def test_nystroem_callable():
# Test Nystroem on a callable.
rnd = np.random.RandomState(42)
n_samples = 10
X = rnd.uniform(size=(n_samples, 4))
def logging_histogram_kernel(x, y, log):
"""Histogram kernel that writes to a log."""
log.append(1)
return np.minimum(x, y).sum()
kernel_log = []
X = list(X) # test input validation
Nystroem(kernel=logging_histogram_kernel,
n_components=(n_samples - 1),
kernel_params={
'log': kernel_log
}).fit(X)
assert len(kernel_log) == n_samples * (n_samples - 1) / 2
def linear_kernel(X, Y):
return np.dot(X, Y.T)
# if degree, gamma or coef0 is passed, we raise a warning
msg = "Don't pass gamma, coef0 or degree to Nystroem"
params = ({'gamma': 1}, {'coef0': 1}, {'degree': 2})
for param in params:
ny = Nystroem(kernel=linear_kernel, **param)
with pytest.raises(ValueError, match=msg):
ny.fit(X)
def test_nystroem_approximation():
# some basic tests
rnd = np.random.RandomState(0)
X = rnd.uniform(size=(10, 4))
# With n_components = n_samples this is exact
X_transformed = Nystroem(n_components=X.shape[0]).fit_transform(X)
K = rbf_kernel(X)
assert_array_almost_equal(np.dot(X_transformed, X_transformed.T), K)
trans = Nystroem(n_components=2, random_state=rnd)
X_transformed = trans.fit(X).transform(X)
assert X_transformed.shape == (X.shape[0], 2)
# test callable kernel
def linear_kernel(X, Y):
return np.dot(X, Y.T)
trans = Nystroem(n_components=2, kernel=linear_kernel, random_state=rnd)
X_transformed = trans.fit(X).transform(X)
assert X_transformed.shape == (X.shape[0], 2)
# test that available kernels fit and transform
kernels_available = kernel_metrics()
for kern in kernels_available:
trans = Nystroem(n_components=2, kernel=kern, random_state=rnd)
X_transformed = trans.fit(X).transform(X)
assert X_transformed.shape == (X.shape[0], 2)
def test_nystroem_poly_kernel_params():
# Non-regression: Nystroem should pass other parameters beside gamma.
rnd = np.random.RandomState(37)
X = rnd.uniform(size=(10, 4))
K = polynomial_kernel(X, degree=3.1, coef0=.1)
nystroem = Nystroem(kernel="polynomial",
n_components=X.shape[0],
degree=3.1,
coef0=.1)
X_transformed = nystroem.fit_transform(X)
assert_array_almost_equal(np.dot(X_transformed, X_transformed.T), K)
def test_nystroem_singular_kernel():
# test that nystroem works with singular kernel matrix
rng = np.random.RandomState(0)
X = rng.rand(10, 20)
X = np.vstack([X] * 2) # duplicate samples
gamma = 100
N = Nystroem(gamma=gamma, n_components=X.shape[0]).fit(X)
X_transformed = N.transform(X)
K = rbf_kernel(X, gamma=gamma)
assert_array_almost_equal(K, np.dot(X_transformed, X_transformed.T))
assert np.all(np.isfinite(Y))
def test_nystroem_precomputed_kernel():
# Non-regression: test Nystroem on precomputed kernel.
# PR - 14706
rnd = np.random.RandomState(12)
X = rnd.uniform(size=(10, 4))
K = polynomial_kernel(X, degree=2, coef0=.1)
nystroem = Nystroem(kernel='precomputed', n_components=X.shape[0])
X_transformed = nystroem.fit_transform(K)
assert_array_almost_equal(np.dot(X_transformed, X_transformed.T), K)
# if degree, gamma or coef0 is passed, we raise a ValueError
msg = "Don't pass gamma, coef0 or degree to Nystroem"
params = ({'gamma': 1}, {'coef0': 1}, {'degree': 2})
for param in params:
ny = Nystroem(kernel='precomputed', n_components=X.shape[0], **param)
with pytest.raises(ValueError, match=msg):
ny.fit(K)
def test_nystroem_default_parameters():
rnd = np.random.RandomState(42)
X = rnd.uniform(size=(10, 4))
# rbf kernel should behave as gamma=None by default
# aka gamma = 1 / n_features
nystroem = Nystroem(n_components=10)
X_transformed = nystroem.fit_transform(X)
K = rbf_kernel(X, gamma=None)
K2 = np.dot(X_transformed, X_transformed.T)
assert_array_almost_equal(K, K2)
# chi2 kernel should behave as gamma=1 by default
nystroem = Nystroem(kernel='chi2', n_components=10)
X_transformed = nystroem.fit_transform(X)
K = chi2_kernel(X, gamma=1)
K2 = np.dot(X_transformed, X_transformed.T)
assert_array_almost_equal(K, K2)
n_train = 60000
X_train = X[:n_train]
y_train = y[:n_train]
X_test = X[n_train:]
y_test = y[n_train:]
return X_train, X_test, y_train, y_test
ESTIMATORS = {
"dummy": DummyClassifier(),
'CART': DecisionTreeClassifier(),
'ExtraTrees': ExtraTreesClassifier(),
'RandomForest': RandomForestClassifier(),
'Nystroem-SVM': make_pipeline(
Nystroem(gamma=0.015, n_components=1000), LinearSVC(C=100)),
'SampledRBF-SVM': make_pipeline(
RBFSampler(gamma=0.015, n_components=1000), LinearSVC(C=100)),
'LogisticRegression-SAG': LogisticRegression(solver='sag', tol=1e-1,
C=1e4),
'LogisticRegression-SAGA': LogisticRegression(solver='saga', tol=1e-1,
C=1e4),
'MultilayerPerceptron': MLPClassifier(
hidden_layer_sizes=(100, 100), max_iter=400, alpha=1e-4,
solver='sgd', learning_rate_init=0.2, momentum=0.9, verbose=1,
tol=1e-4, random_state=1),
'MLP-adam': MLPClassifier(
hidden_layer_sizes=(100, 100), max_iter=400, alpha=1e-4,
solver='adam', learning_rate_init=0.001, verbose=1,
tol=1e-4, random_state=1)
}
data_train, targets_train = (data[:n_samples // 2],
digits.target[:n_samples // 2])
# Now predict the value of the digit on the second half:
data_test, targets_test = (data[n_samples // 2:],
digits.target[n_samples // 2:])
# data_test = scaler.transform(data_test)
# Create a classifier: a support vector classifier
kernel_svm = svm.SVC(gamma=.2)
linear_svm = svm.LinearSVC()
# create pipeline from kernel approximation
# and linear svm
feature_map_fourier = RBFSampler(gamma=.2, random_state=1)
feature_map_nystroem = Nystroem(gamma=.2, random_state=1)
fourier_approx_svm = pipeline.Pipeline([("feature_map", feature_map_fourier),
("svm", svm.LinearSVC())])
nystroem_approx_svm = pipeline.Pipeline([("feature_map", feature_map_nystroem),
("svm", svm.LinearSVC())])
# fit and predict using linear and kernel svm:
kernel_svm_time = time()
kernel_svm.fit(data_train, targets_train)
kernel_svm_score = kernel_svm.score(data_test, targets_test)
kernel_svm_time = time() - kernel_svm_time
linear_svm_time = time()
linear_svm.fit(data_train, targets_train)