
||||||
|
# check for existence of given path
|
||||||
|
if isinstance(saving_path_folder, str):
|
||||||
|
saving_path_folder = Path(saving_path_folder)
|
||||||
|
if not saving_path_folder.exists():
|
||||||
|
saving_path_folder.mkdir(parents=True)
|
||||||
|
else:
|
||||||
|
if overwrite_existing:
|
||||||
|
# overwrite if desired (deletes whole path and re-creates it)
|
||||||
|
shutil.rmtree(saving_path_folder)
|
||||||
|
saving_path_folder.mkdir(parents=True)
|
||||||
|
else:
|
||||||
|
logger.info(
|
||||||
|
(
|
||||||
|
'Path >>%s<< already exists and remained unchanged. If you want to '
|
||||||
|
'overwrite this path, use parameter >>overwrite_existing<<.',
|
||||||
|
),
|
||||||
|
saving_path_folder,
|
||||||
|
)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.io.decode_from_base64_str"><code class="name flex">
|
||||||
|
<span>def <span class="ident">decode_from_base64_str</span></span>(<span>b64_str: str, encoding: str = 'utf-8') ‑> Any</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def decode_from_base64_str(
|
||||||
|
b64_str: str,
|
||||||
|
encoding: str = 'utf-8',
|
||||||
|
) -> Any:
|
||||||
|
b64_bytes = b64_str.encode(encoding=encoding)
|
||||||
|
decoded = base64.b64decode(b64_bytes)
|
||||||
|
return pickle.loads(decoded)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.io.encode_file_to_base64_str"><code class="name flex">
|
||||||
|
<span>def <span class="ident">encode_file_to_base64_str</span></span>(<span>path: pathlib.Path, encoding: str = 'utf-8') ‑> str</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def encode_file_to_base64_str(
|
||||||
|
path: Path,
|
||||||
|
encoding: str = 'utf-8',
|
||||||
|
) -> str:
|
||||||
|
with open(path, 'rb') as file:
|
||||||
|
b64_bytes = base64.b64encode(file.read())
|
||||||
|
return b64_bytes.decode(encoding=encoding)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.io.encode_to_base64_str"><code class="name flex">
|
||||||
|
<span>def <span class="ident">encode_to_base64_str</span></span>(<span>obj: Any, encoding: str = 'utf-8') ‑> str</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def encode_to_base64_str(
|
||||||
|
obj: Any,
|
||||||
|
encoding: str = 'utf-8',
|
||||||
|
) -> str:
|
||||||
|
serialised = pickle.dumps(obj, protocol=PICKLE_PROTOCOL_VERSION)
|
||||||
|
b64_bytes = base64.b64encode(serialised)
|
||||||
|
return b64_bytes.decode(encoding=encoding)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.io.get_entry_point"><code class="name flex">
|
||||||
|
<span>def <span class="ident">get_entry_point</span></span>(<span>saving_path: pathlib.Path,<br>filename: str,<br>file_ext: str = '.pkl',<br>check_existence: bool = True) ‑> pathlib.Path</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def get_entry_point(
|
||||||
|
saving_path: Path,
|
||||||
|
filename: str,
|
||||||
|
file_ext: str = '.pkl',
|
||||||
|
check_existence: bool = True,
|
||||||
|
) -> Path:
|
||||||
|
entry_point_path = (saving_path / filename).with_suffix(file_ext)
|
||||||
|
if check_existence and not entry_point_path.exists():
|
||||||
|
raise FileNotFoundError(
|
||||||
|
f'Could not find provided entry data under path: >>{entry_point_path}<<'
|
||||||
|
)
|
||||||
|
|
||||||
|
return entry_point_path</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.io.load_pickle"><code class="name flex">
|
||||||
|
<span>def <span class="ident">load_pickle</span></span>(<span>path: str | pathlib.Path) ‑> Any</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def load_pickle(
|
||||||
|
path: str | Path,
|
||||||
|
) -> Any:
|
||||||
|
with open(path, 'rb') as file:
|
||||||
|
obj = pickle.load(file)
|
||||||
|
logger.info('Loaded file successfully.')
|
||||||
|
return obj</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.io.save_pickle"><code class="name flex">
|
||||||
|
<span>def <span class="ident">save_pickle</span></span>(<span>obj: Any, path: str | pathlib.Path) ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def save_pickle(
|
||||||
|
obj: Any,
|
||||||
|
path: str | Path,
|
||||||
|
) -> None:
|
||||||
|
with open(path, 'wb') as file:
|
||||||
|
pickle.dump(obj, file, protocol=PICKLE_PROTOCOL_VERSION)
|
||||||
|
logger.info('Saved file successfully under %s', path)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
</dl>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
</article>
|
||||||
|
<nav id="sidebar">
|
||||||
|
<div class="toc">
|
||||||
|
<ul></ul>
|
||||||
|
</div>
|
||||||
|
<ul id="index">
|
||||||
|
<li><h3>Super-module</h3>
|
||||||
|
<ul>
|
||||||
|
<li><code><a title="lang_main" href="index.html">lang_main</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
<li><h3><a href="#header-functions">Functions</a></h3>
|
||||||
|
<ul class="">
|
||||||
|
<li><code><a title="lang_main.io.create_saving_folder" href="#lang_main.io.create_saving_folder">create_saving_folder</a></code></li>
|
||||||
|
<li><code><a title="lang_main.io.decode_from_base64_str" href="#lang_main.io.decode_from_base64_str">decode_from_base64_str</a></code></li>
|
||||||
|
<li><code><a title="lang_main.io.encode_file_to_base64_str" href="#lang_main.io.encode_file_to_base64_str">encode_file_to_base64_str</a></code></li>
|
||||||
|
<li><code><a title="lang_main.io.encode_to_base64_str" href="#lang_main.io.encode_to_base64_str">encode_to_base64_str</a></code></li>
|
||||||
|
<li><code><a title="lang_main.io.get_entry_point" href="#lang_main.io.get_entry_point">get_entry_point</a></code></li>
|
||||||
|
<li><code><a title="lang_main.io.load_pickle" href="#lang_main.io.load_pickle">load_pickle</a></code></li>
|
||||||
|
<li><code><a title="lang_main.io.save_pickle" href="#lang_main.io.save_pickle">save_pickle</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
</ul>
|
||||||
|
</nav>
|
||||||
|
</main>
|
||||||
|
<footer id="footer">
|
||||||
|
<p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.11.5</a>.</p>
|
||||||
|
</footer>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
66
docs/lang_main/loggers.html
Normal file
66
docs/lang_main/loggers.html
Normal file
@ -0,0 +1,66 @@
|
|||||||
|
<!doctype html>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="utf-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1">
|
||||||
|
<meta name="generator" content="pdoc3 0.11.5">
|
||||||
|
<title>lang_main.loggers API documentation</title>
|
||||||
|
<meta name="description" content="">
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/sanitize.min.css" integrity="sha512-y1dtMcuvtTMJc1yPgEqF0ZjQbhnc/bFhyvIyVNb9Zk5mIGtqVaAB1Ttl28su8AvFMOY0EwRbAe+HCLqj6W7/KA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/typography.min.css" integrity="sha512-Y1DYSb995BAfxobCkKepB1BqJJTPrOp3zPL74AWFugHHmmdcvO+C48WLrUOlhGMc0QG7AE3f7gmvvcrmX2fDoA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/styles/default.min.css" crossorigin>
|
||||||
|
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:1.5em;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:2em 0 .50em 0}h3{font-size:1.4em;margin:1.6em 0 .7em 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .2s ease-in-out}a:visited{color:#503}a:hover{color:#b62}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900;font-weight:bold}pre code{font-size:.8em;line-height:1.4em;padding:1em;display:block}code{background:#f3f3f3;font-family:"DejaVu Sans Mono",monospace;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source > summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible;min-width:max-content}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em 1em;margin:1em 0}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
|
||||||
|
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul ul{padding-left:1em}.toc > ul > li{margin-top:.5em}}</style>
|
||||||
|
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
|
||||||
|
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/highlight.min.js" integrity="sha512-D9gUyxqja7hBtkWpPWGt9wfbfaMGVt9gnyCvYa+jojwwPHLCzUm5i8rpk7vD7wNee9bA35eYIjobYPaQuKS1MQ==" crossorigin></script>
|
||||||
|
<script>window.addEventListener('DOMContentLoaded', () => {
|
||||||
|
hljs.configure({languages: ['bash', 'css', 'diff', 'graphql', 'ini', 'javascript', 'json', 'plaintext', 'python', 'python-repl', 'rust', 'shell', 'sql', 'typescript', 'xml', 'yaml']});
|
||||||
|
hljs.highlightAll();
|
||||||
|
/* Collapse source docstrings */
|
||||||
|
setTimeout(() => {
|
||||||
|
[...document.querySelectorAll('.hljs.language-python > .hljs-string')]
|
||||||
|
.filter(el => el.innerHTML.length > 200 && ['"""', "'''"].includes(el.innerHTML.substring(0, 3)))
|
||||||
|
.forEach(el => {
|
||||||
|
let d = document.createElement('details');
|
||||||
|
d.classList.add('hljs-string');
|
||||||
|
d.innerHTML = '<summary>"""</summary>' + el.innerHTML.substring(3);
|
||||||
|
el.replaceWith(d);
|
||||||
|
});
|
||||||
|
}, 100);
|
||||||
|
})</script>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<main>
|
||||||
|
<article id="content">
|
||||||
|
<header>
|
||||||
|
<h1 class="title">Module <code>lang_main.loggers</code></h1>
|
||||||
|
</header>
|
||||||
|
<section id="section-intro">
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
</article>
|
||||||
|
<nav id="sidebar">
|
||||||
|
<div class="toc">
|
||||||
|
<ul></ul>
|
||||||
|
</div>
|
||||||
|
<ul id="index">
|
||||||
|
<li><h3>Super-module</h3>
|
||||||
|
<ul>
|
||||||
|
<li><code><a title="lang_main" href="index.html">lang_main</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
</ul>
|
||||||
|
</nav>
|
||||||
|
</main>
|
||||||
|
<footer id="footer">
|
||||||
|
<p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.11.5</a>.</p>
|
||||||
|
</footer>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
162
docs/lang_main/model_loader.html
Normal file
162
docs/lang_main/model_loader.html
Normal file
@ -0,0 +1,162 @@
|
|||||||
|
<!doctype html>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="utf-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1">
|
||||||
|
<meta name="generator" content="pdoc3 0.11.5">
|
||||||
|
<title>lang_main.model_loader API documentation</title>
|
||||||
|
<meta name="description" content="">
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/sanitize.min.css" integrity="sha512-y1dtMcuvtTMJc1yPgEqF0ZjQbhnc/bFhyvIyVNb9Zk5mIGtqVaAB1Ttl28su8AvFMOY0EwRbAe+HCLqj6W7/KA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/typography.min.css" integrity="sha512-Y1DYSb995BAfxobCkKepB1BqJJTPrOp3zPL74AWFugHHmmdcvO+C48WLrUOlhGMc0QG7AE3f7gmvvcrmX2fDoA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/styles/default.min.css" crossorigin>
|
||||||
|
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:1.5em;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:2em 0 .50em 0}h3{font-size:1.4em;margin:1.6em 0 .7em 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .2s ease-in-out}a:visited{color:#503}a:hover{color:#b62}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900;font-weight:bold}pre code{font-size:.8em;line-height:1.4em;padding:1em;display:block}code{background:#f3f3f3;font-family:"DejaVu Sans Mono",monospace;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source > summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible;min-width:max-content}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em 1em;margin:1em 0}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
|
||||||
|
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul ul{padding-left:1em}.toc > ul > li{margin-top:.5em}}</style>
|
||||||
|
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
|
||||||
|
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/highlight.min.js" integrity="sha512-D9gUyxqja7hBtkWpPWGt9wfbfaMGVt9gnyCvYa+jojwwPHLCzUm5i8rpk7vD7wNee9bA35eYIjobYPaQuKS1MQ==" crossorigin></script>
|
||||||
|
<script>window.addEventListener('DOMContentLoaded', () => {
|
||||||
|
hljs.configure({languages: ['bash', 'css', 'diff', 'graphql', 'ini', 'javascript', 'json', 'plaintext', 'python', 'python-repl', 'rust', 'shell', 'sql', 'typescript', 'xml', 'yaml']});
|
||||||
|
hljs.highlightAll();
|
||||||
|
/* Collapse source docstrings */
|
||||||
|
setTimeout(() => {
|
||||||
|
[...document.querySelectorAll('.hljs.language-python > .hljs-string')]
|
||||||
|
.filter(el => el.innerHTML.length > 200 && ['"""', "'''"].includes(el.innerHTML.substring(0, 3)))
|
||||||
|
.forEach(el => {
|
||||||
|
let d = document.createElement('details');
|
||||||
|
d.classList.add('hljs-string');
|
||||||
|
d.innerHTML = '<summary>"""</summary>' + el.innerHTML.substring(3);
|
||||||
|
el.replaceWith(d);
|
||||||
|
});
|
||||||
|
}, 100);
|
||||||
|
})</script>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<main>
|
||||||
|
<article id="content">
|
||||||
|
<header>
|
||||||
|
<h1 class="title">Module <code>lang_main.model_loader</code></h1>
|
||||||
|
</header>
|
||||||
|
<section id="section-intro">
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
<h2 class="section-title" id="header-functions">Functions</h2>
|
||||||
|
<dl>
|
||||||
|
<dt id="lang_main.model_loader.instantiate_model"><code class="name flex">
|
||||||
|
<span>def <span class="ident">instantiate_model</span></span>(<span>model_load_map: ModelLoaderMap, model: LanguageModels) ‑> sentence_transformers.SentenceTransformer.SentenceTransformer | spacy.language.Language</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def instantiate_model(
|
||||||
|
model_load_map: ModelLoaderMap,
|
||||||
|
model: LanguageModels,
|
||||||
|
) -> Model:
|
||||||
|
if model not in model_load_map:
|
||||||
|
raise KeyError(f'Model >>{model}<< not known. Choose from: {model_load_map.keys()}')
|
||||||
|
builder_func = model_load_map[model]['func']
|
||||||
|
func_kwargs = model_load_map[model]['kwargs']
|
||||||
|
|
||||||
|
return builder_func(**func_kwargs)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.model_loader.load_sentence_transformer"><code class="name flex">
|
||||||
|
<span>def <span class="ident">load_sentence_transformer</span></span>(<span>model_name: STFRModelTypes | str,<br>similarity_func: SimilarityFunction = SimilarityFunction.COSINE,<br>backend: STFRBackends = torch,<br>device: STFRDeviceTypes = cpu,<br>local_files_only: bool = True,<br>trust_remote_code: bool = False,<br>model_save_folder: str | None = None,<br>model_kwargs: STFRModelArgs | dict[str, Any] | None = None,<br>force_download: bool = False) ‑> sentence_transformers.SentenceTransformer.SentenceTransformer</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def load_sentence_transformer(
|
||||||
|
model_name: STFRModelTypes | str,
|
||||||
|
similarity_func: SimilarityFunction = SimilarityFunction.COSINE,
|
||||||
|
backend: STFRBackends = STFRBackends.TORCH,
|
||||||
|
device: STFRDeviceTypes = STFRDeviceTypes.CPU,
|
||||||
|
local_files_only: bool = True,
|
||||||
|
trust_remote_code: bool = False,
|
||||||
|
model_save_folder: str | None = None,
|
||||||
|
model_kwargs: STFRModelArgs | dict[str, Any] | None = None,
|
||||||
|
force_download: bool = False,
|
||||||
|
) -> SentenceTransformer:
|
||||||
|
model_name_or_path = _preprocess_STFR_model_name(
|
||||||
|
model_name=model_name, backend=backend, force_download=force_download
|
||||||
|
)
|
||||||
|
model = SentenceTransformer(
|
||||||
|
model_name_or_path=model_name_or_path,
|
||||||
|
similarity_fn_name=similarity_func,
|
||||||
|
backend=backend, # type: ignore Literal matches Enum
|
||||||
|
device=device,
|
||||||
|
cache_folder=model_save_folder,
|
||||||
|
local_files_only=local_files_only,
|
||||||
|
trust_remote_code=trust_remote_code,
|
||||||
|
model_kwargs=model_kwargs, # type: ignore
|
||||||
|
)
|
||||||
|
logger.info('[MODEL LOADING] Loaded model >>%s<< successfully', model_name)
|
||||||
|
|
||||||
|
return model</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.model_loader.load_spacy"><code class="name flex">
|
||||||
|
<span>def <span class="ident">load_spacy</span></span>(<span>model_name: str) ‑> spacy.language.Language</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def load_spacy(
|
||||||
|
model_name: str,
|
||||||
|
) -> SpacyModel:
|
||||||
|
try:
|
||||||
|
spacy_model_obj = importlib.import_module(model_name)
|
||||||
|
except ModuleNotFoundError:
|
||||||
|
raise LanguageModelNotFoundError(
|
||||||
|
(
|
||||||
|
f'Could not find spaCy model >>{model_name}<<. '
|
||||||
|
f'Check if it is installed correctly.'
