/
utils.html
405 lines (384 loc) · 18.4 KB
/
utils.html
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
<!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="pdoc 0.10.0" />
<title>ktrain.text.shallownlp.utils API documentation</title>
<meta name="description" content="" />
<link rel="preload stylesheet" as="style" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/11.0.1/sanitize.min.css" integrity="sha256-PK9q560IAAa6WVRRh76LtCaI8pjTJ2z11v0miyNNjrs=" crossorigin>
<link rel="preload stylesheet" as="style" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/11.0.1/typography.min.css" integrity="sha256-7l/o7C8jubJiy74VsKTidCy1yBkRtiUGbVkYBylBqUg=" crossorigin>
<link rel="stylesheet preload" as="style" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/10.1.1/styles/github.min.css" crossorigin>
<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:30px;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:1em 0 .50em 0}h3{font-size:1.4em;margin:25px 0 10px 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 .3s ease-in-out}a:hover{color:#e82}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900}pre code{background:#f8f8f8;font-size:.8em;line-height:1.4em}code{background:#f2f2f1;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{background:#f8f8f8;border:0;border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0;padding:1ex}#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-weight:bold;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}.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 .5em;margin-bottom:1em}.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}.item .name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul{padding-left:1.5em}.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/10.1.1/highlight.min.js" integrity="sha256-Uv3H6lx7dJmRfRvH8TH6kJD1TSK1aFcwgx+mdg3epi8=" crossorigin></script>
<script>window.addEventListener('DOMContentLoaded', () => hljs.initHighlighting())</script>
</head>
<body>
<main>
<article id="content">
<header>
<h1 class="title">Module <code>ktrain.text.shallownlp.utils</code></h1>
</header>
<section id="section-intro">
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">#
# The ShallowNLP is kept self-contained for now.
# Thus, some or all of the functions here are copied from
# ktrain.text.textutils
from .imports import *
def extract_filenames(corpus_path, follow_links=False):
if os.listdir(corpus_path) == []:
raise ValueError("%s: path is empty" % corpus_path)
for root, _, fnames in os.walk(corpus_path, followlinks=follow_links):
for filename in fnames:
try:
yield os.path.join(root, filename)
except Exception:
continue
def detect_lang(texts, sample_size=32):
"""
detect language
"""
if not LANGDETECT:
raise ValueError("langdetect is missing - install with pip install langdetect")
if isinstance(texts, str):
texts = [texts]
if not isinstance(texts, (list, np.ndarray)):
raise ValueError("texts must be a list or NumPy array of strings")
lst = []
for doc in texts[:sample_size]:
try:
lst.append(langdetect.detect(doc))
except:
continue
if len(lst) == 0:
raise Exception(
"could not detect language in random sample of %s docs." % (sample_size)
)
return max(set(lst), key=lst.count)
def is_chinese(lang):
"""
include additional languages due to mistakes on short texts by langdetect
"""
return lang is not None and lang.startswith("zh-") or lang in ["ja", "ko"]
def split_chinese(texts):
if not JIEBA:
raise ValueError("jieba is missing - install with pip install jieba")
if isinstance(texts, str):
texts = [texts]
split_texts = []
for doc in texts:
seg_list = jieba.cut(doc, cut_all=False)
seg_list = list(seg_list)
split_texts.append(seg_list)
return [" ".join(tokens) for tokens in split_texts]
def decode_by_line(texts, encoding="utf-8", verbose=1):
"""
Decode text line by line and skip over errors.
