added test cases

This commit is contained in:
Florian Förster
2025-01-22 16:54:15 +01:00
parent 30fe71e80a
commit fb28b8548b
28 changed files with 17721 additions and 17 deletions

View 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() -&gt; Pipeline:
pipe_target_feat = Pipeline(name=&#39;Target_Feature&#39;, working_dir=SAVE_PATH_FOLDER)
pipe_target_feat.add(
load_raw_data,
{
&#39;date_cols&#39;: DATE_COLS,
},
)
pipe_target_feat.add(remove_duplicates)
pipe_target_feat.add(remove_NA, save_result=True)
pipe_target_feat.add(
entry_wise_cleansing,
{
&#39;target_features&#39;: (TARGET_FEATURE,),
&#39;cleansing_func&#39;: clean_string_slim,
},
save_result=True,
filename=EntryPoints.TIMELINE,
)
pipe_target_feat.add(
analyse_feature,
{
&#39;target_feature&#39;: 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() -&gt; Pipeline:
pipe_merge = Pipeline(name=&#39;Merge_Duplicates&#39;, working_dir=SAVE_PATH_FOLDER)
pipe_merge.add(
numeric_pre_filter_feature,
{
&#39;feature&#39;: &#39;len&#39;,
&#39;bound_lower&#39;: THRESHOLD_AMOUNT_CHARACTERS,
&#39;bound_upper&#39;: None,
},
)
pipe_merge.add(
merge_similarity_duplicates,
{
&#39;model&#39;: STFR_MODEL,
&#39;cos_sim_threshold&#39;: 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() -&gt; Pipeline:
pipe_timeline = Pipeline(name=&#39;Timeline_Analysis&#39;, working_dir=SAVE_PATH_FOLDER)
pipe_timeline.add(
cleanup_descriptions,
{
&#39;properties&#39;: [&#39;ErledigungsBeschreibung&#39;],
},
)
pipe_timeline.add(
calc_delta_to_repair,
{
&#39;date_feature_start&#39;: &#39;ErstellungsDatum&#39;,
&#39;date_feature_end&#39;: &#39;ErledigungsDatum&#39;,
&#39;name_delta_feature&#39;: NAME_DELTA_FEAT_TO_REPAIR,
&#39;convert_to_days&#39;: True,
},
save_result=True,
filename=EntryPoints.TIMELINE_POST,
)
pipe_timeline.add(
remove_non_relevant_obj_ids,
{
&#39;thresh_unique_feat_per_id&#39;: THRESHOLD_UNIQUE_TEXTS,
&#39;feature_uniqueness&#39;: UNIQUE_CRITERION_FEATURE,
&#39;feature_obj_id&#39;: FEATURE_NAME_OBJ_ID,
},
save_result=True,
)
pipe_timeline.add(
generate_model_input,
{
&#39;target_feature_name&#39;: &#39;nlp_model_input&#39;,
&#39;model_input_features&#39;: MODEL_INPUT_FEATURES,
},
)
pipe_timeline.add(
filter_activities_per_obj_id,
{
&#39;activity_feature&#39;: ACTIVITY_FEATURE,
&#39;relevant_activity_types&#39;: ACTIVITY_TYPES,
&#39;feature_obj_id&#39;: FEATURE_NAME_OBJ_ID,
&#39;threshold_num_activities&#39;: THRESHOLD_NUM_ACTIVITIES,
},
)
pipe_timeline.add(
get_timeline_candidates,
{
&#39;model&#39;: STFR_MODEL,
&#39;cos_sim_threshold&#39;: THRESHOLD_TIMELINE_SIMILARITY,
&#39;feature_obj_id&#39;: FEATURE_NAME_OBJ_ID,
&#39;feature_obj_text&#39;: FEATURE_NAME_OBJ_TEXT,
&#39;model_input_feature&#39;: &#39;nlp_model_input&#39;,
},
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() -&gt; Pipeline:
pipe_token_analysis = Pipeline(name=&#39;Token_Analysis&#39;, working_dir=SAVE_PATH_FOLDER)
pipe_token_analysis.add(
build_token_graph,
{
&#39;model&#39;: SPACY_MODEL,
&#39;target_feature&#39;: &#39;entry&#39;,
&#39;weights_feature&#39;: &#39;num_occur&#39;,
&#39;batch_idx_feature&#39;: &#39;batched_idxs&#39;,
&#39;build_map&#39;: False,
&#39;batch_size_model&#39;: 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() -&gt; Pipeline:
pipe_graph_postprocessing = Pipeline(
name=&#39;Graph_Postprocessing&#39;, working_dir=SAVE_PATH_FOLDER
)
pipe_graph_postprocessing.add(
graphs.filter_graph_by_number_edges,
{
&#39;limit&#39;: MAX_EDGE_NUMBER,
&#39;property&#39;: &#39;weight&#39;,
},
)
pipe_graph_postprocessing.add(
graphs.filter_graph_by_node_degree,
{
&#39;bound_lower&#39;: 1,
&#39;bound_upper&#39;: 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,
) -&gt; 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(
(
&#39;Dependencies for Cytoscape interaction not found.&#39;
&#39;Install package with optional dependencies.&#39;
)
)
pipe_graph_rendering = Pipeline(
name=&#39;Graph_Static-Rendering&#39;,
working_dir=SAVE_PATH_FOLDER,
)
pipe_graph_rendering.add(
cyto.import_to_cytoscape,
{
&#39;network_name&#39;: base_network_name,
},
)
pipe_graph_rendering.add(
cyto.layout_network,
{
&#39;network_name&#39;: base_network_name,
},
)
pipe_graph_rendering.add(
cyto.apply_style_to_network,
{
&#39;network_name&#39;: base_network_name,
},
)
pipe_graph_rendering.add(
cyto.export_network_to_image,
{
&#39;filename&#39;: base_network_name,
&#39;target_folder&#39;: export_folder,
&#39;network_name&#39;: base_network_name,
},
)
if with_subgraphs:
pipe_graph_rendering.add(
cyto.get_subgraph_node_selection,
{
&#39;network_name&#39;: base_network_name,
},
)
pipe_graph_rendering.add(
cyto.build_subnetworks,
{
&#39;export_image&#39;: True,
&#39;target_folder&#39;: export_folder,
&#39;network_name&#39;: 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,
) -&gt; Pipeline:
pipe_graph_rescaling = Pipeline(name=&#39;Graph_Rescaling&#39;, 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>