|
||||||
|
)
|
||||||
|
)
|
||||||
|
pretrained_model = cast(SpacyModel, spacy_model_obj.load())
|
||||||
|
logger.info('[MODEL LOADING] Loaded model >>%s<< successfully', model_name)
|
||||||
|
|
||||||
|
return pretrained_model</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
</dl>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
</article>
|
||||||
|
<nav id="sidebar">
|
||||||
|
<div class="toc">
|
||||||
|
<ul></ul>
|
||||||
|
</div>
|
||||||
|
<ul id="index">
|
||||||
|
<li><h3>Super-module</h3>
|
||||||
|
<ul>
|
||||||
|
<li><code><a title="lang_main" href="index.html">lang_main</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
<li><h3><a href="#header-functions">Functions</a></h3>
|
||||||
|
<ul class="">
|
||||||
|
<li><code><a title="lang_main.model_loader.instantiate_model" href="#lang_main.model_loader.instantiate_model">instantiate_model</a></code></li>
|
||||||
|
<li><code><a title="lang_main.model_loader.load_sentence_transformer" href="#lang_main.model_loader.load_sentence_transformer">load_sentence_transformer</a></code></li>
|
||||||
|
<li><code><a title="lang_main.model_loader.load_spacy" href="#lang_main.model_loader.load_spacy">load_spacy</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
</ul>
|
||||||
|
</nav>
|
||||||
|
</main>
|
||||||
|
<footer id="footer">
|
||||||
|
<p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.11.5</a>.</p>
|
||||||
|
</footer>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
755
docs/lang_main/pipelines/base.html
Normal file
755
docs/lang_main/pipelines/base.html
Normal file
@ -0,0 +1,755 @@
|
|||||||
|
<!doctype html>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="utf-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1">
|
||||||
|
<meta name="generator" content="pdoc3 0.11.5">
|
||||||
|
<title>lang_main.pipelines.base API documentation</title>
|
||||||
|
<meta name="description" content="">
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/sanitize.min.css" integrity="sha512-y1dtMcuvtTMJc1yPgEqF0ZjQbhnc/bFhyvIyVNb9Zk5mIGtqVaAB1Ttl28su8AvFMOY0EwRbAe+HCLqj6W7/KA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/typography.min.css" integrity="sha512-Y1DYSb995BAfxobCkKepB1BqJJTPrOp3zPL74AWFugHHmmdcvO+C48WLrUOlhGMc0QG7AE3f7gmvvcrmX2fDoA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/styles/default.min.css" crossorigin>
|
||||||
|
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:1.5em;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:2em 0 .50em 0}h3{font-size:1.4em;margin:1.6em 0 .7em 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .2s ease-in-out}a:visited{color:#503}a:hover{color:#b62}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900;font-weight:bold}pre code{font-size:.8em;line-height:1.4em;padding:1em;display:block}code{background:#f3f3f3;font-family:"DejaVu Sans Mono",monospace;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source > summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible;min-width:max-content}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em 1em;margin:1em 0}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
|
||||||
|
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul ul{padding-left:1em}.toc > ul > li{margin-top:.5em}}</style>
|
||||||
|
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
|
||||||
|
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/highlight.min.js" integrity="sha512-D9gUyxqja7hBtkWpPWGt9wfbfaMGVt9gnyCvYa+jojwwPHLCzUm5i8rpk7vD7wNee9bA35eYIjobYPaQuKS1MQ==" crossorigin></script>
|
||||||
|
<script>window.addEventListener('DOMContentLoaded', () => {
|
||||||
|
hljs.configure({languages: ['bash', 'css', 'diff', 'graphql', 'ini', 'javascript', 'json', 'plaintext', 'python', 'python-repl', 'rust', 'shell', 'sql', 'typescript', 'xml', 'yaml']});
|
||||||
|
hljs.highlightAll();
|
||||||
|
/* Collapse source docstrings */
|
||||||
|
setTimeout(() => {
|
||||||
|
[...document.querySelectorAll('.hljs.language-python > .hljs-string')]
|
||||||
|
.filter(el => el.innerHTML.length > 200 && ['"""', "'''"].includes(el.innerHTML.substring(0, 3)))
|
||||||
|
.forEach(el => {
|
||||||
|
let d = document.createElement('details');
|
||||||
|
d.classList.add('hljs-string');
|
||||||
|
d.innerHTML = '<summary>"""</summary>' + el.innerHTML.substring(3);
|
||||||
|
el.replaceWith(d);
|
||||||
|
});
|
||||||
|
}, 100);
|
||||||
|
})</script>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<main>
|
||||||
|
<article id="content">
|
||||||
|
<header>
|
||||||
|
<h1 class="title">Module <code>lang_main.pipelines.base</code></h1>
|
||||||
|
</header>
|
||||||
|
<section id="section-intro">
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
<h2 class="section-title" id="header-classes">Classes</h2>
|
||||||
|
<dl>
|
||||||
|
<dt id="lang_main.pipelines.base.BasePipeline"><code class="flex name class">
|
||||||
|
<span>class <span class="ident">BasePipeline</span></span>
|
||||||
|
<span>(</span><span>name: str, working_dir: Path)</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">class BasePipeline(ABC):
|
||||||
|
def __init__(
|
||||||
|
self,
|
||||||
|
name: str,
|
||||||
|
working_dir: Path,
|
||||||
|
) -> None:
|
||||||
|
# init base class
|
||||||
|
super().__init__()
|
||||||
|
|
||||||
|
# name of pipeline
|
||||||
|
self.name = name
|
||||||
|
# working directory for pipeline == output path
|
||||||
|
self.working_dir = working_dir
|
||||||
|
|
||||||
|
# container for actions to perform during pass
|
||||||
|
self.actions: list[Callable] = []
|
||||||
|
self.action_names: list[str] = []
|
||||||
|
self.action_skip: list[bool] = []
|
||||||
|
# progress tracking, start at 1
|
||||||
|
self.curr_proc_idx: int = 1
|
||||||
|
|
||||||
|
def __repr__(self) -> str:
|
||||||
|
return (
|
||||||
|
f'{self.__class__.__name__}(name: {self.name}, '
|
||||||
|
f'working dir: {self.working_dir}, contents: {self.action_names})'
|
||||||
|
)
|
||||||
|
|
||||||
|
def panic_wrong_action_type(
|
||||||
|
self,
|
||||||
|
action: Any,
|
||||||
|
compatible_type: str,
|
||||||
|
) -> Never:
|
||||||
|
raise WrongActionTypeError(
|
||||||
|
(
|
||||||
|
f'Action must be of type {compatible_type}, '
|
||||||
|
f'but is of type >>{type(action)}<<.'
|
||||||
|
)
|
||||||
|
)
|
||||||
|
|
||||||
|
def prep_run(self) -> None:
|
||||||
|
logger.info('Starting pipeline >>%s<<...', self.name)
|
||||||
|
# progress tracking
|
||||||
|
self.curr_proc_idx = 1
|
||||||
|
# check if performable actions available
|
||||||
|
if len(self.actions) == 0:
|
||||||
|
raise NoPerformableActionError(
|
||||||
|
'The pipeline does not contain any performable actions.'
|
||||||
|
)
|
||||||
|
|
||||||
|
def post_run(self) -> None:
|
||||||
|
logger.info(
|
||||||
|
'Processing pipeline >>%s<< successfully ended after %d steps.',
|
||||||
|
self.name,
|
||||||
|
(self.curr_proc_idx - 1),
|
||||||
|
)
|
||||||
|
|
||||||
|
@abstractmethod
|
||||||
|
def add(self) -> None: ...
|
||||||
|
|
||||||
|
@abstractmethod
|
||||||
|
def logic(self) -> None: ...
|
||||||
|
|
||||||
|
def run(self, *args, **kwargs) -> Any:
|
||||||
|
self.prep_run()
|
||||||
|
ret = self.logic(*args, **kwargs)
|
||||||
|
self.post_run()
|
||||||
|
return ret</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Helper class that provides a standard way to create an ABC using
|
||||||
|
inheritance.</p></div>
|
||||||
|
<h3>Ancestors</h3>
|
||||||
|
<ul class="hlist">
|
||||||
|
<li>abc.ABC</li>
|
||||||
|
</ul>
|
||||||
|
<h3>Subclasses</h3>
|
||||||
|
<ul class="hlist">
|
||||||
|
<li><a title="lang_main.pipelines.base.Pipeline" href="#lang_main.pipelines.base.Pipeline">Pipeline</a></li>
|
||||||
|
<li><a title="lang_main.pipelines.base.PipelineContainer" href="#lang_main.pipelines.base.PipelineContainer">PipelineContainer</a></li>
|
||||||
|
</ul>
|
||||||
|
<h3>Methods</h3>
|
||||||
|
<dl>
|
||||||
|
<dt id="lang_main.pipelines.base.BasePipeline.add"><code class="name flex">
|
||||||
|
<span>def <span class="ident">add</span></span>(<span>self) ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">@abstractmethod
|
||||||
|
def add(self) -> None: ...</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.pipelines.base.BasePipeline.logic"><code class="name flex">
|
||||||
|
<span>def <span class="ident">logic</span></span>(<span>self) ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">@abstractmethod
|
||||||
|
def logic(self) -> None: ...</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.pipelines.base.BasePipeline.panic_wrong_action_type"><code class="name flex">
|
||||||
|
<span>def <span class="ident">panic_wrong_action_type</span></span>(<span>self, action: Any, compatible_type: str) ‑> Never</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def panic_wrong_action_type(
|
||||||
|
self,
|
||||||
|
action: Any,
|
||||||
|
compatible_type: str,
|
||||||
|
) -> Never:
|
||||||
|
raise WrongActionTypeError(
|
||||||
|
(
|
||||||
|
f'Action must be of type {compatible_type}, '
|
||||||
|
f'but is of type >>{type(action)}<<.'
|
||||||
|
)
|
||||||
|
)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.pipelines.base.BasePipeline.post_run"><code class="name flex">
|
||||||
|
<span>def <span class="ident">post_run</span></span>(<span>self) ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def post_run(self) -> None:
|
||||||
|
logger.info(
|
||||||
|
'Processing pipeline >>%s<< successfully ended after %d steps.',
|
||||||
|
self.name,
|
||||||
|
(self.curr_proc_idx - 1),
|
||||||
|
)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.pipelines.base.BasePipeline.prep_run"><code class="name flex">
|
||||||
|
<span>def <span class="ident">prep_run</span></span>(<span>self) ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def prep_run(self) -> None:
|
||||||
|
logger.info('Starting pipeline >>%s<<...', self.name)
|
||||||
|
# progress tracking
|
||||||
|
self.curr_proc_idx = 1
|
||||||
|
# check if performable actions available
|
||||||
|
if len(self.actions) == 0:
|
||||||
|
raise NoPerformableActionError(
|
||||||
|
'The pipeline does not contain any performable actions.'
|
||||||
|
)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.pipelines.base.BasePipeline.run"><code class="name flex">
|
||||||
|
<span>def <span class="ident">run</span></span>(<span>self, *args, **kwargs) ‑> Any</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def run(self, *args, **kwargs) -> Any:
|
||||||
|
self.prep_run()
|
||||||
|
ret = self.logic(*args, **kwargs)
|
||||||
|
self.post_run()
|
||||||
|
return ret</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
</dl>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.pipelines.base.Pipeline"><code class="flex name class">
|
||||||
|
<span>class <span class="ident">Pipeline</span></span>
|
||||||
|
<span>(</span><span>name: str, working_dir: Path)</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">class Pipeline(BasePipeline):
|
||||||
|
def __init__(
|
||||||
|
self,
|
||||||
|
name: str,
|
||||||
|
working_dir: Path,
|
||||||
|
) -> None:
|
||||||
|
# init base class
|
||||||
|
super().__init__(name=name, working_dir=working_dir)
|
||||||
|
# name of pipeline
|
||||||
|
self.name = name
|
||||||
|
# working directory for pipeline == output path
|
||||||
|
self.working_dir = working_dir
|
||||||
|
# container for actions to perform during pass
|
||||||
|
self.actions_kwargs: list[dict[str, Any]] = []
|
||||||
|
self.save_results: ResultHandling = []
|
||||||
|
self.load_results: ResultHandling = []
|
||||||
|
# intermediate result
|
||||||
|
self._intermediate_result: tuple[Any, ...] | None = None
|
||||||
|
|
||||||
|
def __repr__(self) -> str:
|
||||||
|
return (
|
||||||
|
f'{self.__class__.__name__}(name: {self.name}, '
|
||||||
|
f'working dir: {self.working_dir}, contents: {self.action_names})'
|
||||||
|
)
|
||||||
|
|
||||||
|
@override
|
||||||
|
def add(
|
||||||
|
self,
|
||||||
|
action: Callable,
|
||||||
|
action_kwargs: dict[str, Any] | None = None,
|
||||||
|
skip: bool = False,
|
||||||
|
save_result: bool = False,
|
||||||
|
load_result: bool = False,
|
||||||
|
filename: str | None = None,
|
||||||
|
) -> None:
|
||||||
|
# check explicitly for function type
|
||||||
|
# if isinstance(action, FunctionType):
|
||||||
|
if action_kwargs is None:
|
||||||
|
action_kwargs = {}
|
||||||
|
|
||||||
|
if isinstance(action, Callable):
|
||||||
|
self.actions.append(action)
|
||||||
|
self.action_names.append(action.__name__)
|
||||||
|
self.actions_kwargs.append(action_kwargs.copy())
|
||||||
|
self.action_skip.append(skip)
|
||||||
|
self.save_results.append((save_result, filename))
|
||||||
|
self.load_results.append((load_result, filename))
|
||||||
|
else:
|
||||||
|
self.panic_wrong_action_type(action=action, compatible_type=Callable.__name__)
|
||||||
|
|
||||||
|
def get_result_path(
|
||||||
|
self,
|
||||||
|
action_idx: int,
|
||||||
|
filename: str | None,
|
||||||
|
) -> tuple[Path, str]:
|
||||||
|
action_name = self.action_names[action_idx]
|
||||||
|
if filename is None:
|
||||||
|
target_filename = f'Pipe-{self.name}_Step-{self.curr_proc_idx}_{action_name}'
|
||||||
|
else:
|
||||||
|
target_filename = filename
|
||||||
|
target_path = self.working_dir.joinpath(target_filename).with_suffix('.pkl')
|
||||||
|
return target_path, action_name
|
||||||
|
|
||||||
|
def load_step(
|
||||||
|
self,
|
||||||
|
action_idx: int,
|
||||||
|
filename: str | None,
|
||||||
|
) -> tuple[Any, ...]:
|
||||||
|
target_path, action_name = self.get_result_path(action_idx, filename)
|
||||||
|
|
||||||
|
if not target_path.exists():
|
||||||
|
raise FileNotFoundError(
|
||||||
|
(
|
||||||
|
f'No intermediate results for action >>{action_name}<< '
|
||||||
|
f'under >>{target_path}<< found'
|
||||||
|
)
|
||||||
|
)
|
||||||
|
# results should be tuple, but that is not guaranteed
|
||||||
|
result_loaded = cast(tuple[Any, ...], load_pickle(target_path))
|
||||||
|
if not isinstance(result_loaded, tuple):
|
||||||
|
raise TypeError(f'Loaded results must be tuple, not {type(result_loaded)}')
|
||||||
|
|
||||||
|
return result_loaded
|
||||||
|
|
||||||
|
def save_step(
|
||||||
|
self,
|
||||||
|
action_idx: int,
|
||||||
|
filename: str | None,
|
||||||
|
) -> None:
|
||||||
|
target_path, _ = self.get_result_path(action_idx, filename)
|
||||||
|
save_pickle(obj=self._intermediate_result, path=target_path)
|
||||||
|
|
||||||
|
@override
|
||||||
|
def logic(
|
||||||
|
self,
|
||||||
|
starting_values: tuple[Any, ...] | None = None,
|
||||||
|
) -> tuple[Any, ...]:
|
||||||
|
first_performed: bool = False
|
||||||
|
|
||||||
|
for idx, (action, action_kwargs) in enumerate(zip(self.actions, self.actions_kwargs)):
|
||||||
|
if self.action_skip[idx]:
|
||||||
|
self.curr_proc_idx += 1
|
||||||
|
continue
|
||||||
|
|
||||||
|
# loading
|
||||||
|
if self.load_results[idx][0]:
|
||||||
|
filename = self.load_results[idx][1]
|
||||||
|
ret = self.load_step(action_idx=idx, filename=filename)
|
||||||
|
self._intermediate_result = ret
|
||||||
|
logger.info(
|
||||||
|
'[No Calculation] Loaded result for action >>%s<< successfully',
|
||||||
|
self.action_names[idx],
|
||||||
|
)
|
||||||
|
self.curr_proc_idx += 1
|
||||||
|
continue
|
||||||
|
# calculation
|
||||||
|
if not first_performed:
|
||||||
|
args = starting_values
|
||||||
|
first_performed = True
|
||||||
|
else:
|
||||||
|
args = ret
|
||||||
|
|
||||||
|
if args is not None:
|
||||||
|
ret = action(*args, **action_kwargs)
|
||||||
|
else:
|
||||||
|
ret = action(**action_kwargs)
|
||||||
|
|
||||||
|
if ret is not None and not isinstance(ret, tuple):
|
||||||
|
ret = (ret,)
|
||||||
|
ret = cast(tuple[Any, ...], ret)
|
||||||
|
# save intermediate result
|
||||||
|
self._intermediate_result = ret
|
||||||
|
# saving result locally, always save last action
|
||||||
|
if self.save_results[idx][0] or idx == (len(self.actions) - 1):
|
||||||
|
filename = self.save_results[idx][1]
|
||||||
|
self.save_step(action_idx=idx, filename=filename)
|
||||||
|
# processing tracking
|
||||||
|
self.curr_proc_idx += 1
|
||||||
|
|
||||||
|
return ret</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Helper class that provides a standard way to create an ABC using
|
||||||
|
inheritance.</p></div>
|
||||||
|
<h3>Ancestors</h3>
|
||||||
|
<ul class="hlist">
|
||||||
|
<li><a title="lang_main.pipelines.base.BasePipeline" href="#lang_main.pipelines.base.BasePipeline">BasePipeline</a></li>
|
||||||
|
<li>abc.ABC</li>
|
||||||
|
</ul>
|
||||||
|
<h3>Methods</h3>
|
||||||
|
<dl>
|
||||||
|
<dt id="lang_main.pipelines.base.Pipeline.add"><code class="name flex">
|
||||||
|
<span>def <span class="ident">add</span></span>(<span>self,<br>action: Callable,<br>action_kwargs: dict[str, Any] | None = None,<br>skip: bool = False,<br>save_result: bool = False,<br>load_result: bool = False,<br>filename: str | None = None) ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">@override
|
||||||
|
def add(
|
||||||
|
self,
|
||||||
|
action: Callable,
|
||||||
|
action_kwargs: dict[str, Any] | None = None,
|
||||||
|
skip: bool = False,
|
||||||
|
save_result: bool = False,
|
||||||
|
load_result: bool = False,
|
||||||
|
filename: str | None = None,
|
||||||
|
) -> None:
|
||||||
|
# check explicitly for function type
|
||||||
|
# if isinstance(action, FunctionType):
|
||||||
|
if action_kwargs is None:
|
||||||
|
action_kwargs = {}
|
||||||
|
|
||||||
|
if isinstance(action, Callable):
|
||||||
|
self.actions.append(action)
|
||||||
|
self.action_names.append(action.__name__)
|
||||||
|
self.actions_kwargs.append(action_kwargs.copy())
|
||||||
|
self.action_skip.append(skip)
|
||||||
|
self.save_results.append((save_result, filename))
|
||||||
|
self.load_results.append((load_result, filename))
|
||||||
|
else:
|
||||||
|
self.panic_wrong_action_type(action=action, compatible_type=Callable.__name__)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.pipelines.base.Pipeline.get_result_path"><code class="name flex">
|
||||||
|
<span>def <span class="ident">get_result_path</span></span>(<span>self, action_idx: int, filename: str | None) ‑> tuple[pathlib.Path, str]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def get_result_path(
|
||||||
|
self,
|
||||||
|
action_idx: int,
|
||||||
|
filename: str | None,
|
||||||
|
) -> tuple[Path, str]:
|
||||||
|
action_name = self.action_names[action_idx]
|
||||||
|
if filename is None:
|
||||||
|
target_filename = f'Pipe-{self.name}_Step-{self.curr_proc_idx}_{action_name}'
|
||||||
|
else:
|
||||||
|
target_filename = filename
|
||||||
|
target_path = self.working_dir.joinpath(target_filename).with_suffix('.pkl')
|
||||||
|
return target_path, action_name</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.pipelines.base.Pipeline.load_step"><code class="name flex">
|
||||||
|
<span>def <span class="ident">load_step</span></span>(<span>self, action_idx: int, filename: str | None) ‑> tuple[typing.Any, ...]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def load_step(
|
||||||
|
self,
|
||||||
|
action_idx: int,
|
||||||
|
filename: str | None,
|
||||||
|
) -> tuple[Any, ...]:
|
||||||
|
target_path, action_name = self.get_result_path(action_idx, filename)
|
||||||
|
|
||||||
|
if not target_path.exists():
|
||||||
|
raise FileNotFoundError(
|
||||||
|
(
|
||||||
|
f'No intermediate results for action >>{action_name}<< '
|
||||||
|
f'under >>{target_path}<< found'
|
||||||
|
)
|
||||||
|
)
|
||||||
|
# results should be tuple, but that is not guaranteed
|
||||||
|
result_loaded = cast(tuple[Any, ...], load_pickle(target_path))
|
||||||
|
if not isinstance(result_loaded, tuple):
|
||||||
|
raise TypeError(f'Loaded results must be tuple, not {type(result_loaded)}')
|
||||||
|
|
||||||
|
return result_loaded</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.pipelines.base.Pipeline.logic"><code class="name flex">
|
||||||
|
<span>def <span class="ident">logic</span></span>(<span>self, starting_values: tuple[Any, ...] | None = None) ‑> tuple[typing.Any, ...]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">@override
|
||||||
|
def logic(
|
||||||
|
self,
|
||||||
|
starting_values: tuple[Any, ...] | None = None,
|
||||||
|
) -> tuple[Any, ...]:
|
||||||
|
first_performed: bool = False
|
||||||
|
|
||||||
|
for idx, (action, action_kwargs) in enumerate(zip(self.actions, self.actions_kwargs)):
|
||||||
|
if self.action_skip[idx]:
|
||||||
|
self.curr_proc_idx += 1
|
||||||
|
continue
|
||||||
|
|
||||||
|
# loading
|
||||||
|
if self.load_results[idx][0]:
|
||||||
|
filename = self.load_results[idx][1]
|
||||||
|
ret = self.load_step(action_idx=idx, filename=filename)
|
||||||
|
self._intermediate_result = ret
|
||||||
|
logger.info(
|
||||||
|
'[No Calculation] Loaded result for action >>%s<< successfully',
|
||||||
|
self.action_names[idx],
|
||||||
|
)
|
||||||
|
self.curr_proc_idx += 1
|
||||||
|
continue
|
||||||
|
# calculation
|
||||||
|
if not first_performed:
|
||||||
|
args = starting_values
|
||||||
|
first_performed = True
|
||||||
|
else:
|
||||||
|
args = ret
|
||||||
|
|
||||||
|
if args is not None:
|
||||||
|
ret = action(*args, **action_kwargs)
|
||||||
|
else:
|
||||||
|
ret = action(**action_kwargs)
|
||||||
|
|
||||||
|
if ret is not None and not isinstance(ret, tuple):
|
||||||
|
ret = (ret,)
|
||||||
|
ret = cast(tuple[Any, ...], ret)
|
||||||
|
# save intermediate result
|
||||||
|
self._intermediate_result = ret
|
||||||
|
# saving result locally, always save last action
|
||||||
|
if self.save_results[idx][0] or idx == (len(self.actions) - 1):
|
||||||
|
filename = self.save_results[idx][1]
|
||||||
|
self.save_step(action_idx=idx, filename=filename)
|
||||||
|
# processing tracking
|
||||||
|
self.curr_proc_idx += 1
|
||||||
|
|
||||||
|
return ret</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.pipelines.base.Pipeline.save_step"><code class="name flex">
|
||||||
|
<span>def <span class="ident">save_step</span></span>(<span>self, action_idx: int, filename: str | None) ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def save_step(
|
||||||
|
self,
|
||||||
|
action_idx: int,
|
||||||
|
filename: str | None,
|
||||||
|
) -> None:
|
||||||
|
target_path, _ = self.get_result_path(action_idx, filename)
|
||||||
|
save_pickle(obj=self._intermediate_result, path=target_path)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
</dl>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.pipelines.base.PipelineContainer"><code class="flex name class">
|
||||||
|
<span>class <span class="ident">PipelineContainer</span></span>
|
||||||
|
<span>(</span><span>name: str, working_dir: Path)</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">class PipelineContainer(BasePipeline):
|
||||||
|
"""Container class for basic actions.
