274 lines
15 KiB
HTML
274 lines
15 KiB
HTML
<!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>
|