Transformação nas tabelas para modelagem

%load_ext pretty_jupyter

Importar Bibliotecas¶

import pandas as pd
import os
import numpy as np

import matplotlib as plt
import seaborn as sns

Definir Diretório¶

os.chdir("C:/0.Projetos/5.Sistema_de_Recomendacao_MovieLens_2")

Carregar Arquivos¶

ratings_treino_transformado_modelagem = pd.read_pickle("C:/0.Projetos/5.Sistema_de_Recomendacao_MovieLens_2/Datasets/3.Datasets_Transformação/3.1_Datasets_Transformação_parte_1/ratings_treino_transformado_modelagem.pickle", compression='gzip')
ratings_teste_transformado_modelagem = pd.read_pickle("C:/0.Projetos/5.Sistema_de_Recomendacao_MovieLens_2/Datasets/3.Datasets_Transformação/3.1_Datasets_Transformação_parte_1/ratings_teste_transformado_modelagem.pickle", compression='gzip')

ratings_teste_transformado_modelagem.head()

	userId	Numero_de_Avaliacoes_por_usuarios	movieId	Numero_de_Avaliacoes_por_Filme	rating	timestamp	rating_times	rating_medio_simples	rating_medio_ponderado
0	128	19	168	81	3.0	1998-07-28 13:16:18	0.026268	3.166667	0.851209
1	2311	148	168	81	4.0	2011-07-22 12:26:00	0.375046	3.166667	0.851209
2	2647	128	168	81	5.0	1997-03-31 15:23:45	0.034370	3.166667	0.851209
3	9051	18	168	81	3.0	2005-03-24 17:36:55	0.088577	3.166667	0.851209
4	9595	45	168	81	3.0	1996-05-19 18:24:49	0.017608	3.166667	0.851209

movies_treino_transformado = pd.read_pickle("C:/0.Projetos/5.Sistema_de_Recomendacao_MovieLens_2/Datasets/3.Datasets_Transformação/3.2_Datasets_Transformação_parte_2/movies_treino_transformado.pickle", compression='gzip')
movies_teste_transformado = pd.read_pickle("C:/0.Projetos/5.Sistema_de_Recomendacao_MovieLens_2/Datasets/3.Datasets_Transformação/3.2_Datasets_Transformação_parte_2/movies_teste_transformado.pickle", compression='gzip')

movies_treino_transformado.head()

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

Tabelas de apoio¶

catalago = movies_treino_transformado[['title', 'genres_separado']]
catalago

	title	genres_separado
0	Toy Story (1995)	Adventure
1	Jumanji (1995)	Adventure
2	Grumpier Old Men (1995)	Comedy
3	Waiting to Exhale (1995)	Comedy
4	Father of the Bride Part II (1995)	Comedy
...	...	...
86397	Initial D: Third Stage (2001)	Action
86427	Everybody's Oma (2022)	Documentary
86435	Insidious: The Red Door (2023)	Horror
86439	The Out-Laws (2023)	Action
86470	Novalis - Die blaue Blume (1993)	Drama

24345 rows × 2 columns

genero_user_treino1 = pd.merge(movies_treino_transformado , ratings_treino_transformado_modelagem, on=['movieId'], how='left')
genero_user_treino1

