def test_linearsvm_liblinear_sample_weight(SVM, params):
X = np.array(
[[1, 3], [1, 3], [1, 3], [1, 3], [2, 1], [2, 1], [2, 1], [2, 1],
[3, 3], [3, 3], [3, 3], [3, 3], [4, 1], [4, 1], [4, 1], [4, 1]],
dtype=np.dtype('float'))
y = np.array([1, 1, 1, 1, 2, 2, 2, 2, 1, 1, 1, 1, 2, 2, 2, 2],
dtype=np.dtype('int'))
X2 = np.vstack([X, X])
y2 = np.hstack([y, 3 - y])
sample_weight = np.ones(shape=len(y) * 2)
sample_weight[len(y):] = 0
X2, y2, sample_weight = shuffle(X2, y2, sample_weight, random_state=0)
base_estimator = SVM(random_state=42)
base_estimator.set_params(**params)
base_estimator.set_params(tol=1e-12, max_iter=1000)
est_no_weight = base.clone(base_estimator).fit(X, y)
est_with_weight = base.clone(base_estimator).fit(
X2, y2, sample_weight=sample_weight)
for method in ("predict", "decision_function"):
if hasattr(base_estimator, method):
X_est_no_weight = getattr(est_no_weight, method)(X)
X_est_with_weight = getattr(est_with_weight, method)(X)
assert_allclose(X_est_no_weight, X_est_with_weight)
def test_kernel_clone_after_set_params(kernel):
# This test is to verify that using set_params does not
# break clone on kernels.
# This used to break because in kernels such as the RBF, non-trivial
# logic that modified the length scale used to be in the constructor
# See https://github.com/scikit-learn/scikit-learn/issues/6961
# for more details.
bounds = (1e-5, 1e5)
kernel_cloned = clone(kernel)
params = kernel.get_params()
# RationalQuadratic kernel is isotropic.
isotropic_kernels = (ExpSineSquared, RationalQuadratic)
if 'length_scale' in params and not isinstance(kernel, isotropic_kernels):
length_scale = params['length_scale']
if np.iterable(length_scale):
params['length_scale'] = length_scale[0]
params['length_scale_bounds'] = bounds
else:
params['length_scale'] = [length_scale] * 2
params['length_scale_bounds'] = bounds * 2
kernel_cloned.set_params(**params)
kernel_cloned_clone = clone(kernel_cloned)
assert (kernel_cloned_clone.get_params() == kernel_cloned.get_params())
assert id(kernel_cloned_clone) != id(kernel_cloned)
check_hyperparameters_equal(kernel_cloned, kernel_cloned_clone)
def test_clone_empty_array():
# Regression test for cloning estimators with empty arrays
clf = MyEstimator(empty=np.array([]))
clf2 = clone(clf)
assert_array_equal(clf.empty, clf2.empty)
clf = MyEstimator(empty=sp.csr_matrix(np.array([[0]])))
clf2 = clone(clf)
assert_array_equal(clf.empty.data, clf2.empty.data)
def test_stacking_randomness(estimator, X, y):
# checking that fixing the random state of the CV will lead to the same
# results
estimator_full = clone(estimator)
estimator_full.set_params(
cv=KFold(shuffle=True, random_state=np.random.RandomState(0)))
estimator_drop = clone(estimator)
estimator_drop.set_params(lr='drop')
estimator_drop.set_params(
cv=KFold(shuffle=True, random_state=np.random.RandomState(0)))
assert_allclose(
estimator_full.fit(X, y).transform(X)[:, 1:],
estimator_drop.fit(X, y).transform(X))
def test_transform_target_regressor_2d_transformer(X, y):
