def test_regression(
regression_data,
multi_target,
embed_categorical,
continuous_cols,
categorical_cols,
continuous_feature_transform,
normalize_continuous_features,
):
(train, test, target) = regression_data
if len(continuous_cols) + len(categorical_cols) == 0:
assert True
else:
data_config = DataConfig(
target=target + ["MedInc"] if multi_target else target,
continuous_cols=continuous_cols,
categorical_cols=categorical_cols,
continuous_feature_transform=continuous_feature_transform,
normalize_continuous_features=normalize_continuous_features,
)
model_config_params = dict(task="regression",
depth=2,
embed_categorical=embed_categorical)
model_config = NodeConfig(**model_config_params)
# model_config_params = dict(task="regression")
# model_config = NodeConfig(**model_config_params)
trainer_config = TrainerConfig(max_epochs=1,
checkpoints=None,
early_stopping=None)
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)
result = tabular_model.evaluate(test)
if multi_target:
assert result[0]["valid_loss"] < 30
else:
assert result[0]["valid_loss"] < 8
pred_df = tabular_model.predict(test)
assert pred_df.shape[0] == test.shape[0]
from sklearn.preprocessing import PowerTransformer
tr = PowerTransformer()
tabular_model = TabularModel(
data_config=data_config,
model_config=model_config,
optimizer_config=optimizer_config,
trainer_config=trainer_config,
# experiment_config=experiment_config,
)
tabular_model.fit(
train=train,
test=test,
metrics=[fake_metric],
target_transform=tr,
loss=torch.nn.L1Loss(),
optimizer=torch.optim.Adagrad,
optimizer_params={},
)
from pytorch_tabular.feature_extractor import DeepFeatureExtractor
# dt = DeepFeatureExtractor(tabular_model)
# enc_df = dt.fit_transform(test)
# print(enc_df.head())
# tabular_model.save_model("examples/sample")
result = tabular_model.evaluate(test)
print(result)
# # # print(result[0]['train_loss'])
# new_mdl = TabularModel.load_from_checkpoint("examples/sample")
run_name="node_forest_cov",
exp_watch="gradients",
log_target="wandb",
log_logits=True)
optimizer_config = OptimizerConfig()
# tabular_model = TabularModel(
# data_config="examples/data_config.yml",
# model_config="examples/model_config.yml",
# optimizer_config="examples/optimizer_config.yml",
# trainer_config="examples/trainer_config.yml",
# # experiment_config=experiment_config,
# )
tabular_model = TabularModel(
data_config=data_config,
model_config=model_config,
optimizer_config=optimizer_config,
trainer_config=trainer_config,
# experiment_config=experiment_config,
)
tabular_model.fit(
train=train, validation=val)
result = tabular_model.evaluate(test)
print(result)
test.drop(columns=target_name, inplace=True)
pred_df = tabular_model.predict(test)
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)
True, #If True, will use a learned embedding, else it will use LeaveOneOutEncoding for categorical columns
learning_rate=0.02,
additional_tree_output_dim=25,
)
# model_config.validate()
# model_config = NodeConfig(task="regression", depth=2, embed_categorical=False)
# trainer_config = TrainerConfig(checkpoints=None, max_epochs=5, gpus=1, profiler=None)
# experiment_config = ExperimentConfig(
# project_name="DeepGMM_test",
# run_name="wand_debug",
# log_target="wandb",
# exp_watch="gradients",
# log_logits=True
# )
# optimizer_config = OptimizerConfig()
tabular_model = TabularModel(
data_config=data_config,
model_config=model_config,
optimizer_config=optimizer_config,
trainer_config=trainer_config,
# experiment_config=experiment_config,
model_callable=MultiStageModel)
tabular_model.fit(train=train, test=test)
result = tabular_model.evaluate(test)
# print(result)
# # print(result[0]['train_loss'])
pred_df = tabular_model.predict(test, quantiles=[0.25])
print(pred_df.head())
# pred_df.to_csv("output/temp2.csv")
# optimizer_config="examples/optimizer_config.yml",
# trainer_config="examples/trainer_config.yml",
# # experiment_config=experiment_config,
# )
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")