helper.py

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