def run(dataset: Dataset, config: TaskConfig):
from frameworks.shared.caller import run_in_venv
X_train, X_test = impute_array(
*unsparsify(dataset.train.X_enc, dataset.test.X_enc, fmt='array'))
y_train, y_test = unsparsify(dataset.train.y_enc,
dataset.test.y_enc,
fmt='array')
data = dict(train=dict(X=X_train, y=y_train),
test=dict(X=X_test, y=y_test))
def process_results(results):
if results.probabilities is not None and not results.probabilities.shape: # numpy load always return an array
prob_format = results.probabilities.item()
if prob_format == "predictions":
target_values_enc = dataset.target.label_encoder.transform(
dataset.target.values)
results.probabilities = Encoder(
'one-hot', target=False,
encoded_type=float).fit(target_values_enc).transform(
results.predictions)
else:
raise ValueError(
f"Unknown probabilities format: {prob_format}")
return results
return run_in_venv(__file__,
"exec.py",
input_data=data,
dataset=dataset,
config=config,
process_results=process_results)
def run(dataset: Dataset, config: TaskConfig):
log.info(f"\n**** Decision Tree [sklearn v{sklearn.__version__}] ****\n")
is_classification = config.type == 'classification'
X_train, X_test = impute_array(*unsparsify(dataset.train.X_enc, dataset.test.X_enc, fmt='array'))
y_train, y_test = unsparsify(dataset.train.y_enc, dataset.test.y_enc, fmt='array')
estimator = DecisionTreeClassifier if is_classification else DecisionTreeRegressor
predictor = estimator(random_state=config.seed, **config.framework_params)
with Timer() as training:
predictor.fit(X_train, y_train)
with Timer() as predict:
predictions = predictor.predict(X_test)
probabilities = predictor.predict_proba(X_test) if is_classification else None
save_predictions(dataset=dataset,
output_file=config.output_predictions_file,
probabilities=probabilities,
predictions=predictions,
truth=y_test,
target_is_encoded=is_classification)
return dict(
models_count=1,
training_duration=training.duration,
predict_duration=predict.duration
)
def run(dataset: Dataset, config: TaskConfig):
log.info("\n**** Constant predictor (sklearn dummy) ****\n")
is_classification = config.type == 'classification'
predictor = DummyClassifier(
strategy='prior') if is_classification else DummyRegressor(
strategy='median')
encode = config.framework_params.get('_encode', False)
X_train = unsparsify(dataset.train.X_enc if encode else dataset.train.X,
fmt='array')
y_train = unsparsify(dataset.train.y_enc if encode else dataset.train.y,
fmt='array')
X_test = unsparsify(dataset.test.X_enc if encode else dataset.test.X,
fmt='array')
y_test = unsparsify(dataset.test.y_enc if encode else dataset.test.y,
fmt='array')
with Timer() as training:
predictor.fit(X_train, y_train)
with Timer() as predict:
predictions = predictor.predict(X_test)
probabilities = predictor.predict_proba(
X_test) if is_classification else None
save_predictions(dataset=dataset,
output_file=config.output_predictions_file,
probabilities=probabilities,
predictions=predictions,
truth=y_test,
target_is_encoded=encode)
return dict(models_count=1,
training_duration=training.duration,
predict_duration=predict.duration)
def run(dataset: Dataset, config: TaskConfig):
from frameworks.shared.caller import run_in_venv
X_train, X_test = dataset.train.X_enc, dataset.test.X_enc
y_train, y_test = unsparsify(dataset.train.y_enc, dataset.test.y_enc)
data = dict(train=dict(X=X_train, y=y_train),
test=dict(X=X_test, y=y_test),
predictors_type=[
'Numerical' if p.is_numerical() else 'Categorical'
for p in dataset.predictors
])
return run_in_venv(__file__,
"exec.py",
input_data=data,
dataset=dataset,
config=config)