def test_only_1_categorical(self, net):
# Note: afm_nets needs embedding array, and at least 2 elements
# Note: opnn_nets,ipnn_nets,pnn_nets, needs at least 2 embedding to build `layers.InnerProduct`
# Note: dnn_nets,cross_dnn_nets,cross_nets,dcn_nets, does not using embedding
# Note: fibi_nets,fibi_dnn_nets needs at least 2 embedding because of `BilinearInteraction`
df = dsutils.load_movielens()
y = df['rating'].values.astype('float32')
X = df[['movie_id']]
conf = deeptable.ModelConfig(nets=[net],
task=consts.TASK_REGRESSION,
categorical_columns=["movie_id"],
metrics=['mse'],
fixed_embedding_dim=True,
embeddings_output_dim=4,
apply_gbm_features=False,
apply_class_weight=True,
earlystopping_patience=5)
dt = deeptable.DeepTable(config=conf)
model, history = dt.fit(X,
y,
validation_split=0.2,
epochs=10,
batch_size=32)
assert model
def test_var_len_encoder(self):
df = dd.from_pandas(dsutils.load_movielens(), npartitions=2)
config = deeptable.ModelConfig(nets=['dnn_nets'],
task=consts.TASK_REGRESSION,
categorical_columns=["movie_id", "user_id", "gender", "occupation", "zip",
"title", "age"],
metrics=['mse'],
fixed_embedding_dim=True,
embeddings_output_dim=4,
apply_gbm_features=False,
apply_class_weight=True,
earlystopping_patience=5,
var_len_categorical_columns=[('genres', "|", "max")])
self.run_dt(config, df=df, target='rating')
def setup_class(cls):
cls.df = dsutils.load_movielens().drop(['timestamp', "title"], axis=1)
def setup_class(cls):
cls.df_bank = dsutils.load_bank().sample(frac=0.01)
cls.df_movielens = dsutils.load_movielens()