def test_error_if_select_model_performance_and_y_is_none(df_single):
X, y = df_single
transformer = SmartCorrelatedSelection(
selection_method="model_performance",
estimator=RandomForestClassifier(n_estimators=10, random_state=1),
scoring="roc_auc",
)
with pytest.raises(ValueError):
transformer.fit(X)
def test_error_if_select_model_performance_and_y_is_none(df_single):
X, y = df_single
transformer = SmartCorrelatedSelection(
variables=None,
method="pearson",
threshold=0.8,
missing_values="raise",
selection_method="model_performance",
estimator=RandomForestClassifier(n_estimators=10, random_state=1),
scoring="roc_auc",
cv=3,
)
with pytest.raises(ValueError):
transformer.fit(X)
def test_KFold_generators(df_test):
X, y = df_test
# Kfold
sel = SmartCorrelatedSelection(
variables=None,
method="pearson",
threshold=0.8,
missing_values="raise",
selection_method="model_performance",
estimator=RandomForestClassifier(n_estimators=10, random_state=1),
scoring="roc_auc",
cv=KFold(n_splits=3),
)
sel.fit(X, y)
Xtransformed = sel.transform(X)
# test fit attrs
assert isinstance(sel.features_to_drop_, list)
assert all([x for x in sel.features_to_drop_ if x in X.columns])
assert len(sel.features_to_drop_) < X.shape[1]
assert not Xtransformed.empty
assert all(
[x for x in Xtransformed.columns if x not in sel.features_to_drop_])
# Stratfied
sel = SmartCorrelatedSelection(
variables=None,
method="pearson",
threshold=0.8,
missing_values="raise",
selection_method="model_performance",
estimator=RandomForestClassifier(n_estimators=10, random_state=1),
scoring="roc_auc",
cv=StratifiedKFold(n_splits=3),
)
sel.fit(X, y)
Xtransformed = sel.transform(X)
# test fit attrs
assert isinstance(sel.features_to_drop_, list)
assert all([x for x in sel.features_to_drop_ if x in X.columns])
assert len(sel.features_to_drop_) < X.shape[1]
assert not Xtransformed.empty
assert all(
[x for x in Xtransformed.columns if x not in sel.features_to_drop_])
# None
sel = SmartCorrelatedSelection(
variables=None,
method="pearson",
threshold=0.8,
missing_values="raise",
selection_method="model_performance",
estimator=RandomForestClassifier(n_estimators=10, random_state=1),
scoring="roc_auc",
cv=None,
)
sel.fit(X, y)
Xtransformed = sel.transform(X)
# test fit attrs
assert isinstance(sel.features_to_drop_, list)
assert all([x for x in sel.features_to_drop_ if x in X.columns])
assert len(sel.features_to_drop_) < X.shape[1]
assert not Xtransformed.empty
assert all(
[x for x in Xtransformed.columns if x not in sel.features_to_drop_])