-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathhelper.py
124 lines (81 loc) · 3.41 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
from urlextract import URLExtract
from wordcloud import WordCloud
from collections import Counter
import pandas as pd
import emoji
def fetch_stats(selected_user,df):
if selected_user!='Overall':
df=df[df['Contact']==selected_user] #separate users dataframe
num_message=df.shape[0] #number of messages
words=[]
for m in df['Message']:
words.extend(m.split()) #number of words
num_media=df[df['Message']=='<Media omitted>'].shape[0] #number of media shared
extractor=URLExtract()
urls=[]
for m in df['Message']:
urls.extend(extractor.find_urls(m)) #number of urls
return num_message,len(words),num_media,len(urls)
def fetch_most_busy_users(df):
x=df['Contact'].value_counts().head()
df_most_busy=round((df['Contact'].value_counts()/df.shape[0])*100,2).reset_index().rename(
columns={'Contact':'Name','count':'Percent'})
return x,df_most_busy
def create_word_cloud(selected_user,df):
f = open("stop_hinglish.txt",'r')
stop_words = f.read()
if selected_user != 'Overall':
df = df[df['Contact'] == selected_user] #separate users dataframe
temp = df[df['Contact'] != 'group_notfication']
temp = temp[temp['Message'] != '<Media omitted>']
def remove_stopwords(text):
l=[]
for word in text.lower().split():
if word not in stop_words:
l.append(word)
return " ".join(l)
wc = WordCloud(width=500,height=500,min_font_size=10,background_color='white')
temp['Message']=temp['Message'].apply(remove_stopwords)
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['Contact'] == selected_user]
temp = df[df['Contact'] != 'group_notfication']
temp = temp[temp['Message'] != '<Media omitted>']
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 monthly_timeline(selected_user,df):
if selected_user != 'Overall':
df = df[df['Contact'] == 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['Contact'] == 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['Contact'] == selected_user]
return df['day_name'].value_counts()
def month_activity_map(selected_user,df):
if selected_user != 'Overall':
df = df[df['Contact'] == selected_user]
return df['Month'].value_counts()
def activity_heatmap(selected_user,df):
if selected_user != 'Overall':
df = df[df['Contact'] == selected_user]
user_heatmap = df.pivot_table(index='day_name', columns='period', values='Message',aggfunc='count').fillna(0)
return user_heatmap