sentiment_api/sentimentanalysis.py at master · DevclanII/sentiment_api · GitHub

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
# coding: utf-8

import tweepy
from tweepy import OAuthHandler
from textblob import TextBlob as tb
import pandas as pd
import json
from flask import jsonify
import datetime
from tweepy.error import TweepError

time = datetime.datetime.now()

consumerKey = 'SV8UUKCsWGbHB0fBG9xEWdDDl'
consumerSecret = 'gu7fZc75qzoZ20Cf1Y4FDSBGiX40H5L5dlMhmVqFecMZzUzBuo'
accessToken = '1074255938-ea90Lx6fUeZ6MW780cHpmmozr4XDmC47VH4cKpM'
accessTokenSecret = 'Npsz59fFPutq2aCbdfO6l0ylYjHZAgZxkojUoWHV8gsIh'

auth = tweepy.OAuthHandler(consumerKey, consumerSecret)
auth.set_access_token(accessToken, accessTokenSecret)
api = tweepy.API(auth)

def scrape_tweet(searchTweet, no_of_tweet):
    try:
        tweets = tweepy.Cursor(api.search, q=searchTweet).items((no_of_tweet))
    except (TweepError, ValueError):
        print("Too many requests")

    data=[]

    try:
        for tweet in tweets:
            text=tweet.text
            tweet_time = tweet.created_at
            textWords=text

            analysis = tb(textWords)
            polarity = 'Positive'
            if(analysis.sentiment.polarity < 0):
                polarity = 'Negative'
            if(0<=analysis.sentiment.polarity <=0.2):
                polarity = 'Neutral'

            dic={}
            dic['Sentiment']=polarity
            dic['Tweet'] = textWords
            dic['Tweettime'] = tweet_time
            data.append(dic)
    except UnboundLocalError:
        pass
    df=pd.DataFrame(data)
    df.to_csv('devclan.csv')

    train = pd.read_csv('devclan.csv', usecols = ['Sentiment', "Tweettime"])
    #  open('devclan.json', 'r') as f:
    #     train_json = json.loatrain.to_json('devclan.json')
    # withd(f)


    # positive = train['Sentiment'] == 'Positive'
    # negative = train['Sentiment'] == 'Negative'
    # neutral = train['Sentiment'] == 'Neutral'
    Sentiment = train["Sentiment"]
    size = Sentiment.tolist()
    total = len(size)
    pos = size.count("Positive")
    neg = size.count("Negative")
    neu = size.count("Neutral")
    per_pos = float(pos/total* 100)
    per_neg = float(neg/total* 100)
    per_neu = float(neu/total* 100)
    train_json ={"percentages":
                    {
                    "positive": round(per_pos, 3),
                    "negative":round(per_neg, 3),
                    "neutral":round(per_neu, 3)
                    },
                "time" : time
                }
    train_json = jsonify(train_json)


   # time = train['Tweettime'] .

    # Sentiment = train['Sentiment']

    # size = train['Sentiment'].value_counts().tolist()
    # sice = Sentiment.tolist()
    # labels = list(set(sice))

    # colors = ['yellow', 'blue', 'red']
    # explode = (0.1, 0.1, 0.1)
    # explode_list = list(explode)
    # if len(labels) == 2:
    #     colors = colors[:2]
    #     explode = explode[:2]
    # elif len(labels) == 3:
    #     colors = colors
    #     explode = explode
    # elif len(labels) == 1:
    #     colors = colors[:1]
    #     explode = explode[:1]

    # plt.pie(size, colors=colors, labels=labels, shadow=True, startangle= 90, autopct='%1.1f%%', explode = explode)
    # plt.legend(labels)
    # return plt.show()

    return train_json