	movieId	title	genres	Ano_do_filme	titulo_sem_ano	genres_separado	userId	Numero_de_Avaliacoes_por_usuarios	Numero_de_Avaliacoes_por_Filme	rating	timestamp	rating_times	rating_medio_simples	rating_medio_ponderado
0	1	Toy Story (1995)	Adventure\|Animation\|Children\|Comedy\|Fantasy	1995	Toy Story	Adventure	144	154	1848	3.5	2014-01-12 03:50:37	0.515954	3.928842	3.264437
1	1	Toy Story (1995)	Adventure\|Animation\|Children\|Comedy\|Fantasy	1995	Toy Story	Adventure	304	498	1848	3.0	2023-06-01 19:24:35	2.453737	3.928842	3.264437
2	1	Toy Story (1995)	Adventure\|Animation\|Children\|Comedy\|Fantasy	1995	Toy Story	Adventure	461	1692	1848	4.5	2020-08-28 20:04:03	2.225713	3.928842	3.264437
3	1	Toy Story (1995)	Adventure\|Animation\|Children\|Comedy\|Fantasy	1995	Toy Story	Adventure	751	469	1848	3.0	2012-09-30 20:05:17	0.349977	3.928842	3.264437
4	1	Toy Story (1995)	Adventure\|Animation\|Children\|Comedy\|Fantasy	1995	Toy Story	Adventure	974	1160	1848	5.0	1999-09-17 11:01:24	0.053903	3.928842	3.264437
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
820503	288557	Initial D: Third Stage (2001)	Action\|Animation\|Romance	2001	Initial D: Third Stage	Action	256559	803	2	4.0	2023-06-30 15:36:23	3.319434	4.000000	0.140522
820504	288647	Everybody's Oma (2022)	Documentary	2022	Everybody's Oma	Documentary	218862	886	1	4.5	2023-07-05 08:02:09	3.743711	4.500000	0.126201
820505	288669	Insidious: The Red Door (2023)	Horror\|Mystery\|Thriller	2023	Insidious: The Red Door	Horror	324508	1126	1	2.5	2023-07-15 02:49:04	2.090265	2.500000	0.070112
820506	288679	The Out-Laws (2023)	Action\|Comedy\|Romance	2023	The Out-Laws	Action	65065	2569	1	2.5	2023-07-09 01:00:03	2.084003	2.500000	0.070112
820507	288761	Novalis - Die blaue Blume (1993)	Drama	1993	Novalis - Die blaue Blume	Drama	222466	571	1	4.0	2023-07-11 09:29:45	3.337741	4.000000	0.112179

820508 rows × 14 columns

genero_user_teste1 = pd.merge(movies_teste_transformado , ratings_teste_transformado_modelagem, on=['movieId'], how='left')
genero_user_teste1.head()

	movieId	title	genres	Ano_do_filme	titulo_sem_ano	genres_separado	userId	Numero_de_Avaliacoes_por_usuarios	Numero_de_Avaliacoes_por_Filme	rating	timestamp	rating_times	rating_medio_simples	rating_medio_ponderado
0	1	Toy Story (1995)	Adventure\|Animation\|Children\|Comedy\|Fantasy	1995	Toy Story	Adventure	465	98	494	5.0	2017-02-16 04:44:41	1.297498	3.799595	2.333916
1	1	Toy Story (1995)	Adventure\|Animation\|Children\|Comedy\|Fantasy	1995	Toy Story	Adventure	598	124	494	4.0	1997-09-22 16:26:23	0.030011	3.799595	2.333916
2	1	Toy Story (1995)	Adventure\|Animation\|Children\|Comedy\|Fantasy	1995	Toy Story	Adventure	1931	264	494	5.0	2020-04-12 18:15:52	2.306977	3.799595	2.333916
3	1	Toy Story (1995)	Adventure\|Animation\|Children\|Comedy\|Fantasy	1995	Toy Story	Adventure	2311	148	494	4.0	2011-07-23 16:52:35	0.375234	3.799595	2.333916
4	1	Toy Story (1995)	Adventure\|Animation\|Children\|Comedy\|Fantasy	1995	Toy Story	Adventure	2647	128	494	3.0	1997-03-31 15:11:04	0.020622	3.799595	2.333916

# Salvar tabela 
catalago.to_pickle("C:/0.Projetos/5.Sistema_de_Recomendacao_MovieLens_2/Datasets/3.Datasets_Transformação/3.3_Datasets_Transformação_parte_3/catalogo.pickle", compression='gzip')

genero_user_treino1.to_pickle("C:/0.Projetos/5.Sistema_de_Recomendacao_MovieLens_2/Datasets/3.Datasets_Transformação/3.3_Datasets_Transformação_parte_3/genero_user_treino1.pickle", compression='gzip')
genero_user_teste1.to_pickle("C:/0.Projetos/5.Sistema_de_Recomendacao_MovieLens_2/Datasets/3.Datasets_Transformação/3.3_Datasets_Transformação_parte_3/genero_user_teste1.pickle", compression='gzip')

Tabela para modelagem: Algoritmo NearestNeighbors¶

Dados de Treino - (KNN)¶

# Selecionar as colunas de interesse
movie_knn_treino = movies_treino_transformado[['movieId', 'title', 'genres_separado']]
ratings_knn_treino = ratings_treino_transformado_modelagem[['userId', 'movieId', 'rating_times']]

