processing.py

# imported essesntial libraries
import streamlit as st
import preprocessor
import helpers
import matplotlib.pyplot as plt
import seaborn as sns


# st.title('Chat Analyzer')
# st.image('./media/background5.jpeg', width=700)


# sidebar

st.sidebar.title("Chat Analyzer Primary version")

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

    # fetch unique users
    user_list = df['user'].unique().tolist()

    for x in user_list:
        if x == 'group_notification':
            user_list.remove('group_notification')
            break
    # sort the user_list in accending order of names
    user_list.insert(0, "Overall")

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

    if st.sidebar.button("Show analysis"):
        # Statistics Area starts

        num_messages, words, num_media_messages, num_links = helpers.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)

        # finding the most active users in the group(Group level)
        if selected_user == 'Overall':
            st.title('Most Busy Users')
            x, new_df = helpers.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 provides the representation all the words with different font size
        st.title("Wordcloud")
        df_wc = helpers.create_wordcloud(selected_user, df)
        fig, ax = plt.subplots()
        ax.imshow(df_wc)
        st.pyplot(fig)

        # most common words

        most_common_df = helpers.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 commmon words')
        st.pyplot(fig)

        # emoji analysis
        emoji_df = helpers.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)

        # monthly timeline
        st.title("Monthly Timeline")
        timeline = helpers.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 = helpers.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 = helpers.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 = helpers.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 of activity
        st.title("Weekly Activity Map")
        user_heatmap = helpers.activity_heatmap(selected_user, df)
        fig, ax = plt.subplots()
        ax = sns.heatmap(user_heatmap)
        st.pyplot(fig)