321 lines
16 KiB
HTML
321 lines
16 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.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>
|