def test_KerasClassifier_loss_invariance(y, y_type):
"""Test that KerasClassifier can use both
categorical_crossentropy and sparse_categorical_crossentropy
with either one-hot encoded targets or sparse targets.
"""
X = np.arange(0, y.shape[0]).reshape(-1, 1)
clf_1 = KerasClassifier(
model=dynamic_classifier,
hidden_layer_sizes=(100,),
loss="categorical_crossentropy",
random_state=0,
)
clf_1.fit(X, y)
clf_1.partial_fit(X, y)
y_1 = clf_1.predict(X)
if y_type != "multilabel-indicator":
# sparse_categorical_crossentropy is not compatible with
# one-hot encoded targets, and one-hot encoded targets are not used in sklearn
# This is a use case that does not natively succeed in Keras or skelarn estimators
# and thus SciKeras does not intend to auto-convert data to support it
clf_2 = KerasClassifier(
model=dynamic_classifier,
hidden_layer_sizes=(100,),
loss="sparse_categorical_crossentropy",
random_state=0,
)
clf_2.fit(X, y)
y_2 = clf_1.predict(X)
np.testing.assert_equal(y_1, y_2)
def test_target_shape_changes_incremental_fit_clf():
X = np.array([[1, 2], [2, 3]])
y = np.array([1, 3]).reshape(-1, 1)
est = KerasClassifier(model=dynamic_classifier, hidden_layer_sizes=(100,))
est.fit(X, y)
with pytest.raises(ValueError, match="features"): # raised by transformers
est.partial_fit(X, np.column_stack([y, y]))
def test_X_dtype_changes_incremental_fit():
X = np.array([[1, 2], [2, 3]])
y = np.array([1, 3])
est = KerasClassifier(model=dynamic_classifier, hidden_layer_sizes=(100,))
est.fit(X, y)
est.partial_fit(X.astype(np.uint8), y)
with pytest.raises(
ValueError, match="Got `X` with dtype",
):
est.partial_fit(X.astype(np.float64), y)
def test_target_dims_changes_incremental_fit():
X = np.array([[1, 2], [2, 3]])
y = np.array([1, 3])
est = KerasClassifier(model=dynamic_classifier, hidden_layer_sizes=(100,))
est.fit(X, y)
y_new = y.reshape(-1, 1)
with pytest.raises(
ValueError, match="`y` has 2 dimensions, but this ",
):
est.partial_fit(X, y_new)
def test_target_classes_change_incremental_fit():
X = np.array([[1, 2], [2, 3]])
y = np.array([1, 3])
est = KerasClassifier(model=dynamic_classifier, hidden_layer_sizes=(100,))
est.fit(X, y)
est.partial_fit(X.astype(np.uint8), y)
with pytest.raises(
ValueError, match="Found unknown categories",
):
y[0] = 10
est.partial_fit(X, y)
def test_KerasClassifier_transformers_can_be_reused(y, y_type, loss):
"""Test that KerasClassifier can use both
categorical_crossentropy and sparse_categorical_crossentropy
with either one-hot encoded targets or sparse targets.
"""
if y_type == "multilabel-indicator" and loss == "sparse_categorical_crossentropy":
return # not compatible, see test_KerasClassifier_loss_invariance
X1, y1 = np.array([[1, 2, 3]]).T, np.array([1, 2, 3])
clf = KerasClassifier(
model=dynamic_classifier, hidden_layer_sizes=(100,), loss=loss, random_state=0,
)
clf.fit(X1, y1)
tfs = clf.target_encoder_
X2, y2 = X1, np.array([1, 1, 1]) # only 1 out or 3 classes
clf.partial_fit(X2, y2)
tfs_new = clf.target_encoder_
assert tfs_new is tfs # same transformer was re-used
assert set(clf.classes_) == set(y1)
def test_class_weight_param():
"""Backport of sklearn.utils.estimator_checks.check_class_weight_classifiers
for sklearn <= 0.23.0.
Tests that fit and partial_fit correctly handle the class_weight parameter.
"""
clf = KerasClassifier(
model=dynamic_classifier,
model__hidden_layer_sizes=(100, ),
random_state=0,
)
problems = (2, 3)
for n_centers in problems:
# create a very noisy dataset
X, y = make_blobs(centers=n_centers, random_state=0, cluster_std=20)
X_train, X_test, y_train, _ = train_test_split(X,
y,
test_size=0.5,
random_state=0)
n_centers = len(np.unique(y_train))
if n_centers == 2:
class_weight = {0: 1000, 1: 0.0001}
fit_epochs = 4
partial_fit_epochs = 3
else:
class_weight = {0: 1000, 1: 0.0001, 2: 0.0001}
fit_epochs = 8
partial_fit_epochs = 6
clf.set_params(class_weight=class_weight)
# run fit epochs followed by several partial_fit iterations
# these numbers are purely empirical, just like they are in the
# original sklearn test
clf.set_params(fit__epochs=fit_epochs)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
assert np.mean(y_pred == 0) > 0.8
for _ in range(partial_fit_epochs):
clf.partial_fit(X_train, y_train)
y_pred = clf.predict(X_test)
assert np.mean(y_pred == 0) > 0.95
def test_partial_fit_classes_param(self):
"""Test use of `partial_fit` with the `classes` parameter
and incomplete classes in the first pass.
"""
clf = KerasClassifier(
model=dynamic_classifier,
loss="sparse_categorical_crossentropy",
model__hidden_layer_sizes=[
100,
],
)
X1 = np.array([[1, 2, 3], [4, 5, 6]]).T
y1 = np.array([1, 2, 2])
X2 = X1
y2 = np.array([2, 3, 3])
classes = np.unique(np.concatenate([y1, y2]))
clf.partial_fit(X=X1, y=y1, classes=classes)
clf.score(X1, y1)
clf.score(X2, y2)
clf.partial_fit(X=X2, y=y2)
clf.score(X1, y1)
clf.score(X2, y2)
def test_partial_fit_epoch_kwargs(kwargs):
est = KerasClassifier(dynamic_classifier)
with pytest.raises(TypeError, match="Invalid argument"):
est.partial_fit([[1]], [1], **kwargs)
