def apply_test_data():
data, test_data, cat_col_names, num_col_names = data_load()
bsize = 2500 * 3 * 2 * 2
data_config = DataConfig(target=["target"],
continuous_cols=num_col_names,
categorical_cols=cat_col_names,
num_workers=4)
trainer_config = TrainerConfig(auto_lr_find=True,
batch_size=bsize,
max_epochs=100,
gpus=1)
optimizer_config = OptimizerConfig()
model_config = TabNetModelConfig(task="classification",
learning_rate=1e-3 * bsize / 1024,
n_d=24,
n_a=24,
n_steps=5,
gamma=1.3)
tabular_mode = TabularModel(data_config=data_config,
optimizer_config=optimizer_config,
model_config=model_config,
trainer_config=trainer_config)
for i in range(10):
diri = f"Analysis/basic_tabnet_rep{i}"
tabular_mode.load_from_checkpoint(dir=diri)
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")
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 = TabNetModelConfig(**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_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 = {
"task": "ssl",
"ssl_task": ssl_task,
"aug_task": aug_task,
}
model_config = TabNetModelConfig(**model_config_params)
trainer_config = TrainerConfig(
max_epochs=3,
checkpoints=None,
early_stopping=None,
gpus=None,
fast_dev_run=True,
)
optimizer_config = OptimizerConfig()
with pytest.raises(AssertionError):
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)
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 = TabNetModelConfig(**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_64():
# Generate Synthetic Data
global train
data, test_data, cat_col_names, num_col_names = data_load()
bsize = 2500*3*2*2
# ##########Define the Configs############
data_config = DataConfig(
target=["target"],
continuous_cols=num_col_names,
categorical_cols=cat_col_names,
num_workers=4
)
trainer_config = TrainerConfig(
auto_lr_find=True,
batch_size=bsize,
max_epochs=100,
gpus=1
)
optimizer_config = OptimizerConfig()
model_config = TabNetModelConfig(
task="classification",
learning_rate=1e-3*bsize/1024,
n_d=64,
n_a=64,
n_steps=5,
gamma=1.3
)
# Training the Model
# tabular_mode.fit(train=train, validation=val)
# # Evaluating the Model
# # #Loss and Metrics on New Data¶
# result = tabular_mode.evaluate(test)
cv = StratifiedKFold(n_splits=10, shuffle=True)
res_pred = []
res_test = []
for i, (train_idx, test_idx) in enumerate(cv.split(X=data, y=data.target.values)):
train, test = data.iloc[train_idx], data.iloc[test_idx]
train, val = train_test_split(train, random_state=42)
tabular_mode = TabularModel(
data_config=data_config,
optimizer_config=optimizer_config,
model_config=model_config,
trainer_config=trainer_config
)
weighted_loss = get_class_weighted_cross_entropy(train["target"].values.ravel(), mu=0.1)
# Training the Model
tabular_mode.fit(train=train, validation=val, max_epochs=100, loss=weighted_loss)
pred_df = tabular_mode.predict(test).loc[:, ["prediction"]]
res_pred.append(pred_df)
tabular_mode.save_model(f"Analysis/basic_tabnet_rep{i}")
pred = tabular_mode.predict(test_data)
res_test.append(pred)
# #New Predictions as DataFrame
pred_tot = pd.concat(res_pred).sort_index()
print_metrics(data['target'], pred_tot["prediction"], tag="Holdout")
pred_df = pd.concat([res_testi.loc[:, ["0_probability"]] for res_testi in res_test], axis=1).apply(np.mean, axis=1)
pred_df2 = pred_df.map(lambda x: 1 if x>0.5 else 0)
sample_submisson = pd.read_csv("Data/sample_submission.csv")
sample_submisson["target"] = pred_df2.values
sample_submisson.to_csv("Analysis/submission_2.csv", index=False)
print(confusion_matrix(data['target'], pred_tot["prediction"]))