|
||||||
|
Basic actions are usually functions, which do not take any parameters
|
||||||
|
and return nothing. Indeed, if an action returns any values after its
|
||||||
|
procedure is finished, an error is raised. Therefore, PipelineContainers
|
||||||
|
can be seen as a concatenation of many (independent) simple procedures
|
||||||
|
which are executed in the order in which they were added to the pipe.
|
||||||
|
With a simple call of the ``run`` method the actions are performed.
|
||||||
|
Additionally, there is an option to skip actions which can be set in
|
||||||
|
the ``add`` method. This allows for easily configurable pipelines,
|
||||||
|
e.g., via a user configuration.
|
||||||
|
"""
|
||||||
|
|
||||||
|
def __init__(
|
||||||
|
self,
|
||||||
|
name: str,
|
||||||
|
working_dir: Path,
|
||||||
|
) -> None:
|
||||||
|
super().__init__(name=name, working_dir=working_dir)
|
||||||
|
|
||||||
|
@override
|
||||||
|
def add(
|
||||||
|
self,
|
||||||
|
action: Callable,
|
||||||
|
skip: bool = False,
|
||||||
|
) -> None:
|
||||||
|
if isinstance(action, Callable):
|
||||||
|
self.actions.append(action)
|
||||||
|
self.action_names.append(action.__name__)
|
||||||
|
self.action_skip.append(skip)
|
||||||
|
else:
|
||||||
|
self.panic_wrong_action_type(action=action, compatible_type=Callable.__name__)
|
||||||
|
|
||||||
|
@override
|
||||||
|
def logic(self) -> None:
|
||||||
|
for idx, (action, action_name) in enumerate(zip(self.actions, self.action_names)):
|
||||||
|
# loading
|
||||||
|
if self.action_skip[idx]:
|
||||||
|
logger.info('[No Calculation] Skipping >>%s<<...', action_name)
|
||||||
|
self.curr_proc_idx += 1
|
||||||
|
continue
|
||||||
|
# calculation
|
||||||
|
ret = action()
|
||||||
|
if ret is not None:
|
||||||
|
raise OutputInPipelineContainerError(
|
||||||
|
(
|
||||||
|
f'Output in PipelineContainers not allowed. Action {action_name} '
|
||||||
|
f'returned values in Container {self.name}.'
|
||||||
|
)
|
||||||
|
)
|
||||||
|
# processing tracking
|
||||||
|
self.curr_proc_idx += 1</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Container class for basic actions.
|
||||||
|
Basic actions are usually functions, which do not take any parameters
|
||||||
|
and return nothing. Indeed, if an action returns any values after its
|
||||||
|
procedure is finished, an error is raised. Therefore, PipelineContainers
|
||||||
|
can be seen as a concatenation of many (independent) simple procedures
|
||||||
|
which are executed in the order in which they were added to the pipe.
|
||||||
|
With a simple call of the <code>run</code> method the actions are performed.
|
||||||
|
Additionally, there is an option to skip actions which can be set in
|
||||||
|
the <code>add</code> method. This allows for easily configurable pipelines,
|
||||||
|
e.g., via a user configuration.</p></div>
|
||||||
|
<h3>Ancestors</h3>
|
||||||
|
<ul class="hlist">
|
||||||
|
<li><a title="lang_main.pipelines.base.BasePipeline" href="#lang_main.pipelines.base.BasePipeline">BasePipeline</a></li>
|
||||||
|
<li>abc.ABC</li>
|
||||||
|
</ul>
|
||||||
|
<h3>Methods</h3>
|
||||||
|
<dl>
|
||||||
|
<dt id="lang_main.pipelines.base.PipelineContainer.add"><code class="name flex">
|
||||||
|
<span>def <span class="ident">add</span></span>(<span>self, action: Callable, skip: bool = False) ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">@override
|
||||||
|
def add(
|
||||||
|
self,
|
||||||
|
action: Callable,
|
||||||
|
skip: bool = False,
|
||||||
|
) -> None:
|
||||||
|
if isinstance(action, Callable):
|
||||||
|
self.actions.append(action)
|
||||||
|
self.action_names.append(action.__name__)
|
||||||
|
self.action_skip.append(skip)
|
||||||
|
else:
|
||||||
|
self.panic_wrong_action_type(action=action, compatible_type=Callable.__name__)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.pipelines.base.PipelineContainer.logic"><code class="name flex">
|
||||||
|
<span>def <span class="ident">logic</span></span>(<span>self) ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">@override
|
||||||
|
def logic(self) -> None:
|
||||||
|
for idx, (action, action_name) in enumerate(zip(self.actions, self.action_names)):
|
||||||
|
# loading
|
||||||
|
if self.action_skip[idx]:
|
||||||
|
logger.info('[No Calculation] Skipping >>%s<<...', action_name)
|
||||||
|
self.curr_proc_idx += 1
|
||||||
|
continue
|
||||||
|
# calculation
|
||||||
|
ret = action()
|
||||||
|
if ret is not None:
|
||||||
|
raise OutputInPipelineContainerError(
|
||||||
|
(
|
||||||
|
f'Output in PipelineContainers not allowed. Action {action_name} '
|
||||||
|
f'returned values in Container {self.name}.'
|
||||||
|
)
|
||||||
|
)
|
||||||
|
# processing tracking
|
||||||
|
self.curr_proc_idx += 1</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
</dl>
|
||||||
|
</dd>
|
||||||
|
</dl>
|
||||||
|
</section>
|
||||||
|
</article>
|
||||||
|
<nav id="sidebar">
|
||||||
|
<div class="toc">
|
||||||
|
<ul></ul>
|
||||||
|
</div>
|
||||||
|
<ul id="index">
|
||||||
|
<li><h3>Super-module</h3>
|
||||||
|
<ul>
|
||||||
|
<li><code><a title="lang_main.pipelines" href="index.html">lang_main.pipelines</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
<li><h3><a href="#header-classes">Classes</a></h3>
|
||||||
|
<ul>
|
||||||
|
<li>
|
||||||
|
<h4><code><a title="lang_main.pipelines.base.BasePipeline" href="#lang_main.pipelines.base.BasePipeline">BasePipeline</a></code></h4>
|
||||||
|
<ul class="">
|
||||||
|
<li><code><a title="lang_main.pipelines.base.BasePipeline.add" href="#lang_main.pipelines.base.BasePipeline.add">add</a></code></li>
|
||||||
|
<li><code><a title="lang_main.pipelines.base.BasePipeline.logic" href="#lang_main.pipelines.base.BasePipeline.logic">logic</a></code></li>
|
||||||
|
<li><code><a title="lang_main.pipelines.base.BasePipeline.panic_wrong_action_type" href="#lang_main.pipelines.base.BasePipeline.panic_wrong_action_type">panic_wrong_action_type</a></code></li>
|
||||||
|
<li><code><a title="lang_main.pipelines.base.BasePipeline.post_run" href="#lang_main.pipelines.base.BasePipeline.post_run">post_run</a></code></li>
|
||||||
|
<li><code><a title="lang_main.pipelines.base.BasePipeline.prep_run" href="#lang_main.pipelines.base.BasePipeline.prep_run">prep_run</a></code></li>
|
||||||
|
<li><code><a title="lang_main.pipelines.base.BasePipeline.run" href="#lang_main.pipelines.base.BasePipeline.run">run</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
<li>
|
||||||
|
<h4><code><a title="lang_main.pipelines.base.Pipeline" href="#lang_main.pipelines.base.Pipeline">Pipeline</a></code></h4>
|
||||||
|
<ul class="">
|
||||||
|
<li><code><a title="lang_main.pipelines.base.Pipeline.add" href="#lang_main.pipelines.base.Pipeline.add">add</a></code></li>
|
||||||
|
<li><code><a title="lang_main.pipelines.base.Pipeline.get_result_path" href="#lang_main.pipelines.base.Pipeline.get_result_path">get_result_path</a></code></li>
|
||||||
|
<li><code><a title="lang_main.pipelines.base.Pipeline.load_step" href="#lang_main.pipelines.base.Pipeline.load_step">load_step</a></code></li>
|
||||||
|
<li><code><a title="lang_main.pipelines.base.Pipeline.logic" href="#lang_main.pipelines.base.Pipeline.logic">logic</a></code></li>
|
||||||
|
<li><code><a title="lang_main.pipelines.base.Pipeline.save_step" href="#lang_main.pipelines.base.Pipeline.save_step">save_step</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
<li>
|
||||||
|
<h4><code><a title="lang_main.pipelines.base.PipelineContainer" href="#lang_main.pipelines.base.PipelineContainer">PipelineContainer</a></code></h4>
|
||||||
|
<ul class="">
|
||||||
|
<li><code><a title="lang_main.pipelines.base.PipelineContainer.add" href="#lang_main.pipelines.base.PipelineContainer.add">add</a></code></li>
|
||||||
|
<li><code><a title="lang_main.pipelines.base.PipelineContainer.logic" href="#lang_main.pipelines.base.PipelineContainer.logic">logic</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
</ul>
|
||||||
|
</nav>
|
||||||
|
</main>
|
||||||
|
<footer id="footer">
|
||||||
|
<p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.11.5</a>.</p>
|
||||||
|
</footer>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
83
docs/lang_main/pipelines/index.html
Normal file
83
docs/lang_main/pipelines/index.html
Normal file
@ -0,0 +1,83 @@
|
|||||||
|
<!doctype html>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="utf-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1">
|
||||||
|
<meta name="generator" content="pdoc3 0.11.5">
|
||||||
|
<title>lang_main.pipelines API documentation</title>
|
||||||
|
<meta name="description" content="">
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/sanitize.min.css" integrity="sha512-y1dtMcuvtTMJc1yPgEqF0ZjQbhnc/bFhyvIyVNb9Zk5mIGtqVaAB1Ttl28su8AvFMOY0EwRbAe+HCLqj6W7/KA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/typography.min.css" integrity="sha512-Y1DYSb995BAfxobCkKepB1BqJJTPrOp3zPL74AWFugHHmmdcvO+C48WLrUOlhGMc0QG7AE3f7gmvvcrmX2fDoA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/styles/default.min.css" crossorigin>
|
||||||
|
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:1.5em;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:2em 0 .50em 0}h3{font-size:1.4em;margin:1.6em 0 .7em 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .2s ease-in-out}a:visited{color:#503}a:hover{color:#b62}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900;font-weight:bold}pre code{font-size:.8em;line-height:1.4em;padding:1em;display:block}code{background:#f3f3f3;font-family:"DejaVu Sans Mono",monospace;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source > summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible;min-width:max-content}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em 1em;margin:1em 0}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
|
||||||
|
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul ul{padding-left:1em}.toc > ul > li{margin-top:.5em}}</style>
|
||||||
|
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
|
||||||
|
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/highlight.min.js" integrity="sha512-D9gUyxqja7hBtkWpPWGt9wfbfaMGVt9gnyCvYa+jojwwPHLCzUm5i8rpk7vD7wNee9bA35eYIjobYPaQuKS1MQ==" crossorigin></script>
|
||||||
|
<script>window.addEventListener('DOMContentLoaded', () => {
|
||||||
|
hljs.configure({languages: ['bash', 'css', 'diff', 'graphql', 'ini', 'javascript', 'json', 'plaintext', 'python', 'python-repl', 'rust', 'shell', 'sql', 'typescript', 'xml', 'yaml']});
|
||||||
|
hljs.highlightAll();
|
||||||
|
/* Collapse source docstrings */
|
||||||
|
setTimeout(() => {
|
||||||
|
[...document.querySelectorAll('.hljs.language-python > .hljs-string')]
|
||||||
|
.filter(el => el.innerHTML.length > 200 && ['"""', "'''"].includes(el.innerHTML.substring(0, 3)))
|
||||||
|
.forEach(el => {
|
||||||
|
let d = document.createElement('details');
|
||||||
|
d.classList.add('hljs-string');
|
||||||
|
d.innerHTML = '<summary>"""</summary>' + el.innerHTML.substring(3);
|
||||||
|
el.replaceWith(d);
|
||||||
|
});
|
||||||
|
}, 100);
|
||||||
|
})</script>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<main>
|
||||||
|
<article id="content">
|
||||||
|
<header>
|
||||||
|
<h1 class="title">Module <code>lang_main.pipelines</code></h1>
|
||||||
|
</header>
|
||||||
|
<section id="section-intro">
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
<h2 class="section-title" id="header-submodules">Sub-modules</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code class="name"><a title="lang_main.pipelines.base" href="base.html">lang_main.pipelines.base</a></code></dt>
|
||||||
|
<dd>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt><code class="name"><a title="lang_main.pipelines.predefined" href="predefined.html">lang_main.pipelines.predefined</a></code></dt>
|
||||||
|
<dd>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
</dl>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
</article>
|
||||||
|
<nav id="sidebar">
|
||||||
|
<div class="toc">
|
||||||
|
<ul></ul>
|
||||||
|
</div>
|
||||||
|
<ul id="index">
|
||||||
|
<li><h3>Super-module</h3>
|
||||||
|
<ul>
|
||||||
|
<li><code><a title="lang_main" href="../index.html">lang_main</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
<li><h3><a href="#header-submodules">Sub-modules</a></h3>
|
||||||
|
<ul>
|
||||||
|
<li><code><a title="lang_main.pipelines.base" href="base.html">lang_main.pipelines.base</a></code></li>
|
||||||
|
<li><code><a title="lang_main.pipelines.predefined" href="predefined.html">lang_main.pipelines.predefined</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
</ul>
|
||||||
|
</nav>
|
||||||
|
</main>
|
||||||
|
<footer id="footer">
|
||||||
|
<p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.11.5</a>.</p>
|
||||||
|
</footer>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
386
docs/lang_main/pipelines/predefined.html
Normal file
386
docs/lang_main/pipelines/predefined.html
Normal file
@ -0,0 +1,386 @@
|
|||||||
|
<!doctype html>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="utf-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1">
|
||||||
|
<meta name="generator" content="pdoc3 0.11.5">
|
||||||
|
<title>lang_main.pipelines.predefined API documentation</title>
|
||||||
|
<meta name="description" content="">
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/sanitize.min.css" integrity="sha512-y1dtMcuvtTMJc1yPgEqF0ZjQbhnc/bFhyvIyVNb9Zk5mIGtqVaAB1Ttl28su8AvFMOY0EwRbAe+HCLqj6W7/KA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/typography.min.css" integrity="sha512-Y1DYSb995BAfxobCkKepB1BqJJTPrOp3zPL74AWFugHHmmdcvO+C48WLrUOlhGMc0QG7AE3f7gmvvcrmX2fDoA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/styles/default.min.css" crossorigin>
|
||||||
|
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:1.5em;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:2em 0 .50em 0}h3{font-size:1.4em;margin:1.6em 0 .7em 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .2s ease-in-out}a:visited{color:#503}a:hover{color:#b62}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900;font-weight:bold}pre code{font-size:.8em;line-height:1.4em;padding:1em;display:block}code{background:#f3f3f3;font-family:"DejaVu Sans Mono",monospace;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source > summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible;min-width:max-content}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em 1em;margin:1em 0}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
|
||||||
|
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul ul{padding-left:1em}.toc > ul > li{margin-top:.5em}}</style>
|
||||||
|
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
|
||||||
|
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/highlight.min.js" integrity="sha512-D9gUyxqja7hBtkWpPWGt9wfbfaMGVt9gnyCvYa+jojwwPHLCzUm5i8rpk7vD7wNee9bA35eYIjobYPaQuKS1MQ==" crossorigin></script>
|
||||||
|
<script>window.addEventListener('DOMContentLoaded', () => {
|
||||||
|
hljs.configure({languages: ['bash', 'css', 'diff', 'graphql', 'ini', 'javascript', 'json', 'plaintext', 'python', 'python-repl', 'rust', 'shell', 'sql', 'typescript', 'xml', 'yaml']});
|
||||||
|
hljs.highlightAll();
|
||||||
|
/* Collapse source docstrings */
|
||||||
|
setTimeout(() => {
|
||||||
|
[...document.querySelectorAll('.hljs.language-python > .hljs-string')]
|
||||||
|
.filter(el => el.innerHTML.length > 200 && ['"""', "'''"].includes(el.innerHTML.substring(0, 3)))
|
||||||
|
.forEach(el => {
|
||||||
|
let d = document.createElement('details');
|
||||||
|
d.classList.add('hljs-string');
|
||||||
|
d.innerHTML = '<summary>"""</summary>' + el.innerHTML.substring(3);
|
||||||
|
el.replaceWith(d);
|
||||||
|
});
|
||||||
|
}, 100);
|
||||||
|
})</script>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<main>
|
||||||
|
<article id="content">
|
||||||
|
<header>
|
||||||
|
<h1 class="title">Module <code>lang_main.pipelines.predefined</code></h1>
|
||||||
|
</header>
|
||||||
|
<section id="section-intro">
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
<h2 class="section-title" id="header-functions">Functions</h2>
|
||||||
|
<dl>
|
||||||
|
<dt id="lang_main.pipelines.predefined.build_base_target_feature_pipe"><code class="name flex">
|
||||||
|
<span>def <span class="ident">build_base_target_feature_pipe</span></span>(<span>) ‑> <a title="lang_main.pipelines.base.Pipeline" href="base.html#lang_main.pipelines.base.Pipeline">Pipeline</a></span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def build_base_target_feature_pipe() -> Pipeline:
|
||||||
|
pipe_target_feat = Pipeline(name='Target_Feature', working_dir=SAVE_PATH_FOLDER)
|
||||||
|
pipe_target_feat.add(
|
||||||
|
load_raw_data,
|
||||||
|
{
|
||||||
|
'date_cols': DATE_COLS,
|
||||||
|
},
|
||||||
|
)
|
||||||
|
pipe_target_feat.add(remove_duplicates)
|
||||||
|
pipe_target_feat.add(remove_NA, save_result=True)
|
||||||
|
pipe_target_feat.add(
|
||||||
|
entry_wise_cleansing,
|
||||||
|
{
|
||||||
|
'target_features': (TARGET_FEATURE,),
|
||||||
|
'cleansing_func': clean_string_slim,
|
||||||
|
},
|
||||||
|
save_result=True,
|
||||||
|
filename=EntryPoints.TIMELINE,
|
||||||
|
)
|
||||||
|
pipe_target_feat.add(
|
||||||
|
analyse_feature,
|
||||||
|
{
|
||||||
|
'target_feature': TARGET_FEATURE,
|
||||||
|
},
|
||||||
|
save_result=True,
|
||||||
|
)
|
||||||
|
|
||||||
|
return pipe_target_feat</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.pipelines.predefined.build_merge_duplicates_pipe"><code class="name flex">
