def test_only_transform_train(random_xy_dataset_clf):
X, y = random_xy_dataset_clf
X_train, X_test, y_train, y_test = train_test_split(X, y)
random_adder = RandomAdder()
random_adder.fit(X_train, y_train)
assert np.all(random_adder.transform(X_train) != X_train)
assert np.all(random_adder.transform(X_test) == X_test)
from collections import defaultdict
import pytest
from sklearn.linear_model import LinearRegression
from sklearn.utils import estimator_checks
from sklego.dummy import RandomRegressor
from sklego.transformers import EstimatorTransformer, RandomAdder
from tests.conftest import id_func
@pytest.mark.parametrize("estimator", [
RandomAdder(),
EstimatorTransformer(LinearRegression()),
RandomRegressor(),
],
ids=id_func)
def test_check_estimator(estimator, monkeypatch):
"""Uses the sklearn `check_estimator` method to verify our custom estimators"""
# Not all estimators CAN adhere to the defined sklearn api. An example of this is the random adder as sklearn
# expects methods to be invariant to whether they are applied to the full dataset or a subset.
# These tests can be monkey patched out using the skips dictionary.
skips = defaultdict(
list,
{
RandomAdder: [
# Since we add noise, the method is not invariant on a subset
'check_methods_subset_invariance',
# The transformerselectormixin needs to compute a hash and it can't on a 'NotAnArray'
'check_transformer_data_not_an_array',
def test_dtype_regression(random_xy_dataset_regr):
X, y = random_xy_dataset_regr
assert RandomAdder().fit(X, y).transform(X).dtype == np.float
def test_dtype_classification(random_xy_dataset_clf):
X, y = random_xy_dataset_clf
assert RandomAdder().fit(X, y).transform(X).dtype == np.float