# Unir as tabelas
movie_ratings_knn_treino = pd.merge(ratings_knn_treino , movie_knn_treino , how="left" , on="movieId" )

movie_ratings_knn_treino

	userId	movieId	rating_times	title	genres_separado
0	5	47	0.091853	Seven (a.k.a. Se7en) (1995)	Mystery
1	5	175	0.073483	Kids (1995)	Drama
2	5	257	0.073483	Just Cause (1995)	Mystery
3	5	318	0.073483	Shawshank Redemption, The (1994)	Crime
4	5	319	0.073483	Shallow Grave (1994)	Comedy
...	...	...	...	...	...
820503	330963	53953	0.029359	1408 (2007)	Drama
820504	330963	54190	0.176156	Across the Universe (2007)	Drama
820505	330963	55069	0.293593	4 Months, 3 Weeks and 2 Days (4 luni, 3 saptam...	Drama
820506	330963	55282	0.293593	30 Days of Night (2007)	Horror
820507	330963	58293	0.029359	10,000 BC (2008)	Adventure

820508 rows × 5 columns

Tabela : Filmes¶

knn_filmes_treino = movie_ratings_knn_treino.pivot_table(columns='title', index='userId', values="rating_times").fillna(0)
knn_filmes_treino

title	(2019)	"Great Performances" Cats (1998)	#Alive (2020)	#Female Pleasure (2018)	#Iamhere (2020)	#UNFIT: The Psychology of Donald Trump (2019)	$ (Dollars) (1971)	$5 a Day (2008)	$9.99 (2008)	$ellebrity (Sellebrity) (2012)	...	Üvegtigris (2001)	Τέλειοι Ξένοι (2016)	Χούλιγκανς: Κάτω τα χέρια απ' τα νιάτα! (1983)	Делай - раз! (1989)	Каменная башка (2008)	Карусель (1970)	Он вам не Димон (2017)	Пес Барбос и необычный кросс (1961)	Я худею (2018)	…And the Fifth Horseman Is Fear (1965)
userId
5	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	0.0	0.0	0.0	0.0	0.0	0.0
15	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	0.0	0.0	0.0	0.0	0.0	0.0
49	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	0.0	0.0	0.0	0.0	0.0	0.0
119	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	0.0	0.0	0.0	0.0	0.0	0.0
134	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	0.0	0.0	0.0	0.0	0.0	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
330651	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	0.0	0.0	0.0	0.0	0.0	0.0
330661	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	0.0	0.0	0.0	0.0	0.0	0.0
330811	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	0.0	0.0	0.0	0.0	0.0	0.0
330949	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	0.0	0.0	0.0	0.0	0.0	0.0
330963	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	0.0	0.0	0.0	0.0	0.0	0.0

7943 rows × 24326 columns

Dados de Teste - KNN¶

# Selecionar as colunas de interesse
movie_knn_teste = movies_teste_transformado[['movieId', 'title', 'genres_separado']]
ratings_knn_teste = ratings_teste_transformado_modelagem[['userId', 'movieId', 'rating_times']]

# Unir as tabelas
movie_ratings_knn_teste = pd.merge(ratings_knn_teste , movie_knn_teste , how="left" , on="movieId" )
movie_ratings_knn_teste

	userId	movieId	rating_times	title	genres_separado
0	128	168	0.026308	First Knight (1995)	Action
1	128	208	0.008769	Waterworld (1995)	Action
2	128	356	0.035077	Forrest Gump (1994)	Comedy
3	128	480	0.017539	Jurassic Park (1993)	Action
4	128	590	0.017539	Dances with Wolves (1990)	Adventure
...	...	...	...	...	...
207989	330948	115210	0.212142	Fury (2014)	Action
207990	330948	129779	0.318213	Ghost in the Shell Arise - Border 1: Ghost Pai...	Action
207991	330948	130634	0.106071	Furious 7 (2015)	Action
207992	330948	132584	0.106071	The Even Stevens Movie (2003)	Children
207993	330948	136459	0.318213	Jeff Dunham: Spark of Insanity (2007)	Comedy

