def test_fista_multiclass_l1_no_line_search():
for data in (mult_dense, mult_csr):
clf = FistaClassifier(max_iter=500,
penalty="l1",
multiclass=True,
max_steps=0)
clf.fit(data, mult_target)
assert_almost_equal(clf.score(data, mult_target), 0.95, 2)
def test_fista_multiclass_l1l2_log_margin():
for data in (mult_dense, mult_csr):
clf = FistaClassifier(max_iter=200,
penalty="l1/l2",
loss="log_margin",
multiclass=True)
clf.fit(data, mult_target)
assert_almost_equal(clf.score(data, mult_target), 0.95, 2)
def test_fista_multiclass_tv1d():
for data in (mult_dense, mult_csr):
clf = FistaClassifier(max_iter=200, penalty="tv1d", multiclass=True)
clf.fit(data, mult_target)
assert_almost_equal(clf.score(data, mult_target), 0.97, 2)
# adding a lot of regularization coef_ should be constant
clf = FistaClassifier(max_iter=200, penalty="tv1d", multiclass=True, alpha=1e6)
clf.fit(data, mult_target)
for i in range(clf.coef_.shape[0]):
np.testing.assert_array_almost_equal(
clf.coef_[i], np.mean(clf.coef_[i]) * np.ones(data.shape[1]))
def test_fista_multiclass_tv1d(data, request):
X, y = request.getfixturevalue(data)
clf = FistaClassifier(max_iter=200, penalty="tv1d", multiclass=True)
clf.fit(X, y)
np.testing.assert_almost_equal(clf.score(X, y), 0.97, 2)
# adding a lot of regularization coef_ should be constant
clf = FistaClassifier(max_iter=200, penalty="tv1d", multiclass=True, alpha=1e6)
clf.fit(X, y)
for i in range(clf.coef_.shape[0]):
np.testing.assert_array_almost_equal(
clf.coef_[i], np.mean(clf.coef_[i]) * np.ones(X.shape[1]))
def test_fista_multiclass_tv1d():
for data in (mult_dense, mult_csr):
clf = FistaClassifier(max_iter=200, penalty="tv1d", multiclass=True)
clf.fit(data, mult_target)
np.testing.assert_almost_equal(clf.score(data, mult_target), 0.97, 2)
# adding a lot of regularization coef_ should be constant
clf = FistaClassifier(max_iter=200, penalty="tv1d", multiclass=True, alpha=1e6)
clf.fit(data, mult_target)
for i in range(clf.coef_.shape[0]):
np.testing.assert_array_almost_equal(
clf.coef_[i], np.mean(clf.coef_[i]) * np.ones(data.shape[1]))
def test_fista_bin_l1_no_line_search():
for data in (bin_dense, bin_csr):
clf = FistaClassifier(max_iter=500, penalty="l1", max_steps=0)
clf.fit(data, bin_target)
assert_almost_equal(clf.score(data, bin_target), 1.0, 2)
def test_fista_bin_l1():
for data in (bin_dense, bin_csr):
clf = FistaClassifier(max_iter=200, penalty="l1")
clf.fit(data, bin_target)
assert_almost_equal(clf.score(data, bin_target), 1.0, 2)
def test_fista_multiclass_l1_no_line_search():
for data in (mult_dense, mult_csr):
clf = FistaClassifier(max_iter=500, penalty="l1", multiclass=True,
max_steps=0)
clf.fit(data, mult_target)
assert_almost_equal(clf.score(data, mult_target), 0.95, 2)
def test_fista_multiclass_l1l2_log_margin():
for data in (mult_dense, mult_csr):
clf = FistaClassifier(max_iter=200, penalty="l1/l2", loss="log_margin",
multiclass=True)
clf.fit(data, mult_target)
assert_almost_equal(clf.score(data, mult_target), 0.95, 2)
def test_fista_bin_l1_no_line_search():
for data in (bin_dense, bin_csr):
clf = FistaClassifier(max_iter=500, penalty="l1", max_steps=0)
clf.fit(data, bin_target)
assert_almost_equal(clf.score(data, bin_target), 1.0, 2)
def test_fista_multiclass_no_line_search(data, penalty, request):
X, y = request.getfixturevalue(data)
clf = FistaClassifier(max_iter=500, penalty=penalty, multiclass=True,
max_steps=0)
clf.fit(X, y)
np.testing.assert_almost_equal(clf.score(X, y), 0.94, 2)
def test_fista_multiclass_l1l2_log_margin(data, request):
X, y = request.getfixturevalue(data)
clf = FistaClassifier(max_iter=200, penalty="l1/l2", loss="log_margin",
multiclass=True)
clf.fit(X, y)
