-
Notifications
You must be signed in to change notification settings - Fork 0
/
helper.py
139 lines (93 loc) · 3.88 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
from urlextract import URLExtract
from wordcloud import WordCloud
import pandas as pd
from collections import Counter
import emoji
extract = URLExtract()
def fetch_stats(selected_user,df):
if selected_user != 'Overall':
df = df[df['user'] == selected_user]
# fetch the number of messages
num_messages = df.shape[0]
# fetch the total number of words
words = []
for message in df['message']:
words.extend(message.split())
# fetch number of media messages
num_media_messages = df[df['message'] == '<Media omitted>\n'].shape[0]
# fetch number of links shared
links = []
for message in df['message']:
links.extend(extract.find_urls(message))
return num_messages,len(words),num_media_messages,len(links)
def most_busy_users(df):
x = df['user'].value_counts().head()
df = round((df['user'].value_counts() / df.shape[0]) * 100, 2).reset_index().rename(
columns={'index': 'name', 'user': 'percent'})
return x,df
def create_wordcloud(selected_user,df):
f = open('stop_hinglish.txt', 'r')
stop_words = f.read()
if selected_user != 'Overall':
df = df[df['user'] == selected_user]
temp = df[df['user'] != 'group_notification']
temp = temp[temp['message'] != '<Media omitted>\n']
def remove_stop_words(message):
y = []
for word in message.lower().split():
if word not in stop_words:
y.append(word)
return " ".join(y)
wc = WordCloud(width=500,height=500,min_font_size=10,background_color='white')
temp['message'] = temp['message'].apply(remove_stop_words)
df_wc = wc.generate(temp['message'].str.cat(sep=" "))
return df_wc
def most_common_words(selected_user,df):
f = open('stop_hinglish.txt','r')
stop_words = f.read()
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.UNICODE_EMOJI_ALIAS])
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