Twitter-Data-Analysis/extract_dataframe.py at main · SamDewriter/Twitter-Data-Analysis · 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
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
import json
import pandas as pd
from textblob import TextBlob

def read_json(json_file: str)->list:
    """
    json file reader to open and read json files into a list
    Args:
    -----
    json_file: str - path of a json file

    Returns
    -------
    length of the json file and a list of json
    """

    tweets_data = []
    for tweets in open(json_file,'r'):
        tweets_data.append(json.loads(tweets))


    return len(tweets_data), tweets_data
    global tweets_data

class TweetDfExtractor:
    """
    this function will parse tweets json into a pandas dataframe

    Return
    ------
    dataframe
    """
    tweets_list = pd.DataFrame(tweet_data)
    global tweets_list

    def __init__(self, tweets_list):

        self.tweets_list = tweets_list

    # an example function
    def find_statuses_count(self)->list:
        statuses_count = tweets_list['quoted_status'].tolist()
        return text


    def find_full_text(self)->list:
        text = tweets_list['text'].tolist()
        return text

    def find_sentiments(self, text)->list:

        return polarity, self.subjectivity

    def find_created_time(self)->list:
        created_at = tweets_list['created_time'].tolist()
        return created_at

    def find_source(self)->list:
        source = tweets_list['source'].tolist()
        return source

    def find_screen_name(self)->list:
        screen_name = tweets_list['display_text_range'].tolist()
        return screen_name


    def find_followers_count(self)->list:
        followers_count =
        return followers_count

    def find_friends_count(self)->list:
        friends_count =
        return friends_count

    def is_sensitive(self)->list:
        try:
            is_sensitive = [x['possibly_sensitive'] for x in self.tweets_list]
        except KeyError:
            is_sensitive = None
        return is_sensitive

    def find_favourite_count(self)->list:
        favorite_count = tweets_list['favorite_count']
        return favorite_count

    def find_retweet_count(self)->list:
        retweet_count = tweets_list['retweet_count']
        return retweek_count

    def find_hashtags(self)->list:
        hashtags =
        return hashtags

    def find_lang(self)->list:
        lang = tweets_list['lang'].tolist()
        return lang

    def find_mentions(self)->list:
        mentions =

        return mention

    def find_location(self)->list:
        try:
            location = self.tweets_list['user']['location']
        except TypeError:
            location = ''

        return location


    def get_tweet_df(self, save=False)->pd.DataFrame:
        """required column to be generated you should be creative and add more features"""

        columns = ['created_at', 'source', 'original_text','polarity','subjectivity', 'lang', 'favorite_count', 'retweet_count',
            'original_author', 'followers_count','friends_count','possibly_sensitive', 'hashtags', 'user_mentions', 'place']

        created_at = self.find_created_time()
        source = self.find_source()
        text = self.find_full_text()
        polarity, subjectivity = self.find_sentiments(text)
        lang = self.find_lang()
        fav_count = self.find_favourite_count()
        retweet_count = self.find_retweet_count()
        screen_name = self.find_screen_name()
        follower_count = self.find_followers_count()
        friends_count = self.find_friends_count()
        sensitivity = self.is_sensitive()
        hashtags = self.find_hashtags()
        mentions = self.find_mentions()
        location = self.find_location()
        data = zip(created_at, source, text, polarity, subjectivity, lang, fav_count, retweet_count, screen_name, follower_count, friends_count, sensitivity, hashtags, mentions, location)
        df = pd.DataFrame(data=data, columns=columns)

        if save:
            df.to_csv('processed_tweet_data.csv', index=False)
            print('File Successfully Saved.!!!')

        return df


if __name__ == "__main__":
    # required column to be generated you should be creative and add more features
    columns = ['created_at', 'source', 'original_text','clean_text', 'sentiment','polarity','subjectivity', 'lang', 'favorite_count', 'retweet_count',
    'original_author', 'screen_count', 'followers_count','friends_count','possibly_sensitive', 'hashtags', 'user_mentions', 'place', 'place_coord_boundaries']
    _, tweet_list = read_json("../covid19.json")
    tweet = TweetDfExtractor(tweet_list)
    tweet_df = tweet.get_tweet_df()

    # use all defined functions to generate a dataframe with the specified columns above