# Import libraries
import numpy as np
import pandas as pd  

# Read movies data
movies_df = pd.read_csv('movies.csv')

# Display first few rows of movies dataframe
movies_df.head()

# Read ratings data
ratings_df = pd.read_csv('ratings.csv')

# Display first few rows of ratings dataframe
ratings_df.head()

# Join the movies and ratings tables
movies_ratings_df = pd.merge(movies_df, ratings_df, on = 'movieId')

# Remove timestamp column
del movies_ratings_df['timestamp']

# Display first few rows of merged movies and ratings dataframe
movies_ratings_df.head()

# Convert movieId, userId and rating to numeric
movies_ratings_df[['movieId','userId','rating']] = movies_ratings_df[['movieId','userId','rating']].apply(pd.to_numeric)

# Convert table to pivot table
movies_ratings_pivot = movies_ratings_df.pivot_table(values = 'rating', index = 'title', columns = 'userId')  

# Replace NaNs with 0s
movies_ratings_pivot.fillna(0, inplace = True)

# Display first few rows and columns of movies and ratings pivot table
movies_ratings_pivot.head()

# Extract and save movie titles
movie_titles = movies_ratings_pivot.index

# Define correlation matrix to get correlation between movies
corr_matrix = np.corrcoef(movies_ratings_pivot)

# Display correlation matrix
corr_matrix

array([[ 1.        , -0.00289353, -0.00171802, ..., -0.00940622,
        -0.00171802, -0.00171802],
       [-0.00289353,  1.        , -0.00251377, ...,  0.04586879,
        -0.00251377, -0.00251377],
       [-0.00171802, -0.00251377,  1.        , ..., -0.00817171,
        -0.00149254, -0.00149254],
       ..., 
       [-0.00940622,  0.04586879, -0.00817171, ...,  1.        ,
        -0.00817171, -0.00817171],
       [-0.00171802, -0.00251377, -0.00149254, ..., -0.00817171,
         1.        , -0.00149254],
       [-0.00171802, -0.00251377, -0.00149254, ..., -0.00817171,
        -0.00149254,  1.        ]])

# Define function provide top recommendations
def recommender(movie_names):  
    # Initialize recommendations output length of number of movies
    recommendations = np.zeros(corr_matrix.shape[0])
    # Loop through the movie titles that the user has rated
    for movie in movie_names:
        # Sum the correlations
        recommendations = recommendations + corr_matrix[list(movie_titles).index(movie)]
    # Convert recommendations into dataframe
    recommendations_df = pd.DataFrame({
            'Title': movie_titles,
            'Recommendation': recommendations})
    # Remove movie titles that the user has already rated
    recommendations_df = recommendations_df[~(recommendations_df.Title.isin(movie_names))]
    # Sort from most correlated to least correlated
    recommendations_df = recommendations_df.sort_values(by=['Recommendation'], ascending = False)
    return recommendations_df

# Define user
user = 1

# Get list of movies user has rated
user_movies = movies_ratings_df[movies_ratings_df.userId == user].title.tolist()  
print('Movies rated by user\n')
print(user_movies)
# Get list of recommendations
recommendations = recommender(user_movies)

# Print out top 10 recommendations
print('\nRecommendations for user\n')
print(recommendations.Title.head(10))

Movies rated by user

['Dangerous Minds (1995)', 'Dumbo (1941)', 'Sleepers (1996)', 'Escape from New York (1981)', 'Cinema Paradiso (Nuovo cinema Paradiso) (1989)', 'Deer Hunter, The (1978)', 'Ben-Hur (1959)', 'Gandhi (1982)', "Dracula (Bram Stoker's Dracula) (1992)", 'Cape Fear (1991)', 'Star Trek: The Motion Picture (1979)', 'Beavis and Butt-Head Do America (1996)', 'French Connection, The (1971)', 'Tron (1982)', 'Gods Must Be Crazy, The (1980)', 'Willow (1988)', 'Antz (1998)', 'Fly, The (1986)', 'Time Bandits (1981)', 'Blazing Saddles (1974)']

Recommendations for user

2831     Fisher King, The (1991)
8450           Unforgiven (1992)
4406            King Kong (1933)
4203                 Jaws (1975)
8473    Untouchables, The (1987)
2700             Fantasia (1940)
6471      Raising Arizona (1987)
6211          Player, The (1992)
2776      Field of Dreams (1989)
6665       Risky Business (1983)
Name: Title, dtype: object