app.py

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

st.set_page_config(layout="wide")
st.sidebar.title("📊 WhatsApp Chat Analyzer")

uploaded_file = st.sidebar.file_uploader("📁 Upload your chat file")
if uploaded_file is not None:
    bytes_data = uploaded_file.getvalue()
    data = bytes_data.decode("utf-8")

    # Use updated preprocessor (supports am/pm)
    df = preprocessor.preprocess(data)

    # Get 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("👤 Analyze chat for", user_list)

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

        # === Top Stats ===
        st.title("📈 Top Statistics")
        num_messages, words, num_media_messages, num_links = helper.fetch_stats(selected_user, df)

        col1, col2, col3, col4 = st.columns(4)
        col1.metric("Total Messages", num_messages)
        col2.metric("Total Words", words)
        col3.metric("Media Shared", num_media_messages)
        col4.metric("Links Shared", 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 Maps ===
        st.title("🗓 Weekly & Monthly Activity")
        col1, col2 = st.columns(2)

        with col1:
            st.subheader("Most Active 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.subheader("Most Active 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)

        # === Heatmap ===
        st.title("🔥 Weekly Activity Heatmap")
        user_heatmap = helper.activity_heatmap(selected_user, df)
        fig, ax = plt.subplots()
        sns.heatmap(user_heatmap, ax=ax)
        st.pyplot(fig)

        # === Most Busy Users ===
        if selected_user == 'Overall':
            st.title("🏆 Most Active Users")
            x, new_df = helper.most_busy_users(df)
            col1, col2 = st.columns(2)
            with col1:
                fig, ax = plt.subplots()
                ax.bar(x.index, x.values, color='gray')
                plt.xticks(rotation='vertical')
                st.pyplot(fig)
            with col2:
                renamed_df = new_df.rename(columns={'Percentage': 'Name', 'count': 'Ratio'})
                # st.write("DataFrame column names:", list(new_df.columns))
                st.dataframe(renamed_df)

        # === WordCloud ===
        st.title("☁️ Word Clouds")

        # Create tabs for different word cloud types
        wc_tab1, wc_tab2 = st.tabs(["Extended Word Cloud", "Standard Word Cloud"])

        with wc_tab1:
            st.subheader("Extended Word Cloud")
            df_wc = helper.create_wordcloud(selected_user, df)
            fig, ax = plt.subplots()
            ax.imshow(df_wc)
            ax.axis("off")
            st.pyplot(fig)

        with wc_tab2:
            st.subheader("Standard Word Cloud")
            df_sw_wc = helper.create_modern_wordcloud(selected_user, df)
            fig, ax = plt.subplots(figsize=(10, 6))
            ax.imshow(df_sw_wc)
            ax.axis("off")
            st.pyplot(fig)

        # === Most Common Words ===
        st.title("🔠 Most Common Words")
        most_common_df = helper.most_common_words(selected_user, df)
        fig, ax = plt.subplots()
        ax.barh(most_common_df['word'], most_common_df['count'], color='teal')
        plt.xticks(rotation='horizontal')
        st.pyplot(fig)

        # === Emoji Analysis ===
        st.title("😀 Emoji Analysis")
        emoji_df = helper.emoji_helper(selected_user, df)
        col1, col2 = st.columns(2)
        with col1:
            st.dataframe(emoji_df)
        with col2:
            fig, ax = plt.subplots()
            ax.pie(emoji_df['count'].head(), labels=emoji_df['emoji'].head(), autopct="%0.2f%%")
            st.pyplot(fig)

        # === Top 5 Words Per User ===
        if selected_user == 'Overall':
            st.title("🗣 Top 10 Words Per User")
            top_words = helper.top_10_words_per_user(df)
            for user, words in top_words.items():
                st.markdown(f"**{user}**: {', '.join([w[0] for w in words])}")
                
        # === Sentiment Analysis ===
        # st.title("🧠 Sentiment Analysis")
        # sentiment_summary, sentiment_data = helper.sentiment_analysis(
        #     df if selected_user == 'Overall' else df[df['user'] == selected_user]
        # )
        # st.subheader("Polarity Summary (range -1 to 1)")
        # st.json(sentiment_summary.to_dict())
        from sentiment_analysis import render_sentiment_analysis_ui
        render_sentiment_analysis_ui(df, selected_user)