Spaces:
Sleeping
Sleeping
| from urlextract import URLExtract | |
| from wordcloud import WordCloud | |
| from collections import Counter | |
| import pandas as pd | |
| import emoji | |
| extractor = URLExtract() | |
| def fetch_states(selected_user, df): | |
| if selected_user != 'Overall': | |
| df = df[df['user'] == selected_user] | |
| # 1. Number of messages | |
| num_messages = df.shape[0] | |
| # 2. Number of words | |
| words = [] | |
| for message in df['message']: | |
| words.extend(message.split()) | |
| # 3. Number of media | |
| num_media_messages = df[df['message'] == '<Media omitted>\n'].shape[0] | |
| # 4. Number of Links | |
| links = [] | |
| for message in df['message']: | |
| links.extend(extractor.find_urls(message)) | |
| return num_messages, len(words), num_media_messages, len(links) | |
| def monthly_timeline(selected_user, df): | |
| if selected_user != 'Overall': | |
| df = df[df['user'] == selected_user] | |
| df['month_num'] = df['date'].dt.month | |
| timeline = df.groupby(['year', 'month_num', 'month']).count()[ | |
| 'message'].reset_index() | |
| time = [] | |
| for i in range(timeline.shape[0]): | |
| time.append(timeline['month'][i] + '-' + str(timeline['year'][i])) | |
| timeline['time'] = time | |
| return timeline.rename(columns={'message': 'Message', 'time': '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() | |
| daily_timeline = daily_timeline.rename( | |
| columns={'only_date': 'Date', 'message': 'Message'}) | |
| return daily_timeline | |
| def week_activity_map(selected_user, df): | |
| if selected_user != 'Overall': | |
| df = df[df['user'] == selected_user] | |
| week_activity = df['day_name'].value_counts().reset_index() | |
| week_activity = week_activity.rename( | |
| columns={'day_name': 'Day', 'count': "Message"}) | |
| return week_activity | |
| def month_activity_map(selected_user, df): | |
| if selected_user != 'Overall': | |
| df = df[df['user'] == selected_user] | |
| month_activity = df['month'].value_counts().reset_index() | |
| month_activity = month_activity.rename( | |
| columns={'month': 'Month', 'count': "Message"}) | |
| return month_activity | |
| 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) | |
| user_heatmap = user_heatmap.rename_axis('Day', axis='index') | |
| user_heatmap = user_heatmap.rename_axis('Time Period', axis='columns') | |
| # user_heatmap = user_heatmap.rename_axis('Message', axis='color') | |
| return user_heatmap | |
| def most_active_user(df): | |
| temp = df[df['user'] != 'group_notification'] | |
| x = (temp['user'].value_counts().head()).reset_index().rename( | |
| columns={'user': 'User', 'count': 'Count'}) | |
| per = round(((temp['user'].value_counts() / temp.shape[0]) * 100), | |
| 2).reset_index().rename(columns={'user': 'User', 'count': 'Percent(%)'}) | |
| return x, per | |
| def create_wordcloud(selected_user, df): | |
| f = open('stop_ben-hin-eng.txt', 'r') | |
| stop_words = f.read() | |
| if selected_user != 'Overall': | |
| df = df[df['user'] == selected_user] | |
| temp = df[df['user'] != 'group_notification'] | |
| temp = temp[temp['message'] != '<Media omitted>\n'] | |
| def remove_stop_words(message): | |
| y = [] | |
| for word in message.lower().split(): | |
| if word not in stop_words: | |
| y.append(word) | |
| return " ".join(y) | |
| wc = WordCloud(width=500, height=500, min_font_size=10, | |
| background_color='white') | |
| temp['message'] = temp['message'].apply(remove_stop_words) | |
| df_wc = wc.generate(temp['message'].str.cat(sep=" ")) | |
| return df_wc | |
| def most_common_words(selected_user, df): | |
| f = open('stop_ben-hin-eng.txt', 'r') | |
| stop_words = f.read() | |
| if selected_user != 'Overall': | |
| df = df[df['user'] == selected_user] | |
| temp = df[df['user'] != 'group_notification'] | |
| temp = temp[temp['message'] != '<Media omitted>\n'] | |
| words = [] | |
| for message in temp['message']: | |
| for word in message.lower().split(): | |
| if word not in stop_words: | |
| words.append(word) | |
| most_common_df = pd.DataFrame(Counter(words).most_common( | |
| 20)).iloc[::-1].rename(columns={0: 'Message', 1: 'Count'}) | |
| return most_common_df | |
| def emoji_data(selected_user, df): | |
| if selected_user != 'Overall': | |
| df = df[df['user'] == selected_user] | |
| emojis = [] | |
| for message in df['message']: | |
| emojis.extend([c for c in message if c in emoji.EMOJI_DATA]) | |
| emoji_df = pd.DataFrame(Counter(emojis).most_common( | |
| len(Counter(emojis)))) | |
| if emojis: | |
| emoji_df = emoji_df.rename(columns={0: 'Emoji', 1: 'Count'}) | |
| return emoji_df | |
| def data_timeframe(df): | |
| df_first = df.iloc[0] | |
| df_last = df.iloc[-1] | |
| timeframe = str(df_first['day']) + " " + str(df_first['month']) + " " + str(df_first['year']) + \ | |
| " to " + str(df_last['day']) + " " + \ | |
| str(df_last['month']) + " " + str(df_last['year']) | |
| return timeframe | |