helper.py

from urlextract import URLExtract
from wordcloud import WordCloud 
from collections import Counter
import pandas as pd 
import emoji
urlextractor = URLExtract()
def fetch_stats(selected_user,df):
    if selected_user != "Overall":
        df = df[df['user'] == selected_user]
    words = []
    for word in df['message']:
        words.extend(word.split(" "))
    #fetch number of media messages
    num_media_messages = df[df['message'] == '<Media omitted>\n']

    links = []
    for message in df['message']:
        links.extend(urlextractor.find_urls(message))
    
    return df.shape[0],len(words),len(num_media_messages),len(links)

def most_busy_users(df):
    x = df['user'].value_counts().head()
    new_df = round(df['user'].value_counts()/df.shape[0]*100,2).reset_index().rename(columns={'index':'name','user':'percent'})
    return x,new_df

def create_wordcloud(selected_user,df):

    f = open("stop_hinglish.txt",'r')
    stop_words = f.read()

    if selected_user != 'Overall':
        df = df[df['user'] == selected_user]
    
    temp = df[df['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_hinglish.txt",'r')
    stop_words = f.read()

    if selected_user != "Overall":
        df = df[df['user'] == selected_user]

    temp = df[df['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))
    return most_common_df

def emoji_helper(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))))
    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 = []
    for i in range(timeline.shape[0]):
        time.append(timeline['month'][i] + "-" + str(timeline['year'][i]))
    timeline['time'] = time

    return timeline

def daily_timeline(selected_user,df):
    if selected_user != 'Overall':
        df = df[df['user'] == selected_user]
    daily_time = df.groupby(df['only_date']).count()['message'].reset_index()

    return daily_time

def weekly_activity(selected_user,df):
    if selected_user != 'Overall':
        df = df[df['user'] == selected_user]
    return df['day_name'].value_counts()

def monthly_activity(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