mop-tom/lang-main
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects 3 Releases Wiki Activity

added test cases

Browse Source
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
Download Patch File Download Diff File Expand all files Collapse all files

451
docs/lang_main/analysis/preprocessing.html Normal file
View 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,
) -&gt; tuple[DataFrame]:
# feature columns
feature_entries = data[target_feature]
logger.info(
&#39;Number of entries for feature &gt;&gt;%s&lt;&lt;: %d&#39;, target_feature, len(feature_entries)
)
# obtain unique entries
unique_feature_entries = feature_entries.unique()
# prepare result DataFrame
cols = [&#39;batched_idxs&#39;, &#39;entry&#39;, &#39;len&#39;, &#39;num_occur&#39;, &#39;assoc_obj_ids&#39;, &#39;num_assoc_obj_ids&#39;]
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[&#39;ObjektID&#39;].unique()
assoc_obj_ids = np.sort(assoc_obj_ids, kind=&#39;stable&#39;)
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=[&#39;num_occur&#39;, &#39;len&#39;], 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] = (
&#39;VorgangsDatum&#39;,
&#39;ErledigungsDatum&#39;,
&#39;Arbeitsbeginn&#39;,
&#39;ErstellungsDatum&#39;,
),
) -&gt; tuple[DataFrame]:
&#34;&#34;&#34;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 (
&#39;VorgangsDatum&#39;,
&#39;ErledigungsDatum&#39;,
&#39;Arbeitsbeginn&#39;,
&#39;ErstellungsDatum&#39;,
)
Returns
-------
DataFrame
raw dataset as DataFrame
&#34;&#34;&#34;
# load dataset
date_cols = list(date_cols)
data = pd.read_csv(
filepath_or_buffer=path,
sep=&#39;;&#39;,
encoding=&#39;cp1252&#39;,
parse_dates=list(date_cols),
dayfirst=True,
)
logger.info(&#39;Loaded dataset successfully.&#39;)
logger.info(
(
f&#39;Dataset properties: number of entries: {len(data)}, &#39;
f&#39;number of features {len(data.columns)}&#39;
)
)
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> :&ensp;<code>str</code></dt>
<dd>path to dataset file, usually CSV file</dd>
<dt><strong><code>date_cols</code></strong> :&ensp;<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,
) -&gt; tuple[DataFrame]:
logger.info(&#39;Start merging of similarity candidates...&#39;)
# data
merged_data = data.copy()
model_input = merged_data[&#39;entry&#39;]
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=[&#39;num_occur&#39;, &#39;num_assoc_obj_ids&#39;, &#39;len&#39;],
ascending=[False, False, False],
)
# merge information to first entry
data_idx = cast(PandasIndex, similar_data.index[0])
similar_data.at[data_idx, &#39;num_occur&#39;] = similar_data[&#39;num_occur&#39;].sum()
assoc_obj_ids = similar_data[&#39;assoc_obj_ids&#39;].to_numpy()
assoc_obj_ids = np.concatenate(assoc_obj_ids)
assoc_obj_ids = np.unique(assoc_obj_ids)
similar_data.at[data_idx, &#39;assoc_obj_ids&#39;] = assoc_obj_ids
similar_data.at[data_idx, &#39;num_assoc_obj_ids&#39;] = 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(&#39;Similarity candidates merged successfully.&#39;)
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,
) -&gt; tuple[DataFrame]:
&#34;&#34;&#34;filter DataFrame for a given numerical feature regarding their bounds
bounds are inclusive: entries (bound_lower &lt;= entry &lt;= 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
&#34;&#34;&#34;
if not any([bound_lower, bound_upper]):
raise ValueError(&#39;No bounds for filtering provided&#39;)
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] &gt;= bound_lower
filter_upper = data[feature] &lt;= bound_upper
filter = filter_lower &amp; 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 &lt;= entry &lt;= bound_upper) are retained</p>
<h2 id="parameters">Parameters</h2>
<dl>
<dt><strong><code>data</code></strong> :&ensp;<code>DataFrame</code></dt>
<dd>DataFrame to filter</dd>
<dt><strong><code>feature</code></strong> :&ensp;<code>str</code></dt>
<dd>feature name to filter</dd>
<dt><strong><code>bound_lower</code></strong> :&ensp;<code>int | None</code></dt>
<dd>lower bound of values to retain</dd>
<dt><strong><code>bound_upper</code></strong> :&ensp;<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] = (&#39;VorgangsBeschreibung&#39;,),
) -&gt; tuple[DataFrame]:
&#34;&#34;&#34;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 (&#39;VorgangsBeschreibung&#39;,)
Returns
-------
DataFrame
dataset with removed NA entries for given subset of features
&#34;&#34;&#34;
target_features = list(target_features)
wo_NA = data.dropna(axis=0, subset=target_features, ignore_index=True).copy() # type: ignore
logger.info(
f&#39;Removed NA entries for features &gt;&gt;{target_features}&lt;&lt; from dataset successfully.&#39;
)
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> :&ensp;<code>DataFrame</code></dt>
<dd>standard IHM dataset, perhaps pre-cleaned</dd>
<dt><strong><code>target_features</code></strong> :&ensp;<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,
) -&gt; tuple[DataFrame]:
&#34;&#34;&#34;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
&#34;&#34;&#34;
# obtain info about duplicates over all features
duplicates_filt = data.duplicated()
logger.info(f&#39;Number of duplicates over all features: {duplicates_filt.sum()}&#39;)
# drop duplicates
wo_duplicates = data.drop_duplicates(ignore_index=True)
duplicates_subset: list[str] = [
&#39;VorgangsID&#39;,
&#39;ObjektID&#39;,
]
duplicates_subset_filt = wo_duplicates.duplicated(subset=duplicates_subset)
logger.info(
(
&#39;Number of duplicates over subset &#39;
f&#39;&gt;&gt;{duplicates_subset}&lt;&lt;: {duplicates_subset_filt.sum()}&#39;
)
)
wo_duplicates = wo_duplicates.drop_duplicates(
subset=duplicates_subset, ignore_index=True
).copy()
logger.info(&#39;Removed all duplicates from dataset successfully.&#39;)
logger.info(
&#39;New Dataset properties: number of entries: %d, number of features %d&#39;,
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> :&ensp;<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>