np.testing.assert_almost_equal(clf.score(X, y), 0.93, 2)
def test_fista_multiclass_l1():
for data in (mult_dense, mult_csr):
clf = FistaClassifier(max_iter=200, penalty="l1", multiclass=True)
clf.fit(data, mult_target)
np.testing.assert_almost_equal(clf.score(data, mult_target), 0.98, 2)
def rank(M, eps=1e-9):
U, s, V = svd(M, full_matrices=False)
return np.sum(s > eps)
bunch = fetch_20newsgroups_vectorized(subset="train")
X_train = bunch.data
y_train = bunch.target
# Reduces dimensionality to make the example faster
ch2 = SelectKBest(chi2, k=5000)
X_train = ch2.fit_transform(X_train, y_train)
bunch = fetch_20newsgroups_vectorized(subset="test")
X_test = bunch.data
y_test = bunch.target
X_test = ch2.transform(X_test)
clf = FistaClassifier(C=1.0 / X_train.shape[0],
max_iter=200,
penalty="trace",
multiclass=True)
for alpha in (1e-3, 1e-2, 0.1, 0.2, 0.3):
print("alpha=", alpha)
clf.alpha = alpha
clf.fit(X_train, y_train)
print(clf.score(X_test, y_test))
print(rank(clf.coef_))
def rank(M, eps=1e-9):
U, s, V = svd(M, full_matrices=False)
return np.sum(s > eps)
bunch = fetch_20newsgroups_vectorized(subset="train")
X_train = bunch.data
y_train = bunch.target
# Reduces dimensionality to make the example faster
ch2 = SelectKBest(chi2, k=5000)
X_train = ch2.fit_transform(X_train, y_train)
bunch = fetch_20newsgroups_vectorized(subset="test")
X_test = bunch.data
y_test = bunch.target
X_test = ch2.transform(X_test)
clf = FistaClassifier(C=1.0 / X_train.shape[0],
max_iter=200,
penalty="trace",
multiclass=True)
for alpha in (1e-3, 1e-2, 0.1, 0.2, 0.3):
print "alpha=", alpha
clf.alpha = alpha
clf.fit(X_train, y_train)
print clf.score(X_test, y_test)
print rank(clf.coef_)
def test_fista_multiclass_trace():
for data in (mult_dense, mult_csr):
clf = FistaClassifier(max_iter=100, penalty="trace", multiclass=True)
clf.fit(data, mult_target)
assert_almost_equal(clf.score(data, mult_target), 0.98, 2)
def test_fista_bin_l1():
for data in (bin_dense, bin_csr):
clf = FistaClassifier(max_iter=200, penalty="l1")
clf.fit(data, bin_target)
assert_almost_equal(clf.score(data, bin_target), 1.0, 2)
def test_fista_bin_l1(data, request):
X, y = request.getfixturevalue(data)
clf = FistaClassifier(max_iter=200, penalty="l1")
clf.fit(X, y)
np.testing.assert_almost_equal(clf.score(X, y), 1.0, 2)
def test_fista_multiclass_trace():
for data in (mult_dense, mult_csr):
clf = FistaClassifier(max_iter=100, penalty="trace", multiclass=True)
clf.fit(data, mult_target)
assert_almost_equal(clf.score(data, mult_target), 0.98, 2)
def test_fista_bin_l1_no_line_search(data, request):
X, y = request.getfixturevalue(data)
clf = FistaClassifier(max_iter=500, penalty="l1", max_steps=0)
clf.fit(X, y)
np.testing.assert_almost_equal(clf.score(X, y), 1.0, 2)
def test_fista_multiclass_trace(data, request):
X, y = request.getfixturevalue(data)
clf = FistaClassifier(max_iter=100, penalty="trace", multiclass=True)
clf.fit(X, y)
np.testing.assert_almost_equal(clf.score(X, y), 0.96, 2)
def rank(M, eps=1e-9):
U, s, V = svd(M, full_matrices=False)
return np.sum(s > eps)
bunch = fetch_20newsgroups_vectorized(subset="train")
X_train = bunch.data
y_train = bunch.target
# Reduces dimensionality to make the example faster
ch2 = SelectKBest(chi2, k=5000)
X_train = ch2.fit_transform(X_train, y_train)
bunch = fetch_20newsgroups_vectorized(subset="test")
X_test = bunch.data
y_test = bunch.target
X_test = ch2.transform(X_test)
clf = FistaClassifier(C=1.0 / X_train.shape[0],
max_iter=200,
penalty="trace",
multiclass=True)
for alpha in (1e-3, 1e-2, 0.1, 0.2, 0.3):
print "alpha=", alpha
clf.alpha = alpha
clf.fit(X_train, y_train)
print clf.score(X_test, y_test)
print rank(clf.coef_)