def test_sag_proba():
n_samples = 10
X, y = make_classification(n_samples, random_state=0)
sag = SAGClassifier(eta=1e-3, alpha=0.0, beta=0.0, max_iter=10,
loss='log', random_state=0)
sag.fit(X, y)
check_predict_proba(sag, X)
def test_sag_proba():
n_samples = 10
X, y = make_classification(n_samples, random_state=0)
sag = SAGClassifier(eta=1e-3, alpha=0.0, beta=0.0, max_iter=10,
loss='log', random_state=0)
sag.fit(X, y)
probas = sag.predict_proba(X)
assert_equal(probas.sum(), n_samples)
def test_sag_proba():
n_samples = 10
X, y = make_classification(n_samples, random_state=0)
sag = SAGClassifier(eta=1e-3, alpha=0.0, beta=0.0, max_iter=10,
loss='log', random_state=0)
sag.fit(X, y)
probas = sag.predict_proba(X)
assert_equal(probas.sum(), n_samples)
def test_no_reg_sag(bin_train_data):
X_bin, y_bin = bin_train_data
pysag = PySAGClassifier(eta=1e-3, alpha=0.0, max_iter=10, random_state=0)
sag = SAGClassifier(eta=1e-3, alpha=0.0, max_iter=10, random_state=0)
pysag.fit(X_bin, y_bin)
sag.fit(X_bin, y_bin)
np.testing.assert_array_almost_equal(pysag.coef_, sag.coef_)
def test_sag_multiclass_classes():
X, y = make_classification(n_samples=10,
random_state=0,
n_classes=3,
n_informative=4)
sag = SAGClassifier()
sag.fit(X, y)
assert list(sag.classes_) == [0, 1, 2]
def test_l2_regularized_sag():
pysag = PySAGClassifier(eta=1e-3, alpha=1.0, max_iter=10, random_state=0)
sag = SAGClassifier(eta=1e-3, alpha=1.0, max_iter=10, random_state=0)
pysag.fit(X_bin, y_bin)
sag.fit(X_bin, y_bin)
np.testing.assert_array_almost_equal(pysag.coef_, sag.coef_)
def test_l2_regularized_sag():
pysag = PySAGClassifier(eta=1e-3, alpha=1.0, max_iter=10, random_state=0)
sag = SAGClassifier(eta=1e-3, alpha=1.0, max_iter=10, random_state=0)
pysag.fit(X_bin, y_bin)
sag.fit(X_bin, y_bin)
np.testing.assert_array_almost_equal(pysag.coef_, sag.coef_)
def test_sag_score():
X, y = make_classification(1000, random_state=0)
pysag = PySAGClassifier(eta=1e-3, alpha=0.0, beta=0.0, max_iter=10, random_state=0)
sag = SAGClassifier(eta=1e-3, alpha=0.0, beta=0.0, max_iter=10, random_state=0)
pysag.fit(X, y)
sag.fit(X, y)
assert_equal(pysag.score(X, y), sag.score(X, y))
def test_sag_score():
X, y = make_classification(1000, random_state=0)
pysag = PySAGClassifier(eta=1e-3, alpha=0.0, beta=0.0, max_iter=10,
random_state=0)
sag = SAGClassifier(eta=1e-3, alpha=0.0, beta=0.0, max_iter=10,
random_state=0)
pysag.fit(X, y)
sag.fit(X, y)
assert_equal(pysag.score(X, y), sag.score(X, y))
def test_sag_sparse():
# FIX for https://github.com/mblondel/lightning/issues/33
# check that SAG has the same results with dense
# and sparse data
X = sparse.rand(100, 50, density=.5, random_state=0)
y = np.random.randint(0, high=2, size=100)
for alpha in np.logspace(-3, 3, 10):
clf_sparse = SAGClassifier(max_iter=1, random_state=0, alpha=alpha)
clf_sparse.fit(X, y)
clf_dense = SAGClassifier(max_iter=1, random_state=0, alpha=alpha)
clf_dense.fit(X.toarray(), y)
assert_equal(clf_sparse.score(X, y), clf_dense.score(X, y))
def test_sag_sparse():
# FIX for https://github.com/mblondel/lightning/issues/33
# check that SAG has the same results with dense
# and sparse data
X = sparse.rand(100, 50, density=.5, random_state=0)
y = np.random.randint(0, high=2, size=100)
for alpha in np.logspace(-3, 3, 10):
clf_sparse = SAGClassifier(max_iter=1, random_state=0, alpha=alpha)
clf_sparse.fit(X, y)
clf_dense = SAGClassifier(max_iter=1, random_state=0, alpha=alpha)
clf_dense.fit(X.toarray(), y)
assert_equal(clf_sparse.score(X, y), clf_dense.score(X, y))
def test_sag_adaptive():
"""Check that the adaptive step size strategy yields the same
solution as the non-adaptive"""
np.random.seed(0)