# Check consistency with transformer accepting only 2D array and a 1D/2D y
# array.
transformer = StandardScaler()
regr = TransformedTargetRegressor(regressor=LinearRegression(),
transformer=transformer)
y_pred = regr.fit(X, y).predict(X)
assert y.shape == y_pred.shape
# consistency forward transform
if y.ndim == 1: # create a 2D array and squeeze results
y_tran = regr.transformer_.transform(y.reshape(-1, 1)).squeeze()
else:
y_tran = regr.transformer_.transform(y)
_check_standard_scaled(y, y_tran)
assert y.shape == y_pred.shape
# consistency inverse transform
assert_allclose(y, regr.transformer_.inverse_transform(y_tran).squeeze())
# consistency of the regressor
lr = LinearRegression()
transformer2 = clone(transformer)
if y.ndim == 1: # create a 2D array and squeeze results
lr.fit(X, transformer2.fit_transform(y.reshape(-1, 1)).squeeze())
else:
lr.fit(X, transformer2.fit_transform(y))
y_lr_pred = lr.predict(X)
assert_allclose(y_pred, transformer2.inverse_transform(y_lr_pred))
assert_allclose(regr.regressor_.coef_, lr.coef_)
def test_classifier_results():
"""tests if classifier results match target"""
alpha = .1
n_features = 20
n_samples = 10
tol = .01
max_iter = 200
rng = np.random.RandomState(0)
X = rng.normal(size=(n_samples, n_features))
w = rng.normal(size=n_features)
y = np.dot(X, w)
y = np.sign(y)
clf1 = LogisticRegression(solver='sag',
C=1. / alpha / n_samples,
max_iter=max_iter,
tol=tol,
random_state=77)
clf2 = clone(clf1)
clf1.fit(X, y)
clf2.fit(sp.csr_matrix(X), y)
pred1 = clf1.predict(X)
pred2 = clf2.predict(X)
assert_almost_equal(pred1, y, decimal=12)
assert_almost_equal(pred2, y, decimal=12)
def test_clone_pandas_dataframe():
class DummyEstimator(TransformerMixin, BaseEstimator):
"""This is a dummy class for generating numerical features
This feature extractor extracts numerical features from pandas data
frame.
Parameters
----------
df: pandas data frame
The pandas data frame parameter.
Notes
-----
"""
def __init__(self, df=None, scalar_param=1):
self.df = df
self.scalar_param = scalar_param
def fit(self, X, y=None):
pass
def transform(self, X):
pass
# build and clone estimator
d = np.arange(10)
df = MockDataFrame(d)
e = DummyEstimator(df, scalar_param=1)
cloned_e = clone(e)
# the test
assert (e.df == cloned_e.df).values.all()
assert e.scalar_param == cloned_e.scalar_param
def test_clone():
# Tests that clone creates a correct deep copy.
# We create an estimator, make a copy of its original state
# (which, in this case, is the current state of the estimator),
# and check that the obtained copy is a correct deep copy.
from sklearn_lib.feature_selection import SelectFpr, f_classif
selector = SelectFpr(f_classif, alpha=0.1)
new_selector = clone(selector)
assert selector is not new_selector
assert selector.get_params() == new_selector.get_params()
selector = SelectFpr(f_classif, alpha=np.zeros((10, 2)))
new_selector = clone(selector)
assert selector is not new_selector
def test_svc_clone_with_callable_kernel():
# create SVM with callable linear kernel, check that results are the same
# as with built-in linear kernel
svm_callable = svm.SVC(kernel=lambda x, y: np.dot(x, y.T),
probability=True,
random_state=0,
decision_function_shape='ovr')
# clone for checking clonability with lambda functions..
svm_cloned = base.clone(svm_callable)
svm_cloned.fit(iris.data, iris.target)
svm_builtin = svm.SVC(kernel='linear',
probability=True,
random_state=0,
decision_function_shape='ovr')
svm_builtin.fit(iris.data, iris.target)
assert_array_almost_equal(svm_cloned.dual_coef_, svm_builtin.dual_coef_)
assert_array_almost_equal(svm_cloned.intercept_, svm_builtin.intercept_)
assert_array_equal(svm_cloned.predict(iris.data),
svm_builtin.predict(iris.data))
assert_array_almost_equal(svm_cloned.predict_proba(iris.data),
svm_builtin.predict_proba(iris.data),
decimal=4)
assert_array_almost_equal(svm_cloned.decision_function(iris.data),
svm_builtin.decision_function(iris.data))
def test_clone_estimator_types():
# Check that clone works for parameters that are types rather than
# instances
clf = MyEstimator(empty=MyEstimator)
clf2 = clone(clf)
assert clf.empty is clf2.empty
def test_ensemble_heterogeneous_estimators_behavior(X, y, estimator):
