-
Notifications
You must be signed in to change notification settings - Fork 0
/
wordCloud_FN.py
248 lines (227 loc) · 8.89 KB
/
wordCloud_FN.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
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
import pandas as pd
import numpy as np
import os
import re
import string
import matplotlib.pyplot as plt
import time
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
from wordcloud import WordCloud, STOPWORDS
from sklearn.feature_extraction.text import CountVectorizer
https = 'https://t.co/'
wordnet_lemmatizer = WordNetLemmatizer()
STOPWORDS = set(stopwords.words('english'))
olympic = ['olympi','2020','tokyo2020','tokyo','olympic','watching olympic', 'tokyo olympic','olympic olympic game',\
'watching olympic', 'olympics', 'olympics got', 'olympic', 'olympics olympic', 'olympics woman',\
'day olympic', 'sport olympic', 'win olympic', 'tokyoolympic', 'go olympics','olympic', 'tokyoolympic','tokyoolympic',\
'athlete', 'olympicgame', 'tokyoolympic ', 's2021']
gold = ['gold medal', 'gold', 'medal olympic', 'olympics gold', 'olympics medal', 'gold olympic', 'medal']
common = ['gon na', 'gon na','gon', 'na','got','watching olympic', 'game', 'guy', 'people', 'time', 'mean', 'get', 'play', 'sport',\
'got answer', 'make', 'watch olympic', 'olympics live', 'story', 'could', 'see', 'made', 'one', 'think',\
'watching', 'going', 'would', 'also', 'still', 'watch', 'much', 'win', 'go', 'athlete', 'look',\
'today', 'many', 'first', 'dont','didnt', 'cant', 'man', 'woman','oh','know', 'year', 'day', 'even', 'let', 'give', 'everything',\
'anyone', 'must', 'may', 'watch','alway', 'winning', 'went','event', 'new', 'need', 'want','said','watched','take',\
'world', 'someone','everyone', 'done', 'next', 'last','getting']
ateez = ['ateez', 'ateezofficial', 'ateezofficial ateez', 'olympicslovesateez ateez', 'olympicslovesateez ateezofficial',\
'answer olympicslovesateez', 'olympicslovesateez dreamer', 'olympicslovesateez', 'win olympicslovesateez',\
'olympicslovesateez', 'slovesateez dreamer', 'slovesateez']
expression =['congratulation', 'well done','proud','happy', 'incredible','thank', 'amazing','great','right','well', 'congrat'\
'lol', 'love','say','good', 'like'\
'best']
alphabet = ['n', 'c', 'b', 'f', 'im','u','h',"\'", '\"', 'v']
numbers = ['1', '2', '3', '4', '5','6', '7', '8', '9','0', '2021']
interest = ['new', 'even','country','japan','really', 'team', 'hope', 'thing', 'every', 'lot']
unknown = ['amp', 'omg']
#ANOTHER_STOPWORDS = []
ANOTHER_STOPWORDS = olympic + gold + common +\
ateez +\
alphabet +\
numbers + interest + unknown
# #expression +\
def remove_http (text):
'''
remove_http (text):
This function remove 'https' + 10 following characters in
a string
parameter:
text (string)
return:
text (string)
'''
try:
id = text.find(https,0)
if id > -1:
return text[:id] + text[id+23:]
else:
return text
except:
print ("error:" + str(text))
return ""
def df_remove_http(dataframe, inputName, newColName):
'''
df_remove_http (dataframe, inputName, newColName):
parameter:
dataframe(dataframe)
inputName (string)
newColName (string)
return:
dataframe (dataframe)
'''
newCol = dataframe[inputName].apply (lambda x:remove_http(x))
dataframe.insert(loc = 1, column = newColName, value = newCol)
del dataframe[inputName]
return dataframe
def remove_punctuation (text):
'''
remove_punctuation ( ) -> remove all punctuation that listed in the library of string.punctuation
parameters:
text (string)
return:
list of string without any punctuation
'''
punctuationFree="".join([i for i in text if i not in string.punctuation])
return punctuationFree
def df_remove_punctuation (dataframe, inputName, newColName):
