def test_no_auto_cpu_params(ray_start_4_cpus, tmpdir):
train_dataset = ray.data.from_pandas(train_df)
valid_dataset = ray.data.from_pandas(test_df)
class DummyPreprocessor(Preprocessor):
def __init__(self):
super().__init__()
self.is_same = True
def fit(self, dataset):
self.fitted_ = True
def _transform_pandas(self, df: "pd.DataFrame") -> "pd.DataFrame":
return df
trainer = SklearnTrainer(
estimator=RandomForestClassifier(n_jobs=1),
scaling_config=scale_config,
label_column="target",
datasets={
TRAIN_DATASET_KEY: train_dataset,
"valid": valid_dataset
},
preprocessor=DummyPreprocessor(),
set_estimator_cpus=False,
)
result = trainer.fit()
model, _ = load_checkpoint(result.checkpoint)
assert model.n_jobs == 1
def from_checkpoint(cls, checkpoint: Checkpoint) -> "SklearnPredictor":
"""Instantiate the predictor from a Checkpoint.
The checkpoint is expected to be a result of ``SklearnTrainer``.
Args:
checkpoint: The checkpoint to load the model and
preprocessor from. It is expected to be from the result of a
``SklearnTrainer`` run.
"""
estimator, preprocessor = load_checkpoint(checkpoint)
return SklearnPredictor(estimator=estimator, preprocessor=preprocessor)
def test_preprocessor_in_checkpoint(ray_start_4_cpus, tmpdir):
train_dataset = ray.data.from_pandas(train_df)
valid_dataset = ray.data.from_pandas(test_df)
class DummyPreprocessor(Preprocessor):
def __init__(self):
super().__init__()
self.is_same = True
def fit(self, dataset):
self.fitted_ = True
def _transform_pandas(self, df: "pd.DataFrame") -> "pd.DataFrame":
return df
trainer = SklearnTrainer(
estimator=RandomForestClassifier(),
scaling_config=scale_config,
label_column="target",
datasets={
TRAIN_DATASET_KEY: train_dataset,
"valid": valid_dataset
},
preprocessor=DummyPreprocessor(),
)
result = trainer.fit()
# Move checkpoint to a different directory.
checkpoint_dict = result.checkpoint.to_dict()
checkpoint = Checkpoint.from_dict(checkpoint_dict)
checkpoint_path = checkpoint.to_directory(tmpdir)
resume_from = Checkpoint.from_directory(checkpoint_path)
model, preprocessor = load_checkpoint(resume_from)
assert hasattr(model, "feature_importances_")
assert preprocessor.is_same
assert preprocessor.fitted_