-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathpreprocessing.html
More file actions
597 lines (561 loc) · 24.6 KB
/
preprocessing.html
File metadata and controls
597 lines (561 loc) · 24.6 KB
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
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
<!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>preprocessing.preprocessing 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>preprocessing.preprocessing</code></h1>
</header>
<section id="section-intro">
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">from nltk.util import pr
import numpy as np
import nltk
# nltk.download('stopwords')
# nltk.download('punkt')
# nltk.download('wordnet')
from nltk.corpus import stopwords
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
from nltk.stem import PorterStemmer
from nltk.tokenize import word_tokenize
from nltk.tokenize import sent_tokenize
from num2words import num2words
import json
def split_sentences(data):
"""
Split sentences
return: sentences
"""
sentences = sent_tokenize(str(data))
return sentences
def split_paragraphs(data):
"""
Split paragraphs
return: paragraphs
"""
paragraphs = data.split('\n')
return paragraphs
def convert_to_lowercase(data):
#convert string to lowercase
data = data.lower()
return data
def remove_apostrophe(data):
return np.char.replace(data, "'", "")
def remove_special_characters(data):
"""
Remove all special characters
return: data without special characters numpy array
"""
#vineet irfan
symbols = "!\"#$%&()*+-,/:;<=>?@[\]^_`{|}~\n"
for i in range(len(symbols)):
data = np.char.replace(data, symbols[i], ' ')
data = np.char.replace(data, " ", " ")
data = np.char.replace(data, ',', '')
data = remove_apostrophe(data)
return data
def remove_stop_words(data):
"""
Remove all stop words
return: data without stop words strings
"""
# remove all stop words
stop_words = set(stopwords.words('english'))
data = np.char.replace(data, '\s' + '|'.join(stop_words) + '\s', ' ')
return data
def stemming(data):
"""
Stemming
return: words after stemming
"""
stemmer= PorterStemmer()
tokens = word_tokenize(str(data))
new_text = ""
for w in tokens:
new_text = new_text + " " + stemmer.stem(w)
return new_text
def convert_numbers_to_words(data):
"""
Convert numbers to words
return: data without numbers
"""
# convert numbers to words
#vineet-irfan
tokens = word_tokenize(str(data))
new_text = ""
for w in tokens:
try:
w = num2words(int(w))
except:
pass
new_text = new_text + " " + w
new_text = np.char.replace(new_text, "-", " ")
return new_text
def lemmatization(data):
"""
Lemmatization
return: words after lemmatization
"""
lemmatizer = WordNetLemmatizer()
tokens = word_tokenize(str(data))
new_text = ""
for w in tokens:
new_text = new_text + " " + lemmatizer.lemmatize(w)
return new_text
def expand_contradictions(data):
"""
Expand contradictions
return: data without contradictions
"""
# expand contradictions
with open('contradiction_map.txt') as f:
CONTRACTION_MAP = f.read()
js = json.loads(CONTRACTION_MAP)
list_Of_tokens = data.split(' ')
# Checking for whether the given token matches with the Key & replacing word with key's value.
# Check whether Word is in list_Of_tokens or not.
for Word in list_Of_tokens:
# Check whether found word is in dictionary "Contraction Map" or not as a key.
if Word in js:
# If Word is present in both dictionary & list_Of_tokens, replace that word with the key value.
list_Of_tokens = [item.replace(Word, js[Word]) for item in list_Of_tokens]
