def test_io_datagenerator_wy_unlabeled():
X = numpy.random.randn(500, 13)
w = numpy.abs(numpy.random.randn(500))
y = numpy.random.randint(5, size=500) - 1
data = DataGenerator(X, w, y)
X_ = numpy.concatenate([batch[0] for batch in data.unlabeled_batches()])
w_ = numpy.concatenate([batch[1] for batch in data.unlabeled_batches()])
assert_true(X.shape[0] > X_.shape[0])
assert_almost_equal(X[y == -1], X_)
assert_almost_equal(w[y == -1], w_)
def test_io_fit():
X = numpy.random.randn(100, 5) + 0.5
weights = numpy.abs(numpy.random.randn(100))
y = numpy.random.randint(2, size=100)
data_generator = DataGenerator(X, weights, y)
d1 = IndependentComponentsDistribution(
[NormalDistribution(0, 1) for i in range(5)])
d2 = IndependentComponentsDistribution(
[NormalDistribution(1, 1) for i in range(5)])
nb1 = NaiveBayes([d1, d2])
nb1.fit(X, y, weights)
d1 = IndependentComponentsDistribution(
[NormalDistribution(0, 1) for i in range(5)])
d2 = IndependentComponentsDistribution(
[NormalDistribution(1, 1) for i in range(5)])
nb2 = NaiveBayes([d1, d2])
nb2.fit(data_generator)
logp1 = nb1.log_probability(X)
logp2 = nb2.log_probability(X)
assert_array_almost_equal(logp1, logp2)
def test_io_predict_log_proba():
X2 = DataGenerator(X)
X3 = DataFrameGenerator(pandas.DataFrame(X))
y_hat1 = model.predict_log_proba(X)
y_hat2 = model.predict_log_proba(X2)
y_hat3 = model.predict_log_proba(X3)
assert_array_almost_equal(y_hat1, y_hat2)
assert_array_almost_equal(y_hat1, y_hat3)
def test_io_log_probability():
X2 = DataGenerator(X)
X3 = DataFrameGenerator(pandas.DataFrame(X))
logp1 = model.log_probability(X)
logp2 = model.log_probability(X2)
logp3 = model.log_probability(X3)
assert_array_almost_equal(logp1, logp2)
assert_array_almost_equal(logp1, logp3)
def test_numpy_predict_datagenerator():
obs = numpy.array([['A', None, 'B'], ['A', None, 'C'], ['A', 'B', 'C']])
X = DataGenerator(obs)
predictions = monty_network.predict(X)
assert_array_equal(predictions,
[['A', 'C', 'B'], ['A', 'B', 'C'], ['A', 'B', 'C']])
assert_array_equal(obs,
[['A', None, 'B'], ['A', None, 'C'], ['A', 'B', 'C']])
def test_io_log_probability(): X = numpy.random.randn(100, 5) + 0.5 X2 = DataGenerator(X) X3 = DataFrameGenerator(pandas.DataFrame(X)) d = MultivariateGaussianDistribution model = GeneralMixtureModel.from_samples(d, n_components=2, X=X) logp1 = model.log_probability(X) logp2 = model.log_probability(X2) logp3 = model.log_probability(X3) assert_array_almost_equal(logp1, logp2) assert_array_almost_equal(logp1, logp3)
def test_io_predict_log_proba(): X = numpy.random.randn(100, 5) + 0.5 X2 = DataGenerator(X) X3 = DataFrameGenerator(pandas.DataFrame(X)) d = MultivariateGaussianDistribution model = GeneralMixtureModel.from_samples(d, n_components=2, X=X) y_hat1 = model.predict_log_proba(X) y_hat2 = model.predict_log_proba(X2) y_hat3 = model.predict_log_proba(X3) assert_array_almost_equal(y_hat1, y_hat2) assert_array_almost_equal(y_hat1, y_hat3)
def test_io_from_samples():
X = numpy.random.randn(100, 5) + 0.5
weights = numpy.abs(numpy.random.randn(100))
y = numpy.random.randint(2, size=100)
data_generator = DataGenerator(X, weights, y)
d = MultivariateGaussianDistribution
bc1 = BayesClassifier.from_samples(d, X=X, y=y, weights=weights)
bc2 = BayesClassifier.from_samples(d, X=data_generator)
logp1 = bc1.log_probability(X)
logp2 = bc2.log_probability(X)
assert_array_almost_equal(logp1, logp2)
def test_io_from_samples():
X = numpy.random.randn(100, 5) + 0.5
weights = numpy.abs(numpy.random.randn(100))
y = numpy.random.randint(2, size=100)
data_generator = DataGenerator(X, weights, y)
d = NormalDistribution
nb1 = NaiveBayes.from_samples(d, X=X, weights=weights, y=y)
nb2 = NaiveBayes.from_samples(d, X=data_generator)
logp1 = nb1.log_probability(X)
logp2 = nb2.log_probability(X)
assert_array_almost_equal(logp1, logp2)
