def test_regression(
regression_data,
multi_target,
continuous_cols,
categorical_cols,
continuous_feature_transform,
normalize_continuous_features,
target_range,
deep_layers,
batch_norm_continuous_input,
attention_pooling,
):
(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")
if target_range:
_target_range = []
for target in data_config.target:
_target_range.append(
(
float(train[target].min()),
float(train[target].max()),
)
)
model_config_params["target_range"] = _target_range
model_config_params["deep_layers"] = deep_layers
model_config_params["batch_norm_continuous_input"] = batch_norm_continuous_input
model_config_params["attention_pooling"] = attention_pooling
model_config = AutoIntConfig(**model_config_params)
trainer_config = TrainerConfig(
max_epochs=3,
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)
result = tabular_model.evaluate(test)
# print(result[0]["valid_loss"])
assert "test_mean_squared_error" in result[0].keys()
pred_df = tabular_model.predict(test)
assert pred_df.shape[0] == test.shape[0]
def test_regression(
regression_data,
multi_target,
continuous_cols,
categorical_cols,
continuous_feature_transform,
normalize_continuous_features,
target_range,
):
(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",
input_embed_dim=8,
num_attn_blocks=1,
num_heads=2,
)
if target_range:
_target_range = []
for target in data_config.target:
_target_range.append((
float(train[target].min()),
float(train[target].max()),
))
model_config_params["target_range"] = _target_range
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)
result = tabular_model.evaluate(test)
assert "test_mean_squared_error" in result[0].keys()
pred_df = tabular_model.predict(test)
assert pred_df.shape[0] == test.shape[0]
def test_regression(
regression_data,
multi_target,
embed_categorical,
continuous_cols,
categorical_cols,
continuous_feature_transform,
normalize_continuous_features,
target_range,
):
(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,
num_trees=50,
embed_categorical=embed_categorical,
)
if target_range:
_target_range = []
for target in data_config.target:
_target_range.append((
train[target].min().item(),
train[target].max().item(),
))
model_config_params["target_range"] = _target_range
model_config = NodeConfig(**model_config_params)
trainer_config = TrainerConfig(max_epochs=1,
checkpoints=None,
early_stopping=None,
gpus=0,
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)
result = tabular_model.evaluate(test)
assert "valid_loss" in result[0].keys()
pred_df = tabular_model.predict(test)
assert pred_df.shape[0] == test.shape[0]
def test2(nrows=10000):
"""
python source/models/torch_tabular.py test
"""
global model, session
df,colcat, colnum, coly = test_dataset_covtype(1000)
target_name = coly
df.head()
train, test = train_test_split(df, random_state=42)
train, val = train_test_split(train, random_state=42)
num_classes = len(set(train[target_name].values.ravel()))
data_config = DataConfig(
target=target_name,
continuous_cols=colnum,
categorical_cols=colcat,
continuous_feature_transform=None,#"quantile_normal",
normalize_continuous_features=False
)
model_config = CategoryEmbeddingModelConfig(task="classification",
metrics=["f1","accuracy"],
metrics_params=[{"num_classes":num_classes},{}])
trainer_config = TrainerConfig(gpus=None, fast_dev_run=True)
experiment_config = ExperimentConfig(project_name="PyTorch Tabular Example",
run_name="node_forest_cov",
exp_watch="gradients",
log_target="wandb",
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,
)
tabular_model.fit( train=train, validation=val)
result = tabular_model.evaluate(val)
log(result)
test.drop(columns=target_name, inplace=True)
pred_df = tabular_model.predict(val.iloc[:100,:])
log(pred_df)
def test_save_load(
regression_data,
model_config_class,
continuous_cols,
categorical_cols,
custom_metrics,
custom_loss,
custom_optimizer,
tmpdir,
):
(train, test, target) = regression_data
data_config = DataConfig(
target=target,
continuous_cols=continuous_cols,
categorical_cols=categorical_cols,
)
model_config_class, model_config_params = model_config_class
model_config_params["task"] = "regression"
model_config = model_config_class(**model_config_params)