# Converting list of tokens to String.
String_Of_tokens = ' '.join(str(e) for e in list_Of_tokens)
return String_Of_tokens
def remove_abbriviation(data):
# read abbriviation from file and replace all instances of abbreviations from data
# Riya Payal
with open('abbreviations.json', 'r') as f:
abbrevs_dict = json.load(f)
for key, value in abbrevs_dict.items():
text = text.replace(" "+key+".", " "+value+" ")
text = text.replace(" "+key+" ", " "+value+" ")
return text
def preprocess_data(data,ec=True,sc=True,sw=True,sn=True,st=True,sl=True,ab=True,rsc=True):
"""
Preprocess data
return: preprocessed data
"""
# convert to lowercase
if sc:
data = convert_to_lowercase(data)
# convert data to string
#expand contradictions
if ec:
data = expand_contradictions(str(data))
# remove special characters
if rsc:
data = remove_special_characters(data)
# remove single character words
if sw:
data = remove_stop_words(data)
# stemming
if st:
data = stemming(data)
# convert numbers to words
if sn:
data = convert_numbers_to_words(data)
# lemmatization
if sl:
data = lemmatization(data)
# remove abbriviation
if ab:
data = remove_abbriviation(str(data))
return str(data)
def preprocess_file(file_path,ec=True,sc=True,sw=True,sn=True,st=True,sl=True,cn=True,exp=True,ab=True,rsc=True):
"""
Preprocess file
return: preprocessed file
"""
#write funtion docstring
# read file
with open(file_path, 'r') as f:
data = f.read()
# preprocess data
data = preprocess_data(data,ec=ec,sc=sc,sw=sw,sn=sn,st=st,sl=sl,ab=ab,rsc=rsc)
return data
def preprocess_file(input_file_path,output_file_path,ec=True,sc=True,sw=True,sn=True,st=True,sl=True,cn=True,exp=True,ab=True,rsc=True):
"""
Preprocess file
return: preprocessed file
"""
with open(input_file_path, 'r') as f:
data = f.read()
data = preprocess_data(data,ec=ec,sc=sc,sw=sw,sn=sn,st=st,sl=sl,ab=ab,rsc=rsc)
with open(output_file_path, 'w') as f:
f.write(data)
return data</code></pre>
</details>
</section>
<section>
</section>
<section>
</section>
<section>
<h2 class="section-title" id="header-functions">Functions</h2>
<dl>
<dt id="preprocessing.preprocessing.convert_numbers_to_words"><code class="name flex">
<span>def <span class="ident">convert_numbers_to_words</span></span>(<span>data)</span>
</code></dt>
<dd>
<div class="desc"><p>Convert numbers to words
return: data without numbers</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def convert_numbers_to_words(data):
"""
Convert numbers to words
return: data without numbers
"""
# convert numbers to words
#vineet-irfan
tokens = word_tokenize(str(data))
new_text = ""
for w in tokens:
try:
w = num2words(int(w))
except:
pass
new_text = new_text + " " + w
new_text = np.char.replace(new_text, "-", " ")
return new_text</code></pre>
</details>
</dd>
<dt id="preprocessing.preprocessing.convert_to_lowercase"><code class="name flex">
<span>def <span class="ident">convert_to_lowercase</span></span>(<span>data)</span>
</code></dt>
<dd>
<div class="desc"></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def convert_to_lowercase(data):
#convert string to lowercase
data = data.lower()
return data</code></pre>
</details>
</dd>
<dt id="preprocessing.preprocessing.expand_contradictions"><code class="name flex">
<span>def <span class="ident">expand_contradictions</span></span>(<span>data)</span>
</code></dt>
<dd>
<div class="desc"><p>Expand contradictions
return: data without contradictions</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def expand_contradictions(data):
"""
Expand contradictions
return: data without contradictions
"""
# expand contradictions
with open('contradiction_map.txt') as f:
CONTRACTION_MAP = f.read()
js = json.loads(CONTRACTION_MAP)
list_Of_tokens = data.split(' ')
# Checking for whether the given token matches with the Key & replacing word with key's value.
# Check whether Word is in list_Of_tokens or not.
for Word in list_Of_tokens:
# Check whether found word is in dictionary "Contraction Map" or not as a key.
if Word in js:
# If Word is present in both dictionary & list_Of_tokens, replace that word with the key value.
list_Of_tokens = [item.replace(Word, js[Word]) for item in list_Of_tokens]
