-
Notifications
You must be signed in to change notification settings - Fork 0
/
Sentiment Analysis.py
146 lines (118 loc) · 6.09 KB
/
Sentiment Analysis.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
import sys,tweepy,csv,re
from textblob import TextBlob
import matplotlib.pyplot as plt
class SentimentAnalysis:
def __init__(self):
self.tweets = []
self.tweetText = []
def DownloadData(self):
# authenticating
consumerKey = 'Your Twitter API Consumer Key'
consumerSecret = 'Your Twitter API Consumer Secret'
accessToken = Your 'Twitter API Access Token'
accessTokenSecret = 'Your Twitter API Access Token Secret'
auth = tweepy.OAuthHandler(consumerKey, consumerSecret)
auth.set_access_token(accessToken, accessTokenSecret)
api = tweepy.API(auth)
# input for term to be searched and how many tweets to search
searchTerm = input("Enter Keyword/Tag to search about: ")
NoOfTerms = int(input("Enter how many tweets to search: "))
# searching for tweets
self.tweets = tweepy.Cursor(api.search, q=searchTerm, lang = "en").items(NoOfTerms)
# Open/create a file to append data to
csvFile = open('result.csv', 'a')
# Use csv writer
csvWriter = csv.writer(csvFile)
# creating some variables to store info
polarity = 0
positive = 0
wpositive = 0
spositive = 0
negative = 0
wnegative = 0
snegative = 0
neutral = 0
# iterating through tweets fetched
for tweet in self.tweets:
#Append to temp so that we can store in csv later. I use encode UTF-8
self.tweetText.append(self.cleanTweet(tweet.text).encode('utf-8'))
# print (tweet.text.translate(non_bmp_map)) #print tweet's text
analysis = TextBlob(tweet.text)
# print(analysis.sentiment) # print tweet's polarity
polarity += analysis.sentiment.polarity # adding up polarities to find the average later
if (analysis.sentiment.polarity == 0): # adding reaction of how people are reacting to find average later
neutral += 1
elif (analysis.sentiment.polarity > 0 and analysis.sentiment.polarity <= 0.3):
wpositive += 1
elif (analysis.sentiment.polarity > 0.3 and analysis.sentiment.polarity <= 0.6):
positive += 1
elif (analysis.sentiment.polarity > 0.6 and analysis.sentiment.polarity <= 1):
spositive += 1
elif (analysis.sentiment.polarity > -0.3 and analysis.sentiment.polarity <= 0):
wnegative += 1
elif (analysis.sentiment.polarity > -0.6 and analysis.sentiment.polarity <= -0.3):
negative += 1
elif (analysis.sentiment.polarity > -1 and analysis.sentiment.polarity <= -0.6):
snegative += 1
# Write to csv and close csv file
csvWriter.writerow(self.tweetText)
csvFile.close()
# finding average of how people are reacting
positive = self.percentage(positive, NoOfTerms)
wpositive = self.percentage(wpositive, NoOfTerms)
spositive = self.percentage(spositive, NoOfTerms)
negative = self.percentage(negative, NoOfTerms)
wnegative = self.percentage(wnegative, NoOfTerms)
snegative = self.percentage(snegative, NoOfTerms)
neutral = self.percentage(neutral, NoOfTerms)
# finding average reaction
polarity = polarity / NoOfTerms
# printing out data
print("How people are reacting on " + searchTerm + " by analyzing " + str(NoOfTerms) + " tweets.")
print()
print("General Report: ")
if (polarity == 0):
print("Neutral")
elif (polarity > 0 and polarity <= 0.3):
print("Weakly Positive")
elif (polarity > 0.3 and polarity <= 0.6):
print("Positive")
elif (polarity > 0.6 and polarity <= 1):
print("Strongly Positive")
elif (polarity > -0.3 and polarity <= 0):
print("Weakly Negative")
elif (polarity > -0.6 and polarity <= -0.3):
print("Negative")
elif (polarity > -1 and polarity <= -0.6):
print("Strongly Negative")
print()
print("Detailed Report: ")
print(str(positive) + "% people thought it was positive")
print(str(wpositive) + "% people thought it was weakly positive")
print(str(spositive) + "% people thought it was strongly positive")
print(str(negative) + "% people thought it was negative")
print(str(wnegative) + "% people thought it was weakly negative")
print(str(snegative) + "% people thought it was strongly negative")
print(str(neutral) + "% people thought it was neutral")
self.plotPieChart(positive, wpositive, spositive, negative, wnegative, snegative, neutral, searchTerm, NoOfTerms)
def cleanTweet(self, tweet):
# Remove Links, Special Characters etc from tweet
return ' '.join(re.sub("(@[A-Za-z0-9]+)|([^0-9A-Za-z \t]) | (\w +:\ / \ / \S +)", " ", tweet).split())
# function to calculate percentage
def percentage(self, part, whole):
temp = 100 * float(part) / float(whole)
return format(temp, '.2f')
def plotPieChart(self, positive, wpositive, spositive, negative, wnegative, snegative, neutral, searchTerm, noOfSearchTerms):
labels = ['Positive [' + str(positive) + '%]', 'Weakly Positive [' + str(wpositive) + '%]','Strongly Positive [' + str(spositive) + '%]', 'Neutral [' + str(neutral) + '%]',
'Negative [' + str(negative) + '%]', 'Weakly Negative [' + str(wnegative) + '%]', 'Strongly Negative [' + str(snegative) + '%]']
sizes = [positive, wpositive, spositive, neutral, negative, wnegative, snegative]
colors = ['yellowgreen','lightgreen','darkgreen', 'gold', 'red','lightsalmon','darkred']
patches, texts = plt.pie(sizes, colors=colors, startangle=90)
plt.legend(patches, labels, loc="best")
plt.title('How people are reacting on ' + searchTerm + ' by analyzing ' + str(noOfSearchTerms) + ' Tweets.')
plt.axis('equal')
plt.tight_layout()
plt.show()
if __name__== "__main__":
sa = SentimentAnalysis()
sa.DownloadData()