A similarity-based-recommender in Python

import numpy as np
import pandas as pd

# Load the movie basic information dataset in a Pandas dataframe.
# https://datasets.imdbws.com/title.basics.tsv.gz
movies = pd.read_csv('data.tsv', sep='t', usecols=['tconst', 'primaryTitle'])

# Load the users' rating dataset into a Numpy array.
# The dataset contains 4,669,820 ratings from 1,499,238 users to
# 351,109 movies on the imdb.com website.
# https://ieee-dataport.org/open-access/imdb-users-ratings-dataset
ratings_array = np.load ('Dataset.npy')

# Convert the numpy array to a pandas DataFrame
ratings = pd.DataFrame([x.split(',') for x in ratings_array],
 columns=['userID', 'movieID', 'rating', 'review_date'])
ratings = ratings.iloc[:, 0:3]

# Convert the rating column to numeric type.
ratings['rating'] = pd.to_numeric(ratings['rating'])
#ratings['review_date'] = pd.to_datetime(ratings['review_date'])

print(ratings.shape)
print(ratings.head())

# Sample 0.0025 of the original dataset to reduce the computation complexity.
# Total number of ratings is 11674.
frac_ratings = ratings.sample(frac = 0.0025)

print(frac_ratings.shape)

# Create a data frame of user ratings by pivoting users and their ratings for each movie
user_ratings = frac_ratings.pivot_table(index='userID', columns='movieID', values='rating')

# Compute the mean rating for each user
user_means = user_ratings.mean(axis=1)

# Center the ratings by subtracting the mean rating for each user
centered_ratings = user_ratings.sub(user_means, axis=0)

# Calculate the movie similarities based on the centered ratings
movie_sims = centered_ratings.corr()

# Function to recommend movies based on user history
def recommend_movies(user_id, n=10):
 user_history = centered_ratings.loc[user_id].dropna()
 sim_scores = movie_sims.loc[user_history.index].sum()
 sim_scores = sim_scores.drop(user_history.index)
 rec_movies = sim_scores.nlargest(n).index
 return rec_movies

# Function to create the list of primaryTitles.
def movie_df (rec_movies):
 titles = []
 for movieId in rec_movies:
 title = movies.loc[movies['tconst'] == movieId, 'primaryTitle'].iloc[0]
 titles.append(title)
 # create the DataFrame of tconst and primaryTitle
 rec_movies_df = pd.DataFrame({'tconst': rec_movies, 'primaryTitle': titles})
 return rec_movies_df