|
||||||
|
<span>def <span class="ident">build_merge_duplicates_pipe</span></span>(<span>) ‑> <a title="lang_main.pipelines.base.Pipeline" href="base.html#lang_main.pipelines.base.Pipeline">Pipeline</a></span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def build_merge_duplicates_pipe() -> Pipeline:
|
||||||
|
pipe_merge = Pipeline(name='Merge_Duplicates', working_dir=SAVE_PATH_FOLDER)
|
||||||
|
pipe_merge.add(
|
||||||
|
numeric_pre_filter_feature,
|
||||||
|
{
|
||||||
|
'feature': 'len',
|
||||||
|
'bound_lower': THRESHOLD_AMOUNT_CHARACTERS,
|
||||||
|
'bound_upper': None,
|
||||||
|
},
|
||||||
|
)
|
||||||
|
pipe_merge.add(
|
||||||
|
merge_similarity_duplicates,
|
||||||
|
{
|
||||||
|
'model': STFR_MODEL,
|
||||||
|
'cos_sim_threshold': THRESHOLD_SIMILARITY,
|
||||||
|
},
|
||||||
|
save_result=True,
|
||||||
|
filename=EntryPoints.TOKEN_ANALYSIS,
|
||||||
|
)
|
||||||
|
|
||||||
|
return pipe_merge</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.pipelines.predefined.build_timeline_pipe"><code class="name flex">
|
||||||
|
<span>def <span class="ident">build_timeline_pipe</span></span>(<span>) ‑> <a title="lang_main.pipelines.base.Pipeline" href="base.html#lang_main.pipelines.base.Pipeline">Pipeline</a></span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def build_timeline_pipe() -> Pipeline:
|
||||||
|
pipe_timeline = Pipeline(name='Timeline_Analysis', working_dir=SAVE_PATH_FOLDER)
|
||||||
|
pipe_timeline.add(
|
||||||
|
cleanup_descriptions,
|
||||||
|
{
|
||||||
|
'properties': ['ErledigungsBeschreibung'],
|
||||||
|
},
|
||||||
|
)
|
||||||
|
pipe_timeline.add(
|
||||||
|
calc_delta_to_repair,
|
||||||
|
{
|
||||||
|
'date_feature_start': 'ErstellungsDatum',
|
||||||
|
'date_feature_end': 'ErledigungsDatum',
|
||||||
|
'name_delta_feature': NAME_DELTA_FEAT_TO_REPAIR,
|
||||||
|
'convert_to_days': True,
|
||||||
|
},
|
||||||
|
save_result=True,
|
||||||
|
filename=EntryPoints.TIMELINE_POST,
|
||||||
|
)
|
||||||
|
pipe_timeline.add(
|
||||||
|
remove_non_relevant_obj_ids,
|
||||||
|
{
|
||||||
|
'thresh_unique_feat_per_id': THRESHOLD_UNIQUE_TEXTS,
|
||||||
|
'feature_uniqueness': UNIQUE_CRITERION_FEATURE,
|
||||||
|
'feature_obj_id': FEATURE_NAME_OBJ_ID,
|
||||||
|
},
|
||||||
|
save_result=True,
|
||||||
|
)
|
||||||
|
pipe_timeline.add(
|
||||||
|
generate_model_input,
|
||||||
|
{
|
||||||
|
'target_feature_name': 'nlp_model_input',
|
||||||
|
'model_input_features': MODEL_INPUT_FEATURES,
|
||||||
|
},
|
||||||
|
)
|
||||||
|
pipe_timeline.add(
|
||||||
|
filter_activities_per_obj_id,
|
||||||
|
{
|
||||||
|
'activity_feature': ACTIVITY_FEATURE,
|
||||||
|
'relevant_activity_types': ACTIVITY_TYPES,
|
||||||
|
'feature_obj_id': FEATURE_NAME_OBJ_ID,
|
||||||
|
'threshold_num_activities': THRESHOLD_NUM_ACTIVITIES,
|
||||||
|
},
|
||||||
|
)
|
||||||
|
pipe_timeline.add(
|
||||||
|
get_timeline_candidates,
|
||||||
|
{
|
||||||
|
'model': STFR_MODEL,
|
||||||
|
'cos_sim_threshold': THRESHOLD_TIMELINE_SIMILARITY,
|
||||||
|
'feature_obj_id': FEATURE_NAME_OBJ_ID,
|
||||||
|
'feature_obj_text': FEATURE_NAME_OBJ_TEXT,
|
||||||
|
'model_input_feature': 'nlp_model_input',
|
||||||
|
},
|
||||||
|
save_result=True,
|
||||||
|
filename=EntryPoints.TIMELINE_CANDS,
|
||||||
|
)
|
||||||
|
|
||||||
|
return pipe_timeline</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.pipelines.predefined.build_tk_graph_pipe"><code class="name flex">
|
||||||
|
<span>def <span class="ident">build_tk_graph_pipe</span></span>(<span>) ‑> <a title="lang_main.pipelines.base.Pipeline" href="base.html#lang_main.pipelines.base.Pipeline">Pipeline</a></span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def build_tk_graph_pipe() -> Pipeline:
|
||||||
|
pipe_token_analysis = Pipeline(name='Token_Analysis', working_dir=SAVE_PATH_FOLDER)
|
||||||
|
pipe_token_analysis.add(
|
||||||
|
build_token_graph,
|
||||||
|
{
|
||||||
|
'model': SPACY_MODEL,
|
||||||
|
'target_feature': 'entry',
|
||||||
|
'weights_feature': 'num_occur',
|
||||||
|
'batch_idx_feature': 'batched_idxs',
|
||||||
|
'build_map': False,
|
||||||
|
'batch_size_model': 50,
|
||||||
|
},
|
||||||
|
save_result=True,
|
||||||
|
filename=EntryPoints.TK_GRAPH_POST,
|
||||||
|
)
|
||||||
|
|
||||||
|
return pipe_token_analysis</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.pipelines.predefined.build_tk_graph_post_pipe"><code class="name flex">
|
||||||
|
<span>def <span class="ident">build_tk_graph_post_pipe</span></span>(<span>) ‑> <a title="lang_main.pipelines.base.Pipeline" href="base.html#lang_main.pipelines.base.Pipeline">Pipeline</a></span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def build_tk_graph_post_pipe() -> Pipeline:
|
||||||
|
pipe_graph_postprocessing = Pipeline(
|
||||||
|
name='Graph_Postprocessing', working_dir=SAVE_PATH_FOLDER
|
||||||
|
)
|
||||||
|
pipe_graph_postprocessing.add(
|
||||||
|
graphs.filter_graph_by_number_edges,
|
||||||
|
{
|
||||||
|
'limit': MAX_EDGE_NUMBER,
|
||||||
|
'property': 'weight',
|
||||||
|
},
|
||||||
|
)
|
||||||
|
pipe_graph_postprocessing.add(
|
||||||
|
graphs.filter_graph_by_node_degree,
|
||||||
|
{
|
||||||
|
'bound_lower': 1,
|
||||||
|
'bound_upper': None,
|
||||||
|
},
|
||||||
|
)
|
||||||
|
pipe_graph_postprocessing.add(
|
||||||
|
graphs.static_graph_analysis,
|
||||||
|
save_result=True,
|
||||||
|
filename=EntryPoints.TK_GRAPH_ANALYSIS,
|
||||||
|
)
|
||||||
|
|
||||||
|
return pipe_graph_postprocessing</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.pipelines.predefined.build_tk_graph_render_pipe"><code class="name flex">
|
||||||
|
<span>def <span class="ident">build_tk_graph_render_pipe</span></span>(<span>with_subgraphs: bool,<br>export_folder: pathlib.Path = WindowsPath('A:/Arbeitsaufgaben/lang-data/out'),<br>base_network_name: str = 'token_graph') ‑> <a title="lang_main.pipelines.base.Pipeline" href="base.html#lang_main.pipelines.base.Pipeline">Pipeline</a></span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def build_tk_graph_render_pipe(
|
||||||
|
with_subgraphs: bool,
|
||||||
|
export_folder: Path = SAVE_PATH_FOLDER,
|
||||||
|
base_network_name: str = CYTO_BASE_NETWORK_NAME,
|
||||||
|
) -> Pipeline:
|
||||||
|
# optional dependency: late import
|
||||||
|
# raises exception if necessary modules are not found
|
||||||
|
try:
|
||||||
|
from lang_main.render import cytoscape as cyto
|
||||||
|
except ImportError:
|
||||||
|
raise ImportError(
|
||||||
|
(
|
||||||
|
'Dependencies for Cytoscape interaction not found.'
|
||||||
|
'Install package with optional dependencies.'
|
||||||
|
)
|
||||||
|
)
|
||||||
|
|
||||||
|
pipe_graph_rendering = Pipeline(
|
||||||
|
name='Graph_Static-Rendering',
|
||||||
|
working_dir=SAVE_PATH_FOLDER,
|
||||||
|
)
|
||||||
|
pipe_graph_rendering.add(
|
||||||
|
cyto.import_to_cytoscape,
|
||||||
|
{
|
||||||
|
'network_name': base_network_name,
|
||||||
|
},
|
||||||
|
)
|
||||||
|
pipe_graph_rendering.add(
|
||||||
|
cyto.layout_network,
|
||||||
|
{
|
||||||
|
'network_name': base_network_name,
|
||||||
|
},
|
||||||
|
)
|
||||||
|
pipe_graph_rendering.add(
|
||||||
|
cyto.apply_style_to_network,
|
||||||
|
{
|
||||||
|
'network_name': base_network_name,
|
||||||
|
},
|
||||||
|
)
|
||||||
|
pipe_graph_rendering.add(
|
||||||
|
cyto.export_network_to_image,
|
||||||
|
{
|
||||||
|
'filename': base_network_name,
|
||||||
|
'target_folder': export_folder,
|
||||||
|
'network_name': base_network_name,
|
||||||
|
},
|
||||||
|
)
|
||||||
|
|
||||||
|
if with_subgraphs:
|
||||||
|
pipe_graph_rendering.add(
|
||||||
|
cyto.get_subgraph_node_selection,
|
||||||
|
{
|
||||||
|
'network_name': base_network_name,
|
||||||
|
},
|
||||||
|
)
|
||||||
|
pipe_graph_rendering.add(
|
||||||
|
cyto.build_subnetworks,
|
||||||
|
{
|
||||||
|
'export_image': True,
|
||||||
|
'target_folder': export_folder,
|
||||||
|
'network_name': base_network_name,
|
||||||
|
},
|
||||||
|
)
|
||||||
|
|
||||||
|
return pipe_graph_rendering</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.pipelines.predefined.build_tk_graph_rescaling_pipe"><code class="name flex">
|
||||||
|
<span>def <span class="ident">build_tk_graph_rescaling_pipe</span></span>(<span>save_result: bool, exit_point: lang_main.types.EntryPoints) ‑> <a title="lang_main.pipelines.base.Pipeline" href="base.html#lang_main.pipelines.base.Pipeline">Pipeline</a></span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def build_tk_graph_rescaling_pipe(
|
||||||
|
save_result: bool,
|
||||||
|
exit_point: EntryPoints,
|
||||||
|
) -> Pipeline:
|
||||||
|
pipe_graph_rescaling = Pipeline(name='Graph_Rescaling', working_dir=SAVE_PATH_FOLDER)
|
||||||
|
pipe_graph_rescaling.add(
|
||||||
|
graphs.pipe_rescale_graph_edge_weights,
|
||||||
|
)
|
||||||
|
pipe_graph_rescaling.add(
|
||||||
|
graphs.pipe_add_graph_metrics,
|
||||||
|
save_result=save_result,
|
||||||
|
filename=exit_point,
|
||||||
|
)
|
||||||
|
|
||||||
|
return pipe_graph_rescaling</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
</dl>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
</article>
|
||||||
|
<nav id="sidebar">
|
||||||
|
<div class="toc">
|
||||||
|
<ul></ul>
|
||||||
|
</div>
|
||||||
|
<ul id="index">
|
||||||
|
<li><h3>Super-module</h3>
|
||||||
|
<ul>
|
||||||
|
<li><code><a title="lang_main.pipelines" href="index.html">lang_main.pipelines</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
<li><h3><a href="#header-functions">Functions</a></h3>
|
||||||
|
<ul class="">
|
||||||
|
<li><code><a title="lang_main.pipelines.predefined.build_base_target_feature_pipe" href="#lang_main.pipelines.predefined.build_base_target_feature_pipe">build_base_target_feature_pipe</a></code></li>
|
||||||
|
<li><code><a title="lang_main.pipelines.predefined.build_merge_duplicates_pipe" href="#lang_main.pipelines.predefined.build_merge_duplicates_pipe">build_merge_duplicates_pipe</a></code></li>
|
||||||
|
<li><code><a title="lang_main.pipelines.predefined.build_timeline_pipe" href="#lang_main.pipelines.predefined.build_timeline_pipe">build_timeline_pipe</a></code></li>
|
||||||
|
<li><code><a title="lang_main.pipelines.predefined.build_tk_graph_pipe" href="#lang_main.pipelines.predefined.build_tk_graph_pipe">build_tk_graph_pipe</a></code></li>
|
||||||
|
<li><code><a title="lang_main.pipelines.predefined.build_tk_graph_post_pipe" href="#lang_main.pipelines.predefined.build_tk_graph_post_pipe">build_tk_graph_post_pipe</a></code></li>
|
||||||
|
<li><code><a title="lang_main.pipelines.predefined.build_tk_graph_render_pipe" href="#lang_main.pipelines.predefined.build_tk_graph_render_pipe">build_tk_graph_render_pipe</a></code></li>
|
||||||
|
<li><code><a title="lang_main.pipelines.predefined.build_tk_graph_rescaling_pipe" href="#lang_main.pipelines.predefined.build_tk_graph_rescaling_pipe">build_tk_graph_rescaling_pipe</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
</ul>
|
||||||
|
</nav>
|
||||||
|
</main>
|
||||||
|
<footer id="footer">
|
||||||
|
<p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.11.5</a>.</p>
|
||||||
|
</footer>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
797
docs/lang_main/render/cytoscape.html
Normal file
797
docs/lang_main/render/cytoscape.html
Normal file
@ -0,0 +1,797 @@
|
|||||||
|
<!doctype html>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="utf-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1">
|
||||||
|
<meta name="generator" content="pdoc3 0.11.5">
|
||||||
|
<title>lang_main.render.cytoscape API documentation</title>
|
||||||
|
<meta name="description" content="">
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/sanitize.min.css" integrity="sha512-y1dtMcuvtTMJc1yPgEqF0ZjQbhnc/bFhyvIyVNb9Zk5mIGtqVaAB1Ttl28su8AvFMOY0EwRbAe+HCLqj6W7/KA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/typography.min.css" integrity="sha512-Y1DYSb995BAfxobCkKepB1BqJJTPrOp3zPL74AWFugHHmmdcvO+C48WLrUOlhGMc0QG7AE3f7gmvvcrmX2fDoA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/styles/default.min.css" crossorigin>
|
||||||
|
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:1.5em;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:2em 0 .50em 0}h3{font-size:1.4em;margin:1.6em 0 .7em 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .2s ease-in-out}a:visited{color:#503}a:hover{color:#b62}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900;font-weight:bold}pre code{font-size:.8em;line-height:1.4em;padding:1em;display:block}code{background:#f3f3f3;font-family:"DejaVu Sans Mono",monospace;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source > summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible;min-width:max-content}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em 1em;margin:1em 0}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
|
||||||
|
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul ul{padding-left:1em}.toc > ul > li{margin-top:.5em}}</style>
|
||||||
|
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
|
||||||
|
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/highlight.min.js" integrity="sha512-D9gUyxqja7hBtkWpPWGt9wfbfaMGVt9gnyCvYa+jojwwPHLCzUm5i8rpk7vD7wNee9bA35eYIjobYPaQuKS1MQ==" crossorigin></script>
|
||||||
|
<script>window.addEventListener('DOMContentLoaded', () => {
|
||||||
|
hljs.configure({languages: ['bash', 'css', 'diff', 'graphql', 'ini', 'javascript', 'json', 'plaintext', 'python', 'python-repl', 'rust', 'shell', 'sql', 'typescript', 'xml', 'yaml']});
|
||||||
|
hljs.highlightAll();
|
||||||
|
/* Collapse source docstrings */
|
||||||
|
setTimeout(() => {
|
||||||
|
[...document.querySelectorAll('.hljs.language-python > .hljs-string')]
|
||||||
|
.filter(el => el.innerHTML.length > 200 && ['"""', "'''"].includes(el.innerHTML.substring(0, 3)))
|
||||||
|
.forEach(el => {
|
||||||
|
let d = document.createElement('details');
|
||||||
|
d.classList.add('hljs-string');
|
||||||
|
d.innerHTML = '<summary>"""</summary>' + el.innerHTML.substring(3);
|
||||||
|
el.replaceWith(d);
|
||||||
|
});
|
||||||
|
}, 100);
|
||||||
|
})</script>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<main>
|
||||||
|
<article id="content">
|
||||||
|
<header>
|
||||||
|
<h1 class="title">Module <code>lang_main.render.cytoscape</code></h1>
|
||||||
|
</header>
|
||||||
|
<section id="section-intro">
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
<h2 class="section-title" id="header-functions">Functions</h2>
|
||||||
|
<dl>
|
||||||
|
<dt id="lang_main.render.cytoscape.analyse_network"><code class="name flex">
|
||||||
|
<span>def <span class="ident">analyse_network</span></span>(<span>property_degree_weighted: str = 'degree_weighted',<br>network_name: str = 'token_graph') ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def analyse_network(
|
||||||
|
property_degree_weighted: str = PROPERTY_NAME_DEGREE_WEIGHTED,
|
||||||
|
network_name: str = CYTO_BASE_NETWORK_NAME,
|
||||||
|
) -> None:
|
||||||
|
node_table = p4c.get_table_columns(table='node', network=network_name)
|
||||||
|
net_analyse_possible: bool = True
|
||||||
|
if len(node_table) < 4: # pragma: no cover
|
||||||
|
net_analyse_possible = False
|
||||||
|
|
||||||
|
if net_analyse_possible:
|
||||||
|
p4c.analyze_network(directed=False)
|
||||||
|
node_table = p4c.get_table_columns(table='node', network=network_name)
|
||||||
|
node_table['stress_norm'] = node_table['Stress'] / node_table['Stress'].max()
|
||||||
|
node_table[CYTO_SELECTION_PROPERTY] = (
|
||||||
|
node_table[property_degree_weighted]
|
||||||
|
* node_table['BetweennessCentrality']
|
||||||
|
* node_table['stress_norm']
|
||||||
|
)
|
||||||
|
else: # pragma: no cover
|
||||||
|
node_table[CYTO_SELECTION_PROPERTY] = 1
|
||||||
|
|
||||||
|
p4c.load_table_data(node_table, data_key_column='name', network=network_name)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.render.cytoscape.apply_style_to_network"><code class="name flex">
|
||||||
|
<span>def <span class="ident">apply_style_to_network</span></span>(<span>style_name: str = 'lang_main',<br>pth_to_stylesheet: pathlib.Path = WindowsPath('A:/Arbeitsaufgaben/lang-main/src/lang_main/cytoscape_config/lang_main.xml'),<br>network_name: str = 'token_graph',<br>node_size_property: str = 'node_selection',<br>min_node_size: int = 15,<br>max_node_size: int = 40,<br>sandbox_name: str = 'lang_main') ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def apply_style_to_network(
|
||||||
|
style_name: str = CYTO_STYLESHEET_NAME,
|
||||||
|
pth_to_stylesheet: Path = CYTO_PATH_STYLESHEET,
|
||||||
|
network_name: str = CYTO_BASE_NETWORK_NAME,
|
||||||
|
node_size_property: str = CYTO_SELECTION_PROPERTY,
|
||||||
|
min_node_size: int = 15,
|
||||||
|
max_node_size: int = 40,
|
||||||
|
sandbox_name: str = CYTO_SANDBOX_NAME,
|
||||||
|
) -> None:
|
||||||
|
"""Cytoscape: apply a chosen Cytoscape style to the defined network
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
style_name : str, optional
|
||||||
|
Cytoscape name of the style which should be applied,
|
||||||
|
by default CYTO_STYLESHEET_NAME
|
||||||
|
pth_to_stylesheet : Path, optional
|
||||||
|
path where the stylesheet definition in Cytoscape's XML format can
|
||||||
|
be found,
|
||||||
|
by default CYTO_PATH_STYLESHEET
|
||||||
|
network_name : str, optional
|
||||||
|
network to apply the style on, by default CYTO_BASE_NETWORK_NAME
|
||||||
|
|
||||||
|
Raises
|
||||||
|
------
|
||||||
|
FileNotFoundError
|
||||||
|
if provided stylesheet can not be found under the provided path
|
||||||
|
"""
|
||||||
|
logger.debug('Applying style to network...')