"""
if isinstance(texts, str):
texts = [texts]
new_texts = []
skips = 0
num_lines = 0
for doc in texts:
text = ""
for line in doc.splitlines():
num_lines += 1
try:
line = line.decode(encoding)
except:
skips += 1
continue
text += line
new_texts.append(text)
pct = round((skips * 1.0 / num_lines) * 100, 1)
if verbose:
print("skipped %s lines (%s%%) due to character decoding errors" % (skips, pct))
if pct > 10:
print("If this is too many, try a different encoding")
return new_texts
def detect_encoding(texts, sample_size=32):
if not CHARDET:
raise ValueError("cchardet is missing - install with pip install cchardet")
if isinstance(texts, str):
texts = [texts]
lst = [chardet.detect(doc)["encoding"] for doc in texts[:sample_size]]
encoding = max(set(lst), key=lst.count)
encoding = "utf-8" if encoding.lower() in ["ascii", "utf8", "utf-8"] else encoding
return encoding
def read_text(filename):
with open(filename, "rb") as f:
text = f.read()
encoding = detect_encoding([text])
try:
decoded_text = text.decode(encoding)
except:
U.vprint(
"Decoding with %s failed 1st attempt - using %s with skips"
% (encoding, encoding),
verbose=verbose,
)
decoded_text = decode_by_line(text, encoding=encoding)
return decoded_text.strip()
def sent_tokenize(text):
"""
segment text into sentences
"""
lang = detect_lang(text)
sents = []
if is_chinese(lang):
for sent in re.findall("[^!?。\.\!\?]+[!?。\.\!\?]?", text, flags=re.U):
sents.append(sent)
else:
for paragraph in segmenter.process(text):
for sentence in paragraph:
sents.append(" ".join([t.value for t in sentence]))
return sents</code></pre>
</details>
</section>
<section>
</section>
<section>
</section>
<section>
<h2 class="section-title" id="header-functions">Functions</h2>
<dl>
<dt id="ktrain.text.shallownlp.utils.decode_by_line"><code class="name flex">
<span>def <span class="ident">decode_by_line</span></span>(<span>texts, encoding='utf-8', verbose=1)</span>
</code></dt>
<dd>
<div class="desc"><p>Decode text line by line and skip over errors.</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def decode_by_line(texts, encoding="utf-8", verbose=1):
"""
Decode text line by line and skip over errors.
"""
if isinstance(texts, str):
texts = [texts]
new_texts = []
skips = 0
num_lines = 0
for doc in texts:
text = ""
for line in doc.splitlines():
num_lines += 1
try:
line = line.decode(encoding)
except:
skips += 1
continue
text += line
new_texts.append(text)
pct = round((skips * 1.0 / num_lines) * 100, 1)
if verbose:
print("skipped %s lines (%s%%) due to character decoding errors" % (skips, pct))
if pct > 10:
print("If this is too many, try a different encoding")
return new_texts</code></pre>
</details>
</dd>
<dt id="ktrain.text.shallownlp.utils.detect_encoding"><code class="name flex">
<span>def <span class="ident">detect_encoding</span></span>(<span>texts, sample_size=32)</span>
</code></dt>
<dd>
<div class="desc"></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def detect_encoding(texts, sample_size=32):
if not CHARDET:
raise ValueError("cchardet is missing - install with pip install cchardet")
if isinstance(texts, str):
texts = [texts]
lst = [chardet.detect(doc)["encoding"] for doc in texts[:sample_size]]
encoding = max(set(lst), key=lst.count)
encoding = "utf-8" if encoding.lower() in ["ascii", "utf8", "utf-8"] else encoding
return encoding</code></pre>
</details>
</dd>
<dt id="ktrain.text.shallownlp.utils.detect_lang"><code class="name flex">
<span>def <span class="ident">detect_lang</span></span>(<span>texts, sample_size=32)</span>
</code></dt>
<dd>
<div class="desc"><p>detect language</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def detect_lang(texts, sample_size=32):
"""
detect language
"""
if not LANGDETECT:
raise ValueError("langdetect is missing - install with pip install langdetect")
if isinstance(texts, str):
texts = [texts]
if not isinstance(texts, (list, np.ndarray)):
raise ValueError("texts must be a list or NumPy array of strings")
lst = []
for doc in texts[:sample_size]:
try:
lst.append(langdetect.detect(doc))
except:
continue
if len(lst) == 0:
raise Exception(
"could not detect language in random sample of %s docs." % (sample_size)
)
return max(set(lst), key=lst.count)</code></pre>
</details>
</dd>
<dt id="ktrain.text.shallownlp.utils.extract_filenames"><code class="name flex">
<span>def <span class="ident">extract_filenames</span></span>(<span>corpus_path, follow_links=False)</span>
