def test_can_score_estimator_with_no_y_value(self):
class DummyEstimator(BaseEstimator, RegressorMixin):
def __init__(self):
self.average = None
def fit(self, x, y=None):
self.average = np.mean(x, axis=0)
return self
def predict(self, x):
return self.average
class DummyData(Dataset):
def load_training_data(self):
return pd.DataFrame({
"col1": [1, 2, 3, 4],
"col2": [4, 5, 6, 7]
}), None
def load_prediction_data(self, *args, **kwargs):
return pd.DataFrame({
"col1": [1, 2, 3, 4],
"col2": [4, 5, 6, 7]
})
model = Model(DummyEstimator())
data = DummyData()
model.train_estimator(data)
assert np.all(np.isclose(model.estimator.average, np.array([2.5,
5.5])))
with pytest.raises(DatasetError,
match="The dataset does not define a y value"):
data.create_train_test()
def test_train_model_followed_by_score_model_returns_correctly(
self, pipeline_logistic: Pipeline, train_iris_dataset):
model = Model(pipeline_logistic)
model.train_estimator(train_iris_dataset)
model.score_estimator(train_iris_dataset)
assert isinstance(model.result, Result)
def test_make_prediction_errors_if_asked_for_proba_without_predict_proba_method(
self, train_iris_dataset: Dataset):
with pytest.raises(
MLToolingError,
match="LinearRegression does not have a `predict_proba`"):
model = Model(LinearRegression())
model.train_estimator(train_iris_dataset)
model.make_prediction(train_iris_dataset, 5, proba=True)
def test_save_model_saves_pipeline_correctly(self,
pipeline_logistic: Pipeline,
tmp_path: pathlib.Path,
train_iris_dataset):
model = Model(pipeline_logistic)
model.train_estimator(train_iris_dataset)
saved_model_path = model.save_estimator(FileStorage(tmp_path))
assert saved_model_path.exists()
def test_train_model_errors_correctly_when_not_scored(
self, pipeline_logistic: Pipeline, tmp_path: pathlib.Path,
train_iris_dataset):
model = Model(pipeline_logistic)
with pytest.raises(MLToolingError,
match="You haven't scored the estimator"):
with model.log(str(tmp_path)):
model.train_estimator(train_iris_dataset)
model.save_estimator(FileStorage(tmp_path))
def test_load_prediction_data_works_as_expected(self):
dataset = load_demo_dataset("iris")
dataset.create_train_test(stratify=True)
feature_pipeline = Pipeline([("scale", DFStandardScaler())])
model = Model(LogisticRegression(), feature_pipeline=feature_pipeline)
model.train_estimator(dataset)
result = model.make_prediction(dataset, 5)
expected = pd.DataFrame({"Prediction": [0]})
pd.testing.assert_frame_equal(result, expected, check_dtype=False)
def test_make_prediction_with_regression_sqldataset_works_as_expected(
self, boston_sqldataset, loaded_boston_db):
dataset = boston_sqldataset(loaded_boston_db, schema=None)
dataset.create_train_test(stratify=False)
model = Model(LinearRegression())
model.train_estimator(dataset)
result = model.make_prediction(dataset, 0)
assert result.shape == (1, 1)
assert result.columns.tolist() == ["Prediction"]
def test_make_prediction_with_classification_sqldataset_works_as_expected(
self, iris_sqldataset, loaded_iris_db):
dataset = iris_sqldataset(loaded_iris_db, schema=None)
dataset.create_train_test()
model = Model(LogisticRegression(solver="lbfgs"))
model.train_estimator(dataset)
result = model.make_prediction(dataset, 0, proba=True)
assert result.shape == (1, 2)
assert result.columns.tolist() == [
"Probability Class 0", "Probability Class 1"
]
def test_train_model_sets_result_to_none(self, regression: Model,
train_iris_dataset):
assert regression.result is not None
regression.train_estimator(train_iris_dataset)
assert regression.result is None
