helper.py

from urlextract import URLExtract
from wordcloud import WordCloud
import pandas as pd
from collections import Counter
import emoji
extractor = URLExtract()


def fetch_stats(selected_user, df):
    if selected_user != 'Overall':
        df = df[df['user'] == selected_user]

# 1. fetch no. of message
    num_messages = df.shape[0]
    # 2. words count
    words = []
    for message in df['message']:
        words.extend(message.split())
        # 3. fetch no. of media messages
    num_media_msg = df[df['message'] == '<Media omitted>\n'].shape[0]

    # 4. links extract
    links = []
    for message in df['message']:
        links.extend(extractor.find_urls(message))

    return num_messages, len(words), num_media_msg, len(links)


# finding the most busiest user
def most_busy_user(df):
    x = df['user'].value_counts().head()
    df = round((df['user'].value_counts() / df.shape[0])*100,
               2).reset_index().rename(columns={'index': 'name', 'user': 'percent'})
    return x, df


def create_wordcloud(selected_user, df):
    if selected_user != 'Overall':
        df = df[df['user'] == selected_user]

    wc = WordCloud(width=500, height=500, min_font_size=10,
                   background_color='white')
    df_wc = wc.generate(df['message'].str.cat(sep=" "))
    return df_wc


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 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