207994 rows × 5 columns

Tabela: Filmes¶

knn_filmes_teste = movie_ratings_knn_teste.pivot_table(columns='title', index='userId', values="rating_times").fillna(0)
knn_filmes_teste

title	#Alive (2020)	$ (Dollars) (1971)	'71 (2014)	'83 (2021)	'Hellboy': The Seeds of Creation (2004)	'Round Midnight (1986)	'Salem's Lot (2004)	'Til There Was You (1997)	'burbs, The (1989)	'night Mother (1986)	...	tick, tick...BOOM! (2021)	xXx (2002)	xXx: Return of Xander Cage (2017)	xXx: State of the Union (2005)	¡Three Amigos! (1986)	¿Quién mató a Bambi? (2013)	À nous la liberté (Freedom for Us) (1931)	Ánimas (2018)	Épouse-moi mon pote (2017)	Ужас, который всегда с тобой (2007)
userId
128	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	0.0	0.0	0.0	0.0	0.0	0.0
172	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	0.0	0.0	0.0	0.0	0.0	0.0
465	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	0.0	0.0	0.0	0.0	0.0	0.0
598	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	0.0	0.0	0.0	0.0	0.0	0.0
919	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	0.0	0.0	0.0	0.0	0.0	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
330236	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	0.0	0.0	0.0	0.0	0.0	0.0
330321	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	0.0	0.0	0.0	0.0	0.0	0.0
330496	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	0.0	0.0	0.0	0.0	0.0	0.0
330667	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	0.0	0.0	0.0	0.0	0.0	0.0
330948	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	0.0	0.0	0.0	0.0	0.0	0.0

1986 rows × 15496 columns

Salvar tabelas para KNN¶

# Salvar tabelas 
knn_filmes_treino.to_pickle("C:/0.Projetos/5.Sistema_de_Recomendacao_MovieLens_2/Datasets/3.Datasets_Transformação/3.3_Datasets_Transformação_parte_3/knn_filmes_treino.pickle", compression='gzip')
knn_filmes_teste.to_pickle("C:/0.Projetos/5.Sistema_de_Recomendacao_MovieLens_2/Datasets/3.Datasets_Transformação/3.3_Datasets_Transformação_parte_3/knn_filmes_teste.pickle", compression='gzip')

Tabela para modelagem: Algoritmo FP-Growth¶

Recomendação por gênero¶

Função que cria os generos dummies¶

import pandas as pd
from mlxtend.frequent_patterns import fpgrowth
from mlxtend.preprocessing import TransactionEncoder

def genero_dummy(df):
    # 1. Explodir os gêneros separados por "|" em múltiplas linhas
    recomendacao_exploded = df.assign(genres=df['genres'].str.split('|')).explode('genres')

    # 2. Criar colunas dummies para cada gênero
    genres_dummies = pd.get_dummies(recomendacao_exploded['genres'])

    # Concatenar os dummies com o DataFrame original
    recomendacao_with_dummies = pd.concat([recomendacao_exploded[['userId', 'movieId']], genres_dummies], axis=1)

    # 3. Agregar as dummies de volta ao formato original
    recomendacao_dummies_aggregated = recomendacao_with_dummies.groupby(['userId', 'movieId']).max().reset_index()

    # 4. Remover a coluna movieId
    recomendacao_final = recomendacao_dummies_aggregated.drop(columns=['movieId'])

    # Garantir que os valores sejam binários (0 ou 1)
    for col in recomendacao_final.columns:
        if col not in ['userId']:  # userId não deve ser convertido
            recomendacao_final[col] = recomendacao_final[col].apply(lambda x: 1 if x > 0 else 0)

    return recomendacao_final

Dados de treino¶

# Dados de treino
recomendacao_genero_treino = movies_treino_transformado[['movieId', 'genres']].merge(ratings_treino_transformado_modelagem[['userId','movieId']], on='movieId', how='right')
recomendacao_genero_treino

recomendacao_genero_treino1 = genero_dummy(df=recomendacao_genero_treino)
recomendacao_genero_treino1

	userId	(no genres listed)	Action	Adventure	Animation	Children	Comedy	Crime	Documentary	Drama	...	Film-Noir	Horror	IMAX	Musical	Mystery	Romance	Sci-Fi	Thriller	War	Western
0	5	0	0	0	0	0	0	0	0	0	...	0	0	0	0	1	0	0	1	0	0
1	5	0	0	0	0	0	0	0	0	1	...	0	0	0	0	0	0	0	0	0	0
2	5	0	0	0	0	0	0	0	0	0	...	0	0	0	0	1	0	0	1	0	0
3	5	0	0	0	0	0	0	1	0	1	...	0	0	0	0	0	0	0	0	0	0
4	5	0	0	0	0	0	1	0	0	1	...	0	0	0	0	0	0	0	1	0	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
820503	330963	0	0	0	0	0	0	0	0	1	...	0	1	0	0	0	0	0	1	0	0
820504	330963	0	0	0	0	0	0	0	0	1	...	0	0	0	1	0	1	0	0	0	0
820505	330963	0	0	0	0	0	0	0	0	1	...	0	0	0	0	0	0	0	0	0	0
820506	330963	0	0	0	0	0	0	0	0	0	...	0	1	0	0	0	0	0	1	0	0
820507	330963	0	0	1	0	0	0	0	0	0	...	0	0	0	0	0	1	0	1	0	0

