popularity.py

import pandas as pd
import numpy as np
import streamlit as st
from pathlib import Path
import sys
import os
import time
import matplotlib.pyplot as plt


# ====================== Streamlit Setup ======================
st.set_page_config(layout="wide")
st.title("Popularity Based Filtering")
st.markdown('---')

# ====================== Data Extraction ======================

sys.path.append(os.path.dirname(__file__))
data_dir = Path(__file__).parent / 'data'

movies = 'movies_final.csv'
movies = pd.read_csv(movies)
movies = movies[['movieId','title']]

# ratings dataset
ratings = data_dir / 'ratings.csv'
ratings = st.session_state['ratings_df']
# ratings = ratings.drop(columns=['timestamp'])
ratings = ratings.drop_duplicates(subset=['userId', 'movieId'], keep='first')


st.subheader('👀 Glance of the dataset')
col1 ,col2 = st.columns(2)
with col1:
    st.markdown("Ratings Dataset")
    st.dataframe(ratings.head())
with col2:
    st.markdown("Movies Dataset")
    st.dataframe(movies.head())
st.markdown('---')

# ============================= Most Rated Movies ====================================================
col1, col2 = st.columns(2)

most_rated = ratings.groupby('movieId').count()['userId'].sort_values(ascending=False).head()
most_rated = most_rated.reset_index().rename(columns={'userId': 'No_of_Ratings'})
most_rated_final = pd.merge(most_rated, movies, how='left', on='movieId')
movie_ids = most_rated_final['movieId'].tolist()

avg_ratings = ratings[ratings['movieId'].isin(movie_ids)]
avg_ratings = avg_ratings.groupby('movieId')['rating'].mean().reset_index().rename(columns={'rating': 'Avg_Rating'})
most_rated_final = pd.merge(most_rated_final, avg_ratings, how='left', on='movieId')

with col1:
    st.subheader('📈 Top 5 Most Rated Movies')
    st.dataframe(most_rated_final[['title', 'No_of_Ratings', 'Avg_Rating']])

# ============================= Least Rated Movies ====================================================
most_rated = ratings.groupby('movieId').agg({'rating': 'mean', 'userId': 'count'}).rename(
    columns={'rating': 'Avg_Rating', 'userId': 'No_of_Ratings'}
)
most_rated = most_rated.sort_values(['No_of_Ratings','Avg_Rating']).head()
most_rated_final = pd.merge(most_rated, movies, how='left', on='movieId')

with col2:
    st.subheader('📉 Top 5 Least Rated Movies')
    st.dataframe(most_rated_final[['title', 'No_of_Ratings', 'Avg_Rating']])

# ============================= Highest Average Rated Movies ==========================================
st.markdown('---')

col1, col2 = st.columns(2)

filter_ratings = ratings[ratings['rating'] == 5]
most_rated = filter_ratings.groupby('movieId').count()['userId'].sort_values(ascending=False).head()
most_rated = most_rated.reset_index().rename(columns={'userId': 'No_of_Ratings'})
most_rated_final = pd.merge(most_rated, movies, how='left', on='movieId')

filter_ratings = ratings[ratings['rating'] == 0.5]
most_rated = filter_ratings.groupby('movieId').count()['userId'].sort_values(ascending=False).head()
most_rated = most_rated.reset_index().rename(columns={'userId': 'No_of_Ratings'})
least_most_rated_final = pd.merge(most_rated, movies, how='left', on='movieId')


with col1:
    st.subheader('Highest Rated Movies with 5⭐')
    st.dataframe(most_rated_final[['title', 'No_of_Ratings']])
    st.subheader('Highest Rated Movies with 0.5⭐')
    st.dataframe(least_most_rated_final[['title', 'No_of_Ratings']])

# ============================= Ratings Distribution Graph ============================================
import matplotlib.pyplot as plt

# col1, col2 = st.columns(2)

with col2:
    st.subheader('📊 Ratings Distribution')
    graph = ratings.groupby('rating').count()['userId']
    fig, ax = plt.subplots()
    ax.bar(graph.index, graph.values)
    ax.set_xlabel('Rating')
    ax.set_ylabel('Number of Ratings')
    ax.set_title('Number of Ratings by Rating Value')
    st.pyplot(fig)

st.markdown('---')

# ============================= User Selected Ratings ===================================================
st.subheader('🎯 Movies Filtered by Selected Rating')
ratings_selected = st.selectbox(
    'Select the Rating', 
    pd.Series(ratings['rating'].unique()).sort_values(ascending=False).tolist()
)
filter_ratings = ratings[ratings['rating'] == ratings_selected]

col1, col2 = st.columns(2)

with col1:
    st.markdown('**Most Rated for Selected Rating**')
    most_rated = filter_ratings.groupby('movieId').count()['userId'].sort_values(ascending=False).head()
    most_rated = most_rated.reset_index().rename(columns={'userId': 'No_of_Ratings'})
    most_rated_final = pd.merge(most_rated, movies, how='left', on='movieId')
    st.dataframe(most_rated_final[['title', 'No_of_Ratings']])
with col2:
    st.markdown('**Least Rated for Selected Rating**')
    most_rated = filter_ratings.groupby('movieId').count()['userId'].sort_values().head()
    most_rated = most_rated.reset_index().rename(columns={'userId': 'No_of_Ratings'})
    most_rated_final = pd.merge(most_rated, movies, how='left', on='movieId')
    st.dataframe(most_rated_final[['title', 'No_of_Ratings']])