# check that the behavior of `estimators`, `estimators_`,
# `named_estimators`, `named_estimators_` is consistent across all
# ensemble classes and when using `set_params()`.
# before fit
assert 'svm' in estimator.named_estimators
assert estimator.named_estimators.svm is estimator.estimators[1][1]
assert estimator.named_estimators.svm is estimator.named_estimators['svm']
# check fitted attributes
estimator.fit(X, y)
assert len(estimator.named_estimators) == 3
assert len(estimator.named_estimators_) == 3
assert (sorted(list(estimator.named_estimators_.keys())) == sorted(
['lr', 'svm', 'rf']))
# check that set_params() does not add a new attribute
estimator_new_params = clone(estimator)
svm_estimator = SVC() if is_classifier(estimator) else SVR()
estimator_new_params.set_params(svm=svm_estimator).fit(X, y)
assert not hasattr(estimator_new_params, 'svm')
assert (estimator_new_params.named_estimators.lr.get_params() ==
estimator.named_estimators.lr.get_params())
assert (estimator_new_params.named_estimators.rf.get_params() ==
estimator.named_estimators.rf.get_params())
# check the behavior when setting an dropping an estimator
estimator_dropped = clone(estimator)
estimator_dropped.set_params(svm='drop')
estimator_dropped.fit(X, y)
assert len(estimator_dropped.named_estimators) == 3
assert estimator_dropped.named_estimators.svm == 'drop'
assert len(estimator_dropped.named_estimators_) == 3
assert (sorted(list(estimator_dropped.named_estimators_.keys())) == sorted(
['lr', 'svm', 'rf']))
for sub_est in estimator_dropped.named_estimators_:
# check that the correspondence is correct
assert not isinstance(sub_est, type(estimator.named_estimators.svm))
# check that we can set the parameters of the underlying classifier
estimator.set_params(svm__C=10.0)
estimator.set_params(rf__max_depth=5)
assert (estimator.get_params()['svm__C'] == estimator.get_params()
['svm'].get_params()['C'])
assert (estimator.get_params()['rf__max_depth'] == estimator.get_params()
['rf'].get_params()['max_depth'])
def test_binary_classifier_class_weight():
"""tests binary classifier with classweights for each class"""
alpha = .1
n_samples = 50
n_iter = 20
tol = .00001
fit_intercept = True
X, y = make_blobs(n_samples=n_samples,
centers=2,
random_state=10,
cluster_std=0.1)
step_size = get_step_size(X, alpha, fit_intercept, classification=True)
classes = np.unique(y)
y_tmp = np.ones(n_samples)
y_tmp[y != classes[1]] = -1
y = y_tmp
class_weight = {1: .45, -1: .55}
clf1 = LogisticRegression(solver='sag',
C=1. / alpha / n_samples,
max_iter=n_iter,
tol=tol,
random_state=77,
fit_intercept=fit_intercept,
multi_class='ovr',
class_weight=class_weight)
clf2 = clone(clf1)
clf1.fit(X, y)
clf2.fit(sp.csr_matrix(X), y)
le = LabelEncoder()
class_weight_ = compute_class_weight(class_weight, np.unique(y), y)
sample_weight = class_weight_[le.fit_transform(y)]
spweights, spintercept = sag_sparse(X,
y,
step_size,
alpha,
n_iter=n_iter,
dloss=log_dloss,
sample_weight=sample_weight,
fit_intercept=fit_intercept)
spweights2, spintercept2 = sag_sparse(X,
y,
step_size,
alpha,
n_iter=n_iter,
dloss=log_dloss,
sparse=True,
sample_weight=sample_weight,
fit_intercept=fit_intercept)
assert_array_almost_equal(clf1.coef_.ravel(), spweights.ravel(), decimal=2)
assert_almost_equal(clf1.intercept_, spintercept, decimal=1)
assert_array_almost_equal(clf2.coef_.ravel(),
spweights2.ravel(),
decimal=2)
assert_almost_equal(clf2.intercept_, spintercept2, decimal=1)
def _check_behavior_2d(clf):
# 1d case
X = np.array([[0], [0], [0], [0]]) # ignored
y = np.array([1, 2, 1, 1])
est = clone(clf)
est.fit(X, y)
y_pred = est.predict(X)
assert y.shape == y_pred.shape
# 2d case
y = np.array([[1, 0],
[2, 0],
[1, 0],
[1, 3]])
est = clone(clf)
est.fit(X, y)
y_pred = est.predict(X)
assert y.shape == y_pred.shape
def test_kneighbors_regressor():
# Test chaining KNeighborsTransformer and classifiers/regressors
rng = np.random.RandomState(0)
X = 2 * rng.rand(40, 5) - 1
X2 = 2 * rng.rand(40, 5) - 1
y = rng.rand(40, 1)