'''
remove_punctuation ( , , )-> remove all punctuations in a column of dataframe
parameters:
dataframe (dataframe)
inputName (string)
newColName (string)
return:
single column dataframe
'''
newCol = dataframe[inputName].apply(lambda x:remove_punctuation(x))
dataframe.insert(loc = 1, column = newColName, value = newCol)
del dataframe[inputName]
return dataframe
def df_lowerCase(dataframe, inputName, newColName):
'''
lowerCase ( , , )-> change all the capital letter to lower case
parameters:
dataframe (dataframe)
inputName (string)
newColName (string)
return:
single column dataframe
'''
newCol = dataframe[inputName].apply (lambda x: x.lower())
dataframe.insert(loc = 1, column = newColName, value = newCol)
del dataframe[inputName]
return dataframe
def tokenization(text):
'''
tokenization ( ) -> change a line of string into token in a list
parameters:
text (string)
return:
list of string
'''
tokens =word_tokenize(text)
return tokens
def df_tokenization(dataframe, inputName, newColName):
'''
df_tokenization ( , , )-> tokenize each row of string into a list for each row
parameters:
dataframe (dataframe)
inputName (string)
newColName (string)
return:
single column dataframe
'''
newCol = dataframe[inputName].apply(lambda x:tokenization(x))
dataframe.insert(loc = 1, column = newColName, value = newCol)
del dataframe[inputName]
return dataframe
def remove_stopwords(text):
'''
remove_stopwords ( ) -> input a list of string and remove all English stopwords
parameters:
text (list)
return:
output (list)
'''
output= [i for i in text if i not in STOPWORDS]
return output
def remove_another_stopwords(text):
'''
remove_another_stopwords ( ) -> input tokenList of words
and remove second set of stopwords, "ANOTHER_STOPWORDS"
parameters:
text (list) -> tokenized list
return:
output (list) -> tokenized list
'''
output = [i for i in text if i not in ANOTHER_STOPWORDS]
return output
def df_remove_stopwords(dataframe, inputName, newColName):
'''
df_remove_stopwords ( , , )-> remove stopwords in rows in dataframe
parameters:
dataframe (dataframe)
inputName (string)
newColName (string)
return:
single column dataframe
'''
# stop_words = set (stopwords.words("english"))
newCol = dataframe[inputName].apply(lambda x:remove_stopwords(x))
dataframe.insert(loc = 1, column = newColName, value = newCol)
del dataframe[inputName]
return dataframe
def lemmatizer(text):
'''
lemmatizer ( ) -> lemmatize the words in the list
parameters:
text (list)
return:
output (list)
'''
lemm_text = [wordnet_lemmatizer.lemmatize(word) for word in text]
return lemm_text
def df_lemmatizer(dataframe, inputName, newColName):
'''
df_lemmatizer ( , , )-> lemmatize the words in a row in dataframe
parameters:
dataframe (dataframe)
inputName (string)
newColName (string)
return:
single column dataframe
'''
newCol = dataframe[inputName].apply(lambda x:lemmatizer (x))
dataframe.insert(loc = 1, column = newColName, value = newCol)
del dataframe[inputName]
return dataframe
# Function to remove emoji.
def remove_emoji(string):
'''
remove_emoji ( ) -> remove the emoji in the string
parameters:
string (string)
return:
output (string)
'''
emoji_pattern = re.compile("["
u"\U0001F600-\U0001F64F" # emoticons
u"\U0001F300-\U0001F5FF" # symbols & pictographs
u"\U0001F680-\U0001F6FF" # transport & map symbols
u"\U0001F1E0-\U0001F1FF" # flags (iOS)
#u"\U00002500-\U00002BEF" # chinese char
u"\U00002702-\U000027B0"
u"\U00002702-\U000027B0"
u"\U000024C2-\U0001F251"
u"\U0001f926-\U0001f937"
u"\U00010000-\U0010ffff"
u"\u2640-\u2642"
u"\u2600-\u2B55"
u"\u200d"
u"\u23cf"
u"\u23e9"
u"\u231a"
u"\ufe0f" # dingbats
u"\u3030"
"]+", flags=re.UNICODE)
return emoji_pattern.sub(r'', string)