-
Notifications
You must be signed in to change notification settings - Fork 0
/
Topic Modelling.py
241 lines (126 loc) · 4.64 KB
/
Topic Modelling.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
#!/usr/bin/env python
# coding: utf-8
# In[1]:
import pandas as pd
import pickle
data = pd.read_pickle('dtm_stop.pkl')
data
# In[2]:
from gensim import matutils, models
import scipy.sparse
# In[3]:
tdm = data.transpose()
tdm.head()
# In[5]:
sparse_counts = scipy.sparse.csr_matrix(tdm)
corpus = matutils.Sparse2Corpus(sparse_counts)
# In[6]:
cv = pickle.load(open("cv_stop.pkl", "rb"))
id2word = dict((v, k) for k, v in cv.vocabulary_.items())
# In[7]:
lda = models.LdaModel(corpus=corpus, id2word=id2word, num_topics=2, passes=10)
lda.print_topics()
# In[8]:
lda = models.LdaModel(corpus=corpus, id2word=id2word, num_topics=3, passes=10)
lda.print_topics()
# In[9]:
lda = models.LdaModel(corpus=corpus, id2word=id2word, num_topics=4, passes=10)
lda.print_topics()
# This approach aint working out
# ## Nouns Only
# In[22]:
from nltk import word_tokenize, pos_tag
def nouns(text):
'''Given a string of text, tokenize the text and pull out only the nouns.'''
is_noun = lambda pos: pos[:2] == 'NN'
tokenized = word_tokenize(text)
all_nouns = [word for (word, pos) in pos_tag(tokenized) if is_noun(pos)]
return ' '.join(all_nouns)
# In[23]:
data_clean = pd.read_pickle('data_clean.pkl')
data_clean
# In[26]:
data_nouns = pd.DataFrame(data_clean.transcript.apply(nouns))
data_nouns
# In[28]:
from nltk.corpus import stopwords
add_stop_words = set(stopwords.words('english'))
# In[29]:
# Create a new document-term matrix using only nouns
from sklearn.feature_extraction import text
from sklearn.feature_extraction.text import CountVectorizer
# Re-add the additional stop words since we are recreating the document-term matrix
stop_words = text.ENGLISH_STOP_WORDS.union(add_stop_words)
# Recreate a document-term matrix with only nouns
cvn = CountVectorizer(stop_words=stop_words)
data_cvn = cvn.fit_transform(data_nouns.transcript)
data_dtmn = pd.DataFrame(data_cvn.toarray(), columns=cvn.get_feature_names())
data_dtmn.index = data_nouns.index
data_dtmn
# In[30]:
# Create the gensim corpus
corpusn = matutils.Sparse2Corpus(scipy.sparse.csr_matrix(data_dtmn.transpose()))
# Create the vocabulary dictionary
id2wordn = dict((v, k) for k, v in cvn.vocabulary_.items())
# In[31]:
# Let's start with 2 topics
ldan = models.LdaModel(corpus=corpusn, num_topics=2, id2word=id2wordn, passes=10)
ldan.print_topics()
# In[32]:
# Let's try topics = 3
ldan = models.LdaModel(corpus=corpusn, num_topics=3, id2word=id2wordn, passes=10)
ldan.print_topics()
# In[33]:
# Let's try 4 topics
ldan = models.LdaModel(corpus=corpusn, num_topics=4, id2word=id2wordn, passes=10)
ldan.print_topics()
# ## Nouns And Adjectives Both
# In[35]:
# Let's create a function to pull out nouns from a string of text
def nouns_adj(text):
'''Given a string of text, tokenize the text and pull out only the nouns and adjectives.'''
is_noun_adj = lambda pos: pos[:2] == 'NN' or pos[:2] == 'JJ'
tokenized = word_tokenize(text)
nouns_adj = [word for (word, pos) in pos_tag(tokenized) if is_noun_adj(pos)]
return ' '.join(nouns_adj)
# In[36]:
# Apply the nouns function to the transcripts to filter only on nouns
data_nouns_adj = pd.DataFrame(data_clean.transcript.apply(nouns_adj))
data_nouns_adj
# In[37]:
# Create a new document-term matrix using only nouns and adjectives, also remove common words with max_df
cvna = CountVectorizer(stop_words=stop_words, max_df=.8)
data_cvna = cvna.fit_transform(data_nouns_adj.transcript)
data_dtmna = pd.DataFrame(data_cvna.toarray(), columns=cvna.get_feature_names())
data_dtmna.index = data_nouns_adj.index
data_dtmna
# In[38]:
# Create the gensim corpus
corpusna = matutils.Sparse2Corpus(scipy.sparse.csr_matrix(data_dtmna.transpose()))
# Create the vocabulary dictionary
id2wordna = dict((v, k) for k, v in cvna.vocabulary_.items())
# In[39]:
# Let's start with 2 topics
ldana = models.LdaModel(corpus=corpusna, num_topics=2, id2word=id2wordna, passes=10)
ldana.print_topics()
# In[42]:
# Let's start with 3 topics
ldana = models.LdaModel(corpus=corpusna, num_topics=3, id2word=id2wordna, passes=10)
ldana.print_topics()
# In[41]:
# Let's try 4 topics
ldana = models.LdaModel(corpus=corpusna, num_topics=4, id2word=id2wordna, passes=10)
ldana.print_topics()
# In[44]:
ldana = models.LdaModel(corpus=corpusna, num_topics=2, id2word=id2wordna, passes=80)
ldana.print_topics()
# ## Two Topics estimated
#
# #### 1. Closure of issues, relief among community
#
# #### 2. Party Politics and Media revolvind around the case
# In[45]:
corpus_transformed = ldana[corpusna]
list(zip([a for [(a,b)] in corpus_transformed], data_dtmna.index))
# #### Topic 1 - india today
# #### Topic 2 - ndtv and republic