app.py

import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import linear_kernel
import gradio as gr
import zipfile
import requests
import io

# Download and extract the MovieLens dataset
url = 'https://files.grouplens.org/datasets/movielens/ml-latest-small.zip'
response = requests.get(url)
with zipfile.ZipFile(io.BytesIO(response.content)) as z:
    with z.open('ml-latest-small/movies.csv') as f:
        movies = pd.read_csv(f)

# Define a TF-IDF Vectorizer Object. Remove all english stop words such as 'the', 'a'
tfidf = TfidfVectorizer(stop_words='english')

# Replace NaN with an empty string
movies['genres'] = movies['genres'].fillna('')

# Construct the required TF-IDF matrix by fitting and transforming the data
tfidf_matrix = tfidf.fit_transform(movies['genres'])

# Compute the cosine similarity matrix
cosine_sim = linear_kernel(tfidf_matrix, tfidf_matrix)

# Construct a reverse map of indices and movie titles
indices = pd.Series(movies.index, index=movies['title']).drop_duplicates()

# Function that takes in movie title as input and outputs most similar movies
def get_recommendations(title, cosine_sim=cosine_sim):
    # Get the index of the movie that matches the title
    idx = indices[title]

    # Get the pairwise similarity scores of all movies with that movie
    sim_scores = list(enumerate(cosine_sim[idx]))

    # Sort the movies based on the similarity scores
    sim_scores = sorted(sim_scores, key=lambda x: x[1], reverse=True)

    # Get the scores of the 20 most similar movies
    sim_scores = sim_scores[1:21]

    # Get the movie indices
    movie_indices = [i[0] for i in sim_scores]

    # Return the top 20 most similar movies with their scores
    recommendations = [(movies['title'].iloc[i], sim_scores[idx][1]) for idx, i in enumerate(movie_indices)]
    return recommendations

# Gradio interface
def recommend_movies(movie):
    recommendations = get_recommendations(movie)

    max_length = movies['title'].str.len().max()
    print(f"The longest movie name length is: {max_length}")
    
    headers = "Score{:10}Title".format("")
    return headers + "\n" + "\n".join([f"{score:>10.2f} {title:<20} " for title, score in recommendations])


# Create the Gradio interface
movie_list = movies['title'].tolist()
iface = gr.Interface(fn=recommend_movies, inputs=gr.Dropdown(movie_list), outputs="text", title="Movie Recommender - Content-Based Filtering", description="Select a movie to get recommendations based on content filtering.")

# Launch the app
iface.launch()