-
Notifications
You must be signed in to change notification settings - Fork 1
/
TextCleaner_Contractions.py
215 lines (206 loc) · 9.3 KB
/
TextCleaner_Contractions.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
contraction_mapping2 = {"ain’t": "is not", "aren’t": "are not", "can’t": "cannot", "‘cause": "because",
"could’ve": "could have", "couldn’t": "could not",
"didn’t": "did not", "doesn’t": "does not", "don’t": "do not", "hadn’t": "had not",
"hasn’t": "has not", "haven’t": "have not",
"he’d": "he would", "he’ll": "he will", "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", "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 would",
"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 as",
"this’s": "this is", "that’d": "that would", "that’d’ve": "that would have",
"that’s": "that is", "there’d": "there would",
"there’d’ve": "there would have", "there’s": "there is", "here’s": "here 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 would", "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’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 would", "you’d’ve": "you would have", "you’ll": "you will",
"you’ll’ve": "you will have",
"you’re": "you are", "you’ve": "you have"}
contraction_mapping = {
"ain't": "is 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 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",
"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 would",
"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 as",
"that'd": "that would",
"that'd've": "that would have",
"that's": "that is",
"there'd": "there would",
"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 would",
"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'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 would",
"you'd've": "you would have",
"you'll": "you will",
"you'll've": "you will have",
"you're": "you are",
"you've": "you have"
}
import re
import nltk
nltk.download('stopwords')
nltk.download('punkt')
def text_cleaner_heavy(text):
newString = text.lower()
newString = re.sub('"', '', newString)
newString = re.sub(r'\([^)]*\)', '', newString)
newString = ' '.join([contraction_mapping[t] if t in contraction_mapping else t for t in newString.split(' ')])
newString = re.sub(r"’s\b", "", newString)
newString = re.sub('[^a-zA-Z\s\-]', '', newString)
newString = re.sub('[^a-zA-Z\s]', ' ', newString)
tokens = [w for w in newString.split() if w not in stopwords]
long_words = []
prev_word = []
for i in tokens:
if i not in prev_word and len(i) >= 3: # removing short word
long_words.append(i)
prev_word = [i]
return (" ".join(long_words)).strip()
def text_cleaner(text):
newString = text.lower()
newString = re.sub('"', '', newString)
newString = re.sub(r'\([^)]*\)', '', newString)
newString = ' '.join([contraction_mapping[t] if t in contraction_mapping else t for t in newString.split(' ')])
newString = re.sub(r"(?i)http(s):\/\/[a-z0-9.~_\-\/]+", '', newString)
newString = re.sub(r"(?i)@[a-z0-9_]+", '', newString)
newString = re.sub('[^a-zA-Z\s]', ' ', newString)
return newString
def text_cleaner_light(text):
newString = text.lower()
newString = re.sub('"', '', newString)
newString = re.sub(r'\([^)]*\)', '', newString)
newString = ' '.join([contraction_mapping[t] if t in contraction_mapping else t for t in newString.split(' ')])
newString = re.sub(r"’s\b", "", newString)
return newString