n_neighbors = 12
radius = 1.5
# We precompute more neighbors than necessary, to have equivalence between
# k-neighbors estimator after radius-neighbors transformer, and vice-versa.
factor = 2
k_trans = KNeighborsTransformer(n_neighbors=n_neighbors, mode='distance')
k_trans_factor = KNeighborsTransformer(n_neighbors=int(
n_neighbors * factor), mode='distance')
r_trans = RadiusNeighborsTransformer(radius=radius, mode='distance')
r_trans_factor = RadiusNeighborsTransformer(radius=int(
radius * factor), mode='distance')
k_reg = KNeighborsRegressor(n_neighbors=n_neighbors)
r_reg = RadiusNeighborsRegressor(radius=radius)
test_list = [
(k_trans, k_reg),
(k_trans_factor, r_reg),
(r_trans, r_reg),
(r_trans_factor, k_reg),
]
for trans, reg in test_list:
# compare the chained version and the compact version
reg_compact = clone(reg)
reg_precomp = clone(reg)
reg_precomp.set_params(metric='precomputed')
reg_chain = make_pipeline(clone(trans), reg_precomp)
y_pred_chain = reg_chain.fit(X, y).predict(X2)
y_pred_compact = reg_compact.fit(X, y).predict(X2)
assert_array_almost_equal(y_pred_chain, y_pred_compact)
def _check_behavior_2d_for_constant(clf):
# 2d case only
X = np.array([[0], [0], [0], [0]]) # ignored
y = np.array([[1, 0, 5, 4, 3],
[2, 0, 1, 2, 5],
[1, 0, 4, 5, 2],
[1, 3, 3, 2, 0]])
est = clone(clf)
est.fit(X, y)
y_pred = est.predict(X)
assert y.shape == y_pred.shape
def test_warm_start_equal_n_estimators(GradientBoosting, X, y):
# Test if warm start with equal n_estimators does nothing
gb_1 = GradientBoosting(max_depth=2)
gb_1.fit(X, y)
gb_2 = clone(gb_1)
gb_2.set_params(max_iter=gb_1.max_iter, warm_start=True)
gb_2.fit(X, y)
# Check that both predictors are equal
_assert_predictor_equal(gb_1, gb_2, X)
def test_clone_sparse_matrices():
sparse_matrix_classes = [
getattr(sp, name) for name in dir(sp) if name.endswith('_matrix')
]
for cls in sparse_matrix_classes:
sparse_matrix = cls(np.eye(5))
clf = MyEstimator(empty=sparse_matrix)
clf_cloned = clone(clf)
assert clf.empty.__class__ is clf_cloned.empty.__class__
assert_array_equal(clf.empty.toarray(), clf_cloned.empty.toarray())
def test_sag_regressor():
"""tests if the sag regressor performs well"""
xmin, xmax = -5, 5
n_samples = 20
tol = .001
max_iter = 50
alpha = 0.1
rng = np.random.RandomState(0)
X = np.linspace(xmin, xmax, n_samples).reshape(n_samples, 1)
# simple linear function without noise
y = 0.5 * X.ravel()
clf1 = Ridge(tol=tol,
solver='sag',
max_iter=max_iter,
alpha=alpha * n_samples,
random_state=rng)
clf2 = clone(clf1)
clf1.fit(X, y)
clf2.fit(sp.csr_matrix(X), y)
score1 = clf1.score(X, y)
score2 = clf2.score(X, y)
assert score1 > 0.99
assert score2 > 0.99
# simple linear function with noise
y = 0.5 * X.ravel() + rng.randn(n_samples, 1).ravel()
clf1 = Ridge(tol=tol,
solver='sag',
max_iter=max_iter,
alpha=alpha * n_samples)
clf2 = clone(clf1)
clf1.fit(X, y)
clf2.fit(sp.csr_matrix(X), y)
score1 = clf1.score(X, y)
score2 = clf2.score(X, y)
score2 = clf2.score(X, y)
assert score1 > 0.5
assert score2 > 0.5
def test_clone_2():