|
||||||
|
styles_avail = cast(list[str], p4c.get_visual_style_names())
|
||||||
|
logger.debug('Available styles: %s', styles_avail)
|
||||||
|
if style_name not in styles_avail:
|
||||||
|
if not pth_to_stylesheet.exists():
|
||||||
|
# existence for standard path verified at import, but not for other
|
||||||
|
# provided paths
|
||||||
|
raise FileNotFoundError(
|
||||||
|
f'Visual stylesheet for Cytoscape not found under: >>{pth_to_stylesheet}<<'
|
||||||
|
)
|
||||||
|
# send to sandbox
|
||||||
|
sandbox_filename = pth_to_stylesheet.name
|
||||||
|
p4c.sandbox_send_to(
|
||||||
|
source_file=pth_to_stylesheet,
|
||||||
|
dest_file=sandbox_filename,
|
||||||
|
overwrite=True,
|
||||||
|
sandbox_name=sandbox_name,
|
||||||
|
)
|
||||||
|
# load stylesheet
|
||||||
|
p4c.import_visual_styles(sandbox_filename)
|
||||||
|
|
||||||
|
p4c.set_visual_style(style_name, network=network_name)
|
||||||
|
# node size mapping, only if needed property is available
|
||||||
|
scheme = p4c.scheme_c_number_continuous(
|
||||||
|
start_value=min_node_size, end_value=max_node_size
|
||||||
|
)
|
||||||
|
node_size_map = p4c.gen_node_size_map(
|
||||||
|
node_size_property,
|
||||||
|
number_scheme=scheme,
|
||||||
|
mapping_type='c',
|
||||||
|
style_name=style_name,
|
||||||
|
default_number=min_node_size,
|
||||||
|
)
|
||||||
|
p4c.set_node_size_mapping(**node_size_map)
|
||||||
|
fit_content(network_name=network_name)
|
||||||
|
logger.debug('Style application to network successful.')</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Cytoscape: apply a chosen Cytoscape style to the defined network</p>
|
||||||
|
<h2 id="parameters">Parameters</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><strong><code>style_name</code></strong> : <code>str</code>, optional</dt>
|
||||||
|
<dd>Cytoscape name of the style which should be applied,
|
||||||
|
by default CYTO_STYLESHEET_NAME</dd>
|
||||||
|
<dt><strong><code>pth_to_stylesheet</code></strong> : <code>Path</code>, optional</dt>
|
||||||
|
<dd>path where the stylesheet definition in Cytoscape's XML format can
|
||||||
|
be found,
|
||||||
|
by default CYTO_PATH_STYLESHEET</dd>
|
||||||
|
<dt><strong><code>network_name</code></strong> : <code>str</code>, optional</dt>
|
||||||
|
<dd>network to apply the style on, by default CYTO_BASE_NETWORK_NAME</dd>
|
||||||
|
</dl>
|
||||||
|
<h2 id="raises">Raises</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code>FileNotFoundError</code></dt>
|
||||||
|
<dd>if provided stylesheet can not be found under the provided path</dd>
|
||||||
|
</dl></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.render.cytoscape.build_subnetworks"><code class="name flex">
|
||||||
|
<span>def <span class="ident">build_subnetworks</span></span>(<span>nodes_to_analyse: Iterable[int],<br>network_name: str = 'token_graph',<br>export_image: bool = True,<br>target_folder: pathlib.Path = WindowsPath('A:/Arbeitsaufgaben/lang-data/out')) ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def build_subnetworks(
|
||||||
|
nodes_to_analyse: Iterable[CytoNodeID],
|
||||||
|
network_name: str = CYTO_BASE_NETWORK_NAME,
|
||||||
|
export_image: bool = True,
|
||||||
|
target_folder: Path = SAVE_PATH_FOLDER,
|
||||||
|
) -> None:
|
||||||
|
"""Cytoscape: iteratively build subnetworks from a collection of nodes
|
||||||
|
and their respective neighbouring nodes
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
nodes_to_analyse : Iterable[CytoNodeID]
|
||||||
|
collection of nodes to make subnetworks from, for each node a dedicated
|
||||||
|
subnetwork will be generated
|
||||||
|
network_name : str, optional
|
||||||
|
network which contains the provided nodes,
|
||||||
|
by default CYTO_BASE_NETWORK_NAME
|
||||||
|
export_image : bool, optional
|
||||||
|
trigger image export of newly generated subnetworks, by default True
|
||||||
|
"""
|
||||||
|
logger.debug('Generating all subnetworks for node selection...')
|
||||||
|
for idx, node in enumerate(nodes_to_analyse):
|
||||||
|
select_neighbours_of_node(node=node, network_name=network_name)
|
||||||
|
make_subnetwork(
|
||||||
|
index=idx,
|
||||||
|
network_name=network_name,
|
||||||
|
export_image=export_image,
|
||||||
|
target_folder=target_folder,
|
||||||
|
)
|
||||||
|
logger.debug('Generation of all subnetworks for node selection successful.')</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Cytoscape: iteratively build subnetworks from a collection of nodes
|
||||||
|
and their respective neighbouring nodes</p>
|
||||||
|
<h2 id="parameters">Parameters</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><strong><code>nodes_to_analyse</code></strong> : <code>Iterable[CytoNodeID]</code></dt>
|
||||||
|
<dd>collection of nodes to make subnetworks from, for each node a dedicated
|
||||||
|
subnetwork will be generated</dd>
|
||||||
|
<dt><strong><code>network_name</code></strong> : <code>str</code>, optional</dt>
|
||||||
|
<dd>network which contains the provided nodes,
|
||||||
|
by default CYTO_BASE_NETWORK_NAME</dd>
|
||||||
|
<dt><strong><code>export_image</code></strong> : <code>bool</code>, optional</dt>
|
||||||
|
<dd>trigger image export of newly generated subnetworks, by default True</dd>
|
||||||
|
</dl></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.render.cytoscape.change_default_layout"><code class="name flex">
|
||||||
|
<span>def <span class="ident">change_default_layout</span></span>(<span>) ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def change_default_layout() -> None:
|
||||||
|
"""Cytoscape: resets the default layout to `grid` to accelerate the import process
|
||||||
|
(grid layout one of the fastest)
|
||||||
|
|
||||||
|
Raises
|
||||||
|
------
|
||||||
|
RequestException
|
||||||
|
API endpoint not reachable or CyREST operation not successful
|
||||||
|
"""
|
||||||
|
body: dict[str, str] = {'value': 'grid', 'key': 'layout.default'}
|
||||||
|
try:
|
||||||
|
p4c.cyrest_put('properties/cytoscape3.props/layout.default', body=body)
|
||||||
|
except RequestException as error:
|
||||||
|
logger.error('[CytoAPIConnection] Property change of default layout not successful.')
|
||||||
|
raise error</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Cytoscape: resets the default layout to <code>grid</code> to accelerate the import process
|
||||||
|
(grid layout one of the fastest)</p>
|
||||||
|
<h2 id="raises">Raises</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code>RequestException</code></dt>
|
||||||
|
<dd>API endpoint not reachable or CyREST operation not successful</dd>
|
||||||
|
</dl></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.render.cytoscape.export_network_to_image"><code class="name flex">
|
||||||
|
<span>def <span class="ident">export_network_to_image</span></span>(<span>filename: str,<br>target_folder: pathlib.Path = WindowsPath('A:/Arbeitsaufgaben/lang-data/out'),<br>filetype: Literal['JPEG', 'PDF', 'PNG', 'PS', 'SVG'] = 'SVG',<br>network_name: str = 'token_graph',<br>pdf_export_page_size: Literal['A0', 'A1', 'A2', 'A3', 'A4', 'A5', 'Auto', 'Legal', 'Letter', 'Tabloid'] = 'A4',<br>sandbox_name: str = 'lang_main') ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def export_network_to_image(
|
||||||
|
filename: str,
|
||||||
|
target_folder: Path = SAVE_PATH_FOLDER,
|
||||||
|
filetype: CytoExportFileTypes = 'SVG',
|
||||||
|
network_name: str = CYTO_BASE_NETWORK_NAME,
|
||||||
|
pdf_export_page_size: CytoExportPageSizes = 'A4',
|
||||||
|
sandbox_name: str = CYTO_SANDBOX_NAME,
|
||||||
|
) -> None:
|
||||||
|
"""Cytoscape: export current selected view as image
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
filename : str
|
||||||
|
export filename
|
||||||
|
filetype : CytoExportFileTypes, optional
|
||||||
|
export filetype supported by Cytoscape, by default 'SVG'
|
||||||
|
network_name : str, optional
|
||||||
|
network to export, by default CYTO_BASE_NETWORK_NAME
|
||||||
|
pdf_export_page_size : CytoExportPageSizes, optional
|
||||||
|
page size which should be used for PDF exports supported by Cytoscape,
|
||||||
|
by default 'A4'
|
||||||
|
"""
|
||||||
|
logger.debug('Exporting image to file...')
|
||||||
|
if not target_folder.exists(): # pragma: no cover
|
||||||
|
target_folder.mkdir(parents=True)
|
||||||
|
dst_file_pth = (target_folder / filename).with_suffix(f'.{filetype.lower()}')
|
||||||
|
|
||||||
|
text_as_font = True
|
||||||
|
if filetype == 'SVG':
|
||||||
|
text_as_font = False
|
||||||
|
|
||||||
|
# close non-necessary windows and fit graph in frame before image display
|
||||||
|
fit_content(network_name=network_name)
|
||||||
|
# image is generated in sandbox directory and transferred to target destination
|
||||||
|
# (preparation for remote instances of Cytoscape)
|
||||||
|
p4c.export_image(
|
||||||
|
filename=filename,
|
||||||
|
type=filetype,
|
||||||
|
network=network_name,
|
||||||
|
overwrite_file=True,
|
||||||
|
all_graphics_details=True,
|
||||||
|
export_text_as_font=text_as_font,
|
||||||
|
page_size=pdf_export_page_size,
|
||||||
|
)
|
||||||
|
logger.debug('Exported image to sandbox.')
|
||||||
|
logger.debug('Transferring image from sandbox to target destination...')
|
||||||
|
sandbox_filename = f'{filename}.{filetype.lower()}'
|
||||||
|
p4c.sandbox_get_from(
|
||||||
|
source_file=sandbox_filename,
|
||||||
|
dest_file=str(dst_file_pth),
|
||||||
|
overwrite=True,
|
||||||
|
sandbox_name=sandbox_name,
|
||||||
|
)
|
||||||
|
logger.debug('Transfer of image from sandbox to target destination successful.')</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Cytoscape: export current selected view as image</p>
|
||||||
|
<h2 id="parameters">Parameters</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><strong><code>filename</code></strong> : <code>str</code></dt>
|
||||||
|
<dd>export filename</dd>
|
||||||
|
<dt><strong><code>filetype</code></strong> : <code>CytoExportFileTypes</code>, optional</dt>
|
||||||
|
<dd>export filetype supported by Cytoscape, by default 'SVG'</dd>
|
||||||
|
<dt><strong><code>network_name</code></strong> : <code>str</code>, optional</dt>
|
||||||
|
<dd>network to export, by default CYTO_BASE_NETWORK_NAME</dd>
|
||||||
|
<dt><strong><code>pdf_export_page_size</code></strong> : <code>CytoExportPageSizes</code>, optional</dt>
|
||||||
|
<dd>page size which should be used for PDF exports supported by Cytoscape,
|
||||||
|
by default 'A4'</dd>
|
||||||
|
</dl></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.render.cytoscape.fit_content"><code class="name flex">
|
||||||
|
<span>def <span class="ident">fit_content</span></span>(<span>zoom_factor: float = 0.96, network_name: str = 'token_graph') ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def fit_content(
|
||||||
|
zoom_factor: float = CYTO_NETWORK_ZOOM_FACTOR,
|
||||||
|
network_name: str = CYTO_BASE_NETWORK_NAME,
|
||||||
|
) -> None:
|
||||||
|
p4c.hide_all_panels()
|
||||||
|
p4c.fit_content(selected_only=False, network=network_name)
|
||||||
|
zoom_current = p4c.get_network_zoom(network=network_name)
|
||||||
|
zoom_new = zoom_current * zoom_factor
|
||||||
|
p4c.set_network_zoom_bypass(zoom_new, bypass=False, network=network_name)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.render.cytoscape.get_subgraph_node_selection"><code class="name flex">
|
||||||
|
<span>def <span class="ident">get_subgraph_node_selection</span></span>(<span>network_name: str = 'token_graph', num_subgraphs: int = 5) ‑> list[int]</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def get_subgraph_node_selection(
|
||||||
|
network_name: str = CYTO_BASE_NETWORK_NAME,
|
||||||
|
num_subgraphs: int = CYTO_NUMBER_SUBGRAPHS,
|
||||||
|
) -> list[CytoNodeID]:
|
||||||
|
"""Cytoscape: obtain the relevant nodes for iterative subgraph generation
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
network_name : str, optional
|
||||||
|
network to retrieve the nodes from, by default CYTO_BASE_NETWORK_NAME
|
||||||
|
property_degree_weighted : str, optional
|
||||||
|
property name which contains the weighted degree,
|
||||||
|
by default PROPERTY_NAME_DEGREE_WEIGHTED
|
||||||
|
num_subgraphs : int, optional
|
||||||
|
number of relevant nodes which form the basis to generate subgraphs from,
|
||||||
|
by default CYTO_NUMBER_SUBGRAPHS
|
||||||
|
|
||||||
|
Returns
|
||||||
|
-------
|
||||||
|
list[CytoNodeID]
|
||||||
|
list containing all relevant Cytoscape nodes
|
||||||
|
"""
|
||||||
|
logger.debug('Selecting nodes for subgraph generation...')
|
||||||
|
node_table = p4c.get_table_columns(table='node', network=network_name)
|
||||||
|
node_table = node_table.sort_values(by=CYTO_SELECTION_PROPERTY, ascending=False)
|
||||||
|
p4c.load_table_data(node_table, data_key_column='name', network=network_name)
|
||||||
|
node_table_choice = node_table.iloc[:num_subgraphs]
|
||||||
|
logger.debug('Selection of nodes for subgraph generation successful.')
|
||||||
|
|
||||||
|
return node_table_choice['SUID'].to_list()</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Cytoscape: obtain the relevant nodes for iterative subgraph generation</p>
|
||||||
|
<h2 id="parameters">Parameters</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><strong><code>network_name</code></strong> : <code>str</code>, optional</dt>
|
||||||
|
<dd>network to retrieve the nodes from, by default CYTO_BASE_NETWORK_NAME</dd>
|
||||||
|
<dt><strong><code>property_degree_weighted</code></strong> : <code>str</code>, optional</dt>
|
||||||
|
<dd>property name which contains the weighted degree,
|
||||||
|
by default PROPERTY_NAME_DEGREE_WEIGHTED</dd>
|
||||||
|
<dt><strong><code>num_subgraphs</code></strong> : <code>int</code>, optional</dt>
|
||||||
|
<dd>number of relevant nodes which form the basis to generate subgraphs from,
|
||||||
|
by default CYTO_NUMBER_SUBGRAPHS</dd>
|
||||||
|
</dl>
|
||||||
|
<h2 id="returns">Returns</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code>list[CytoNodeID]</code></dt>
|
||||||
|
<dd>list containing all relevant Cytoscape nodes</dd>
|
||||||
|
</dl></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.render.cytoscape.import_to_cytoscape"><code class="name flex">
|
||||||
|
<span>def <span class="ident">import_to_cytoscape</span></span>(<span>graph: networkx.classes.digraph.DiGraph | networkx.classes.graph.Graph,<br>network_name: str = 'token_graph',<br>sandbox_name: str = 'lang_main',<br>reinitialise_sandbox: bool = True) ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def import_to_cytoscape(
|
||||||
|
graph: DiGraph | Graph,
|
||||||
|
network_name: str = CYTO_BASE_NETWORK_NAME,
|
||||||
|
sandbox_name: str = CYTO_SANDBOX_NAME,
|
||||||
|
reinitialise_sandbox: bool = True,
|
||||||
|
) -> None:
|
||||||
|
"""Cytoscape: import NetworkX graph as new network collection
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
graph : DiGraph | Graph
|
||||||
|
NetworkX graph object
|
||||||
|
"""
|
||||||
|
logger.debug('Checking Cytoscape connection...')
|
||||||
|
verify_connection()
|
||||||
|
logger.debug('Checking graph size for rendering...')
|
||||||
|
verify_graph_render_size(graph)
|
||||||
|
logger.debug('Setting default layout to improve import speed...')
|
||||||
|
change_default_layout()
|
||||||
|
logger.debug('Setting Cytoscape sandbox...')
|
||||||
|
p4c.sandbox_set(
|
||||||
|
sandbox_name=sandbox_name,
|
||||||
|
reinitialize=reinitialise_sandbox,
|
||||||
|
copy_samples=False,
|
||||||
|
)
|
||||||
|
logger.debug('Importing to and analysing network in Cytoscape...')