trainer_config = TrainerConfig(
max_epochs=3,
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,
metrics=custom_metrics,
loss=custom_loss,
optimizer=custom_optimizer,
optimizer_params={},
)
result_1 = tabular_model.evaluate(test)
# sv_dir = tmpdir/"save_model"
# sv_dir.mkdir(exist_ok=True, parents=True)
sv_dir = tmpdir.mkdir("saved_model")
tabular_model.save_model(str(sv_dir))
new_mdl = TabularModel.load_from_checkpoint(str(sv_dir))
result_2 = new_mdl.evaluate(test)
assert (result_1[0][f"test_{tabular_model.model.hparams.metrics[0]}"] ==
result_2[0][f"test_{new_mdl.model.hparams.metrics[0]}"])
def test_ssl(
classification_data,
continuous_cols,
categorical_cols,
continuous_feature_transform,
normalize_continuous_features,
ssl_task,
aug_task,
):
(train, test, target) = classification_data
if len(continuous_cols) + len(categorical_cols) == 0:
assert True
else:
data_config = DataConfig(
target=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="ssl",
input_embed_dim=8,
num_attn_blocks=1,
num_heads=2,
ssl_task=ssl_task,
aug_task=aug_task,
)
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)
result = tabular_model.evaluate(test)
assert "test_mean_squared_error" in result[0].keys()
def test_regression(
regression_data,
multi_target,
continuous_cols,
categorical_cols,
continuous_feature_transform,
normalize_continuous_features,
variant,
num_gaussian,
):
(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")
mdn_config = MixtureDensityHeadConfig(num_gaussian=num_gaussian)
model_config_params["mdn_config"] = mdn_config
model_config = variant(**model_config_params)
trainer_config = TrainerConfig(
max_epochs=3,
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)
result = tabular_model.evaluate(test)
# print(result[0]["valid_loss"])
assert "test_mean_squared_error" in result[0].keys()
pred_df = tabular_model.predict(test)
assert pred_df.shape[0] == test.shape[0]
def test_ssl(
regression_data,
continuous_cols,
categorical_cols,
continuous_feature_transform,
normalize_continuous_features,
deep_layers,
batch_norm_continuous_input,
attention_pooling,
ssl_task,
aug_task,
):
(train, test, target) = regression_data
if len(continuous_cols) + len(categorical_cols) == 0:
assert True
else:
data_config = DataConfig(
target=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="ssl", ssl_task=ssl_task, aug_task=aug_task)
model_config_params["deep_layers"] = deep_layers
model_config_params["batch_norm_continuous_input"] = batch_norm_continuous_input
model_config_params["attention_pooling"] = attention_pooling
model_config = AutoIntConfig(**model_config_params)
trainer_config = TrainerConfig(
max_epochs=3,
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)
result = tabular_model.evaluate(test)
assert "test_mean_squared_error" in result[0].keys()
def test_classification(
classification_data,
continuous_cols,
categorical_cols,
continuous_feature_transform,
normalize_continuous_features,
deep_layers,
batch_norm_continuous_input,
):
(train, test, target) = classification_data
if len(continuous_cols) + len(categorical_cols) == 0:
assert True
else:
data_config = DataConfig(
target=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="classification")
model_config_params["deep_layers"] = deep_layers
model_config_params["batch_norm_continuous_input"] = batch_norm_continuous_input
model_config = AutoIntConfig(**model_config_params)
trainer_config = TrainerConfig(
max_epochs=3,
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)
result = tabular_model.evaluate(test)
# print(result[0]["valid_loss"])
assert "test_accuracy" in result[0].keys()
pred_df = tabular_model.predict(test)
assert pred_df.shape[0] == test.shape[0]
def test_classification(
classification_data,
continuous_cols,
categorical_cols,
embed_categorical,
continuous_feature_transform,
normalize_continuous_features,
):
(train, test, target) = classification_data
if len(continuous_cols) + len(categorical_cols) == 0:
assert True
else:
data_config = DataConfig(
target=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="classification",
depth=2,
num_trees=50,
embed_categorical=embed_categorical,
)
model_config = NodeConfig(**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)