X = sparse.rand(100, 10, density=.5, random_state=0).tocsr()
y = np.random.randint(0, high=2, size=100)
for alpha in np.logspace(-3, 1, 5):
clf_adaptive = SAGClassifier(eta='line-search',
random_state=0,
alpha=alpha)
clf_adaptive.fit(X, y)
clf = SAGClassifier(eta='auto', random_state=0, alpha=alpha)
clf.fit(X, y)
np.testing.assert_almost_equal(clf_adaptive.score(X, y),
clf.score(X, y), 1)
clf_adaptive = SAGAClassifier(eta='line-search',
loss='log',
random_state=0,
alpha=alpha,
max_iter=20)
clf_adaptive.fit(X, y)
assert np.isnan(clf_adaptive.coef_.sum()) == False
clf = SAGAClassifier(eta='auto',
loss='log',
random_state=0,
alpha=alpha,
max_iter=20)
clf.fit(X, y)
np.testing.assert_almost_equal(clf_adaptive.score(X, y),
clf.score(X, y), 1)
def test_sag_callback():
class Callback(object):
def __init__(self, X, y):
self.X = X
self.y = y
self.obj = []
def __call__(self, clf):
clf._finalize_coef()
y_pred = clf.decision_function(self.X).ravel()
loss = (np.maximum(1 - self.y * y_pred, 0) ** 2).mean()
coef = clf.coef_.ravel()
regul = 0.5 * clf.alpha * np.dot(coef, coef)
self.obj.append(loss + regul)
cb = Callback(X_bin, y_bin)
clf = SAGClassifier(loss="squared_hinge", eta=1e-3, max_iter=20,
random_state=0, callback=cb)
clf.fit(X_bin, y_bin)
assert_true(np.all(np.diff(cb.obj) <= 0))
def test_sag_callback():
class Callback(object):
def __init__(self, X, y):
self.X = X
self.y = y
self.obj = []
def __call__(self, clf):
clf._finalize_coef()
y_pred = clf.decision_function(self.X).ravel()
loss = (np.maximum(1 - self.y * y_pred, 0)**2).mean()
coef = clf.coef_.ravel()
regul = 0.5 * clf.alpha * np.dot(coef, coef)
self.obj.append(loss + regul)
cb = Callback(X_bin, y_bin)
clf = SAGClassifier(loss="squared_hinge",
eta=1e-3,
max_iter=20,
random_state=0,
callback=cb)
clf.fit(X_bin, y_bin)
assert_true(np.all(np.diff(cb.obj) <= 0))
def test_sag_adaptive():
"""Check that the adaptive step size strategy yields the same
solution as the non-adaptive"""
np.random.seed(0)
X = sparse.rand(100, 10, density=.5, random_state=0).tocsr()
y = np.random.randint(0, high=2, size=100)
for alpha in np.logspace(-3, 1, 5):
clf_adaptive = SAGClassifier(
eta='line-search', random_state=0, alpha=alpha)
clf_adaptive.fit(X, y)
clf = SAGClassifier(
eta='auto', random_state=0, alpha=alpha)
clf.fit(X, y)
assert_almost_equal(clf_adaptive.score(X, y), clf.score(X, y), 1)
clf_adaptive = SAGAClassifier(
eta='line-search', loss='log', random_state=0, alpha=alpha, max_iter=20)
clf_adaptive.fit(X, y)
assert np.isnan(clf_adaptive.coef_.sum()) == False
clf = SAGAClassifier(
eta='auto', loss='log', random_state=0, alpha=alpha, max_iter=20)
clf.fit(X, y)
assert_almost_equal(clf_adaptive.score(X, y), clf.score(X, y), 1)
import time
import numpy as np
from sklearn.datasets import fetch_20newsgroups_vectorized
from lightning.classification import SAGClassifier
bunch = fetch_20newsgroups_vectorized(subset="all")
X = bunch.data
y = bunch.target
y[y >= 1] = 1
clf = SAGClassifier(eta=1e-4, alpha=1e-5, tol=1e-3, max_iter=20, verbose=1,
random_state=0)
start = time.time()
clf.fit(X, y)
print "Training time", time.time() - start
print "Accuracy", np.mean(clf.predict(X) == y)
print "% non-zero", clf.n_nonzero(percentage=True)
def test_sag():
clf = SAGClassifier(eta=1e-3, max_iter=20, verbose=0, random_state=0)
clf.fit(X_bin, y_bin)
assert_equal(clf.score(X_bin, y_bin), 1.0)
def test_sag_multiclass_classes():
X, y = make_classification(n_samples=10, random_state=0, n_classes=3,
n_informative=4)
sag = SAGClassifier()
sag.fit(X, y)
assert_equal(list(sag.classes_), [0, 1, 2])
def test_sag():
clf = SAGClassifier(eta=1e-3, max_iter=20, verbose=0, random_state=0)
clf.fit(X_bin, y_bin)
assert_equal(clf.score(X_bin, y_bin), 1.0)