|
||||||
|
p4c.delete_all_networks()
|
||||||
|
p4c.create_network_from_networkx(
|
||||||
|
graph,
|
||||||
|
title=network_name,
|
||||||
|
collection=CYTO_COLLECTION_NAME,
|
||||||
|
)
|
||||||
|
analyse_network(network_name=network_name)
|
||||||
|
logger.debug('Import and analysis of network to Cytoscape successful.')</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Cytoscape: import NetworkX graph as new network collection</p>
|
||||||
|
<h2 id="parameters">Parameters</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><strong><code>graph</code></strong> : <code>DiGraph | Graph</code></dt>
|
||||||
|
<dd>NetworkX graph object</dd>
|
||||||
|
</dl></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.render.cytoscape.layout_network"><code class="name flex">
|
||||||
|
<span>def <span class="ident">layout_network</span></span>(<span>layout_name: Literal['attribute-circle', 'attribute-grid', 'attributes-layout', 'circular', 'cose', 'degree-circle', 'force-directed', 'force-directed-cl', 'fruchterman-rheingold', 'grid', 'hierarchical', 'isom', 'kamada-kawai', 'stacked-node-layout'] = 'force-directed',<br>layout_properties: dict[str, float | bool] = {'numIterations': 1000, 'defaultSpringCoefficient': 0.0001, 'defaultSpringLength': 45, 'defaultNodeMass': 11, 'isDeterministic': True, 'singlePartition': False},<br>network_name: str = 'token_graph') ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def layout_network(
|
||||||
|
layout_name: CytoLayouts = CYTO_LAYOUT_NAME,
|
||||||
|
layout_properties: CytoLayoutProperties = CYTO_LAYOUT_PROPERTIES,
|
||||||
|
network_name: str = CYTO_BASE_NETWORK_NAME,
|
||||||
|
) -> None:
|
||||||
|
"""Cytoscape: apply a supported layout algorithm to currently selected
|
||||||
|
network
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
layout_name : CytoLayouts, optional
|
||||||
|
layout algorithm supported by Cytoscape (name of the CyREST API, does not
|
||||||
|
necessarily match the name in the Cytoscape UI),
|
||||||
|
by default CYTO_LAYOUT_NAME
|
||||||
|
layout_properties : CytoLayoutProperties, optional
|
||||||
|
configuration of parameters for the given layout algorithm,
|
||||||
|
by default CYTO_LAYOUT_PROPERTIES
|
||||||
|
network_name : str, optional
|
||||||
|
network to apply the layout algorithm on, by default CYTO_BASE_NETWORK_NAME
|
||||||
|
"""
|
||||||
|
logger.debug('Applying layout to network...')
|
||||||
|
p4c.set_layout_properties(layout_name, layout_properties)
|
||||||
|
p4c.layout_network(layout_name=layout_name, network=network_name)
|
||||||
|
fit_content(network_name=network_name)
|
||||||
|
logger.debug('Layout application to network successful.')</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Cytoscape: apply a supported layout algorithm to currently selected
|
||||||
|
network</p>
|
||||||
|
<h2 id="parameters">Parameters</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><strong><code>layout_name</code></strong> : <code>CytoLayouts</code>, optional</dt>
|
||||||
|
<dd>layout algorithm supported by Cytoscape (name of the CyREST API, does not
|
||||||
|
necessarily match the name in the Cytoscape UI),
|
||||||
|
by default CYTO_LAYOUT_NAME</dd>
|
||||||
|
<dt><strong><code>layout_properties</code></strong> : <code>CytoLayoutProperties</code>, optional</dt>
|
||||||
|
<dd>configuration of parameters for the given layout algorithm,
|
||||||
|
by default CYTO_LAYOUT_PROPERTIES</dd>
|
||||||
|
<dt><strong><code>network_name</code></strong> : <code>str</code>, optional</dt>
|
||||||
|
<dd>network to apply the layout algorithm on, by default CYTO_BASE_NETWORK_NAME</dd>
|
||||||
|
</dl></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.render.cytoscape.make_subnetwork"><code class="name flex">
|
||||||
|
<span>def <span class="ident">make_subnetwork</span></span>(<span>index: int,<br>network_name: str = 'token_graph',<br>export_image: bool = True,<br>target_folder: pathlib.Path = WindowsPath('A:/Arbeitsaufgaben/lang-data/out')) ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def make_subnetwork(
|
||||||
|
index: int,
|
||||||
|
network_name: str = CYTO_BASE_NETWORK_NAME,
|
||||||
|
export_image: bool = True,
|
||||||
|
target_folder: Path = SAVE_PATH_FOLDER,
|
||||||
|
) -> None:
|
||||||
|
"""Cytoscape: generate a new subnetwork based on the currently
|
||||||
|
selected nodes and edges
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
index : int
|
||||||
|
id-like property to identify the subnetwork relative to its parent
|
||||||
|
network_name : str, optional
|
||||||
|
network to generate subnetwork from, by default CYTO_BASE_NETWORK_NAME
|
||||||
|
export_image : bool, optional
|
||||||
|
trigger image export of newly generated subnetwork, by default True
|
||||||
|
"""
|
||||||
|
logger.debug('Generating subnetwork with index %d...', index)
|
||||||
|
subnetwork_name = network_name + f'_sub_{index+1}'
|
||||||
|
p4c.create_subnetwork(
|
||||||
|
nodes='selected',
|
||||||
|
edges='selected',
|
||||||
|
subnetwork_name=subnetwork_name,
|
||||||
|
network=network_name,
|
||||||
|
)
|
||||||
|
p4c.set_current_network(subnetwork_name)
|
||||||
|
|
||||||
|
if export_image:
|
||||||
|
time.sleep(1)
|
||||||
|
export_network_to_image(
|
||||||
|
filename=subnetwork_name,
|
||||||
|
target_folder=target_folder,
|
||||||
|
network_name=subnetwork_name,
|
||||||
|
)
|
||||||
|
|
||||||
|
logger.debug('Generation of subnetwork with index %d successful.', index)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Cytoscape: generate a new subnetwork based on the currently
|
||||||
|
selected nodes and edges</p>
|
||||||
|
<h2 id="parameters">Parameters</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><strong><code>index</code></strong> : <code>int</code></dt>
|
||||||
|
<dd>id-like property to identify the subnetwork relative to its parent</dd>
|
||||||
|
<dt><strong><code>network_name</code></strong> : <code>str</code>, optional</dt>
|
||||||
|
<dd>network to generate subnetwork from, by default CYTO_BASE_NETWORK_NAME</dd>
|
||||||
|
<dt><strong><code>export_image</code></strong> : <code>bool</code>, optional</dt>
|
||||||
|
<dd>trigger image export of newly generated subnetwork, by default True</dd>
|
||||||
|
</dl></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.render.cytoscape.reset_current_network_to_base"><code class="name flex">
|
||||||
|
<span>def <span class="ident">reset_current_network_to_base</span></span>(<span>) ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def reset_current_network_to_base() -> None:
|
||||||
|
"""resets to currently selected network in Cytoscape back to the base one"""
|
||||||
|
p4c.set_current_network(CYTO_BASE_NETWORK_NAME)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>resets to currently selected network in Cytoscape back to the base one</p></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.render.cytoscape.select_neighbours_of_node"><code class="name flex">
|
||||||
|
<span>def <span class="ident">select_neighbours_of_node</span></span>(<span>node: int, neighbour_iter_depth: int = 2, network_name: str = 'token_graph') ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def select_neighbours_of_node(
|
||||||
|
node: CytoNodeID,
|
||||||
|
neighbour_iter_depth: int = CYTO_ITER_NEIGHBOUR_DEPTH,
|
||||||
|
network_name: str = CYTO_BASE_NETWORK_NAME,
|
||||||
|
) -> None:
|
||||||
|
"""Cytoscape: iterative selection of a node's neighbouring nodes and
|
||||||
|
their connecting edges
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
node : CytoNodeID
|
||||||
|
node which neighbours should be selected
|
||||||
|
neighbour_iter_depth : int, optional
|
||||||
|
indicates how many levels of neighbours should be choosen, e.g. 1 --> only
|
||||||
|
first-level neighbours are considered which are directly connected to the node,
|
||||||
|
2 --> all nodes with iteration depth of 1 are chosen and additionally their
|
||||||
|
direct neighbours,
|
||||||
|
by default CYTO_ITER_NEIGHBOUR_DEPTH
|
||||||
|
network_name : str, optional
|
||||||
|
network to perform action on, by default CYTO_BASE_NETWORK_NAME
|
||||||
|
"""
|
||||||
|
logger.debug('Selecting node neighbours for %s...', node)
|
||||||
|
p4c.clear_selection(network=network_name)
|
||||||
|
p4c.select_nodes(node, network=network_name)
|
||||||
|
|
||||||
|
for _ in range(neighbour_iter_depth):
|
||||||
|
_ = p4c.select_first_neighbors(network=network_name)
|
||||||
|
|
||||||
|
_ = p4c.select_edges_connecting_selected_nodes()
|
||||||
|
logger.debug('Selection of node neighbours for %s successful.', node)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Cytoscape: iterative selection of a node's neighbouring nodes and
|
||||||
|
their connecting edges</p>
|
||||||
|
<h2 id="parameters">Parameters</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><strong><code>node</code></strong> : <code>CytoNodeID</code></dt>
|
||||||
|
<dd>node which neighbours should be selected</dd>
|
||||||
|
<dt><strong><code>neighbour_iter_depth</code></strong> : <code>int</code>, optional</dt>
|
||||||
|
<dd>indicates how many levels of neighbours should be choosen, e.g. 1 –> only
|
||||||
|
first-level neighbours are considered which are directly connected to the node,
|
||||||
|
2 –> all nodes with iteration depth of 1 are chosen and additionally their
|
||||||
|
direct neighbours,
|
||||||
|
by default CYTO_ITER_NEIGHBOUR_DEPTH</dd>
|
||||||
|
<dt><strong><code>network_name</code></strong> : <code>str</code>, optional</dt>
|
||||||
|
<dd>network to perform action on, by default CYTO_BASE_NETWORK_NAME</dd>
|
||||||
|
</dl></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.render.cytoscape.verify_connection"><code class="name flex">
|
||||||
|
<span>def <span class="ident">verify_connection</span></span>(<span>) ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def verify_connection() -> None:
|
||||||
|
"""Cytoscape: checks if CyREST and Cytoscape versions are compatible nad
|
||||||
|
if Cytoscape API endpoint is reachable
|
||||||
|
|
||||||
|
Raises
|
||||||
|
------
|
||||||
|
CyError
|
||||||
|
incompatible CyREST or Cytoscape versions
|
||||||
|
RequestException
|
||||||
|
API endpoint not reachable
|
||||||
|
"""
|
||||||
|
try:
|
||||||
|
p4c.cytoscape_ping()
|
||||||
|
except CyError as error: # pragma: no cover
|
||||||
|
logger.error('[CyError] CyREST or Cytoscape version not supported.')
|
||||||
|
raise error
|
||||||
|
except RequestException as error:
|
||||||
|
logger.error('[CytoAPIConnection] Connection to CyREST API failed.')
|
||||||
|
raise error</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Cytoscape: checks if CyREST and Cytoscape versions are compatible nad
|
||||||
|
if Cytoscape API endpoint is reachable</p>
|
||||||
|
<h2 id="raises">Raises</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code>CyError</code></dt>
|
||||||
|
<dd>incompatible CyREST or Cytoscape versions</dd>
|
||||||
|
<dt><code>RequestException</code></dt>
|
||||||
|
<dd>API endpoint not reachable</dd>
|
||||||
|
</dl></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.render.cytoscape.verify_graph_render_size"><code class="name flex">
|
||||||
|
<span>def <span class="ident">verify_graph_render_size</span></span>(<span>graph: networkx.classes.digraph.DiGraph | networkx.classes.graph.Graph,<br>max_node_count: int | None = 500,<br>max_edge_count: int | None = 800) ‑> None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def verify_graph_render_size(
|
||||||
|
graph: Graph | DiGraph,
|
||||||
|
max_node_count: int | None = CYTO_MAX_NODE_COUNT,
|
||||||
|
max_edge_count: int | None = CYTO_MAX_EDGE_COUNT,
|
||||||
|
) -> None:
|
||||||
|
"""verify that the graph size can still be handled within an acceptable time
|
||||||
|
frame for rendering in Cytoscape
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
graph : Graph | DiGraph
|
||||||
|
graph to verify
|
||||||
|
max_node_count : int | None, optional
|
||||||
|
maximum allowed number of nodes, by default CYTO_MAX_NODE_COUNT
|
||||||
|
max_edge_count : int | None, optional
|
||||||
|
maximum allowed number of edges, by default CYTO_MAX_EDGE_COUNT
|
||||||
|
|
||||||
|
Raises
|
||||||
|
------
|
||||||
|
GraphRenderError
|
||||||
|
if any of the provided limits is exceeded
|
||||||
|
"""
|
||||||
|
num_nodes = len(graph.nodes)
|
||||||
|
num_edges = len(graph.edges)
|
||||||
|
if max_node_count is not None and num_nodes > max_node_count:
|
||||||
|
raise GraphRenderError(
|
||||||
|
f'Maximum number of nodes for rendering exceeded. '
|
||||||
|
f'Limit {max_node_count}, Counted: {num_nodes}'
|
||||||
|
)
|
||||||
|
|
||||||
|
if max_edge_count is not None and num_edges > max_edge_count:
|
||||||
|
raise GraphRenderError(
|
||||||
|
f'Maximum number of edges for rendering exceeded. '
|
||||||
|
f'Limit {max_edge_count}, Counted: {num_edges}'
|
||||||
|
)</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>verify that the graph size can still be handled within an acceptable time
|
||||||
|
frame for rendering in Cytoscape</p>
|
||||||
|
<h2 id="parameters">Parameters</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><strong><code>graph</code></strong> : <code>Graph | DiGraph</code></dt>
|
||||||
|
<dd>graph to verify</dd>
|
||||||
|
<dt><strong><code>max_node_count</code></strong> : <code>int | None</code>, optional</dt>
|
||||||
|
<dd>maximum allowed number of nodes, by default CYTO_MAX_NODE_COUNT</dd>
|
||||||
|
<dt><strong><code>max_edge_count</code></strong> : <code>int | None</code>, optional</dt>
|
||||||
|
<dd>maximum allowed number of edges, by default CYTO_MAX_EDGE_COUNT</dd>
|
||||||
|
</dl>
|
||||||
|
<h2 id="raises">Raises</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code>GraphRenderError</code></dt>
|
||||||
|
<dd>if any of the provided limits is exceeded</dd>
|
||||||
|
</dl></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.render.cytoscape.verify_table_property"><code class="name flex">
|
||||||
|
<span>def <span class="ident">verify_table_property</span></span>(<span>property: str,<br>table_type: Literal['node', 'edge', 'network'] = 'node',<br>network_name: str = 'token_graph') ‑> bool</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def verify_table_property(
|
||||||
|
property: str,
|
||||||
|
table_type: Literal['node', 'edge', 'network'] = 'node',
|
||||||
|
network_name: str = CYTO_BASE_NETWORK_NAME,
|
||||||
|
) -> bool:
|
||||||
|
table = p4c.get_table_columns(table=table_type, network=network_name)
|
||||||
|
logger.debug('Table >>%s<< wiht columns: %s', table, table.columns)
|
||||||
|
|
||||||
|
return property in table.columns</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
</dl>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
</article>
|
||||||
|
<nav id="sidebar">
|
||||||
|
<div class="toc">
|
||||||
|
<ul></ul>
|
||||||
|
</div>
|
||||||
|
<ul id="index">
|
||||||
|
<li><h3>Super-module</h3>
|
||||||
|
<ul>
|
||||||
|
<li><code><a title="lang_main.render" href="index.html">lang_main.render</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
<li><h3><a href="#header-functions">Functions</a></h3>
|
||||||
|
<ul class="">
|
||||||
|
<li><code><a title="lang_main.render.cytoscape.analyse_network" href="#lang_main.render.cytoscape.analyse_network">analyse_network</a></code></li>
|
||||||
|
<li><code><a title="lang_main.render.cytoscape.apply_style_to_network" href="#lang_main.render.cytoscape.apply_style_to_network">apply_style_to_network</a></code></li>
|
||||||
|
<li><code><a title="lang_main.render.cytoscape.build_subnetworks" href="#lang_main.render.cytoscape.build_subnetworks">build_subnetworks</a></code></li>
|
||||||
|
<li><code><a title="lang_main.render.cytoscape.change_default_layout" href="#lang_main.render.cytoscape.change_default_layout">change_default_layout</a></code></li>
|
||||||
|
<li><code><a title="lang_main.render.cytoscape.export_network_to_image" href="#lang_main.render.cytoscape.export_network_to_image">export_network_to_image</a></code></li>
|
||||||
|
<li><code><a title="lang_main.render.cytoscape.fit_content" href="#lang_main.render.cytoscape.fit_content">fit_content</a></code></li>
|
||||||
|
<li><code><a title="lang_main.render.cytoscape.get_subgraph_node_selection" href="#lang_main.render.cytoscape.get_subgraph_node_selection">get_subgraph_node_selection</a></code></li>
|
||||||
|
<li><code><a title="lang_main.render.cytoscape.import_to_cytoscape" href="#lang_main.render.cytoscape.import_to_cytoscape">import_to_cytoscape</a></code></li>
|
||||||
|
<li><code><a title="lang_main.render.cytoscape.layout_network" href="#lang_main.render.cytoscape.layout_network">layout_network</a></code></li>
|
||||||
|
<li><code><a title="lang_main.render.cytoscape.make_subnetwork" href="#lang_main.render.cytoscape.make_subnetwork">make_subnetwork</a></code></li>
|
||||||
|
<li><code><a title="lang_main.render.cytoscape.reset_current_network_to_base" href="#lang_main.render.cytoscape.reset_current_network_to_base">reset_current_network_to_base</a></code></li>
|
||||||
|
<li><code><a title="lang_main.render.cytoscape.select_neighbours_of_node" href="#lang_main.render.cytoscape.select_neighbours_of_node">select_neighbours_of_node</a></code></li>
|
||||||
|
<li><code><a title="lang_main.render.cytoscape.verify_connection" href="#lang_main.render.cytoscape.verify_connection">verify_connection</a></code></li>
|
||||||
|
<li><code><a title="lang_main.render.cytoscape.verify_graph_render_size" href="#lang_main.render.cytoscape.verify_graph_render_size">verify_graph_render_size</a></code></li>
|
||||||
|
<li><code><a title="lang_main.render.cytoscape.verify_table_property" href="#lang_main.render.cytoscape.verify_table_property">verify_table_property</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
</ul>
|
||||||
|
</nav>
|
||||||
|
</main>
|
||||||
|
<footer id="footer">
|
||||||
|
<p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.11.5</a>.</p>
|
||||||
|
</footer>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
182
docs/lang_main/render/cytoscape_monkeypatch.html
Normal file
182
docs/lang_main/render/cytoscape_monkeypatch.html
Normal file
@ -0,0 +1,182 @@
|
|||||||
|
<!doctype html>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="utf-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1">
|
||||||
|
<meta name="generator" content="pdoc3 0.11.5">
|
||||||
|
<title>lang_main.render.cytoscape_monkeypatch API documentation</title>
|
||||||
|
<meta name="description" content="">
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/sanitize.min.css" integrity="sha512-y1dtMcuvtTMJc1yPgEqF0ZjQbhnc/bFhyvIyVNb9Zk5mIGtqVaAB1Ttl28su8AvFMOY0EwRbAe+HCLqj6W7/KA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/typography.min.css" integrity="sha512-Y1DYSb995BAfxobCkKepB1BqJJTPrOp3zPL74AWFugHHmmdcvO+C48WLrUOlhGMc0QG7AE3f7gmvvcrmX2fDoA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/styles/default.min.css" crossorigin>
|
||||||
|
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:1.5em;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:2em 0 .50em 0}h3{font-size:1.4em;margin:1.6em 0 .7em 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .2s ease-in-out}a:visited{color:#503}a:hover{color:#b62}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900;font-weight:bold}pre code{font-size:.8em;line-height:1.4em;padding:1em;display:block}code{background:#f3f3f3;font-family:"DejaVu Sans Mono",monospace;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source > summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible;min-width:max-content}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em 1em;margin:1em 0}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
|
||||||
|
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul ul{padding-left:1em}.toc > ul > li{margin-top:.5em}}</style>
|
||||||
|
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
|
||||||
|
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/highlight.min.js" integrity="sha512-D9gUyxqja7hBtkWpPWGt9wfbfaMGVt9gnyCvYa+jojwwPHLCzUm5i8rpk7vD7wNee9bA35eYIjobYPaQuKS1MQ==" crossorigin></script>
|
||||||
|
<script>window.addEventListener('DOMContentLoaded', () => {
|
||||||
|
hljs.configure({languages: ['bash', 'css', 'diff', 'graphql', 'ini', 'javascript', 'json', 'plaintext', 'python', 'python-repl', 'rust', 'shell', 'sql', 'typescript', 'xml', 'yaml']});
|
||||||
|
hljs.highlightAll();
|
||||||
|
/* Collapse source docstrings */
|
||||||
|
setTimeout(() => {
|
||||||
|
[...document.querySelectorAll('.hljs.language-python > .hljs-string')]
|
||||||
|
.filter(el => el.innerHTML.length > 200 && ['"""', "'''"].includes(el.innerHTML.substring(0, 3)))
|
||||||
|
.forEach(el => {
|
||||||
|
let d = document.createElement('details');
|
||||||
|
d.classList.add('hljs-string');
|
||||||
|
d.innerHTML = '<summary>"""</summary>' + el.innerHTML.substring(3);
|
||||||
|
el.replaceWith(d);
|
||||||
|
});
|
||||||
|
}, 100);
|
||||||
|
})</script>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<main>
|
||||||
|
<article id="content">
|
||||||
|
<header>
|
||||||
|
<h1 class="title">Module <code>lang_main.render.cytoscape_monkeypatch</code></h1>
|
||||||
|
</header>
|
||||||
|
<section id="section-intro">
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
<h2 class="section-title" id="header-functions">Functions</h2>
|
||||||
|
<dl>
|
||||||
|
<dt id="lang_main.render.cytoscape_monkeypatch.select_edges_connecting_selected_nodes"><code class="name flex">
|
||||||
|
<span>def <span class="ident">select_edges_connecting_selected_nodes</span></span>(<span>network=None, base_url='http://127.0.0.1:1234/v1')</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">@cy_log # pragma: no cover
|
||||||
|
def select_edges_connecting_selected_nodes(network=None, base_url=DEFAULT_BASE_URL): # noqa: F405 # pragma: no cover
|
||||||
|
"""Select edges in a Cytoscape Network connecting the selected nodes, including self loops connecting single nodes.
