A recommender using deep learning in Python

from google.colab import drive
import os
import pandas as pd
import numpy as np
import pandas as pd
import numpy as np
import re
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MultiLabelBinarizer
from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import Adam

# Mount Google Drive
if not os.path.exists('/content/drive'):
 drive.mount('/content/drive')
# Change directory
os.chdir('drive/MyDrive/recommender-system/code&dataset')

# Load the dataset
ratings = pd.read_csv('ratings.csv', usecols=['userId', 'movieId', 'rating'])
movies = pd.read_csv('movies.csv')

# Merge the ratings and movies dataframes
data = pd.merge(ratings, movies, on='movieId')

# Convert genres into binary labels
genres = set()
for s in data.genres.str.split('|').values:
 genres = genres.union(set(s))
genres = sorted(list(genres))
genre_dummies = data['genres'].str.get_dummies().astype(int)
data = pd.concat([data, genre_dummies], axis=1)

# Split the data into training and testing sets
train, test = train_test_split(data, test_size=0.2, random_state=42)

# Convert genres into binary vectors
mlb = MultiLabelBinarizer()
mlb.fit_transform(data['genres'].str.split('|'))
genres_array = mlb.transform(train['genres'].str.split('|'))
test_genres_array = mlb.transform(test['genres'].str.split('|'))

# Define the model
model = Sequential()
model.add(Dense(units=64, input_shape=(len(genres_array[0]),), activation='relu'))
model.add(Dense(units=32, activation='relu'))
model.add(Dense(units=16, activation='relu'))
model.add(Dense(units=1, activation='linear'))

# Compile the model
model.compile(loss='mean_squared_error', optimizer=Adam(learning_rate=0.001))

# Train the model
model.fit(genres_array, train['rating'], epochs=10, batch_size=128, validation_data=(test_genres_array, test['rating']))

# Get list of all genres in the dataset
genres = set('|'.join(movies['genres']).split('|'))

def recommend_movies(userId, topN):
 user_ratings = data[['userId', 'movieId', 'rating']][data.userId == userId]
 user_unseen_movies = movies[~movies['movieId'].isin(data[data.userId == 1]['movieId'])]
 user_unseen_movies = pd.concat([user_unseen_movies, user_unseen_movies.genres.str.get_dummies()], axis=1)
 user_unseen_movies = pd.merge(user_unseen_movies, user_ratings, how='left', on=['movieId'])
 user_unseen_movies = user_unseen_movies.fillna(0)
 user_unseen_movies['rating'] = model.predict(user_unseen_movies[genres])
 user_unseen_movies = user_unseen_movies.sort_values(by='rating', ascending=False)
 return user_unseen_movies.head(topN)['title'].values