app.py

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

st.set_page_config(
    page_title="WhatsApp Chat Analyzer",
    page_icon="💬",
    initial_sidebar_state="expanded"
)

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

st.sidebar.markdown("### 📱 How to Export Chat")
with st.sidebar.expander("See Instructions"):
    st.markdown("""
    1. Open WhatsApp.
    2. Go to the chat.
    3. Tap on the contact name/three dots.
    4. Select **More > Export Chat**.
    5. Choose **Without Media**.
    6. Upload the `.txt` file here.
    """)

uploaded_file = st.sidebar.file_uploader("Upload your Chat .txt file", type=['txt'])
if uploaded_file is not None:
    bytes_data = uploaded_file.getvalue()
    data = bytes_data.decode("utf-8")
    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 w.r.t", 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")
        monthly_timeline = helper.monthly_timeline(selected_user, df)
        fig, ax = plt.subplots()
        ax.plot(monthly_timeline['time'],
                monthly_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)

        st.title("Weekly Activity Map")
        user_heatmap = helper.activity_heatmap(selected_user, df)
        if not user_heatmap.empty:
            fig, ax = plt.subplots()
            ax = sns.heatmap(user_heatmap)
            st.pyplot(fig)
        else:
            st.warning("Not enough data to generate heatmap.")

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

            col1, col2 = st.columns(2)

            with col1:
                ax.bar(top_five_users.index, top_five_users.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)
        st.title('Most Commmon Words')
        fig, ax = plt.subplots()
        ax.barh(most_common_df[0], most_common_df[1])
        plt.xticks(rotation='vertical')
        st.pyplot(fig)

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

        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)