/
TweetPOS_LM.py
156 lines (136 loc) · 5.38 KB
/
TweetPOS_LM.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
import csv
import CMUTweetTagger
import json
import codecs
import re
import nltk
from collections import defaultdict
class TweetPOS_LM:
def __init__(self):
self.trainFile = 'Train1.csv'
self.tagFile = 'tweet_tags_15k.json'
self.featureFile = 'postags_features_15k.json'
self.tweet_id = []
self.tweet_original = []
self.is_question = []
self.is_answerable = []
self.tweet_unigram = defaultdict(set)
self.tweet_bigram = defaultdict(set)
self.tweet_trigram = defaultdict(set)
self.tweet_feature_list = []
self.tweet_features = {}
def readTweets(self):
with open(self.trainFile, 'rb') as csvfile:
tweetreader = csv.reader(csvfile, delimiter=',', quotechar='"')
header = tweetreader.next()
for row in tweetreader:
self.tweet_id.append(row[0])
self.tweet_original.append(row[1])
self.is_question.append(row[2])
self.is_answerable.append(row[3])
def pos_tagger(self):
tweets = []
for tw in self.tweet_original:
try:
tw = tw.decode('unicode_escape').encode('ascii','ignore')
except:
tw = re.sub(r'\\+', '', tw)
tw = tw.decode('unicode_escape').encode('ascii','ignore')
tweets.append(tw)
# tweets = [tw.encode('utf8') for tw in self.tweet_original[:3]]
sent_tags = CMUTweetTagger.runtagger_parse(tweets)
# fil_tweet = open('tweet_tags.json','w')
i = 0
for sent in sent_tags:
unigrams = [tag_tuple[1] for tag_tuple in sent]
bigrams = set(nltk.bigrams(unigrams))
trigrams = set(nltk.trigrams(unigrams))
self.tweet_unigram[self.tweet_id[i]] = set(unigrams)
self.tweet_bigram[self.tweet_id[i]] = bigrams
self.tweet_trigram[self.tweet_id[i]] = trigrams
self.tweet_feature_list.extend(unigrams)
self.tweet_feature_list.extend(bigrams)
self.tweet_feature_list.extend(trigrams)
i += 1
#json.dump(self.tweet_unigram,fil_tweet)
self.tweet_feature_list = list(set(self.tweet_feature_list))
def pos_tagger_writer(self):
tweets = []
for tw in self.tweet_original:
try:
tw = tw.decode('unicode_escape').encode('ascii','ignore')
except:
tw = re.sub(r'\\+', '', tw)
tw = tw.decode('unicode_escape').encode('ascii','ignore')
tweets.append(tw)
# tweets = [tw.encode('utf8') for tw in self.tweet_original[:3]]
tweet_tags = {}
sent_tags = CMUTweetTagger.runtagger_parse(tweets)
fil_tweet = open(self.tagFile,'w')
i = 0
for sent in sent_tags:
is_question = 1 if self.is_question[i] == "yes" else 0
is_anserable = 1 if self.is_answerable[i] == "yes" else 0
pos = {"tags":sent, "is_question":is_question, "is_answerable":is_anserable}
tweet_tags[self.tweet_id[i]] = pos
i += 1
json.dump(tweet_tags,fil_tweet)
def get_features(self):
feature_index = {}
i = 0
for feature in self.tweet_feature_list:
feature_index[feature] = i
i += 1
i = 0
for tweet in self.tweet_id:
# feature_dict = {}
features = [0,]*len(feature_index)
for unigram in self.tweet_unigram[tweet]:
features[feature_index[unigram]] = 1
for bigram in self.tweet_bigram[tweet]:
features[feature_index[bigram]] = 1
for trigram in self.tweet_trigram[tweet]:
features[feature_index[trigram]] = 1
is_question = 1 if self.is_question[i] == "yes" else 0
is_anserable = 1 if self.is_answerable[i] == "yes" else 0
self.tweet_features[tweet] = {"features":features, "is_question":is_question, "is_answerable":is_anserable}
i += 1
fil_tweet = open(self.featureFile,'w')
json.dump(self.tweet_features,fil_tweet)
def read_csv_tweets(self):
delimiter = ';'
i = 1
reader = codecs.open('Train.csv', 'r', encoding='utf-8')
for line in reader:
print line
row = line.split(delimiter)
self.tweet_id.append(i)
i += 1
self.tweet_original.append(row[1])
self.is_question.append(row[2])
self.is_answerable.append(row[3])
# def pos_tagger_reader(self):
#
# f = open(self.tagFile,'r')
# tweet_tags = json.load(f)
# for tweet_id in in tweet_tags:
# sent = tweet_tags[tweet_id]["tags"]
# label = tweet_tags[tweet_id]["label"]
#
# self.tweet_unigram[i] = set([])
# unigrams = [tag_tuple[1] for tag_tuple in sent]
# bigrams = set(nltk.bigrams(unigrams))
# trigrams = set(nltk.trigrams(unigrams))
# self.tweet_unigram[i] = set(unigrams)
# self.tweet_bigram[i] = bigrams
# self.tweet_trigram[i] = trigrams
#
# self.tweet_feature_list.extend(unigrams)
# self.tweet_feature_list.extend(bigrams)
# self.tweet_feature_list.extend(trigrams)
if __name__ == "__main__":
tp = TweetPOS_LM()
tp.readTweets()
#tp.pos_tagger_writer()
tp.pos_tagger()
tp.get_features()