my app

app.py

@@ -0,0 +1,156 @@
+import streamlit as st
+import preprocessor
+import helper
+import matplotlib.pyplot as plt
+import seaborn as sns
+import pandas as pd 
+
+st.set_option('deprecation.showPyplotGlobalUse', False)
+
+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.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 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
+        st.title("Weekly Activity Map")
+        user_heatmap = helper.activity_heatmap(selected_user, df)
+        fig, ax = plt.subplots()
+        ax = sns.heatmap(user_heatmap, annot=True, fmt="g", cmap="YlGnBu", cbar=False)
+        st.pyplot(fig)
+
+        # Most Busy Users (Overall)
+        if selected_user == 'Overall':
+            st.title('Most Busy Users')
+            x, new_df = helper.most_busy_users(df)
+            fig, ax = plt.subplots(figsize=(8, 6))
+
+            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
+        st.title('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.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[1].head(), labels=emoji_df[0].head(), autopct="%0.2f")
+            st.pyplot(fig)
+
+        # Words per User per Month
+        st.title("Words per User per Month")
+        words_per_month_df = helper.words_per_user_per_month(df)
+        st.dataframe(words_per_month_df)
+
+        # Frequent Hours
+        st.title("Frequent Hours")
+        frequent_hours_df = helper.frequent_hours(selected_user, df)
+        st.bar_chart(frequent_hours_df)
+
+        # Common Words by 4-Hour Intervals
+        st.title("Common Words by 4-Hour Intervals")
+        common_words_by_hour_df = helper.common_words_by_four_hours(selected_user, df)
+        st.dataframe(common_words_by_hour_df)
+
+        # WordClouds by 4-Hour Intervals
+        st.title("WordClouds by 4-Hour Intervals")
+        wordclouds_by_hour = helper.create_wordcloud_by_four_hours(selected_user, df)
+        for period, wc_img in wordclouds_by_hour.items():
+            st.subheader(f"WordCloud for {period}")
+            st.image(wc_img.to_array(), use_column_width=True)
+
+        # Common Words by Month
+        st.title("Common Words by Month")
+        common_words_by_month_df = helper.common_words_by_month(selected_user, df)
+        st.dataframe(common_words_by_month_df)