# Converting list of tokens to String.
String_Of_tokens = ' '.join(str(e) for e in list_Of_tokens)
return String_Of_tokens</code></pre>
</details>
</dd>
<dt id="preprocessing.preprocessing.lemmatization"><code class="name flex">
<span>def <span class="ident">lemmatization</span></span>(<span>data)</span>
</code></dt>
<dd>
<div class="desc"><p>Lemmatization
return: words after lemmatization</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def lemmatization(data):
"""
Lemmatization
return: words after lemmatization
"""
lemmatizer = WordNetLemmatizer()
tokens = word_tokenize(str(data))
new_text = ""
for w in tokens:
new_text = new_text + " " + lemmatizer.lemmatize(w)
return new_text</code></pre>
</details>
</dd>
<dt id="preprocessing.preprocessing.preprocess_data"><code class="name flex">
<span>def <span class="ident">preprocess_data</span></span>(<span>data, ec=True, sc=True, sw=True, sn=True, st=True, sl=True, ab=True, rsc=True)</span>
</code></dt>
<dd>
<div class="desc"><p>Preprocess data
return: preprocessed data</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def preprocess_data(data,ec=True,sc=True,sw=True,sn=True,st=True,sl=True,ab=True,rsc=True):
"""
Preprocess data
return: preprocessed data
"""
# convert to lowercase
if sc:
data = convert_to_lowercase(data)
# convert data to string
#expand contradictions
if ec:
data = expand_contradictions(str(data))
# remove special characters
if rsc:
data = remove_special_characters(data)
# remove single character words
if sw:
data = remove_stop_words(data)
# stemming
if st:
data = stemming(data)
# convert numbers to words
if sn:
data = convert_numbers_to_words(data)
# lemmatization
if sl:
data = lemmatization(data)
# remove abbriviation
if ab:
data = remove_abbriviation(str(data))
return str(data)</code></pre>
</details>
</dd>
<dt id="preprocessing.preprocessing.preprocess_file"><code class="name flex">
<span>def <span class="ident">preprocess_file</span></span>(<span>input_file_path, output_file_path, ec=True, sc=True, sw=True, sn=True, st=True, sl=True, cn=True, exp=True, ab=True, rsc=True)</span>
</code></dt>
<dd>
<div class="desc"><p>Preprocess file
return: preprocessed file</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def preprocess_file(input_file_path,output_file_path,ec=True,sc=True,sw=True,sn=True,st=True,sl=True,cn=True,exp=True,ab=True,rsc=True):
"""
Preprocess file
return: preprocessed file
"""
with open(input_file_path, 'r') as f:
data = f.read()
data = preprocess_data(data,ec=ec,sc=sc,sw=sw,sn=sn,st=st,sl=sl,ab=ab,rsc=rsc)
with open(output_file_path, 'w') as f:
f.write(data)
return data</code></pre>
</details>
</dd>
<dt id="preprocessing.preprocessing.remove_abbriviation"><code class="name flex">
<span>def <span class="ident">remove_abbriviation</span></span>(<span>data)</span>
</code></dt>
<dd>
<div class="desc"></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def remove_abbriviation(data):
# read abbriviation from file and replace all instances of abbreviations from data
# Riya Payal
with open('abbreviations.json', 'r') as f:
abbrevs_dict = json.load(f)
for key, value in abbrevs_dict.items():
text = text.replace(" "+key+".", " "+value+" ")
text = text.replace(" "+key+" ", " "+value+" ")
return text</code></pre>
</details>
</dd>
<dt id="preprocessing.preprocessing.remove_apostrophe"><code class="name flex">
<span>def <span class="ident">remove_apostrophe</span></span>(<span>data)</span>
</code></dt>
<dd>
<div class="desc"></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def remove_apostrophe(data):
return np.char.replace(data, "'", "")</code></pre>
</details>
</dd>
<dt id="preprocessing.preprocessing.remove_special_characters"><code class="name flex">
<span>def <span class="ident">remove_special_characters</span></span>(<span>data)</span>
</code></dt>
<dd>
<div class="desc"><p>Remove all special characters
return: data without special characters numpy array</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def remove_special_characters(data):
"""
Remove all special characters
return: data without special characters numpy array
"""
#vineet irfan
symbols = "!\"#$%&()*+-,/:;<=>?@[\]^_`{|}~\n"
for i in range(len(symbols)):
data = np.char.replace(data, symbols[i], ' ')
data = np.char.replace(data, " ", " ")
data = np.char.replace(data, ',', '')
