-
Notifications
You must be signed in to change notification settings - Fork 0
/
EmoCount.py
159 lines (136 loc) · 4.57 KB
/
EmoCount.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
from count_smilies_class import Emo
from collections import Counter
import os
import json
import codecs
import numpy as np
numOfTotalSentences = 0
messagecounter = 0
foundEmosAndSmilies = []
# emoCount = Emo(language="empty", emoticons=True, secondemo="emoticons")
emoCount = Emo(language="twitchstandard", emoticons=True, secondemo="emoticons")
# import messages and parse
def getData(filename="", dirname='txtfiles/messages'):
messages = []
if filename == "":
for fname in os.listdir(dirname):
print os.listdir(dirname), fname
for line in open(os.path.join(dirname, fname)):
try:
parsed = json.loads(line)
parsed_msg = parsed['msg']
messages.append(parsed_msg)
except ValueError:
print "Error in line"
continue
else:
for line in open(os.path.join(dirname, filename)):
try:
parsed = json.loads(line)
parsed_msg = parsed['msg']
messages.append(parsed_msg)
except ValueError:
print "Error in line"
continue
return messages
def openOurFile(filename):
labeledMessages = []
labels = []
with codecs.open(filename, encoding='UTF-8') as fid:
for n, line in enumerate(fid):
try:
score, word = line.strip().split('\t')
except ValueError:
print 'Error in line %d of %s' % (n + 1, filename)
labeledMessages.append(word)
if score == 'NEUTRAL':
score = 0
if score == 'POSITIVE':
score = 1
if score == 'NEGATIVE':
score = -1
labels.append(score)
labels = np.array(labels, dtype='float')
return labeledMessages, labels
def openTwitterFile(filenameWords, filenameLabels):
labeledMessages = []
labels = []
with codecs.open(filenameWords, encoding='UTF-8') as fid:
for n, line in enumerate(fid):
try:
sentence = line.strip()
print sentence
except ValueError:
print 'Error in line %d of %s' % (n + 1, filenameWords)
labeledMessages.append(sentence)
# if score == 'NEUTRAL':
# score = 0
# if score == 'POSITIVE':
# score = 1
# if score == 'NEGATIVE':
# score = -1
# labels.append(score)
with codecs.open(filenameLabels, encoding='UTF-8') as fid:
for n, line in enumerate(fid):
try:
label = line
except ValueError:
print 'Error in line %d of %s' % (n + 1, filenameWords)
labels.append(label)
labels = np.array(labels, dtype='float')
# print labeledMessages
return labeledMessages, labels
messages, labels = openTwitterFile("txtfiles/labeledData/tweet_semevaltest.txt", "txtfiles/labeledData/tweet_semevaltest_so_score.txt")
# messages, labels = openOurFile("txtfiles/labeledData/TwitchDota.txt")
# print labeledMessages
# messages = getData('admiralbulldog.txt')
# print messages
# messages = getData('imaqtpie.txt')
"""
COUNT
"""
# for message in messages:
# messagecounter += 1
# # for every sentence
# # score, words = emoCount.score(message) #score
# words = emoCount.find_all(message) #count
#
# foundEmosAndSmilies = foundEmosAndSmilies + words
# if len(words) != 0:
# numOfTotalSentences += 1
# print(words)
#
#
# # in the end
# print("Messages total:")
# print messagecounter
# print("found smilies total:")
# print sum(Counter(foundEmosAndSmilies).values())
# print("found smilies examples ordered:")
# print Counter(foundEmosAndSmilies)
# print("found smilies top50")
# print Counter.most_common(Counter(foundEmosAndSmilies), 50)
# print("total number of sentences with smilies:")
# print numOfTotalSentences
"""
Classify
"""
for message in messages:
messagecounter += 1
# for every sentence
score, words = emoCount.score(message)
foundEmosAndSmilies = foundEmosAndSmilies + words
if len(words) != 0:
numOfTotalSentences += 1
print(words)
# in the end
print("Messages total:")
print messagecounter
print("found smilies total:")
print sum(Counter(foundEmosAndSmilies).values())
print("found smilies examples ordered:")
print Counter(foundEmosAndSmilies)
print("found smilies top50")
print Counter.most_common(Counter(foundEmosAndSmilies), 50)
print("total number of sentences with smilies:")
print numOfTotalSentences