# Tests that clone doesn't copy everything.
# We first create an estimator, give it an own attribute, and
# make a copy of its original state. Then we check that the copy doesn't
# have the specific attribute we manually added to the initial estimator.
from sklearn_lib.feature_selection import SelectFpr, f_classif
selector = SelectFpr(f_classif, alpha=0.1)
selector.own_attribute = "test"
new_selector = clone(selector)
assert not hasattr(new_selector, "own_attribute")
def test_sag_classifier_computed_correctly():
"""tests if the binary classifier is computed correctly"""
alpha = .1
n_samples = 50
n_iter = 50
tol = .00001
fit_intercept = True
X, y = make_blobs(n_samples=n_samples,
centers=2,
random_state=0,
cluster_std=0.1)
step_size = get_step_size(X, alpha, fit_intercept, classification=True)
classes = np.unique(y)
y_tmp = np.ones(n_samples)
y_tmp[y != classes[1]] = -1
y = y_tmp
clf1 = LogisticRegression(solver='sag',
C=1. / alpha / n_samples,
max_iter=n_iter,
tol=tol,
random_state=77,
fit_intercept=fit_intercept,
multi_class='ovr')
clf2 = clone(clf1)
clf1.fit(X, y)
clf2.fit(sp.csr_matrix(X), y)
spweights, spintercept = sag_sparse(X,
y,
step_size,
alpha,
n_iter=n_iter,
dloss=log_dloss,
fit_intercept=fit_intercept)
spweights2, spintercept2 = sag_sparse(X,
y,
step_size,
alpha,
n_iter=n_iter,
dloss=log_dloss,
sparse=True,
fit_intercept=fit_intercept)
assert_array_almost_equal(clf1.coef_.ravel(), spweights.ravel(), decimal=2)
assert_almost_equal(clf1.intercept_, spintercept, decimal=1)
assert_array_almost_equal(clf2.coef_.ravel(),
spweights2.ravel(),
decimal=2)
assert_almost_equal(clf2.intercept_, spintercept2, decimal=1)
def test_none_estimator_with_weights(X, y, voter, drop):
# TODO: remove the parametrization on 'drop' when support for None is
# removed.
# check that an estimator can be set to 'drop' and passing some weight
# regression test for
# https://github.com/scikit-learn/scikit-learn/issues/13777
voter = clone(voter)
voter.fit(X, y, sample_weight=np.ones(y.shape))
voter.set_params(lr=drop)
with pytest.warns(None) as record:
voter.fit(X, y, sample_weight=np.ones(y.shape))
assert record if drop is None else not record
y_pred = voter.predict(X)
assert y_pred.shape == y.shape
def test_kernel_clone(kernel):
# Test that sklearn_lib's clone works correctly on kernels.
kernel_cloned = clone(kernel)
# XXX: Should this be fixed?
# This differs from the sklearn_lib's estimators equality check.
assert kernel == kernel_cloned
assert id(kernel) != id(kernel_cloned)
# Check that all constructor parameters are equal.
assert kernel.get_params() == kernel_cloned.get_params()