data = remove_apostrophe(data)
return data</code></pre>
</details>
</dd>
<dt id="preprocessing.preprocessing.remove_stop_words"><code class="name flex">
<span>def <span class="ident">remove_stop_words</span></span>(<span>data)</span>
</code></dt>
<dd>
<div class="desc"><p>Remove all stop words
return: data without stop words strings</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def remove_stop_words(data):
"""
Remove all stop words
return: data without stop words strings
"""
# remove all stop words
stop_words = set(stopwords.words('english'))
data = np.char.replace(data, '\s' + '|'.join(stop_words) + '\s', ' ')
return data</code></pre>
</details>
</dd>
<dt id="preprocessing.preprocessing.split_paragraphs"><code class="name flex">
<span>def <span class="ident">split_paragraphs</span></span>(<span>data)</span>
</code></dt>
<dd>
<div class="desc"><p>Split paragraphs
return: paragraphs</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def split_paragraphs(data):
"""
Split paragraphs
return: paragraphs
"""
paragraphs = data.split('\n')
return paragraphs</code></pre>
</details>
</dd>
<dt id="preprocessing.preprocessing.split_sentences"><code class="name flex">
<span>def <span class="ident">split_sentences</span></span>(<span>data)</span>
</code></dt>
<dd>
<div class="desc"><p>Split sentences
return: sentences</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def split_sentences(data):
"""
Split sentences
return: sentences
"""
sentences = sent_tokenize(str(data))
return sentences</code></pre>
</details>
</dd>
<dt id="preprocessing.preprocessing.stemming"><code class="name flex">
<span>def <span class="ident">stemming</span></span>(<span>data)</span>
</code></dt>
<dd>
<div class="desc"><p>Stemming
return: words after stemming</p></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def stemming(data):
"""
Stemming
return: words after stemming
"""
stemmer= PorterStemmer()
tokens = word_tokenize(str(data))
new_text = ""
for w in tokens:
new_text = new_text + " " + stemmer.stem(w)
return new_text</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="preprocessing" href="index.html">preprocessing</a></code></li>
</ul>
</li>
<li><h3><a href="#header-functions">Functions</a></h3>
<ul class="">
<li><code><a title="preprocessing.preprocessing.convert_numbers_to_words" href="#preprocessing.preprocessing.convert_numbers_to_words">convert_numbers_to_words</a></code></li>
<li><code><a title="preprocessing.preprocessing.convert_to_lowercase" href="#preprocessing.preprocessing.convert_to_lowercase">convert_to_lowercase</a></code></li>
<li><code><a title="preprocessing.preprocessing.expand_contradictions" href="#preprocessing.preprocessing.expand_contradictions">expand_contradictions</a></code></li>
<li><code><a title="preprocessing.preprocessing.lemmatization" href="#preprocessing.preprocessing.lemmatization">lemmatization</a></code></li>
<li><code><a title="preprocessing.preprocessing.preprocess_data" href="#preprocessing.preprocessing.preprocess_data">preprocess_data</a></code></li>
<li><code><a title="preprocessing.preprocessing.preprocess_file" href="#preprocessing.preprocessing.preprocess_file">preprocess_file</a></code></li>
<li><code><a title="preprocessing.preprocessing.remove_abbriviation" href="#preprocessing.preprocessing.remove_abbriviation">remove_abbriviation</a></code></li>
<li><code><a title="preprocessing.preprocessing.remove_apostrophe" href="#preprocessing.preprocessing.remove_apostrophe">remove_apostrophe</a></code></li>
<li><code><a title="preprocessing.preprocessing.remove_special_characters" href="#preprocessing.preprocessing.remove_special_characters">remove_special_characters</a></code></li>
<li><code><a title="preprocessing.preprocessing.remove_stop_words" href="#preprocessing.preprocessing.remove_stop_words">remove_stop_words</a></code></li>
<li><code><a title="preprocessing.preprocessing.split_paragraphs" href="#preprocessing.preprocessing.split_paragraphs">split_paragraphs</a></code></li>
<li><code><a title="preprocessing.preprocessing.split_sentences" href="#preprocessing.preprocessing.split_sentences">split_sentences</a></code></li>
<li><code><a title="preprocessing.preprocessing.stemming" href="#preprocessing.preprocessing.stemming">stemming</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>