forked from amsurve/news-article-classifier
/
clean_text.py
225 lines (211 loc) · 6.15 KB
/
clean_text.py
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
# %%
import string
import textblob
import re
from nltk.stem import PorterStemmer
from sklearn.preprocessing import FunctionTransformer
from sklearn.pipeline import Pipeline
import nltk
nltk.download('wordnet')
nltk.download('punkt')
nltk.download('stopwords')
from nltk.corpus import stopwords
nltk.download('averaged_perceptron_tagger')
from nltk.stem import WordNetLemmatizer
from nltk.corpus import wordnet
import pandas as pd
from nltk.tokenize import MWETokenizer, word_tokenize
# %%
cList = {
"ain't": "am not",
"aren't": "are not",
"can't": "cannot",
"can't've": "cannot have",
"'cause": "because",
"could've": "could have",
"couldn't": "could not",
"couldn't've": "could not have",
"didn't": "did not",
"doesn't": "does not",
"don't": "do not",
"hadn't": "had not",
"hadn't've": "had not have",
"hasn't": "has not",
"haven't": "have not",
"he'd": "he would",
"he'd've": "he would have",
"he'll": "he will",
"he'll've": "he will have",
"he's": "he is",
"how'd": "how did",
"how'd'y": "how do you",
"how'll": "how will",
"how's": "how is",
"i'd": "i would",
"i'd've": "i would have",
"i'll": "i will",
"i'll've": "i will have",
"i'm": "i am",
"i've": "i have",
"isn't": "is not",
"it'd": "it had",
"it'd've": "it would have",
"it'll": "it will",
"it'll've": "it will have",
"it's": "it is",
"let's": "let us",
"ma'am": "madam",
"mayn't": "may not",
"might've": "might have",
"mightn't": "might not",
"mightn't've": "might not have",
"must've": "must have",
"mustn't": "must not",
"mustn't've": "must not have",
"needn't": "need not",
"needn't've": "need not have",
"o'clock": "of the clock",
"oughtn't": "ought not",
"oughtn't've": "ought not have",
"shan't": "shall not",
"sha'n't": "shall not",
"shan't've": "shall not have",
"she'd": "she would",
"she'd've": "she would have",
"she'll": "she will",
"she'll've": "she will have",
"she's": "she is",
"should've": "should have",
"shouldn't": "should not",
"shouldn't've": "should not have",
"so've": "so have",
"so's": "so is",
"that'd": "that would",
"that'd've": "that would have",
"that's": "that is",
"there'd": "there had",
"there'd've": "there would have",
"there's": "there is",
"they'd": "they would",
"they'd've": "they would have",
"they'll": "they will",
"they'll've": "they will have",
"they're": "they are",
"they've": "they have",
"to've": "to have",
"wasn't": "was not",
"we'd": "we had",
"we'd've": "we would have",
"we'll": "we will",
"we'll've": "we will have",
"we're": "we are",
"we've": "we have",
"weren't": "were not",
"what'll": "what will",
"what'll've": "what will have",
"what're": "what are",
"what's": "what is",
"what've": "what have",
"when's": "when is",
"when've": "when have",
"where'd": "where did",
"where's": "where is",
"where've": "where have",
"who'll": "who will",
"who'll've": "who will have",
"who's": "who is",
"who've": "who have",
"why's": "why is",
"why've": "why have",
"will've": "will have",
"won't": "will not",
"won't've": "will not have",
"would've": "would have",
"wouldn't": "would not",
"wouldn't've": "would not have",
"y'all": "you all",
"y'alls": "you alls",
"y'all'd": "you all would",
"y'all'd've": "you all would have",
"y'all're": "you all are",
"y'all've": "you all have",
"you'd": "you had",
"you'd've": "you would have",
"you'll": "you you will",
"you'll've": "you you will have",
"you're": "you are",
"you've": "you have"
}
c_re = re.compile('(%s)' % '|'.join(cList.keys()))
#%%
lemmatizer = WordNetLemmatizer()
def nltk_tag_to_wordnet_tag(nltk_tag):
if nltk_tag.startswith('J'):
return wordnet.ADJ
elif nltk_tag.startswith('V'):
return wordnet.VERB
elif nltk_tag.startswith('N'):
return wordnet.NOUN
elif nltk_tag.startswith('R'):
return wordnet.ADV
else:
return None
#%%
def expandContractions(text, c_re=c_re):
def replace(match):
return cList[match.group(0)]
return c_re.sub(replace, text.lower())
def tokenize_and_remove_punct(text):
text = text.translate(str.maketrans('', '', string.punctuation))
mtokenizer = MWETokenizer()
mwe = mtokenizer.tokenize(text.split())
words =[]
for t in mwe:
if t.isalpha():
words.append(t)
return words
def tags(tokens):
tags = nltk.pos_tag(tokens)
return tags
def lemmatize(tags):
wordnet_tagged = map(lambda x: (x[0], nltk_tag_to_wordnet_tag(x[1])), tags)
lemmatized_sentence = []
for word, tag in wordnet_tagged:
if tag is None:
#if there is no available tag, append the token as is
lemmatized_sentence.append(word)
else:
#else use the tag to lemmatize the token
lemmatized_sentence.append(lemmatizer.lemmatize(word, tag))
return lemmatized_sentence
def stopword_removal(words):
stopwords = nltk.corpus.stopwords.words('english')
newStopWords = ['said','say', 'says','mr']
stopwords.extend(newStopWords)
word_filtered = []
for w in words:
if w not in stopwords:
word_filtered.append(w)
unique = list(dict.fromkeys(word_filtered))
return " ".join(unique)
#%%
def pipelinize(function, active=True):
def list_comprehend_a_function(list_or_series, active=True):
if active:
return [function(i) for i in list_or_series]
else: # if it's not active, just pass it right back
# return list_or_series
return list_or_series
return FunctionTransformer(list_comprehend_a_function, validate=False, kw_args={'active':active})
#%%
estimators = [("expanding_contractions",pipelinize(expandContractions)),("tokenizer", pipelinize(tokenize_and_remove_punct)),("pos", pipelinize(tags)),("lammatizing", pipelinize(lemmatize)),("removing_stopwords",pipelinize(stopword_removal))]
pipe = Pipeline(estimators)
#%%
if __name__ == "__main__":
df = pd.read_csv('/Users/amsurve/PROJECTS/gg2/data/bbc_df.csv')
cleaned_text = []
for t in df['text']:
cleaned_text.append(pipe.transform([t])[0])
df['cleaned_text'] = cleaned_text
df.to_csv('/Users/amsurve/PROJECTS/gg2/data/bbc_cleaned.csv')
# %%