# Check that all hyperparameters are equal.
check_hyperparameters_equal(kernel, kernel_cloned)
def test_stacking_cv_influence(stacker, X, y):
# check that the stacking affects the fit of the final estimator but not
# the fit of the base estimators
# note: ConvergenceWarning are catch since we are not worrying about the
# convergence here
stacker_cv_3 = clone(stacker)
stacker_cv_5 = clone(stacker)
stacker_cv_3.set_params(cv=3)
stacker_cv_5.set_params(cv=5)
stacker_cv_3.fit(X, y)
stacker_cv_5.fit(X, y)
# the base estimators should be identical
for est_cv_3, est_cv_5 in zip(stacker_cv_3.estimators_,
stacker_cv_5.estimators_):
assert_allclose(est_cv_3.coef_, est_cv_5.coef_)
# the final estimator should be different
with pytest.raises(AssertionError, match='Not equal'):
assert_allclose(stacker_cv_3.final_estimator_.coef_,
stacker_cv_5.final_estimator_.coef_)
def test_partial_dependence_dataframe(estimator, preprocessor, features):
# check that the partial dependence support dataframe and pipeline
# including a column transformer
pd = pytest.importorskip("pandas")
df = pd.DataFrame(iris.data, columns=iris.feature_names)
pipe = make_pipeline(preprocessor, estimator)
pipe.fit(df, iris.target)
pdp_pipe, values_pipe = partial_dependence(pipe,
df,
features=features,
grid_resolution=10)
# the column transformer will reorder the column when transforming
# we mixed the index to be sure that we are computing the partial
# dependence of the right columns
if preprocessor is not None:
X_proc = clone(preprocessor).fit_transform(df)
features_clf = [0, 1]
else:
X_proc = df
features_clf = [0, 2]
clf = clone(estimator).fit(X_proc, iris.target)
pdp_clf, values_clf = partial_dependence(clf,
X_proc,
features=features_clf,
method='brute',
grid_resolution=10)
assert_allclose(pdp_pipe, pdp_clf)
if preprocessor is not None:
scaler = preprocessor.named_transformers_['standardscaler']
assert_allclose(values_pipe[1],
values_clf[1] * scaler.scale_[1] + scaler.mean_[1])
else:
assert_allclose(values_pipe[1], values_clf[1])
def test_adaboostregressor_sample_weight():
# check that giving weight will have an influence on the error computed
# for a weak learner
rng = np.random.RandomState(42)
X = np.linspace(0, 100, num=1000)
y = (.8 * X + 0.2) + (rng.rand(X.shape[0]) * 0.0001)
X = X.reshape(-1, 1)
# add an arbitrary outlier
X[-1] *= 10
y[-1] = 10000
# random_state=0 ensure that the underlying bootstrap will use the outlier
regr_no_outlier = AdaBoostRegressor(base_estimator=LinearRegression(),
n_estimators=1,
random_state=0)
regr_with_weight = clone(regr_no_outlier)
regr_with_outlier = clone(regr_no_outlier)
# fit 3 models:
# - a model containing the outlier
# - a model without the outlier
# - a model containing the outlier but with a null sample-weight
regr_with_outlier.fit(X, y)
regr_no_outlier.fit(X[:-1], y[:-1])
sample_weight = np.ones_like(y)
sample_weight[-1] = 0
regr_with_weight.fit(X, y, sample_weight=sample_weight)
score_with_outlier = regr_with_outlier.score(X[:-1], y[:-1])
score_no_outlier = regr_no_outlier.score(X[:-1], y[:-1])
score_with_weight = regr_with_weight.score(X[:-1], y[:-1])
assert score_with_outlier < score_no_outlier
assert score_with_outlier < score_with_weight
assert score_no_outlier == pytest.approx(score_with_weight)
def test_sag_regressor_computed_correctly():
"""tests if the sag regressor is computed correctly"""
alpha = .1
n_features = 10
n_samples = 40
max_iter = 100
tol = .000001
fit_intercept = True
rng = np.random.RandomState(0)
X = rng.normal(size=(n_samples, n_features))
w = rng.normal(size=n_features)
y = np.dot(X, w) + 2.
step_size = get_step_size(X, alpha, fit_intercept, classification=False)
clf1 = Ridge(fit_intercept=fit_intercept,
tol=tol,
solver='sag',
alpha=alpha * n_samples,
max_iter=max_iter,
random_state=rng)
clf2 = clone(clf1)
clf1.fit(X, y)
clf2.fit(sp.csr_matrix(X), y)
spweights1, spintercept1 = sag_sparse(X,
y,
step_size,
alpha,
n_iter=max_iter,
dloss=squared_dloss,
fit_intercept=fit_intercept,
random_state=rng)
spweights2, spintercept2 = sag_sparse(X,
y,
step_size,
alpha,
n_iter=max_iter,
dloss=squared_dloss,
sparse=True,
fit_intercept=fit_intercept,
random_state=rng)
assert_array_almost_equal(clf1.coef_.ravel(),
spweights1.ravel(),
decimal=3)
assert_almost_equal(clf1.intercept_, spintercept1, decimal=1)
def test_sparse_svc_clone_with_callable_kernel():
