from urlextract import URLExtract
from wordcloud import WordCloud
import pandas as pd
from collections import Counter
import emoji
from nltk.sentiment.vader import SentimentIntensityAnalyzer
import nltk

nltk.download('vader_lexicon')

extract = URLExtract()
sentiment_analyzer = SentimentIntensityAnalyzer()

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

    # Number of messahes
    num_messages = df.shape[0]

    # fetch the total number of words
    words = []
    for message in df['message']:
        words.extend(message.split())

    # fetch number of media messages
    num_media_messages = df[df['message'] == '<Media omitted>\n'].shape[0]

    # fetch number of links shared
    links = []
    for message in df['message']:
        links.extend(extract.find_urls(message))

    return num_messages,len(words),num_media_messages,len(links)
    #return num_messages, len(words), num_media_messages, len(links)

def most_busy_users(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):
    f = open('stop_hinglish.txt', 'r')
    stop_words = f.read().splitlines()

    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 = [word for word in message.lower().split() if word not in stop_words]
        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().splitlines()

    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 for message in temp['message'] for word in message.lower().split() if word not in stop_words]
    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.UNICODE_EMOJI['en']]
    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()
    timeline['time'] = timeline['month'] + "-" + timeline['year'].astype(str)
    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 sentiment_analysis(selected_user, df):
    if selected_user != 'Overall':
        df = df[df['user'] == selected_user]

    df['sentiment'] = df['message'].apply(lambda x: sentiment_analyzer.polarity_scores(x))
    df['sentiment_score'] = df['sentiment'].apply(lambda x: x['compound'])
    df['sentiment_label'] = df['sentiment_score'].apply(lambda x: 'Positive' if x > 0 else ('Negative' if x < 0 else 'Neutral'))
    sentiment_df = df.groupby('sentiment_label').count()['message'].reset_index()
    return sentiment_df