result = tabular_model.evaluate(test)
assert "test_accuracy" in result[0].keys()
pred_df = tabular_model.predict(test)
assert pred_df.shape[0] == test.shape[0]
def main():
# Generate Synthetic Data
data, cat_col_names, num_col_names = make_mixed_classification(
n_samples=10000, n_features=20, n_categories=4)
train, test = train_test_split(data, random_state=42)
train, val = train_test_split(train, random_state=42)
# ##########Define the Configs############
data_config = DataConfig(target=["target"],
continuous_cols=num_col_names,
categorical_cols=cat_col_names)
trainer_config = TrainerConfig(auto_lr_find=True,
batch_size=1024,
max_epochs=100,
gpus=1)
optimizer_config = OptimizerConfig()
model_config = CategoryEmbeddingModelConfig(task="classification",
layers="1024-512-512",
activation="LeakyReLU",
learning_rate=1e-3)
tabular_mode = TabularModel(data_config=data_config,
model_config=model_config,
optimizer_config=optimizer_config,
trainer_config=trainer_config)
# Training the Model
tabular_mode.fit(train=train, validation=val)
# Evaluating the Model
# #Loss and Metrics on New Data¶
result = tabular_mode.evaluate(test)
# #New Predictions as DataFrame
pred_df = tabular_mode.predict(test)
pred_df.head()
print_metrics(test['target'], pred_df["prediction"], tag="Holdout")
# saving model
tabular_mode.save_model("Analysis/basic")
def test_classification(
classification_data,
continuous_cols,
categorical_cols,
continuous_feature_transform,
normalize_continuous_features,
):
(train, test, target) = classification_data
if len(continuous_cols) + len(categorical_cols) == 0:
assert True
else:
data_config = DataConfig(
target=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="classification")
model_config = CategoryEmbeddingModelConfig(**model_config_params)
trainer_config = TrainerConfig(max_epochs=3,
checkpoints=None,
early_stopping=None,
gpus=0)
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)
# print(result[0]["valid_loss"])
assert "valid_loss" in result[0].keys()
pred_df = tabular_model.predict(test)
assert pred_df.shape[0] == test.shape[0]
def test_regression(
regression_data,
multi_target,
continuous_cols,
categorical_cols,
continuous_feature_transform,
normalize_continuous_features,
target_range,
target_transform,
custom_metrics,
custom_loss,
custom_optimizer,
):
(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")
if target_range:
_target_range = []
for target in data_config.target:
_target_range.append((
float(train[target].min()),
float(train[target].max()),
))
model_config_params["target_range"] = _target_range
model_config = CategoryEmbeddingModelConfig(**model_config_params)
trainer_config = TrainerConfig(
max_epochs=3,
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,
metrics=custom_metrics,
target_transform=target_transform,
loss=custom_loss,
optimizer=custom_optimizer,
optimizer_params={},
)
result = tabular_model.evaluate(test)
# print(result[0]["valid_loss"])
if custom_metrics is None:
assert "test_mean_squared_error" in result[0].keys()
else:
assert "test_fake_metric" in result[0].keys()
pred_df = tabular_model.predict(test)
assert pred_df.shape[0] == test.shape[0]
'target'
], #target should always be a list. Multi-targets are only supported for regression. Multi-Task Classification is not implemented
continuous_cols=num_col_names,
categorical_cols=cat_col_names,
)
trainer_config = TrainerConfig(
auto_lr_find=
True, # Runs the LRFinder to automatically derive a learning rate
batch_size=1024,
max_epochs=100,
gpus=1, #index of the GPU to use. 0, means CPU
)
optimizer_config = OptimizerConfig()
model_config = CategoryEmbeddingModelConfig(
task="classification",
layers="1024-512-512", # Number of nodes in each layer
activation="LeakyReLU", # Activation between each layers
learning_rate=1e-3)
tabular_model = TabularModel(
data_config=data_config,
model_config=model_config,
optimizer_config=optimizer_config,
trainer_config=trainer_config,
)
tabular_model.fit(train=train, validation=val)
result = tabular_model.evaluate(test)
pred_df = tabular_model.predict(test)
tabular_model.save_model("Analysis/basic")
loaded_model = TabularModel.load_from_checkpoint("Analysis/basic")
