def test_predict_proba_multiclass():
# Test that predict_proba works as expected for multi class.
X = X_digits_multi[:10]
y = y_digits_multi[:10]
clf = MLPClassifier(hidden_layer_sizes=5)
with ignore_warnings(category=ConvergenceWarning):
clf.fit(X, y)
y_proba = clf.predict_proba(X)
y_log_proba = clf.predict_log_proba(X)
(n_samples, n_classes) = y.shape[0], np.unique(y).size
proba_max = y_proba.argmax(axis=1)
proba_log_max = y_log_proba.argmax(axis=1)
assert y_proba.shape == (n_samples, n_classes)
assert_array_equal(proba_max, proba_log_max)
assert_array_equal(y_log_proba, np.log(y_proba))
def test_predict_proba_multilabel():
# Test that predict_proba works as expected for multilabel.
# Multilabel should not use softmax which makes probabilities sum to 1
X, Y = make_multilabel_classification(n_samples=50,
random_state=0,
return_indicator=True)
n_samples, n_classes = Y.shape
clf = MLPClassifier(solver='lbfgs', hidden_layer_sizes=30, random_state=0)
clf.fit(X, Y)
y_proba = clf.predict_proba(X)
assert y_proba.shape == (n_samples, n_classes)
assert_array_equal(y_proba > 0.5, Y)
y_log_proba = clf.predict_log_proba(X)
proba_max = y_proba.argmax(axis=1)
proba_log_max = y_log_proba.argmax(axis=1)
assert (y_proba.sum(1) - 1).dot(y_proba.sum(1) - 1) > 1e-10
assert_array_equal(proba_max, proba_log_max)
assert_array_equal(y_log_proba, np.log(y_proba))
def test_predict_proba_binary():
# Test that predict_proba works as expected for binary class.
X = X_digits_binary[:50]
y = y_digits_binary[:50]
clf = MLPClassifier(hidden_layer_sizes=5,
activation='logistic',
random_state=1)
with ignore_warnings(category=ConvergenceWarning):
clf.fit(X, y)
y_proba = clf.predict_proba(X)
y_log_proba = clf.predict_log_proba(X)
(n_samples, n_classes) = y.shape[0], 2
proba_max = y_proba.argmax(axis=1)
proba_log_max = y_log_proba.argmax(axis=1)
assert y_proba.shape == (n_samples, n_classes)
assert_array_equal(proba_max, proba_log_max)
assert_array_equal(y_log_proba, np.log(y_proba))
assert roc_auc_score(y, y_proba[:, 1]) == 1.0
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)