app.py

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


def create_matrix(df):
    N = len(df['userId'].unique())
    M = len(df['movieId'].unique())
    # Map Ids to indices
    user_mapper = dict(zip(np.unique(df["userId"]), list(range(N))))
    movie_mapper = dict(zip(np.unique(df["movieId"]), list(range(M))))
    # Map indices to IDs
    user_inv_mapper = dict(zip(list(range(N)), np.unique(df["userId"])))
    movie_inv_mapper = dict(zip(list(range(M)), np.unique(df["movieId"])))
    user_index = [user_mapper[i] for i in df['userId']]
    movie_index = [movie_mapper[i] for i in df['movieId']]
    X = csr_matrix((df["rating"], (movie_index, user_index)), shape=(M, N))
    return X, user_mapper, movie_mapper, user_inv_mapper, movie_inv_mapper


def find_similar_movies(movie_id, X, k, metric='cosine', show_distance=False):
    neighbour_ids = []
    movie_ind = movie_mapper[movie_id]
    movie_vec = X[movie_ind]
    k += 1
    kNN = NearestNeighbors(n_neighbors=k, algorithm="brute", metric=metric)
    kNN.fit(X)
    movie_vec = movie_vec.reshape(1, -1)
    neighbour = kNN.kneighbors(movie_vec, return_distance=show_distance)
    for i in range(0, k):
        n = neighbour.item(i)
        neighbour_ids.append(movie_inv_mapper[n])
    neighbour_ids.pop(0)
    return neighbour_ids


def recommend_movies(movie_name):
    movie_id = [k for k, v in movie_titles.items() if movie_name.lower() in v.lower()]
    if len(movie_id) == 0:
        return "Movie not found. Please check the spelling and try again"
    movie_id = movie_id[0]
    similar_ids = find_similar_movies(movie_id, X, k=10)
    recommendations = "\n".join([movie_titles[i] for i in similar_ids])
    return recommendations


# Load data
ratings = pd.read_csv("ratings.csv")
movies = pd.read_csv("movies.csv")
n_ratings = len(ratings)
n_movies = len(ratings['movieId'].unique())
n_users = len(ratings['userId'].unique())
user_freq = ratings[['userId', 'movieId']].groupby('userId').count().reset_index()
user_freq.columns = ['userId', 'n_ratings']
mean_rating = ratings.groupby('movieId')[['rating']].mean()
lowest_rated = mean_rating['rating'].idxmin()
highest_rated = mean_rating['rating'].idxmax()
movie_stats = ratings.groupby('movieId')[['rating']].agg(['count', 'mean'])
movie_stats.columns = movie_stats.columns.droplevel()
X, user_mapper, movie_mapper, user_inv_mapper, movie_inv_mapper = create_matrix(ratings)
movie_titles = dict(zip(movies['movieId'], movies['title']))

# Set up Gradio interface
movie_name = gr.inputs.Textbox(label="Movie Name")
outputs = gr.outputs.Textbox(label="Recommended Movies", type="text")

iface = gr.Interface(
    fn=recommend_movies, 
    inputs=movie_name, 
    outputs=outputs,
    theme=gr.themes.Default(primary_hue="slate"))
)
iface.launch()