helper.py

@@ -0,0 +1,146 @@
+from urlextract import URLExtract
+from wordcloud import WordCloud
+import pandas as pd
+from collections import Counter
+import emoji
+
+extract = URLExtract()
+
+def fetch_stats(selected_user, df):
+    if selected_user != 'Overall':
+        df = df[df['user'] == selected_user]
+
+    num_messages = df.shape[0]
+    words = [word for message in df['message'] for word in message.split()]
+    num_media_messages = df[df['message'] == '<Media omitted>\n'].shape[0]
+    links = [url for message in df['message'] for url in extract.find_urls(message)]
+
+    return num_messages, len(words), num_media_messages, len(links)
+
+def most_busy_users(df):
+    x = df['user'].value_counts().head()
+    percent_df = round((df['user'].value_counts() / df.shape[0]) * 100, 2).reset_index().rename(columns={'index': 'name', 'user': 'percent'})
+    return x, percent_df
+
+def create_wordcloud(selected_user, df):
+    if selected_user != 'Overall':
+        df = df[df['user'] == selected_user]
+
+    temp = df[df['user'] != 'group_notification']
+    temp = temp[temp['message'] != '<Media omitted>\n']
+
+    wc = WordCloud(width=500, height=500, min_font_size=10, background_color='white')
+    df_wc = wc.generate(temp['message'].str.cat(sep=" "))
+    return df_wc
+
+def most_common_words(selected_user, df):
+    if selected_user != 'Overall':
+        df = df[df['user'] == selected_user]
+
+    temp = df[df['user'] != 'group_notification']
+    temp = temp[temp['message'] != '<Media omitted>\n']
+
+    words = [word.lower() for message in temp['message'] for word in message.split()]
+    most_common_df = pd.DataFrame(Counter(words).most_common(20))
+    return most_common_df
+
+def emoji_helper(selected_user, df):
+    if selected_user != 'Overall':
+        df = df[df['user'] == selected_user]
+
+    emojis = [c for message in df['message'] for c in message if c in emoji.EMOJI_DATA]
+    emoji_df = pd.DataFrame(Counter(emojis).most_common(len(Counter(emojis))))
+    return emoji_df
+
+def monthly_timeline(selected_user, df):
+    if selected_user != 'Overall':
+        df = df[df['user'] == selected_user]
+
+    timeline = df.groupby(['year', 'month_num', 'month']).count()['message'].reset_index()
+
+    time = [f"{timeline['month'][i]}-{timeline['year'][i]}" for i in range(timeline.shape[0])]
+    timeline['time'] = time
+    return timeline
+
+def daily_timeline(selected_user, df):
+    if selected_user != 'Overall':
+        df = df[df['user'] == selected_user]
+
+    daily_timeline = df.groupby('only_date').count()['message'].reset_index()
+    return daily_timeline
+
+def week_activity_map(selected_user, df):
+    if selected_user != 'Overall':
+        df = df[df['user'] == selected_user]
+    return df['day_name'].value_counts()
+
+def month_activity_map(selected_user, df):
+    if selected_user != 'Overall':
+        df = df[df['user'] == selected_user]
+    return df['month'].value_counts()
+
+def activity_heatmap(selected_user, df):
+    if selected_user != 'Overall':
+        df = df[df['user'] == selected_user]
+    user_heatmap = df.pivot_table(index='day_name', columns='period', values='message', aggfunc='count').fillna(0)
+    return user_heatmap
+
+def words_per_user_per_month(df):
+    words_per_month = df.groupby(['user', 'year', 'month_num'])['message'].apply(lambda x: ' '.join(x)).reset_index()
+    words_per_month['word_count'] = words_per_month['message'].apply(lambda x: len(x.split()))
+    words_per_month_df = words_per_month.pivot(index=['year', 'month_num'], columns='user', values='word_count').fillna(0).astype(int)
+    return words_per_month_df
+
+def frequent_hours(selected_user, df):
+    if selected_user != 'Overall':
+        df = df[df['user'] == selected_user]
+    frequent_hours_df = df['hour'].value_counts().sort_index()
+    return frequent_hours_df
+
+def common_words_by_four_hours(selected_user, df):
+    if selected_user != 'Overall':
+        df = df[df['user'] == selected_user]
+
+    temp = df[df['user'] != 'group_notification']
+    temp = temp[temp['message'] != '<Media omitted>\n']
+
+    common_words_by_hour = {}
+    for hour in range(0, 24, 4):
+        period = temp[(temp['hour'] >= hour) & (temp['hour'] < hour + 4)]
+        words = [word.lower() for message in period['message'] for word in message.split()]
+        common_words_by_hour[f"{hour}-{hour + 4}"] = Counter(words).most_common(10)
+
+    common_words_by_hour_df = pd.DataFrame.from_dict(common_words_by_hour, orient='index').fillna('').astype(str)
+    return common_words_by_hour_df
+
+def create_wordcloud_by_four_hours(selected_user, df):
+    if selected_user != 'Overall':
+        df = df[df['user'] == selected_user]
+
+    temp = df[df['user'] != 'group_notification']
+    temp = temp[temp['message'] != '<Media omitted>\n']
+
+    wordclouds = {}
+    for hour in range(0, 24, 4):
+        period = temp[(temp['hour'] >= hour) & (temp['hour'] < hour + 4)]
+        wc = WordCloud(width=500, height=500, min_font_size=10, background_color='white')
+        wc_img = wc.generate(period['message'].str.cat(sep=" "))
+        wordclouds[f"{hour}-{hour + 4}"] = wc_img
+
+    return wordclouds
+
+def common_words_by_month(selected_user, df):
+    if selected_user != 'Overall':
+        df = df[df['user'] == selected_user]
+
+    temp = df[df['user'] != 'group_notification']
+    temp = temp[temp['message'] != '<Media omitted>\n']
+
+    common_words_by_month = {}
+    for month in df['month_num'].unique():
+        monthly_messages = temp[temp['month_num'] == month]
+        words = [word.lower() for message in monthly_messages['message'] for word in message.split()]
+        common_words_by_month[month] = Counter(words).most_common(10)
+
+    common_words_by_month_df = pd.DataFrame.from_dict(common_words_by_month, orient='index').fillna('').astype(str)
+    return common_words_by_month_df

preprocessor.py

@@ -0,0 +1,51 @@
+import re
+import pandas as pd
+
+def preprocess(data):
+    pattern = '\d{1,2}/\d{1,2}/\d{2,4},\s\d{1,2}:\d{2}\s-\s'
+
+    messages = re.split(pattern, data)[1:]
+    dates = re.findall(pattern, data)
+
+    df = pd.DataFrame({'user_message': messages, 'message_date': dates})
+    # convert message_date type
+    df['message_date'] = pd.to_datetime(df['message_date'], format='%d/%m/%Y, %H:%M - ')
+
+    df.rename(columns={'message_date': 'date'}, inplace=True)
+
+    users = []
+    messages = []
+    for message in df['user_message']:
+        entry = re.split('([\w\W]+?):\s', message)
+        if entry[1:]:  # user name
+            users.append(entry[1])
+            messages.append(" ".join(entry[2:]))
+        else:
+            users.append('group_notification')
+            messages.append(entry[0])
+
+    df['user'] = users
+    df['message'] = messages
+    df.drop(columns=['user_message'], inplace=True)
+
+    df['only_date'] = df['date'].dt.date
+    df['year'] = df['date'].dt.year
+    df['month_num'] = df['date'].dt.month
+    df['month'] = df['date'].dt.month_name()
+    df['day'] = df['date'].dt.day
+    df['day_name'] = df['date'].dt.day_name()
+    df['hour'] = df['date'].dt.hour
+    df['minute'] = df['date'].dt.minute
+
+    period = []
+    for hour in df[['day_name', 'hour']]['hour']:
+        if hour == 23:
+            period.append(str(hour) + "-" + str('00'))
+        elif hour == 0:
+            period.append(str('00') + "-" + str(hour + 1))
+        else:
+            period.append(str(hour) + "-" + str(hour + 1))
+
+    df['period'] = period
+
+    return df

requirements.txt

@@ -0,0 +1,7 @@
+streamlit
+matplotlib
+seaborn
+urlextract
+wordcloud
+pandas
+emoji