</code></dt>
<dd>
<div class="desc"></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def extract_filenames(corpus_path, follow_links=False):
if os.listdir(corpus_path) == []:
raise ValueError("%s: path is empty" % corpus_path)
for root, _, fnames in os.walk(corpus_path, followlinks=follow_links):
for filename in fnames:
try:
yield os.path.join(root, filename)
except Exception:
continue</code></pre>
</details>
</dd>
<dt id="ktrain.text.shallownlp.utils.is_chinese"><code class="name flex">
<span>def <span class="ident">is_chinese</span></span>(<span>lang)</span>
</code></dt>
<dd>
<div class="desc"><p>include additional languages due to mistakes on short texts by langdetect</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def is_chinese(lang):
"""
include additional languages due to mistakes on short texts by langdetect
"""
return lang is not None and lang.startswith("zh-") or lang in ["ja", "ko"]</code></pre>
</details>
</dd>
<dt id="ktrain.text.shallownlp.utils.read_text"><code class="name flex">
<span>def <span class="ident">read_text</span></span>(<span>filename)</span>
</code></dt>
<dd>
<div class="desc"></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def read_text(filename):
with open(filename, "rb") as f:
text = f.read()
encoding = detect_encoding([text])
try:
decoded_text = text.decode(encoding)
except:
U.vprint(
"Decoding with %s failed 1st attempt - using %s with skips"
% (encoding, encoding),
verbose=verbose,
)
decoded_text = decode_by_line(text, encoding=encoding)
return decoded_text.strip()</code></pre>
</details>
</dd>
<dt id="ktrain.text.shallownlp.utils.sent_tokenize"><code class="name flex">
<span>def <span class="ident">sent_tokenize</span></span>(<span>text)</span>
</code></dt>
<dd>
<div class="desc"><p>segment text into sentences</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def sent_tokenize(text):
"""
segment text into sentences
"""
lang = detect_lang(text)
sents = []
if is_chinese(lang):
for sent in re.findall("[^!?。\.\!\?]+[!?。\.\!\?]?", text, flags=re.U):
sents.append(sent)
else:
for paragraph in segmenter.process(text):
for sentence in paragraph:
sents.append(" ".join([t.value for t in sentence]))
return sents</code></pre>
</details>
</dd>
<dt id="ktrain.text.shallownlp.utils.split_chinese"><code class="name flex">
<span>def <span class="ident">split_chinese</span></span>(<span>texts)</span>
</code></dt>
<dd>
<div class="desc"></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def split_chinese(texts):
if not JIEBA:
raise ValueError("jieba is missing - install with pip install jieba")
if isinstance(texts, str):
texts = [texts]
split_texts = []
for doc in texts:
seg_list = jieba.cut(doc, cut_all=False)
seg_list = list(seg_list)
split_texts.append(seg_list)
return [" ".join(tokens) for tokens in split_texts]</code></pre>
</details>
</dd>
</dl>
</section>
<section>
</section>
</article>
<nav id="sidebar">
<h1>Index</h1>
<div class="toc">
<ul></ul>
</div>
<ul id="index">
<li><h3>Super-module</h3>
<ul>
<li><code><a title="ktrain.text.shallownlp" href="index.html">ktrain.text.shallownlp</a></code></li>
</ul>
</li>
<li><h3><a href="#header-functions">Functions</a></h3>
<ul class="two-column">
<li><code><a title="ktrain.text.shallownlp.utils.decode_by_line" href="#ktrain.text.shallownlp.utils.decode_by_line">decode_by_line</a></code></li>
<li><code><a title="ktrain.text.shallownlp.utils.detect_encoding" href="#ktrain.text.shallownlp.utils.detect_encoding">detect_encoding</a></code></li>
<li><code><a title="ktrain.text.shallownlp.utils.detect_lang" href="#ktrain.text.shallownlp.utils.detect_lang">detect_lang</a></code></li>
<li><code><a title="ktrain.text.shallownlp.utils.extract_filenames" href="#ktrain.text.shallownlp.utils.extract_filenames">extract_filenames</a></code></li>
<li><code><a title="ktrain.text.shallownlp.utils.is_chinese" href="#ktrain.text.shallownlp.utils.is_chinese">is_chinese</a></code></li>
<li><code><a title="ktrain.text.shallownlp.utils.read_text" href="#ktrain.text.shallownlp.utils.read_text">read_text</a></code></li>
<li><code><a title="ktrain.text.shallownlp.utils.sent_tokenize" href="#ktrain.text.shallownlp.utils.sent_tokenize">sent_tokenize</a></code></li>
<li><code><a title="ktrain.text.shallownlp.utils.split_chinese" href="#ktrain.text.shallownlp.utils.split_chinese">split_chinese</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> 0.10.0</a>.</p>
</footer>
</body>
</html>