Content Based Recommendations using DNN#

[1]:

import pandas as pd
import numpy as np
import tensorflow as tf

[2]:

ratings = pd.read_csv('/opt/datasetsRepo/RecommendationData/ratings.csv')
ratings.head(5)

[2]:

	userId	movieId	rating	timestamp
0	1	1	4.0	964982703
1	1	3	4.0	964981247
2	1	6	4.0	964982224
3	1	47	5.0	964983815
4	1	50	5.0	964982931

[3]:

movies = pd.read_csv("/opt/datasetsRepo/RecommendationData/movies.csv")
movies.head(5)

[3]:

	movieId	title	genres
0	1	Toy Story (1995)	Adventure\|Animation\|Children\|Comedy\|Fantasy
1	2	Jumanji (1995)	Adventure\|Children\|Fantasy
2	3	Grumpier Old Men (1995)	Comedy\|Romance
3	4	Waiting to Exhale (1995)	Comedy\|Drama\|Romance
4	5	Father of the Bride Part II (1995)	Comedy

[4]:

idx_to_movieid_mapper = dict(enumerate(movies.movieId.unique()))
movieid_to_idx_mapper = dict(zip(idx_to_movieid_mapper.values(), idx_to_movieid_mapper.keys()))

idx_to_userid_mapper = dict(enumerate(ratings.userId.unique()))
userid_to_idx_mapper = dict(zip(idx_to_userid_mapper.values(), idx_to_userid_mapper.keys()))

[9]:

ratings['user_idx'] = ratings['userId'].map(userid_to_idx_mapper)
ratings['movie_idx'] = ratings['movieId'].map(movieid_to_idx_mapper)

[10]:

movies['movie_idx'] = movies['movieId'].map(movieid_to_idx_mapper)

[11]:

movies['genres_arr'] = movies['genres'].apply(lambda x: x.split("|"))

movies_tmp = movies[['movie_idx','genres_arr']].explode('genres_arr').drop_duplicates()

movies_tmp.insert(loc=0, value=1, column='cnt')

movie_features_sparse_matrix =  movies_tmp.pivot_table(index='movie_idx', columns='genres_arr',
                                                       values='cnt', aggfunc='count').fillna(0)

movie_features_sparse_matrix.head()

[11]:

genres_arr	(no genres listed)	Action	Adventure	Animation	Children	Comedy	Crime	Documentary	Drama	Fantasy	Film-Noir	Horror	IMAX	Musical	Mystery	Romance	Sci-Fi	Thriller	War	Western
movie_idx
0	0.0	0.0	1.0	1.0	1.0	1.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1	0.0	0.0	1.0	0.0	1.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
2	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0
3	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0
4	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0

[15]:

user_movies_sparse_matrix = ratings[['user_idx', 'movie_idx', 'rating']].pivot_table(index='user_idx', columns='movie_idx',
                                                                                     values='rating', aggfunc='sum')
user_movies_sparse_matrix.head(5)

[15]:

movie_idx	0	1	2	3	4	5	6	7	8	9	...	9732	9733	9734	9735	9736	9737	9738	9739	9740	9741
user_idx
0	4.0	NaN	4.0	NaN	NaN	4.0	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
1	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
3	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
4	4.0	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN

5 rows × 9724 columns

[ ]:

Recommendation-Systems

Content Based Recommendations using DNN

Content Based Recommendations using DNN#