def test2(nrows=10000):
"""
python source/models/torch_tabular.py test
"""
global model, session
#X = np.random.rand(10000,20)
#y = np.random.binomial(n=1, p=0.5, size=[10000])
BASE_DIR = Path.home().joinpath('data/input/covtype/')
datafile = BASE_DIR.joinpath('covtype.data.gz')
datafile.parent.mkdir(parents=True, exist_ok=True)
url = "https://archive.ics.uci.edu/ml/machine-learning-databases/covtype/covtype.data.gz"
if not datafile.exists():
wget.download(url, datafile.as_posix())
target_name = ["Covertype"]
colcat = [
"Wilderness_Area1", "Wilderness_Area2", "Wilderness_Area3",
"Wilderness_Area4", "Soil_Type1", "Soil_Type2", "Soil_Type3",
"Soil_Type4", "Soil_Type5", "Soil_Type6", "Soil_Type7", "Soil_Type8",
"Soil_Type9", "Soil_Type10", "Soil_Type11", "Soil_Type12",
"Soil_Type13", "Soil_Type14", "Soil_Type15", "Soil_Type16",
"Soil_Type17", "Soil_Type18", "Soil_Type19", "Soil_Type20",
"Soil_Type21", "Soil_Type22", "Soil_Type23", "Soil_Type24",
"Soil_Type25", "Soil_Type26", "Soil_Type27", "Soil_Type28",
"Soil_Type29", "Soil_Type30", "Soil_Type31", "Soil_Type32",
"Soil_Type33", "Soil_Type34", "Soil_Type35", "Soil_Type36",
"Soil_Type37", "Soil_Type38", "Soil_Type39", "Soil_Type40"
]
colnum = [
"Elevation", "Aspect", "Slope", "Horizontal_Distance_To_Hydrology",
"Vertical_Distance_To_Hydrology", "Horizontal_Distance_To_Roadways",
"Hillshade_9am", "Hillshade_Noon", "Hillshade_3pm",
"Horizontal_Distance_To_Fire_Points"
]
feature_columns = (colnum + colcat + target_name)
df = pd.read_csv(datafile, header=None, names=feature_columns, nrows=nrows)
df.head()
train, test = train_test_split(df, random_state=42)
train, val = train_test_split(train, random_state=42)
num_classes = len(set(train[target_name].values.ravel()))
data_config = DataConfig(
target=target_name,
continuous_cols=colnum,
categorical_cols=colcat,
continuous_feature_transform=None, #"quantile_normal",
normalize_continuous_features=False)
model_config = CategoryEmbeddingModelConfig(task="classification",
metrics=["f1", "accuracy"],
metrics_params=[{
"num_classes":
num_classes
}, {}])
trainer_config = TrainerConfig(gpus=None, fast_dev_run=True)
experiment_config = ExperimentConfig(
project_name="PyTorch Tabular Example",
run_name="node_forest_cov",
exp_watch="gradients",
log_target="wandb",
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,
)
tabular_model.fit(train=train, validation=val)
result = tabular_model.evaluate(val)
log(result)
test.drop(columns=target_name, inplace=True)
pred_df = tabular_model.predict(val.iloc[:100, :])
log(pred_df)
def test_pretrained_backbone(
regression_data,
model_config_class,
continuous_cols,
categorical_cols,
custom_metrics,
custom_loss,
custom_optimizer,
tmpdir,
):
(train, test, target) = regression_data
data_config = DataConfig(
target=target,
continuous_cols=continuous_cols,
categorical_cols=categorical_cols,
)
model_config_class, model_config_params = model_config_class
model_config_params["task"] = "ssl"
model_config_params["ssl_task"] = "Denoising"
model_config_params["aug_task"] = "cutmix"
model_config = model_config_class(**model_config_params)
trainer_config = TrainerConfig(
max_epochs=3,
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,
metrics=custom_metrics,
loss=custom_loss,
optimizer=custom_optimizer,
optimizer_params={},
)
result_1 = tabular_model.evaluate(test)
with pytest.raises(AssertionError):
tabular_model.predict(test)
assert "test_mean_squared_error" in result_1[0].keys()
sv_dir = tmpdir.mkdir("saved_model")
tabular_model.save_model(str(sv_dir))
old_mdl = TabularModel.load_from_checkpoint(str(sv_dir))
model_config_params["task"] = "regression"
model_config_params["ssl_task"] = None
model_config_params["aug_task"] = None
model_config = model_config_class(**model_config_params)
trainer_config = TrainerConfig(
max_epochs=1,
checkpoints=None,
early_stopping=None,
gpus=None,
fast_dev_run=True,
)
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,
metrics=custom_metrics,
loss=custom_loss,
optimizer=custom_optimizer,
optimizer_params={},
trained_backbone=old_mdl.model.backbone,
)
result_2 = tabular_model.evaluate(test)
assert "test_mean_squared_error" in result_2[0].keys()
