app.py

import pandas as pd
import numpy as np
from scipy.sparse import csr_matrix
from sklearn.neighbors import NearestNeighbors
import gradio as gr
import zipfile
import random

input_count = 300
result_count = 21

# Extract the MovieLens dataset
with zipfile.ZipFile('ml-latest-small.zip') as z:
    with z.open('ml-latest-small/movies.csv') as f:
        movies = pd.read_csv(f)
    with z.open('ml-latest-small/ratings.csv') as f:
        ratings = pd.read_csv(f)

# Create a user-item matrix
user_item_matrix = ratings.pivot(index='userId', columns='movieId', values='rating').fillna(0)

# Create a sparse matrix
user_item_matrix_sparse = csr_matrix(user_item_matrix.values)

# Fit the NearestNeighbors model
model_knn = NearestNeighbors(metric='cosine', algorithm='brute', n_neighbors=20, n_jobs=-1)
model_knn.fit(user_item_matrix_sparse)

# Function to get movie recommendations using collaborative filtering
def get_cf_recommendations(user_id, user_item_matrix=user_item_matrix, model_knn=model_knn, movies=movies):
    if user_id not in user_item_matrix.index:
        return []

    user_vector = user_item_matrix.loc[user_id].values.reshape(1, -1)
    distances, indices = model_knn.kneighbors(user_vector, n_neighbors=result_count)
    
    similar_users = user_item_matrix.index[indices.flatten()]
    similar_users_df = pd.DataFrame({'userId': similar_users, 'distance': distances.flatten()})
    
    user_seen_movies = set(user_item_matrix.columns[user_item_matrix.loc[user_id] > 0])
    
    recommendations = []
    for _, row in similar_users_df.iterrows():
        similar_user_id = row['userId']
        similar_user_movies = set(user_item_matrix.columns[user_item_matrix.loc[similar_user_id] > 0])
        new_movies = similar_user_movies - user_seen_movies
        
        for movie_id in new_movies:
            movie_title = movies.loc[movies['movieId'] == movie_id, 'title'].values[0]
            score = 1 - row['distance']  # Convert distance to similarity score
            recommendations.append((movie_title, score))
    
    recommendations.sort(key=lambda x: x[1], reverse=True)
    return recommendations[:result_count]

# Gradio interface for collaborative filtering
def recommend_movies_cf(user_id):
    try:
        user_id = int(user_id)
    except ValueError:
        return "Please enter a valid user ID (integer)."
    
    if user_id not in user_item_matrix.index:
        return f"User ID {user_id} not found in the dataset."
    
    recommendations = get_cf_recommendations(user_id)
    format_string = "{:>5.2f}       {:<20}"
    return "Score     Title\n" + "\n".join([format_string.format(score, title) for title, score in recommendations])

# Update the existing Gradio interface
with gr.Blocks() as iface:
    with gr.Tab("Content-Based Filtering"):
        gr.Interface(fn=recommend_movies, 
                     inputs=gr.Dropdown(movie_list, label=f"Select a Movie (Total movies: {total_movies}, randomly list {input_count} for demo purpose.)"), 
                     outputs=[gr.Textbox(label="Recommended Movies:")],
                     title="Movie Recommender - Content-Based Filtering", 
                     description="Select a movie to get recommendations based on content filtering.")
    
    with gr.Tab("Collaborative Filtering"):
        gr.Interface(fn=recommend_movies_cf,
                     inputs=gr.Number(label="Enter User ID"),
                     outputs=[gr.Textbox(label="Recommended Movies:")],
                     title="Movie Recommender - Collaborative Filtering",
                     description="Enter a user ID to get movie recommendations based on collaborative filtering.")

# Launch the app
iface.launch()