820508 rows × 21 columns

Dados de treino¶

# Dados de teste
recomendacao_genero_teste = movies_teste_transformado[['movieId', 'genres']].merge(ratings_teste_transformado_modelagem[['userId','movieId']], on='movieId', how='right')
recomendacao_genero_teste

	movieId	genres	userId
0	168	Action\|Drama\|Romance	128
1	168	Action\|Drama\|Romance	2311
2	168	Action\|Drama\|Romance	2647
3	168	Action\|Drama\|Romance	9051
4	168	Action\|Drama\|Romance	9595
...	...	...	...
207989	162566	(no genres listed)	330667
207990	6572	Comedy\|Crime	330948
207991	106542	Action\|Comedy\|Romance	330948
207992	132584	Children\|Comedy	330948
207993	136459	Comedy	330948

207994 rows × 3 columns

recomendacao_genero_teste1 = genero_dummy(df=recomendacao_genero_teste)
recomendacao_genero_teste1

	userId	(no genres listed)	Action	Adventure	Animation	Children	Comedy	Crime	Documentary	Drama	...	Film-Noir	Horror	IMAX	Musical	Mystery	Romance	Sci-Fi	Thriller	War	Western
0	128	0	1	0	0	0	0	0	0	1	...	0	0	0	0	0	1	0	0	0	0
1	128	0	1	1	0	0	0	0	0	0	...	0	0	0	0	0	0	1	0	0	0
2	128	0	0	0	0	0	1	0	0	1	...	0	0	0	0	0	1	0	0	1	0
3	128	0	1	1	0	0	0	0	0	0	...	0	0	0	0	0	0	1	1	0	0
4	128	0	0	1	0	0	0	0	0	1	...	0	0	0	0	0	0	0	0	0	1
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
207989	330948	0	1	0	0	0	0	0	0	1	...	0	0	0	0	0	0	0	0	1	0
207990	330948	0	1	0	1	0	0	0	0	0	...	0	0	0	0	0	0	1	0	0	0
207991	330948	0	1	0	0	0	0	1	0	0	...	0	0	0	0	0	0	0	1	0	0
207992	330948	0	0	0	0	1	1	0	0	0	...	0	0	0	0	0	0	0	0	0	0
207993	330948	0	0	0	0	0	1	0	0	0	...	0	0	0	0	0	0	0	0	0	0

207994 rows × 21 columns

Salvar tabelas para FP-Growth¶

# Salvar tabelas 
recomendacao_genero_treino1.to_pickle("C:/0.Projetos/5.Sistema_de_Recomendacao_MovieLens_2/Datasets/3.Datasets_Transformação/3.3_Datasets_Transformação_parte_3/recomendacao_genero_treino1.pickle", compression='gzip')
recomendacao_genero_teste1.to_pickle("C:/0.Projetos/5.Sistema_de_Recomendacao_MovieLens_2/Datasets/3.Datasets_Transformação/3.3_Datasets_Transformação_parte_3/recomendacao_genero_teste1.pickle", compression='gzip')

⚠ Arquivos para a modelagem¶

knn_filmes_treino

knn_filmes_teste

recomendacao_genero_treino1

recomendacao_genero_teste1

catalogo

Ver README do projeto

Sistema de Recomendação MovieLens

Transformação dos dados: Parte 3

Catarina Aguiar

Importar Bibliotecas¶

Definir Diretório¶

Carregar Arquivos¶

Tabelas de apoio¶

Tabela para modelagem: Algoritmo NearestNeighbors¶

Dados de Treino - (KNN)¶

Tabela : Filmes¶

Dados de Teste - KNN¶

Tabela: Filmes¶

Salvar tabelas para KNN¶

Tabela para modelagem: Algoritmo FP-Growth¶

Recomendação por gênero¶

Função que cria os generos dummies¶

Dados de treino¶

Dados de treino¶

Salvar tabelas para FP-Growth¶

⚠ Arquivos para a modelagem¶