app.py

import streamlit as st
import matplotlib.pyplot as plt
import preprocessor
import helper
import seaborn as sns

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

upload_file = st.sidebar.file_uploader("Choose a file")
if upload_file is not None:
    bytes_data = upload_file.getvalue()
    data = bytes_data.decode('utf-8')
    df = preprocessor.preprocess(data)

    # st.dataframe(df)

    # fetch unique user
    # Check if 'group_notification' exists in the 'user' column
    if 'group_notification' in df['user'].unique():
        user_list = df['user'].unique().tolist()
        user_list.remove('group_notification')
        user_list.sort()
        user_list.insert(0, "Overall")
    else:
        # If 'group_notification' doesn't exist, proceed with usual process
        user_list = df['user'].unique().tolist()
        user_list.sort()
        user_list.insert(0, "Overall")

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

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

        # Start 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)

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

        # activity map
        st.title('Actvity 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)
            st.pyplot(fig)

        with col2:
            st.header("Most Busy Month")
            busy_day = helper.month_activity_map(selected_user, df)
            fig,ax = plt.subplots()
            ax.bar(busy_day.index, busy_day.values, color = 'orange')
            st.pyplot(fig)

        st.title("Weekly Activiry Map")
        user_activity_heatmap = helper.activity_heatmap(selected_user, df)
        fig,ax = plt.subplots()
        ax = sns.heatmap(user_activity_heatmap)
        st.pyplot(fig)

        # finding the busiest users in the group(Group level)
        if selected_user == 'Overall':
           st.title('Most Bussy Users')
           x, new_df = helper.most_busy_user(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("Word Cloud")
        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)