def test_partial_fit_classification():
# Test partial_fit on classification.
# `partial_fit` should yield the same results as 'fit' for binary and
# multi-class classification.
for X, y in classification_datasets:
X = X
y = y
mlp = MLPClassifier(solver='sgd',
max_iter=100,
random_state=1,
tol=0,
alpha=1e-5,
learning_rate_init=0.2)
with ignore_warnings(category=ConvergenceWarning):
mlp.fit(X, y)
pred1 = mlp.predict(X)
mlp = MLPClassifier(solver='sgd',
random_state=1,
alpha=1e-5,
learning_rate_init=0.2)
for i in range(100):
mlp.partial_fit(X, y, classes=np.unique(y))
pred2 = mlp.predict(X)
assert_array_equal(pred1, pred2)
assert mlp.score(X, y) > 0.95
def test_partial_fit_classes_error():
# Tests that passing different classes to partial_fit raises an error
X = [[3, 2]]
y = [0]
clf = MLPClassifier(solver='sgd')
clf.partial_fit(X, y, classes=[0, 1])
assert_raises(ValueError, clf.partial_fit, X, y, classes=[1, 2])
def test_multilabel_classification():
# Test that multi-label classification works as expected.
# test fit method
X, y = make_multilabel_classification(n_samples=50,
random_state=0,
return_indicator=True)
mlp = MLPClassifier(solver='lbfgs',
hidden_layer_sizes=50,
alpha=1e-5,
max_iter=150,
random_state=0,
activation='logistic',
learning_rate_init=0.2)
mlp.fit(X, y)
assert mlp.score(X, y) > 0.97
# test partial fit method
mlp = MLPClassifier(solver='sgd',
hidden_layer_sizes=50,
max_iter=150,
random_state=0,
activation='logistic',
alpha=1e-5,
learning_rate_init=0.2)
for i in range(100):
mlp.partial_fit(X, y, classes=[0, 1, 2, 3, 4])
assert mlp.score(X, y) > 0.9
# Make sure early stopping still work now that spliting is stratified by
# default (it is disabled for multilabel classification)
mlp = MLPClassifier(early_stopping=True)
mlp.fit(X, y).predict(X)
def test_partial_fit_unseen_classes():
# Non regression test for bug 6994
# Tests for labeling errors in partial fit
clf = MLPClassifier(random_state=0)
clf.partial_fit([[1], [2], [3]], ["a", "b", "c"],
classes=["a", "b", "c", "d"])
clf.partial_fit([[4]], ["d"])
assert clf.score([[1], [2], [3], [4]], ["a", "b", "c", "d"]) > 0
def test_verbose_sgd():
# Test verbose.
X = [[3, 2], [1, 6]]
y = [1, 0]
clf = MLPClassifier(solver='sgd',
max_iter=2,
verbose=10,
hidden_layer_sizes=2)
old_stdout = sys.stdout
sys.stdout = output = StringIO()
with ignore_warnings(category=ConvergenceWarning):
clf.fit(X, y)
clf.partial_fit(X, y)
sys.stdout = old_stdout
assert 'Iteration' in output.getvalue()
def test_fit():
