def build_gmf(user_num, item_num):
input = Input(shape=[2])
user_emb = LatentFactorMapper(column_id=0,
num_of_entities=user_num,
embedding_dim=64)(input)
item_emb = LatentFactorMapper(column_id=1,
num_of_entities=item_num,
embedding_dim=64)(input)
output = InnerProductInteraction()([user_emb, item_emb])
output = RatingPredictionOptimizer()(output)
model = RPRecommender(inputs=input, outputs=output)
return model
def build_mlp(user_num, item_num):
input = Input(shape=[2])
user_emb_mlp = LatentFactorMapper(feat_column_id=0,
id_num=user_num,
embedding_dim=64)(input)
item_emb_mlp = LatentFactorMapper(feat_column_id=1,
id_num=user_num,
embedding_dim=64)(input)
output = MLPInteraction()([user_emb_mlp, item_emb_mlp])
output = RatingPredictionOptimizer()(output)
model = RPRecommender(inputs=input, outputs=output)
return model
def build_gmf(user_num, item_num):
input = Input(shape=[2])
user_emb = LatentFactorMapper(feat_column_id=0,
id_num=user_num,
embedding_dim=64)(input)
item_emb = LatentFactorMapper(feat_column_id=1,
id_num=item_num,
embedding_dim=64)(input)
output = ElementwiseInteraction(elementwise_type="innerporduct")(
[user_emb, item_emb])
output = RatingPredictionOptimizer()(output)
model = RPRecommender(inputs=input, outputs=output)
return model
def build_autorec(user_num, item_num):
input = Input(shape=[2])
user_emb_1 = LatentFactorMapper(column_id=0,
num_of_entities=user_num,
embedding_dim=64)(input)
item_emb_1 = LatentFactorMapper(column_id=1,
num_of_entities=item_num,
embedding_dim=64)(input)
user_emb_2 = LatentFactorMapper(column_id=0,
num_of_entities=user_num,
embedding_dim=64)(input)
item_emb_2 = LatentFactorMapper(column_id=1,
num_of_entities=item_num,
embedding_dim=64)(input)
output = HyperInteraction()(
[user_emb_1, item_emb_1, user_emb_2, item_emb_2])
output = RatingPredictionOptimizer()(output)
model = RPRecommender(inputs=input, outputs=output)
return model
def build_neumf(user_num, item_num):
input = Input(shape=[2])
user_emb_gmf = LatentFactorMapper(column_id=0,
num_of_entities=user_num,
embedding_dim=64)(input)
item_emb_gmf = LatentFactorMapper(column_id=1,
num_of_entities=item_num,
embedding_dim=64)(input)
innerproduct_output = InnerProductInteraction()(
[user_emb_gmf, item_emb_gmf])
user_emb_mlp = LatentFactorMapper(column_id=0,
num_of_entities=user_num,
embedding_dim=64)(input)
item_emb_mlp = LatentFactorMapper(column_id=1,
num_of_entities=item_num,
embedding_dim=64)(input)
mlp_output = MLPInteraction()([user_emb_mlp, item_emb_mlp])
output = RatingPredictionOptimizer()([innerproduct_output, mlp_output])
model = RPRecommender(inputs=input, outputs=output)
return model
# dataset_paths = ["./examples/datasets/netflix-prize-data/combined_data_" + str(i) + ".txt" for i in range(1, 5)]
# data = NetflixPrizePreprocessor(dataset_paths)
# Step 1: Preprocess data
movielens = MovielensPreprocessor()
train_X, train_y, val_X, val_y, test_X, test_y = movielens.preprocess()
train_X_categorical = movielens.get_x_categorical(train_X)
val_X_categorical = movielens.get_x_categorical(val_X)
test_X_categorical = movielens.get_x_categorical(test_X)
user_num, item_num = movielens.get_hash_size()
# Step 2: Build the recommender, which provides search space
# Step 2.1: Setup mappers to handle inputs
input = Input(shape=[2])
user_emb_gmf = LatentFactorMapper(column_id=0,
num_of_entities=user_num,
embedding_dim=64)(input)
item_emb_gmf = LatentFactorMapper(column_id=1,
num_of_entities=item_num,
embedding_dim=64)(input)
user_emb_mlp = LatentFactorMapper(column_id=0,
num_of_entities=user_num,
embedding_dim=64)(input)
item_emb_mlp = LatentFactorMapper(column_id=1,
num_of_entities=item_num,
embedding_dim=64)(input)
# Step 2.2: Setup interactors to handle models
innerproduct_output = InnerProductInteraction()([user_emb_gmf, item_emb_gmf])
mlp_output = MLPInteraction()([user_emb_mlp, item_emb_mlp])
level=logging.INFO,
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
logging.basicConfig(
level=logging.DEBUG,
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
logger = logging.getLogger(__name__)
# load dataset
ml_1m = MovielensCTRPreprocessor("./examples/datasets/ml-1m/ratings.dat")
ml_1m.preprocessing(test_size=0.1, random_state=1314, num_neg=10, mult=2)
train_X, train_y, val_X, val_y = ml_1m.train_X, ml_1m.train_y, ml_1m.val_X, ml_1m.val_y
# build the pipeline.
input = Input(shape=[2])
user_emb_gmf = LatentFactorMapper(feat_column_id=0,
id_num=10000,
embedding_dim=64)(input)
item_emb_gmf = LatentFactorMapper(feat_column_id=1,
id_num=10000,
embedding_dim=64)(input)
user_emb_mlp = LatentFactorMapper(feat_column_id=0,
id_num=10000,
embedding_dim=64)(input)
item_emb_mlp = LatentFactorMapper(feat_column_id=1,
id_num=10000,
embedding_dim=64)(input)
innerproduct_output = ElementwiseInteraction(elementwise_type="innerporduct")(
[user_emb_gmf, item_emb_gmf])
mlp_output = MLPInteraction()([user_emb_mlp, item_emb_mlp])
output = PointWiseOptimizer()([innerproduct_output, mlp_output])
test_X, test_y = data.test_X, data.test_y
user_num, item_num = data.user_num, data.item_num
logger.info('train_X size: {}'.format(train_X.shape))
logger.info('train_y size: {}'.format(train_y.shape))
logger.info('val_X size: {}'.format(val_X.shape))
logger.info('val_y size: {}'.format(val_y.shape))
logger.info('test_X size: {}'.format(test_X.shape))
logger.info('test_y size: {}'.format(test_y.shape))
logger.info('user total number: {}'.format(user_num))
logger.info('item total number: {}'.format(item_num))
# build the pipeline.
input = Input(shape=[2])
user_emb = LatentFactorMapper(feat_column_id=0,
id_num=user_num,
embedding_dim=64)(input)
item_emb = LatentFactorMapper(feat_column_id=1,
id_num=item_num,
embedding_dim=64)(input)
output1 = HyperInteraction()([user_emb, item_emb])
output2 = HyperInteraction()([output1, user_emb, item_emb])
output3 = HyperInteraction()([output1, output2, user_emb, item_emb])
output4 = HyperInteraction()([output1, output2, output3, user_emb, item_emb])
output = RatingPredictionOptimizer()(output4)
model = RPRecommender(inputs=input, outputs=output)
# AutoML search and predict.
searcher = Search(model=model,
tuner='random', ## hyperband, bayesian
tuner_params={'max_trials': 100, 'overwrite': True},)