File size: 4,755 Bytes
a389b8d
 
 
 
4b88b00
a389b8d
 
 
 
 
4b88b00
46cc02c
 
4b88b00
 
46cc02c
 
 
 
 
 
 
 
 
 
 
 
a389b8d
 
46cc02c
a389b8d
ea85d87
 
a389b8d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fc9f4d7
a389b8d
 
fc9f4d7
 
 
 
 
 
 
a389b8d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4b88b00
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
import streamlit as st
import preprocessor, helper
import matplotlib.pyplot as plt
import seaborn as sns
import chardet

st.sidebar.title("Whatsapp Chat Analyzer")

uploaded_file = st.sidebar.file_uploader("Choose a file")
if uploaded_file is not None:
    bytes_data = uploaded_file.read()

    # Detect the encoding
    result = chardet.detect(bytes_data)
    encoding = result['encoding']

    # Fallback to utf-8 if encoding is None
    if encoding is None:
        encoding = 'utf-8'  # or 'latin1' if utf-8 fails

    # Decode with the detected or fallback encoding
    try:
        data = bytes_data.decode(encoding)
    except UnicodeDecodeError:
        # If utf-8 decoding fails, fallback to latin1
        data = bytes_data.decode('latin1')

    df = preprocessor.preprocess(data)

    # Fetch unique users
    user_list = df['user'].unique().tolist()
    if 'group_notification' in user_list:
        user_list.remove('group_notification')
    user_list.sort()
    user_list.insert(0, "Overall")

    selected_user = st.sidebar.selectbox("Show analysis wrt", user_list)

    if st.sidebar.button("Show Analysis"):

        # Stats Area
        num_messages, words, num_media_messages, num_links = helper.fetch_stats(selected_user, df)
        st.title("Top Statistics")
        col1, col2, col3, col4 = st.columns(4)

        with col1:
            st.header("Total Messages")
            st.title(num_messages)
        with col2:
            st.header("Total Words")
            st.title(words)
        with col3:
            st.header("Media Shared")
            st.title(num_media_messages)
        with col4:
            st.header("Links Shared")
            st.title(num_links)

        # Monthly timeline
        st.title("Monthly Timeline")
        timeline = helper.monthly_timeline(selected_user, df)
        fig, ax = plt.subplots()
        ax.plot(timeline['time'], timeline['message'], color='green')
        plt.xticks(rotation='vertical')
        st.pyplot(fig)

        # Daily timeline
        st.title("Daily Timeline")
        daily_timeline = helper.daily_timeline(selected_user, df)
        fig, ax = plt.subplots()
        ax.plot(daily_timeline['only_date'], daily_timeline['message'], color='black')
        plt.xticks(rotation='vertical')
        st.pyplot(fig)

        # Activity map
        st.title('Activity Map')
        col1, col2 = st.columns(2)

        with col1:
            st.header("Most busy day")
            busy_day = helper.week_activity_map(selected_user, df)
            fig, ax = plt.subplots()
            ax.bar(busy_day.index, busy_day.values, color='purple')
            plt.xticks(rotation='vertical')
            st.pyplot(fig)

        with col2:
            st.header("Most busy month")
            busy_month = helper.month_activity_map(selected_user, df)
            fig, ax = plt.subplots()
            ax.bar(busy_month.index, busy_month.values, color='orange')
            plt.xticks(rotation='vertical')
            st.pyplot(fig)

        # Weekly Activity Map (Heatmap)
        st.title("Weekly Activity Map")
        user_heatmap = helper.activity_heatmap(selected_user, df)

        if not user_heatmap.empty and user_heatmap.notnull().values.any():
            fig, ax = plt.subplots()
            ax = sns.heatmap(user_heatmap)
            st.pyplot(fig)
        else:
            st.write("Insufficient data to generate a heatmap.")

        # Finding the busiest users in the group (Group level)
        if selected_user == 'Overall':
            st.title('Most Busy Users')
            x, new_df = helper.most_busy_users(df)
            fig, ax = plt.subplots()

            col1, col2 = st.columns(2)

            with col1:
                ax.bar(x.index, x.values, color='red')
                plt.xticks(rotation='vertical')
                st.pyplot(fig)
            with col2:
                st.dataframe(new_df)

        # WordCloud
        st.title("Wordcloud")
        df_wc = helper.create_wordcloud(selected_user, df)
        fig, ax = plt.subplots()
        ax.imshow(df_wc)
        st.pyplot(fig)

        # Most common words
        most_common_df = helper.most_common_words(selected_user, df)
        fig, ax = plt.subplots()
        ax.barh(most_common_df[0], most_common_df[1])
        plt.xticks(rotation='vertical')

        st.title('Most common words')
        st.pyplot(fig)

        # Emoji analysis
        emoji_df = helper.emoji_helper(selected_user, df)
        st.title("Emoji Analysis")

        col1, col2 = st.columns(2)

        with col1:
            st.dataframe(emoji_df)
        with col2:
            fig, ax = plt.subplots()
            ax.pie(emoji_df[1].head(), labels=emoji_df[0].head(), autopct="%0.2f")
            st.pyplot(fig)