def test_grid_search_sparse_scoring():
X_, y_ = make_classification(n_samples=200, n_features=100, random_state=0)
clf = LinearSVC()
cv = DaskGridSearchCV(clf, {'C': [0.1, 1.0]}, scoring="f1")
cv.fit(X_[:180], y_[:180])
y_pred = cv.predict(X_[180:])
C = cv.best_estimator_.C
X_ = sp.csr_matrix(X_)
clf = LinearSVC()
cv = DaskGridSearchCV(clf, {'C': [0.1, 1.0]}, scoring="f1")
cv.fit(X_[:180], y_[:180])
y_pred2 = cv.predict(X_[180:])
C2 = cv.best_estimator_.C
assert_array_equal(y_pred, y_pred2)
assert C == C2
# Smoke test the score
# np.testing.assert_allclose(f1_score(cv.predict(X_[:180]), y[:180]),
# cv.score(X_[:180], y[:180]))
# test loss where greater is worse
def f1_loss(y_true_, y_pred_):
return -f1_score(y_true_, y_pred_)
F1Loss = make_scorer(f1_loss, greater_is_better=False)
cv = DaskGridSearchCV(clf, {'C': [0.1, 1.0]}, scoring=F1Loss)
cv.fit(X_[:180], y_[:180])
y_pred3 = cv.predict(X_[180:])
C3 = cv.best_estimator_.C
assert C == C3
assert_array_equal(y_pred, y_pred3)
def test_grid_search_precomputed_kernel():
# Test that grid search works when the input features are given in the
# form of a precomputed kernel matrix
X_, y_ = make_classification(n_samples=200, n_features=100, random_state=0)
# compute the training kernel matrix corresponding to the linear kernel
K_train = np.dot(X_[:180], X_[:180].T)
y_train = y_[:180]
clf = SVC(kernel='precomputed')
cv = DaskGridSearchCV(clf, {'C': [0.1, 1.0]})
cv.fit(K_train, y_train)
assert cv.best_score_ >= 0
# compute the test kernel matrix
K_test = np.dot(X_[180:], X_[:180].T)
y_test = y_[180:]
y_pred = cv.predict(K_test)
assert np.mean(y_pred == y_test) >= 0
# test error is raised when the precomputed kernel is not array-like
# or sparse
with pytest.raises(ValueError):
cv.fit(K_train.tolist(), y_train)
def test_grid_search_sparse():
# Test that grid search works with both dense and sparse matrices
X_, y_ = make_classification(n_samples=200, n_features=100, random_state=0)
clf = LinearSVC()
cv = DaskGridSearchCV(clf, {'C': [0.1, 1.0]})
cv.fit(X_[:180], y_[:180])
y_pred = cv.predict(X_[180:])
C = cv.best_estimator_.C
X_ = sp.csr_matrix(X_)
clf = LinearSVC()
cv = DaskGridSearchCV(clf, {'C': [0.1, 1.0]})
cv.fit(X_[:180].tocoo(), y_[:180])
y_pred2 = cv.predict(X_[180:])
C2 = cv.best_estimator_.C
assert np.mean(y_pred == y_pred2) >= .9
assert C == C2
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 = DaskGridSearchCV(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_")
def test_pickle():
# Test that a fit search can be pickled
clf = MockClassifier()
grid_search = DaskGridSearchCV(clf, {'foo_param': [1, 2, 3]}, refit=True)
grid_search.fit(X, y)
grid_search_pickled = pickle.loads(pickle.dumps(grid_search))
assert_array_almost_equal(grid_search.predict(X),
grid_search_pickled.predict(X))
random_search = DaskRandomizedSearchCV(clf, {'foo_param': [1, 2, 3]},
refit=True, n_iter=3)
random_search.fit(X, y)
random_search_pickled = pickle.loads(pickle.dumps(random_search))
assert_array_almost_equal(random_search.predict(X),
random_search_pickled.predict(X))