|
||||||
|
|
||||||
|
Any edges selected beforehand are deselected before any new edges are selected
|
||||||
|
|
||||||
|
Args:
|
||||||
|
network (SUID or str or None): Name or SUID of a network. Default is the
|
||||||
|
"current" network active in Cytoscape.
|
||||||
|
base_url (str): Ignore unless you need to specify a custom domain,
|
||||||
|
port or version to connect to the CyREST API. Default is http://127.0.0.1:1234
|
||||||
|
and the latest version of the CyREST API supported by this version of py4cytoscape.
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
dict: {'nodes': [node list], 'edges': [edge list]} or None if no selected nodes
|
||||||
|
Raises:
|
||||||
|
CyError: if network name or SUID doesn't exist
|
||||||
|
requests.exceptions.RequestException: if can't connect to Cytoscape or Cytoscape returns an error
|
||||||
|
|
||||||
|
Examples:
|
||||||
|
>>> select_edges_connecting_selected_nodes()
|
||||||
|
None
|
||||||
|
>>> select_edges_connecting_selected_nodes(network='My Network')
|
||||||
|
{'nodes': [103990, 103991, ...], 'edges': [104432, 104431, ...]}
|
||||||
|
>>> select_edges_connecting_selected_nodes(network=52)
|
||||||
|
{'nodes': [103990, 103991, ...], 'edges': [104432, 104431, ...]}
|
||||||
|
|
||||||
|
Note:
|
||||||
|
In the return value node list is list of all selected nodes, and
|
||||||
|
edge list is the SUIDs of selected edges -- dict is None if no nodes were selected or there were no newly
|
||||||
|
created edges
|
||||||
|
"""
|
||||||
|
net_suid = networks.get_network_suid(network, base_url=base_url)
|
||||||
|
|
||||||
|
selected_nodes = get_selected_nodes(network=net_suid, base_url=base_url)
|
||||||
|
# TODO: In R version, NA test is after len() test ... shouldn't it be before?
|
||||||
|
if not selected_nodes:
|
||||||
|
return None
|
||||||
|
|
||||||
|
all_edges = networks.get_all_edges(net_suid, base_url=base_url)
|
||||||
|
|
||||||
|
selected_sources = set()
|
||||||
|
selected_targets = set()
|
||||||
|
for n in selected_nodes:
|
||||||
|
n = re_parenthesis_1.sub('\(', n) # type: ignore
|
||||||
|
n = re_parenthesis_2.sub('\)', n) # type: ignore
|
||||||
|
selected_sources |= set(filter(re.compile('^' + n).search, all_edges)) # type: ignore
|
||||||
|
selected_targets |= set(filter(re.compile(n + '$').search, all_edges)) # type: ignore
|
||||||
|
|
||||||
|
selected_edges = list(selected_sources.intersection(selected_targets))
|
||||||
|
|
||||||
|
if len(selected_edges) == 0:
|
||||||
|
return None
|
||||||
|
res = select_edges(
|
||||||
|
selected_edges,
|
||||||
|
by_col='name',
|
||||||
|
preserve_current_selection=False,
|
||||||
|
network=net_suid,
|
||||||
|
base_url=base_url,
|
||||||
|
)
|
||||||
|
return res
|
||||||
|
# TODO: isn't the pattern match a bit cheesy ... shouldn't it be ^+n+' (' and ') '+n+$ ???</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Select edges in a Cytoscape Network connecting the selected nodes, including self loops connecting single nodes.</p>
|
||||||
|
<p>Any edges selected beforehand are deselected before any new edges are selected</p>
|
||||||
|
<h2 id="args">Args</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><strong><code>network</code></strong> : <code>SUID</code> or <code>str</code> or <code>None</code></dt>
|
||||||
|
<dd>Name or SUID of a network. Default is the
|
||||||
|
"current" network active in Cytoscape.</dd>
|
||||||
|
<dt><strong><code>base_url</code></strong> : <code>str</code></dt>
|
||||||
|
<dd>Ignore unless you need to specify a custom domain,
|
||||||
|
port or version to connect to the CyREST API. Default is <a href="http://127.0.0.1:1234">http://127.0.0.1:1234</a>
|
||||||
|
and the latest version of the CyREST API supported by this version of py4cytoscape.</dd>
|
||||||
|
</dl>
|
||||||
|
<h2 id="returns">Returns</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code>dict</code></dt>
|
||||||
|
<dd>{'nodes': [node list], 'edges': [edge list]} or None if no selected nodes</dd>
|
||||||
|
</dl>
|
||||||
|
<h2 id="raises">Raises</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code>CyError</code></dt>
|
||||||
|
<dd>if network name or SUID doesn't exist</dd>
|
||||||
|
<dt><code>requests.exceptions.RequestException</code></dt>
|
||||||
|
<dd>if can't connect to Cytoscape or Cytoscape returns an error</dd>
|
||||||
|
</dl>
|
||||||
|
<h2 id="examples">Examples</h2>
|
||||||
|
<pre><code class="language-python-repl">>>> select_edges_connecting_selected_nodes()
|
||||||
|
None
|
||||||
|
>>> select_edges_connecting_selected_nodes(network='My Network')
|
||||||
|
{'nodes': [103990, 103991, ...], 'edges': [104432, 104431, ...]}
|
||||||
|
>>> select_edges_connecting_selected_nodes(network=52)
|
||||||
|
{'nodes': [103990, 103991, ...], 'edges': [104432, 104431, ...]}
|
||||||
|
</code></pre>
|
||||||
|
<h2 id="note">Note</h2>
|
||||||
|
<p>In the return value node list is list of all selected nodes, and
|
||||||
|
edge list is the SUIDs of selected edges – dict is None if no nodes were selected or there were no newly
|
||||||
|
created edges</p></div>
|
||||||
|
</dd>
|
||||||
|
</dl>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
</article>
|
||||||
|
<nav id="sidebar">
|
||||||
|
<div class="toc">
|
||||||
|
<ul></ul>
|
||||||
|
</div>
|
||||||
|
<ul id="index">
|
||||||
|
<li><h3>Super-module</h3>
|
||||||
|
<ul>
|
||||||
|
<li><code><a title="lang_main.render" href="index.html">lang_main.render</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
<li><h3><a href="#header-functions">Functions</a></h3>
|
||||||
|
<ul class="">
|
||||||
|
<li><code><a title="lang_main.render.cytoscape_monkeypatch.select_edges_connecting_selected_nodes" href="#lang_main.render.cytoscape_monkeypatch.select_edges_connecting_selected_nodes">select_edges_connecting_selected_nodes</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
</ul>
|
||||||
|
</nav>
|
||||||
|
</main>
|
||||||
|
<footer id="footer">
|
||||||
|
<p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.11.5</a>.</p>
|
||||||
|
</footer>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
83
docs/lang_main/render/index.html
Normal file
83
docs/lang_main/render/index.html
Normal file
@ -0,0 +1,83 @@
|
|||||||
|
<!doctype html>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="utf-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1">
|
||||||
|
<meta name="generator" content="pdoc3 0.11.5">
|
||||||
|
<title>lang_main.render API documentation</title>
|
||||||
|
<meta name="description" content="">
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/sanitize.min.css" integrity="sha512-y1dtMcuvtTMJc1yPgEqF0ZjQbhnc/bFhyvIyVNb9Zk5mIGtqVaAB1Ttl28su8AvFMOY0EwRbAe+HCLqj6W7/KA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/typography.min.css" integrity="sha512-Y1DYSb995BAfxobCkKepB1BqJJTPrOp3zPL74AWFugHHmmdcvO+C48WLrUOlhGMc0QG7AE3f7gmvvcrmX2fDoA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/styles/default.min.css" crossorigin>
|
||||||
|
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:1.5em;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:2em 0 .50em 0}h3{font-size:1.4em;margin:1.6em 0 .7em 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .2s ease-in-out}a:visited{color:#503}a:hover{color:#b62}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900;font-weight:bold}pre code{font-size:.8em;line-height:1.4em;padding:1em;display:block}code{background:#f3f3f3;font-family:"DejaVu Sans Mono",monospace;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source > summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible;min-width:max-content}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em 1em;margin:1em 0}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
|
||||||
|
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul ul{padding-left:1em}.toc > ul > li{margin-top:.5em}}</style>
|
||||||
|
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
|
||||||
|
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/highlight.min.js" integrity="sha512-D9gUyxqja7hBtkWpPWGt9wfbfaMGVt9gnyCvYa+jojwwPHLCzUm5i8rpk7vD7wNee9bA35eYIjobYPaQuKS1MQ==" crossorigin></script>
|
||||||
|
<script>window.addEventListener('DOMContentLoaded', () => {
|
||||||
|
hljs.configure({languages: ['bash', 'css', 'diff', 'graphql', 'ini', 'javascript', 'json', 'plaintext', 'python', 'python-repl', 'rust', 'shell', 'sql', 'typescript', 'xml', 'yaml']});
|
||||||
|
hljs.highlightAll();
|
||||||
|
/* Collapse source docstrings */
|
||||||
|
setTimeout(() => {
|
||||||
|
[...document.querySelectorAll('.hljs.language-python > .hljs-string')]
|
||||||
|
.filter(el => el.innerHTML.length > 200 && ['"""', "'''"].includes(el.innerHTML.substring(0, 3)))
|
||||||
|
.forEach(el => {
|
||||||
|
let d = document.createElement('details');
|
||||||
|
d.classList.add('hljs-string');
|
||||||
|
d.innerHTML = '<summary>"""</summary>' + el.innerHTML.substring(3);
|
||||||
|
el.replaceWith(d);
|
||||||
|
});
|
||||||
|
}, 100);
|
||||||
|
})</script>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<main>
|
||||||
|
<article id="content">
|
||||||
|
<header>
|
||||||
|
<h1 class="title">Module <code>lang_main.render</code></h1>
|
||||||
|
</header>
|
||||||
|
<section id="section-intro">
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
<h2 class="section-title" id="header-submodules">Sub-modules</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code class="name"><a title="lang_main.render.cytoscape" href="cytoscape.html">lang_main.render.cytoscape</a></code></dt>
|
||||||
|
<dd>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
<dt><code class="name"><a title="lang_main.render.cytoscape_monkeypatch" href="cytoscape_monkeypatch.html">lang_main.render.cytoscape_monkeypatch</a></code></dt>
|
||||||
|
<dd>
|
||||||
|
<div class="desc"></div>
|
||||||
|
</dd>
|
||||||
|
</dl>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
</article>
|
||||||
|
<nav id="sidebar">
|
||||||
|
<div class="toc">
|
||||||
|
<ul></ul>
|
||||||
|
</div>
|
||||||
|
<ul id="index">
|
||||||
|
<li><h3>Super-module</h3>
|
||||||
|
<ul>
|
||||||
|
<li><code><a title="lang_main" href="../index.html">lang_main</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
<li><h3><a href="#header-submodules">Sub-modules</a></h3>
|
||||||
|
<ul>
|
||||||
|
<li><code><a title="lang_main.render.cytoscape" href="cytoscape.html">lang_main.render.cytoscape</a></code></li>
|
||||||
|
<li><code><a title="lang_main.render.cytoscape_monkeypatch" href="cytoscape_monkeypatch.html">lang_main.render.cytoscape_monkeypatch</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
</ul>
|
||||||
|
</nav>
|
||||||
|
</main>
|
||||||
|
<footer id="footer">
|
||||||
|
<p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.11.5</a>.</p>
|
||||||
|
</footer>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
261
docs/lang_main/search.html
Normal file
261
docs/lang_main/search.html
Normal file
@ -0,0 +1,261 @@
|
|||||||
|
<!doctype html>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="utf-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1">
|
||||||
|
<meta name="generator" content="pdoc3 0.11.5">
|
||||||
|
<title>lang_main.search API documentation</title>
|
||||||
|
<meta name="description" content="">
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/sanitize.min.css" integrity="sha512-y1dtMcuvtTMJc1yPgEqF0ZjQbhnc/bFhyvIyVNb9Zk5mIGtqVaAB1Ttl28su8AvFMOY0EwRbAe+HCLqj6W7/KA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/13.0.0/typography.min.css" integrity="sha512-Y1DYSb995BAfxobCkKepB1BqJJTPrOp3zPL74AWFugHHmmdcvO+C48WLrUOlhGMc0QG7AE3f7gmvvcrmX2fDoA==" crossorigin>
|
||||||
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/styles/default.min.css" crossorigin>
|
||||||
|
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:1.5em;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:2em 0 .50em 0}h3{font-size:1.4em;margin:1.6em 0 .7em 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .2s ease-in-out}a:visited{color:#503}a:hover{color:#b62}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900;font-weight:bold}pre code{font-size:.8em;line-height:1.4em;padding:1em;display:block}code{background:#f3f3f3;font-family:"DejaVu Sans Mono",monospace;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source > summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible;min-width:max-content}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em 1em;margin:1em 0}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
|
||||||
|
<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul ul{padding-left:1em}.toc > ul > li{margin-top:.5em}}</style>
|
||||||
|
<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
|
||||||
|
<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/11.9.0/highlight.min.js" integrity="sha512-D9gUyxqja7hBtkWpPWGt9wfbfaMGVt9gnyCvYa+jojwwPHLCzUm5i8rpk7vD7wNee9bA35eYIjobYPaQuKS1MQ==" crossorigin></script>
|
||||||
|
<script>window.addEventListener('DOMContentLoaded', () => {
|
||||||
|
hljs.configure({languages: ['bash', 'css', 'diff', 'graphql', 'ini', 'javascript', 'json', 'plaintext', 'python', 'python-repl', 'rust', 'shell', 'sql', 'typescript', 'xml', 'yaml']});
|
||||||
|
hljs.highlightAll();
|
||||||
|
/* Collapse source docstrings */
|
||||||
|
setTimeout(() => {
|
||||||
|
[...document.querySelectorAll('.hljs.language-python > .hljs-string')]
|
||||||
|
.filter(el => el.innerHTML.length > 200 && ['"""', "'''"].includes(el.innerHTML.substring(0, 3)))
|
||||||
|
.forEach(el => {
|
||||||
|
let d = document.createElement('details');
|
||||||
|
d.classList.add('hljs-string');
|
||||||
|
d.innerHTML = '<summary>"""</summary>' + el.innerHTML.substring(3);
|
||||||
|
el.replaceWith(d);
|
||||||
|
});
|
||||||
|
}, 100);
|
||||||
|
})</script>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<main>
|
||||||
|
<article id="content">
|
||||||
|
<header>
|
||||||
|
<h1 class="title">Module <code>lang_main.search</code></h1>
|
||||||
|
</header>
|
||||||
|
<section id="section-intro">
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
<h2 class="section-title" id="header-functions">Functions</h2>
|
||||||
|
<dl>
|
||||||
|
<dt id="lang_main.search.search_base_path"><code class="name flex">
|
||||||
|
<span>def <span class="ident">search_base_path</span></span>(<span>starting_path: pathlib.Path, stop_folder_name: str | None = None) ‑> pathlib.Path | None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def search_base_path(
|
||||||
|
starting_path: Path,
|
||||||
|
stop_folder_name: str | None = None,
|
||||||
|
) -> Path | None:
|
||||||
|
"""Iteratively searches the parent directories of the starting path
|
||||||
|
and look for folders matching the given name. If a match is encountered,
|
||||||
|
the parent path will be returned.
|
||||||
|
|
||||||
|
Example:
|
||||||
|
starting_path = path/to/start/folder
|
||||||
|
stop_folder_name = 'to'
|
||||||
|
returned path = 'path/'
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
starting_path : Path
|
||||||
|
non-inclusive starting path
|
||||||
|
stop_folder_name : str, optional
|
||||||
|
name of the last folder in the directory tree to search, by default None
|
||||||
|
|
||||||
|
Returns
|
||||||
|
-------
|
||||||
|
Path | None
|
||||||
|
Path if corresponding base path was found, None otherwise
|
||||||
|
"""
|
||||||
|
stop_folder_path: Path | None = None
|
||||||
|
base_path: Path | None = None
|
||||||
|
for search_path in starting_path.parents:
|
||||||
|
if stop_folder_name is not None and search_path.name == stop_folder_name:
|
||||||
|
# library is placed inside a whole python installation for deployment
|
||||||
|
# only look up to this folder
|
||||||
|
stop_folder_path = search_path
|
||||||
|
break
|
||||||
|
|
||||||
|
if stop_folder_path is not None:
|
||||||
|
base_path = stop_folder_path.parent
|
||||||
|
|
||||||
|
return base_path</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Iteratively searches the parent directories of the starting path
|
||||||
|
and look for folders matching the given name. If a match is encountered,
|
||||||
|
the parent path will be returned.</p>
|
||||||
|
<p>Example:
|
||||||
|
starting_path = path/to/start/folder
|
||||||
|
stop_folder_name = 'to'
|
||||||
|
returned path = 'path/'</p>
|
||||||
|
<h2 id="parameters">Parameters</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><strong><code>starting_path</code></strong> : <code>Path</code></dt>
|
||||||
|
<dd>non-inclusive starting path</dd>
|
||||||
|
<dt><strong><code>stop_folder_name</code></strong> : <code>str</code>, optional</dt>
|
||||||
|
<dd>name of the last folder in the directory tree to search, by default None</dd>
|
||||||
|
</dl>
|
||||||
|
<h2 id="returns">Returns</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code>Path | None</code></dt>
|
||||||
|
<dd>Path if corresponding base path was found, None otherwise</dd>
|
||||||
|
</dl></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.search.search_cwd"><code class="name flex">
|
||||||
|
<span>def <span class="ident">search_cwd</span></span>(<span>glob_pattern: str) ‑> pathlib.Path | None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def search_cwd(
|
||||||
|
glob_pattern: str,
|
||||||
|
) -> Path | None:
|
||||||
|
"""Searches the current working directory and looks for files
|
||||||
|
matching the glob pattern.
|
||||||
|
Returns the first match encountered.
