def test_embedding_transformer(regression_data):
(train, test, target) = regression_data
data_config = DataConfig(
target=target,
continuous_cols=[
"AveRooms",
"AveBedrms",
"Population",
"AveOccup",
"Latitude",
"Longitude",
],
categorical_cols=["HouseAgeBin"],
)
model_config_params = dict(
task="regression",
input_embed_dim=8,
num_attn_blocks=1,
num_heads=2,
)
model_config = TabTransformerConfig(**model_config_params)
trainer_config = TrainerConfig(
max_epochs=1,
checkpoints=None,
early_stopping=None,
gpus=None,
fast_dev_run=True,
)
optimizer_config = OptimizerConfig()
tabular_model = TabularModel(
data_config=data_config,
model_config=model_config,
optimizer_config=optimizer_config,
trainer_config=trainer_config,
)
tabular_model.fit(train=train, test=test)
transformer = CategoricalEmbeddingTransformer(tabular_model)
train_transform = transformer.fit_transform(train)
embed_cols = [
col for col in train_transform.columns
if "HouseAgeBin_embed_dim" in col
]
assert len(train["HouseAgeBin"].unique()) + 1 == len(
transformer._mapping["HouseAgeBin"].keys())
assert all([
val.shape[0] == len(embed_cols)
for val in transformer._mapping["HouseAgeBin"].values()
])
# )
tabular_model = TabularModel(
data_config=data_config,
model_config=model_config,
optimizer_config=optimizer_config,
trainer_config=trainer_config,
# experiment_config=experiment_config,
)
sampler = get_balanced_sampler(train[target_name].values.ravel())
# cust_loss = get_class_weighted_cross_entropy(train[target_name].values.ravel())
tabular_model.fit(
train=train,
validation=val,
# loss=cust_loss,
train_sampler=sampler)
from pytorch_tabular.categorical_encoders import CategoricalEmbeddingTransformer
transformer = CategoricalEmbeddingTransformer(tabular_model)
train_transform = transformer.fit_transform(train)
# test_transform = transformer.transform(test)
# ft = tabular_model.model.feature_importance()
# result = tabular_model.evaluate(test)
# print(result)
# test.drop(columns=ta6rget_name, inplace=True)
# pred_df = tabular_model.predict(test)
# print(pred_df.head())
# pred_df.to_csv("output/temp2.csv")
# tabular_model.save_model("test_save")
# new_model = TabularModel.load_from_checkpoint("test_save")
# result = new_model.evaluate(test)
# print(result)