def test_gridsearch_nd():
# Pass X as list in dcv.GridSearchCV
X_4d = np.arange(10 * 5 * 3 * 2).reshape(10, 5, 3, 2)
y_3d = np.arange(10 * 7 * 11).reshape(10, 7, 11)
clf = CheckingClassifier(check_X=lambda x: x.shape[1:] == (5, 3, 2),
check_y=lambda x: x.shape[1:] == (7, 11))
grid_search = dcv.GridSearchCV(clf, {'foo_param': [1, 2, 3]})
grid_search.fit(X_4d, y_3d).score(X, y)
assert hasattr(grid_search, "cv_results_")
def test_y_as_list():
# Pass y as list in dcv.GridSearchCV
X = np.arange(100).reshape(10, 10)
y = np.array([0] * 5 + [1] * 5)
clf = CheckingClassifier(check_y=lambda x: isinstance(x, list))
cv = KFold(n_splits=3)
grid_search = dcv.GridSearchCV(clf, {'foo_param': [1, 2, 3]}, cv=cv)
grid_search.fit(X, y.tolist()).score(X, y)
assert hasattr(grid_search, "cv_results_")
def test_hyperparameter_searcher_with_fit_params(cls, kwargs):
X = np.arange(100).reshape(10, 10)
y = np.array([0] * 5 + [1] * 5)
clf = CheckingClassifier(expected_fit_params=['spam', 'eggs'])
pipe = Pipeline([('clf', clf)])
searcher = cls(pipe, {'clf__foo_param': [1, 2, 3]}, cv=2, **kwargs)
# The CheckingClassifer generates an assertion error if
# a parameter is missing or has length != len(X).
with pytest.raises(AssertionError) as exc:
searcher.fit(X, y, clf__spam=np.ones(10))
assert "Expected fit parameter(s) ['eggs'] not seen." in str(exc.value)
searcher.fit(X, y, clf__spam=np.ones(10), clf__eggs=np.zeros(10))
# Test with dask objects as parameters
searcher.fit(X, y, clf__spam=da.ones(10, chunks=2),
clf__eggs=dask.delayed(np.zeros(10)))
def test_pandas_input():
# check cross_val_score doesn't destroy pandas dataframe
types = [(MockDataFrame, MockDataFrame)]
try:
from pandas import Series, DataFrame
types.append((DataFrame, Series))
except ImportError:
pass
X = np.arange(100).reshape(10, 10)
y = np.array([0] * 5 + [1] * 5)
for InputFeatureType, TargetType in types:
# X dataframe, y series
X_df, y_ser = InputFeatureType(X), TargetType(y)
clf = CheckingClassifier(check_X=lambda x: isinstance(x, InputFeatureType),
check_y=lambda x: isinstance(x, TargetType))
grid_search = dcv.GridSearchCV(clf, {'foo_param': [1, 2, 3]})
grid_search.fit(X_df, y_ser).score(X_df, y_ser)
grid_search.predict(X_df)
assert hasattr(grid_search, "cv_results_")