# Test that the algorithm solution is equal to a worked out example.
X = np.array([[0.6, 0.8, 0.7]])
y = np.array([0])
mlp = MLPClassifier(solver='sgd',
learning_rate_init=0.1,
alpha=0.1,
activation='logistic',
random_state=1,
max_iter=1,
hidden_layer_sizes=2,
momentum=0)
# set weights
mlp.coefs_ = [0] * 2
mlp.intercepts_ = [0] * 2
mlp.n_outputs_ = 1
mlp.coefs_[0] = np.array([[0.1, 0.2], [0.3, 0.1], [0.5, 0]])
mlp.coefs_[1] = np.array([[0.1], [0.2]])
mlp.intercepts_[0] = np.array([0.1, 0.1])
mlp.intercepts_[1] = np.array([1.0])
mlp._coef_grads = [] * 2
mlp._intercept_grads = [] * 2
# Initialize parameters
mlp.n_iter_ = 0
mlp.learning_rate_ = 0.1
# Compute the number of layers
mlp.n_layers_ = 3
# Pre-allocate gradient matrices
mlp._coef_grads = [0] * (mlp.n_layers_ - 1)
mlp._intercept_grads = [0] * (mlp.n_layers_ - 1)
mlp.out_activation_ = 'logistic'
mlp.t_ = 0
mlp.best_loss_ = np.inf
mlp.loss_curve_ = []
mlp._no_improvement_count = 0
mlp._intercept_velocity = [
np.zeros_like(intercepts) for intercepts in mlp.intercepts_
]
mlp._coef_velocity = [np.zeros_like(coefs) for coefs in mlp.coefs_]
mlp.partial_fit(X, y, classes=[0, 1])
# Manually worked out example
# h1 = g(X1 * W_i1 + b11) = g(0.6 * 0.1 + 0.8 * 0.3 + 0.7 * 0.5 + 0.1)
# = 0.679178699175393
# h2 = g(X2 * W_i2 + b12) = g(0.6 * 0.2 + 0.8 * 0.1 + 0.7 * 0 + 0.1)
# = 0.574442516811659
# o1 = g(h * W2 + b21) = g(0.679 * 0.1 + 0.574 * 0.2 + 1)
# = 0.7654329236196236
# d21 = -(0 - 0.765) = 0.765
# d11 = (1 - 0.679) * 0.679 * 0.765 * 0.1 = 0.01667
# d12 = (1 - 0.574) * 0.574 * 0.765 * 0.2 = 0.0374
# W1grad11 = X1 * d11 + alpha * W11 = 0.6 * 0.01667 + 0.1 * 0.1 = 0.0200
# W1grad11 = X1 * d12 + alpha * W12 = 0.6 * 0.0374 + 0.1 * 0.2 = 0.04244
# W1grad21 = X2 * d11 + alpha * W13 = 0.8 * 0.01667 + 0.1 * 0.3 = 0.043336
# W1grad22 = X2 * d12 + alpha * W14 = 0.8 * 0.0374 + 0.1 * 0.1 = 0.03992
# W1grad31 = X3 * d11 + alpha * W15 = 0.6 * 0.01667 + 0.1 * 0.5 = 0.060002
# W1grad32 = X3 * d12 + alpha * W16 = 0.6 * 0.0374 + 0.1 * 0 = 0.02244
# W2grad1 = h1 * d21 + alpha * W21 = 0.679 * 0.765 + 0.1 * 0.1 = 0.5294
# W2grad2 = h2 * d21 + alpha * W22 = 0.574 * 0.765 + 0.1 * 0.2 = 0.45911
# b1grad1 = d11 = 0.01667
# b1grad2 = d12 = 0.0374
# b2grad = d21 = 0.765
# W1 = W1 - eta * [W1grad11, .., W1grad32] = [[0.1, 0.2], [0.3, 0.1],
# [0.5, 0]] - 0.1 * [[0.0200, 0.04244], [0.043336, 0.03992],
# [0.060002, 0.02244]] = [[0.098, 0.195756], [0.2956664,
# 0.096008], [0.4939998, -0.002244]]
# W2 = W2 - eta * [W2grad1, W2grad2] = [[0.1], [0.2]] - 0.1 *
# [[0.5294], [0.45911]] = [[0.04706], [0.154089]]
# b1 = b1 - eta * [b1grad1, b1grad2] = 0.1 - 0.1 * [0.01667, 0.0374]
# = [0.098333, 0.09626]
# b2 = b2 - eta * b2grad = 1.0 - 0.1 * 0.765 = 0.9235
assert_almost_equal(mlp.coefs_[0],
np.array([[0.098, 0.195756], [0.2956664, 0.096008],
[0.4939998, -0.002244]]),
decimal=3)
assert_almost_equal(mlp.coefs_[1],
np.array([[0.04706], [0.154089]]),
decimal=3)
assert_almost_equal(mlp.intercepts_[0],
np.array([0.098333, 0.09626]),
decimal=3)
assert_almost_equal(mlp.intercepts_[1], np.array(0.9235), decimal=3)
# Testing output
# h1 = g(X1 * W_i1 + b11) = g(0.6 * 0.098 + 0.8 * 0.2956664 +
# 0.7 * 0.4939998 + 0.098333) = 0.677
# h2 = g(X2 * W_i2 + b12) = g(0.6 * 0.195756 + 0.8 * 0.096008 +
# 0.7 * -0.002244 + 0.09626) = 0.572
# o1 = h * W2 + b21 = 0.677 * 0.04706 +
# 0.572 * 0.154089 + 0.9235 = 1.043
# prob = sigmoid(o1) = 0.739
assert_almost_equal(mlp.predict_proba(X)[0, 1], 0.739, decimal=3)