def test_fit_replicable():
n_features = 20
X, y = get_fake_data(100, n_features, RandomState(4))
m0 = get_new_model(n_features, RandomState(45))
m0 = binary_fit(m0, X, y)
m1 = get_new_model(n_features, RandomState(45))
m1 = binary_fit(m1, X, y)
assert_array_equal(m0.sgd_weights, m1.sgd_weights)
assert_array_equal(m0.sgd_bias, m1.sgd_bias)
def test_fit_replicable():
n_features = 20
X, y = get_fake_data(100, n_features, RandomState(4))
m0 = get_new_model(n_features, RandomState(45), 100)
m0 = binary_fit(m0, (X, y))
m1 = get_new_model(n_features, RandomState(45), 100)
m1 = binary_fit(m1, (X, y))
assert_array_equal(m0.sgd_weights, m1.sgd_weights)
assert_array_equal(m0.sgd_bias, m1.sgd_bias)
def test_binary_fit():
rstate = RandomState(42)
n_features = 20
for L in [100, DEFAULT_MAX_EXAMPLES, int(DEFAULT_MAX_EXAMPLES * 1.5),
int(DEFAULT_MAX_EXAMPLES * 3)]:
clf = get_new_model(n_features, rstate, L)
X, y = get_fake_data(L, n_features, rstate, separation=0.1)
best = find_sgd_step_size0(clf, (X, y))
_clf = binary_fit(clf, (X, y))
assert _clf is clf
assert 0 < clf.sgd_step_size0 <= best
def train_svm(Xyd, l2_regularization, max_observations):
"""
Return a sklearn-like classification model.
"""
train_X, train_y, decisions = Xyd
if train_X.ndim != 2:
raise ValueError('train_X must be matrix')
assert len(train_X) == len(train_y), (len(train_X), len(train_y))
assert len(train_X) == len(decisions), (len(train_X), len(decisions))
# doctor the decisions so that there is always something to learn
margin = train_y * decisions
margin_mean = margin.mean()
decisions = decisions - margin_mean * train_y
svm = MarginBinaryASGD(
n_features=train_X.shape[1],
l2_regularization=l2_regularization,
dtype=train_X.dtype,
rstate=np.random.RandomState(1234),
max_observations=max_observations,
)
binary_fit(svm, (train_X, train_y, np.asarray(decisions)))
return svm
def test_binary_fit():
rstate = RandomState(42)
n_features = 20
clf100 = get_new_model(n_features, rstate)
X, y = get_fake_data(100, n_features, rstate)
_clf100 = binary_fit(clf100, X, y)
assert _clf100 is clf100
assert_almost_equal(clf100.sgd_step_size0, 0.04812, decimal=4)
# smoke test
clf1000 = get_new_model(n_features, rstate)
X, y = get_fake_data(DEFAULT_MAX_EXAMPLES, n_features, rstate)
_clf1000 = binary_fit(clf1000, X, y)
assert _clf1000 is clf1000
assert_almost_equal(clf1000.sgd_step_size0, 0.0047, decimal=4)
# smoke test that at least it runs
clf2000 = get_new_model(n_features, rstate)
X, y = get_fake_data(2000, n_features, rstate)
_clf2000 = binary_fit(clf2000, X, y)
assert _clf2000 == clf2000
assert_almost_equal(clf2000.sgd_step_size0, 0.0067, decimal=4)
def test_binary_fit():
rstate = RandomState(42)
n_features = 20
clf100 = get_new_model(n_features, rstate)
X, y = get_fake_data(100, n_features, rstate)
_clf100 = binary_fit(clf100, X, y)
assert _clf100 is clf100
assert_almost_equal(clf100.sgd_step_size0, 0.04812, decimal=4)
# smoke test
clf1000 = get_new_model(n_features, rstate)
X, y = get_fake_data(DEFAULT_MAX_EXAMPLES, n_features, rstate)
_clf1000 = binary_fit(clf1000, X, y)
assert _clf1000 is clf1000
assert_almost_equal(clf1000.sgd_step_size0, 0.0047, decimal=4)
# smoke test that at least it runs
clf2000 = get_new_model(n_features, rstate)
X, y = get_fake_data(2000, n_features, rstate)
_clf2000 = binary_fit(clf2000, X, y)
assert _clf2000 == clf2000
assert_almost_equal(clf2000.sgd_step_size0, 0.0067, decimal=4)