# Test that the "dense_fit" is called even though we use sparse input
# meaning that everything works fine.
a = svm.SVC(C=1,
kernel=lambda x, y: x * y.T,
probability=True,
random_state=0)
b = base.clone(a)
b.fit(X_sp, Y)
pred = b.predict(X_sp)
b.predict_proba(X_sp)
dense_svm = svm.SVC(C=1,
kernel=lambda x, y: np.dot(x, y.T),
probability=True,
random_state=0)
pred_dense = dense_svm.fit(X, Y).predict(X)
assert_array_equal(pred_dense, pred)
def test_transform_target_regressor_2d_transformer_multioutput():
# Check consistency with transformer accepting only 2D array and a 2D y
# array.
X = friedman[0]
y = np.vstack((friedman[1], friedman[1]**2 + 1)).T
transformer = StandardScaler()
regr = TransformedTargetRegressor(regressor=LinearRegression(),
transformer=transformer)
y_pred = regr.fit(X, y).predict(X)
assert y.shape == y_pred.shape
# consistency forward transform
y_tran = regr.transformer_.transform(y)
_check_standard_scaled(y, y_tran)
assert y.shape == y_pred.shape
# consistency inverse transform
assert_allclose(y, regr.transformer_.inverse_transform(y_tran).squeeze())
# consistency of the regressor
lr = LinearRegression()
transformer2 = clone(transformer)
lr.fit(X, transformer2.fit_transform(y))
y_lr_pred = lr.predict(X)
assert_allclose(y_pred, transformer2.inverse_transform(y_lr_pred))
assert_allclose(regr.regressor_.coef_, lr.coef_)
def test_sag_pobj_matches_ridge_regression():
"""tests if the sag pobj matches ridge reg"""
n_samples = 100
n_features = 10
alpha = 1.0
n_iter = 100
fit_intercept = False
rng = np.random.RandomState(10)
X = rng.normal(size=(n_samples, n_features))
true_w = rng.normal(size=n_features)
y = X.dot(true_w)
clf1 = Ridge(fit_intercept=fit_intercept,
tol=.00000000001,
solver='sag',
alpha=alpha,
max_iter=n_iter,
random_state=42)
clf2 = clone(clf1)
clf3 = Ridge(fit_intercept=fit_intercept,
tol=.00001,
solver='lsqr',
alpha=alpha,
max_iter=n_iter,
random_state=42)
clf1.fit(X, y)
clf2.fit(sp.csr_matrix(X), y)
clf3.fit(X, y)
pobj1 = get_pobj(clf1.coef_, alpha, X, y, squared_loss)
pobj2 = get_pobj(clf2.coef_, alpha, X, y, squared_loss)
pobj3 = get_pobj(clf3.coef_, alpha, X, y, squared_loss)
assert_array_almost_equal(pobj1, pobj2, decimal=4)
assert_array_almost_equal(pobj1, pobj3, decimal=4)
assert_array_almost_equal(pobj3, pobj2, decimal=4)
def test_sag_pobj_matches_logistic_regression():
"""tests if the sag pobj matches log reg"""
n_samples = 100
alpha = 1.0
max_iter = 20
X, y = make_blobs(n_samples=n_samples,
centers=2,
random_state=0,
cluster_std=0.1)
clf1 = LogisticRegression(solver='sag',
fit_intercept=False,
tol=.0000001,
C=1. / alpha / n_samples,
max_iter=max_iter,
random_state=10,
multi_class='ovr')
clf2 = clone(clf1)
clf3 = LogisticRegression(fit_intercept=False,
tol=.0000001,
C=1. / alpha / n_samples,
max_iter=max_iter,
random_state=10,
multi_class='ovr')
clf1.fit(X, y)
clf2.fit(sp.csr_matrix(X), y)
clf3.fit(X, y)
pobj1 = get_pobj(clf1.coef_, alpha, X, y, log_loss)
pobj2 = get_pobj(clf2.coef_, alpha, X, y, log_loss)
pobj3 = get_pobj(clf3.coef_, alpha, X, y, log_loss)
assert_array_almost_equal(pobj1, pobj2, decimal=4)
assert_array_almost_equal(pobj2, pobj3, decimal=4)
assert_array_almost_equal(pobj3, pobj1, decimal=4)
