forked from Vanesh37/chat-analyzer
-
Notifications
You must be signed in to change notification settings - Fork 0
/
helper.py
190 lines (136 loc) · 5.4 KB
/
helper.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
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
import nltk
from nltk.sentiment.vader import SentimentIntensityAnalyzer
import re
from urlextract import URLExtract
from wordcloud import WordCloud
import pandas as pd
import emoji
from collections import Counter
from nltk.corpus import stopwords
# Download and set stop words
nltk.download('stopwords')
stop_words = set(stopwords.words('english'))
extract = URLExtract()
def fetch_stats(selected_user, df):
if selected_user != 'overall':
df = df[df['user'] == selected_user]
temp = df[df['user'] != 'group_notification']
temp = temp[temp['message'] != '<Media omitted>\n']
num_messages = df.shape[0] # number of messages , words
words = []
for message in temp['message']:
words.extend(message.split())
num_media_msg = df[df['message'] ==
'<Media omitted>\n'].shape[0] # media shared
links = []
for message in temp['message']:
links.extend(extract.find_urls(message))
return num_messages, len(words), num_media_msg, len(links)
def most_busy_users(selected_user, df):
if selected_user != 'overall':
df = df[df['user'] == selected_user]
temp = df[df['user'] != 'group_notification']
temp = temp[temp['message'] != '<Media omitted>\n']
x = temp['user'].value_counts().head()
temp = round((df['user'].value_counts() / df.shape[0]) * 100, 2).reset_index().rename(
columns={'user': 'name', 'count': 'percent'})
return x, temp
def create_wordcloud(selected_user, df):
if selected_user != 'overall':
df = df[df['user'] == selected_user]
temp = df[df['user'] != 'group_notification']
temp = temp[temp['message'] != '<Media omitted>\n']
wc = WordCloud(width=500, height=500, min_font_size=10,
background_color='white')
df_wc = wc.generate(temp['message'].str.cat(sep=" "))
return df_wc
def most_common_words(selected_user, df):
if selected_user != 'overall':
df = df[df['user'] == selected_user]
temp = df[df['user'] != 'group_notification']
temp = temp[temp['message'] != '<Media omitted>\n']
words = []
for message in temp['message']:
for word in message.lower().split():
if word not in stop_words:
words.append(word)
most_common_df = pd.DataFrame(Counter(words).most_common(20))
return most_common_df
def emoji_helper(selected_user, df):
if selected_user != 'overall':
df = df[df['user'] == selected_user]
emojis = []
for message in df['message']:
emojis.extend([c for c in message if c in emoji.EMOJI_DATA])
emoji_df = pd.DataFrame(Counter(emojis).most_common(len(Counter(emojis))))
return emoji_df
def monthly_timeline(selected_user, df):
if selected_user != 'overall':
df = df[df['user'] == selected_user]
timeline = df.groupby(['year', 'month_num', 'month']).count()[
'message'].reset_index()
time = []
for i in range(timeline.shape[0]):
time.append(timeline['month'][i] + "-" + str(timeline['year'][i]))
timeline['time'] = time
return timeline
def daily_timeline(selected_user, df):
if selected_user != 'overall':
df = df[df['user'] == selected_user]
daily_timeline = df.groupby('only_date').count()['message'].reset_index()
return daily_timeline
def week_activity_map(selected_user, df):
if selected_user != 'overall':
df = df[df['user'] == selected_user]
return df['day_name'].value_counts()
def month_activity_map(selected_user, df):
if selected_user != 'overall':
df = df[df['user'] == selected_user]
return df['month'].value_counts()
def activity_heatmap(selected_user, df):
if selected_user != 'overall':
df = df[df['user'] == selected_user]
user_heatmap = df.pivot_table(
index='day_name', columns='period', values='message', aggfunc='count').fillna(0)
return user_heatmap
def preprocess(data):
pattern = r'(\d{1,2}/\d{1,2}/\d{2,4},\s\d{1,2}:\d{2}\s(?:am|pm)\s-\s)'
blocks = re.split(pattern, data)
dates = [block.strip() for block in blocks[1::2]]
messages = blocks[0::2]
if len(messages) != len(dates):
dates.append('')
df = pd.DataFrame({'user_message': messages, 'message_date': dates})
df = df[df['message_date'] != '']
users = []
messages = []
for message in df['user_message']:
entry = re.split('([\w\W]+?):\s', message)
if len(entry) > 1:
users.append(entry[1])
messages.append(entry[2])
else:
users.append('group_notifications')
messages.append(entry[0])
df['user'] = users
df['message'] = messages
df.drop(columns=['user_message', 'message_date'], inplace=True)
# Filter out messages containing <Media omitted> and group_notifications
df = df[~df['message'].str.contains('<Media omitted>')]
df = df[~df['user'].str.contains('group_notifications')]
return df
# Function to perform sentiment analysis
nltk.download('vader_lexicon')
def perform_sentiment_analysis(messages):
sia = SentimentIntensityAnalyzer()
sentiments = []
for message in messages:
sentiment = sia.polarity_scores(message)
if sentiment['compound'] >= 0.05:
sentiment_type = 'Positive'
elif sentiment['compound'] <= -0.05:
sentiment_type = 'Negative'
else:
sentiment_type = 'Neutral'
sentiments.append(sentiment_type)
return sentiments