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
glob_pattern : str, optional
|
||||||
|
pattern to look for, first match will be returned
|
||||||
|
|
||||||
|
Returns
|
||||||
|
-------
|
||||||
|
Path | None
|
||||||
|
Path if corresponding object was found, None otherwise
|
||||||
|
"""
|
||||||
|
path_found: Path | None = None
|
||||||
|
res = tuple(Path.cwd().glob(glob_pattern))
|
||||||
|
if res:
|
||||||
|
path_found = res[0]
|
||||||
|
|
||||||
|
return path_found</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Searches the current working directory and looks for files
|
||||||
|
matching the glob pattern.
|
||||||
|
Returns the first match encountered.</p>
|
||||||
|
<h2 id="parameters">Parameters</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><strong><code>glob_pattern</code></strong> : <code>str</code>, optional</dt>
|
||||||
|
<dd>pattern to look for, first match will be returned</dd>
|
||||||
|
</dl>
|
||||||
|
<h2 id="returns">Returns</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code>Path | None</code></dt>
|
||||||
|
<dd>Path if corresponding object was found, None otherwise</dd>
|
||||||
|
</dl></div>
|
||||||
|
</dd>
|
||||||
|
<dt id="lang_main.search.search_iterative"><code class="name flex">
|
||||||
|
<span>def <span class="ident">search_iterative</span></span>(<span>starting_path: pathlib.Path,<br>glob_pattern: str,<br>stop_folder_name: str | None = None) ‑> pathlib.Path | None</span>
|
||||||
|
</code></dt>
|
||||||
|
<dd>
|
||||||
|
<details class="source">
|
||||||
|
<summary>
|
||||||
|
<span>Expand source code</span>
|
||||||
|
</summary>
|
||||||
|
<pre><code class="python">def search_iterative(
|
||||||
|
starting_path: Path,
|
||||||
|
glob_pattern: str,
|
||||||
|
stop_folder_name: str | None = None,
|
||||||
|
) -> Path | None:
|
||||||
|
"""Iteratively searches the parent directories of the starting path
|
||||||
|
and look for files matching the glob pattern. The starting path is not
|
||||||
|
searched, only its parents. Therefore the starting path can also point
|
||||||
|
to a file. The folder in which it is placed in will be searched.
|
||||||
|
Returns the first match encountered.
|
||||||
|
The parent of the stop folder will be searched if it exists.
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
starting_path : Path
|
||||||
|
non-inclusive starting path
|
||||||
|
glob_pattern : str, optional
|
||||||
|
pattern to look for, first match will be returned
|
||||||
|
stop_folder_name : str, optional
|
||||||
|
name of the last folder in the directory tree to search, by default None
|
||||||
|
|
||||||
|
Returns
|
||||||
|
-------
|
||||||
|
Path | None
|
||||||
|
Path if corresponding object was found, None otherwise
|
||||||
|
"""
|
||||||
|
file_path: Path | None = None
|
||||||
|
stop_folder_reached: bool = False
|
||||||
|
for search_path in starting_path.parents:
|
||||||
|
res = tuple(search_path.glob(glob_pattern))
|
||||||
|
if res:
|
||||||
|
file_path = res[0]
|
||||||
|
break
|
||||||
|
elif stop_folder_reached:
|
||||||
|
break
|
||||||
|
|
||||||
|
if stop_folder_name is not None and search_path.name == stop_folder_name:
|
||||||
|
# library is placed inside a whole python installation for deployment
|
||||||
|
# if this folder is reached, only look up one parent above
|
||||||
|
stop_folder_reached = True
|
||||||
|
|
||||||
|
return file_path</code></pre>
|
||||||
|
</details>
|
||||||
|
<div class="desc"><p>Iteratively searches the parent directories of the starting path
|
||||||
|
and look for files matching the glob pattern. The starting path is not
|
||||||
|
searched, only its parents. Therefore the starting path can also point
|
||||||
|
to a file. The folder in which it is placed in will be searched.
|
||||||
|
Returns the first match encountered.
|
||||||
|
The parent of the stop folder will be searched if it exists.</p>
|
||||||
|
<h2 id="parameters">Parameters</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><strong><code>starting_path</code></strong> : <code>Path</code></dt>
|
||||||
|
<dd>non-inclusive starting path</dd>
|
||||||
|
<dt><strong><code>glob_pattern</code></strong> : <code>str</code>, optional</dt>
|
||||||
|
<dd>pattern to look for, first match will be returned</dd>
|
||||||
|
<dt><strong><code>stop_folder_name</code></strong> : <code>str</code>, optional</dt>
|
||||||
|
<dd>name of the last folder in the directory tree to search, by default None</dd>
|
||||||
|
</dl>
|
||||||
|
<h2 id="returns">Returns</h2>
|
||||||
|
<dl>
|
||||||
|
<dt><code>Path | None</code></dt>
|
||||||
|
<dd>Path if corresponding object was found, None otherwise</dd>
|
||||||
|
</dl></div>
|
||||||
|
</dd>
|
||||||
|
</dl>
|
||||||
|
</section>
|
||||||
|
<section>
|
||||||
|
</section>
|
||||||
|
</article>
|
||||||
|
<nav id="sidebar">
|
||||||
|
<div class="toc">
|
||||||
|
<ul></ul>
|
||||||
|
</div>
|
||||||
|
<ul id="index">
|
||||||
|
<li><h3>Super-module</h3>
|
||||||
|
<ul>
|
||||||
|
<li><code><a title="lang_main" href="index.html">lang_main</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
<li><h3><a href="#header-functions">Functions</a></h3>
|
||||||
|
<ul class="">
|
||||||
|
<li><code><a title="lang_main.search.search_base_path" href="#lang_main.search.search_base_path">search_base_path</a></code></li>
|
||||||
|
<li><code><a title="lang_main.search.search_cwd" href="#lang_main.search.search_cwd">search_cwd</a></code></li>
|
||||||
|
<li><code><a title="lang_main.search.search_iterative" href="#lang_main.search.search_iterative">search_iterative</a></code></li>
|
||||||
|
</ul>
|
||||||
|
</li>
|
||||||
|
</ul>
|
||||||
|
</nav>
|
||||||
|
</main>
|
||||||
|
<footer id="footer">
|
||||||
|
<p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.11.5</a>.</p>
|
||||||
|
</footer>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
10637
docs/lang_main/types.html
Normal file
10637
docs/lang_main/types.html
Normal file
File diff suppressed because it is too large
Load Diff
@ -5,9 +5,6 @@ from typing import cast
|
|||||||
import networkx as nx
|
import networkx as nx
|
||||||
import numpy as np
|
import numpy as np
|
||||||
import numpy.typing as npt
|
import numpy.typing as npt
|
||||||
|
|
||||||
# import sentence_transformers # TODO check removal
|
|
||||||
# import sentence_transformers.util # TODO check removal
|
|
||||||
from networkx import Graph
|
from networkx import Graph
|
||||||
from pandas import DataFrame, Series
|
from pandas import DataFrame, Series
|
||||||
from sentence_transformers import SentenceTransformer
|
from sentence_transformers import SentenceTransformer
|
||||||
|
|||||||
@ -47,7 +47,7 @@ def _non_relevant_obj_ids(
|
|||||||
feats_per_obj_id = feats_per_obj_id.dropna()
|
feats_per_obj_id = feats_per_obj_id.dropna()
|
||||||
unique_feats_per_obj_id = len(feats_per_obj_id.unique())
|
unique_feats_per_obj_id = len(feats_per_obj_id.unique())
|
||||||
|
|
||||||
if unique_feats_per_obj_id > thresh_unique_feat_per_id:
|
if unique_feats_per_obj_id >= thresh_unique_feat_per_id:
|
||||||
ids_to_ignore.add(obj_id)
|
ids_to_ignore.add(obj_id)
|
||||||
|
|
||||||
return tuple(ids_to_ignore)
|
return tuple(ids_to_ignore)
|
||||||
|
|||||||
@ -119,7 +119,7 @@ def _preprocess_STFR_model_name(
|
|||||||
raise FileNotFoundError(
|
raise FileNotFoundError(
|
||||||
f'Target model >{model_name}< not found under {model_path}'
|
f'Target model >{model_name}< not found under {model_path}'
|
||||||
)
|
)
|
||||||
model_name_or_path = str(model_path)
|
model_name_or_path = str(model_path) # pragma: no cover
|
||||||
else:
|
else:
|
||||||
model_name_or_path = model_name
|
model_name_or_path = model_name
|
||||||
|
|
||||||
|
|||||||
@ -30,11 +30,12 @@ from lang_main.constants import (
|
|||||||
DATE_COLS,
|
DATE_COLS,
|
||||||
FEATURE_NAME_OBJ_ID,
|
FEATURE_NAME_OBJ_ID,
|
||||||
FEATURE_NAME_OBJ_TEXT,
|
FEATURE_NAME_OBJ_TEXT,
|
||||||
|
MAX_EDGE_NUMBER,
|
||||||
MODEL_INPUT_FEATURES,
|
MODEL_INPUT_FEATURES,
|
||||||
NAME_DELTA_FEAT_TO_REPAIR,
|
NAME_DELTA_FEAT_TO_REPAIR,
|
||||||
SAVE_PATH_FOLDER,
|
SAVE_PATH_FOLDER,
|
||||||
|
TARGET_FEATURE,
|
||||||
THRESHOLD_AMOUNT_CHARACTERS,
|
THRESHOLD_AMOUNT_CHARACTERS,
|
||||||
THRESHOLD_EDGE_NUMBER,
|
|
||||||
THRESHOLD_NUM_ACTIVITIES,
|
THRESHOLD_NUM_ACTIVITIES,
|
||||||
THRESHOLD_SIMILARITY,
|
THRESHOLD_SIMILARITY,
|
||||||
THRESHOLD_TIMELINE_SIMILARITY,
|
THRESHOLD_TIMELINE_SIMILARITY,
|
||||||
@ -72,7 +73,7 @@ def build_base_target_feature_pipe() -> Pipeline:
|
|||||||
pipe_target_feat.add(
|
pipe_target_feat.add(
|
||||||
entry_wise_cleansing,
|
entry_wise_cleansing,
|
||||||
{
|
{
|
||||||
'target_features': ('VorgangsBeschreibung',),
|
'target_features': (TARGET_FEATURE,),
|
||||||
'cleansing_func': clean_string_slim,
|
'cleansing_func': clean_string_slim,
|
||||||
},
|
},
|
||||||
save_result=True,
|
save_result=True,
|
||||||
@ -81,7 +82,7 @@ def build_base_target_feature_pipe() -> Pipeline:
|
|||||||
pipe_target_feat.add(
|
pipe_target_feat.add(
|
||||||
analyse_feature,
|
analyse_feature,
|
||||||
{
|
{
|
||||||
'target_feature': 'VorgangsBeschreibung',
|
'target_feature': TARGET_FEATURE,
|
||||||
},
|
},
|
||||||
save_result=True,
|
save_result=True,
|
||||||
)
|
)
|
||||||
@ -140,7 +141,7 @@ def build_tk_graph_post_pipe() -> Pipeline:
|
|||||||
pipe_graph_postprocessing.add(
|
pipe_graph_postprocessing.add(
|
||||||
graphs.filter_graph_by_number_edges,
|
graphs.filter_graph_by_number_edges,
|
||||||
{
|
{
|
||||||
'limit': THRESHOLD_EDGE_NUMBER,
|
'limit': MAX_EDGE_NUMBER,
|
||||||
'property': 'weight',
|
'property': 'weight',
|
||||||
},
|
},
|
||||||
)
|
)
|
||||||
|
|||||||
@ -321,7 +321,7 @@ def test_pipe_add_graph_metrics():
|
|||||||
def test_pipe_rescale_graph_edge_weights(tk_graph):
|
def test_pipe_rescale_graph_edge_weights(tk_graph):
|
||||||
rescaled_tkg, rescaled_undir = graphs.pipe_rescale_graph_edge_weights(tk_graph)
|
rescaled_tkg, rescaled_undir = graphs.pipe_rescale_graph_edge_weights(tk_graph)
|
||||||
assert rescaled_tkg[2][1]['weight'] == pytest.approx(1.0)
|
assert rescaled_tkg[2][1]['weight'] == pytest.approx(1.0)
|
||||||
assert rescaled_tkg[1][2]['weight'] == pytest.approx(0.0952)
|
assert rescaled_tkg[1][2]['weight'] == pytest.approx(0.095238)
|
||||||
assert rescaled_undir[2][1]['weight'] == pytest.approx(1.0)
|
assert rescaled_undir[2][1]['weight'] == pytest.approx(1.0)
|
||||||
assert rescaled_undir[1][2]['weight'] == pytest.approx(1.0)
|
assert rescaled_undir[1][2]['weight'] == pytest.approx(1.0)
|
||||||
|
|
||||||
@ -331,7 +331,7 @@ def test_rescale_edge_weights(import_graph, request):
|
|||||||
test_graph = request.getfixturevalue(import_graph)
|
test_graph = request.getfixturevalue(import_graph)
|
||||||
rescaled_graph = graphs.rescale_edge_weights(test_graph)
|
rescaled_graph = graphs.rescale_edge_weights(test_graph)
|
||||||
assert rescaled_graph[2][1]['weight'] == pytest.approx(1.0)
|
assert rescaled_graph[2][1]['weight'] == pytest.approx(1.0)
|
||||||
assert rescaled_graph[1][2]['weight'] == pytest.approx(0.0952)
|
assert rescaled_graph[1][2]['weight'] == pytest.approx(0.095238)
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.parametrize('import_graph', ['graph', 'tk_graph'])
|
@pytest.mark.parametrize('import_graph', ['graph', 'tk_graph'])
|
||||||
|
|||||||
@ -72,7 +72,7 @@ def test_calc_delta_to_repair(data_pre_cleaned, convert_to_days):
|
|||||||
def test_non_relevant_obj_ids(data_pre_cleaned):
|
def test_non_relevant_obj_ids(data_pre_cleaned):
|
||||||
feature_uniqueness = 'HObjektText'
|
feature_uniqueness = 'HObjektText'
|
||||||
feature_obj_id = 'ObjektID'
|
feature_obj_id = 'ObjektID'
|
||||||
threshold = 1
|
threshold = 2
|
||||||
data = data_pre_cleaned.copy()
|
data = data_pre_cleaned.copy()
|
||||||
data.at[0, feature_obj_id] = 1
|
data.at[0, feature_obj_id] = 1
|
||||||
ids_to_ignore = tl._non_relevant_obj_ids(
|
ids_to_ignore = tl._non_relevant_obj_ids(
|
||||||
@ -88,7 +88,7 @@ def test_non_relevant_obj_ids(data_pre_cleaned):
|
|||||||
def test_remove_non_relevant_obj_ids(data_pre_cleaned):
|
def test_remove_non_relevant_obj_ids(data_pre_cleaned):
|
||||||
feature_uniqueness = 'HObjektText'
|
feature_uniqueness = 'HObjektText'
|
||||||
feature_obj_id = 'ObjektID'
|
feature_obj_id = 'ObjektID'
|
||||||
threshold = 1
|
threshold = 2
|
||||||
data = data_pre_cleaned.copy()
|
data = data_pre_cleaned.copy()
|
||||||
data.at[0, feature_obj_id] = 1
|
data.at[0, feature_obj_id] = 1
|
||||||
|
|
||||||
|
|||||||
@ -25,8 +25,6 @@ from lang_main.types import LanguageModels
|
|||||||
@pytest.mark.parametrize(
|
@pytest.mark.parametrize(
|
||||||
'model_name',
|
'model_name',
|
||||||
[
|
[
|
||||||
STFRModelTypes.ALL_DISTILROBERTA_V1,
|
|
||||||
STFRModelTypes.ALL_MINI_LM_L12_V2,
|
|
||||||
STFRModelTypes.ALL_MINI_LM_L6_V2,
|
STFRModelTypes.ALL_MINI_LM_L6_V2,
|
||||||
STFRModelTypes.ALL_MPNET_BASE_V2,
|
STFRModelTypes.ALL_MPNET_BASE_V2,
|
||||||
],
|
],
|
||||||
@ -47,6 +45,25 @@ def test_load_sentence_transformer(
|
|||||||
assert isinstance(model, SentenceTransformer)
|
assert isinstance(model, SentenceTransformer)
|
||||||
|
|
||||||
|
|
||||||
|
def test_preprocess_STFR_model_name() -> None:
|
||||||
|
model_name_not_exist = 'TestModel'
|
||||||
|
ret_model_name = model_loader._preprocess_STFR_model_name(
|
||||||
|
model_name=model_name_not_exist, backend=STFRBackends.TORCH, force_download=True
|
||||||
|
)
|
||||||
|
assert ret_model_name == model_name_not_exist
|
||||||
|
ret_model_name = model_loader._preprocess_STFR_model_name(
|
||||||
|
model_name=model_name_not_exist, backend=STFRBackends.TORCH, force_download=False
|
||||||
|
)
|
||||||
|
assert ret_model_name == model_name_not_exist
|
||||||
|
|
||||||
|
model_name_exist = STFRModelTypes.E5_BASE_STS_EN_DE
|
||||||
|
backend_exist = STFRBackends.ONNX
|
||||||
|
with pytest.raises(FileNotFoundError):
|
||||||
|
_ = model_loader._preprocess_STFR_model_name(
|
||||||
|
model_name=model_name_exist, backend=backend_exist, force_download=False
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.parametrize(
|
@pytest.mark.parametrize(
|
||||||
'similarity_func',
|
'similarity_func',
|
||||||
[
|
[
|
||||||
@ -57,8 +74,6 @@ def test_load_sentence_transformer(
|
|||||||
@pytest.mark.parametrize(
|
@pytest.mark.parametrize(
|
||||||
'model_name',
|
'model_name',
|
||||||
[
|
[
|
||||||
STFRModelTypes.ALL_DISTILROBERTA_V1,
|
|
||||||
STFRModelTypes.ALL_MINI_LM_L12_V2,
|
|
||||||
STFRModelTypes.ALL_MINI_LM_L6_V2,
|
STFRModelTypes.ALL_MINI_LM_L6_V2,
|
||||||
STFRModelTypes.ALL_MPNET_BASE_V2,
|
STFRModelTypes.ALL_MPNET_BASE_V2,
|
||||||
],
|
],
|
||||||
@ -108,6 +123,14 @@ def test_instantiate_spacy_model():
|
|||||||
assert isinstance(model, Language)
|
assert isinstance(model, Language)
|
||||||
|
|
||||||
|
|
||||||
|
def test_fail_instantiate_spacy_model():
|
||||||
|
with pytest.raises(KeyError):
|
||||||
|
_ = model_loader.instantiate_model(
|
||||||
|
model_load_map=model_loader.MODEL_LOADER_MAP,
|
||||||
|
model='test', # type: ignore
|
||||||
|
) # type: ignore
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.mload
|
@pytest.mark.mload
|
||||||
def test_instantiate_stfr_model():
|
def test_instantiate_stfr_model():
|
||||||
model = model_loader.instantiate_model(
|
model = model_loader.instantiate_model(
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user