def test_io_from_samples_gmm(): X = numpy.random.randn(100, 5) + 0.5 weights = numpy.abs(numpy.random.randn(100)) data_generator = DataGenerator(X, weights) d = MultivariateGaussianDistribution gmm1 = GeneralMixtureModel.from_samples(d, n_components=2, X=X, weights=weights, max_iterations=5, init='first-k') gmm2 = GeneralMixtureModel.from_samples(d, n_components=2, X=data_generator, max_iterations=5, init='first-k') logp1 = gmm1.log_probability(X) logp2 = gmm2.log_probability(X) assert_array_almost_equal(logp1, logp2)
def setup_random_mixed():
numpy.random.seed(0)
global X
X = numpy.array([
numpy.random.choice([True, False], size=50),
numpy.random.choice(['A', 'B'], size=50),
numpy.random.choice(2, size=50)
], dtype=object).T.copy()
global weights
weights = numpy.abs(numpy.random.randn(50))
global data_generator
data_generator = DataGenerator(X, weights)
global model
model = BayesianNetwork.from_samples(X)
def test_io_fit(): X = numpy.random.randn(100, 5) + 0.5 weights = numpy.abs(numpy.random.randn(100)) data_generator = DataGenerator(X, weights) mu1 = numpy.array([0, 0, 0, 0, 0]) mu2 = numpy.array([1, 1, 1, 1, 1]) cov = numpy.eye(5) d1 = MultivariateGaussianDistribution(mu1, cov) d2 = MultivariateGaussianDistribution(mu2, cov) gmm1 = GeneralMixtureModel([d1, d2]) gmm1.fit(X, weights, max_iterations=5) d1 = MultivariateGaussianDistribution(mu1, cov) d2 = MultivariateGaussianDistribution(mu2, cov) gmm2 = GeneralMixtureModel([d1, d2]) gmm2.fit(data_generator, max_iterations=5) logp1 = gmm1.log_probability(X) logp2 = gmm2.log_probability(X) assert_array_almost_equal(logp1, logp2)
def test_io_fit():
X = numpy.random.randn(100, 5) + 0.5
weights = numpy.abs(numpy.random.randn(100))
y = numpy.random.randint(2, size=100)
data_generator = DataGenerator(X, weights, y)
mu1 = numpy.array([0, 0, 0, 0, 0])
mu2 = numpy.array([1, 1, 1, 1, 1])
cov = numpy.eye(5)
d1 = MultivariateGaussianDistribution(mu1, cov)
d2 = MultivariateGaussianDistribution(mu2, cov)
bc1 = BayesClassifier([d1, d2])
bc1.fit(X, y, weights)
d1 = MultivariateGaussianDistribution(mu1, cov)
d2 = MultivariateGaussianDistribution(mu2, cov)
bc2 = BayesClassifier([d1, d2])
bc2.fit(data_generator)
logp1 = bc1.log_probability(X)
logp2 = bc2.log_probability(X)
assert_array_almost_equal(logp1, logp2)
def test_io_datagenerator_y_batches():
X = numpy.random.randn(500, 13)
w = numpy.abs(numpy.random.randn(500))
y = numpy.random.randint(5, size=500)
data = DataGenerator(X, y=y)
y_ = numpy.concatenate([batch[1] for batch in data.batches()])
assert_almost_equal(y, y_)
data = DataGenerator(X, y=y, batch_size=123)
y_ = numpy.concatenate([batch[1] for batch in data.batches()])
assert_almost_equal(y, y_)
data = DataGenerator(X, y=y, batch_size=1)
y_ = numpy.concatenate([batch[1] for batch in data.batches()])
assert_almost_equal(y, y_)
data = DataGenerator(X, y=y, batch_size=506)
y_ = numpy.concatenate([batch[1] for batch in data.batches()])
assert_almost_equal(y, y_)
def test_io_datagenerator_w_batches():
X = numpy.random.randn(500, 13)
w = numpy.abs(numpy.random.randn(500))
data = DataGenerator(X, w)
w_ = numpy.concatenate([batch[1] for batch in data.batches()])
assert_almost_equal(w, w_)
data = DataGenerator(X, w, batch_size=123)
w_ = numpy.concatenate([batch[1] for batch in data.batches()])
assert_almost_equal(w, w_)
data = DataGenerator(X, w, batch_size=1)
w_ = numpy.concatenate([batch[1] for batch in data.batches()])
assert_almost_equal(w, w_)
data = DataGenerator(X, w, batch_size=506)
w_ = numpy.concatenate([batch[1] for batch in data.batches()])
assert_almost_equal(w, w_)
def test_io_datagenerator_x_batches():
X = numpy.random.randn(500, 13)
w = numpy.ones(500)
data = DataGenerator(X)
X_ = numpy.concatenate([batch[0] for batch in data.batches()])
w_ = numpy.concatenate([batch[1] for batch in data.batches()])
assert_almost_equal(X, X_)
assert_almost_equal(w, w_)
data = DataGenerator(X, batch_size=123)
X_ = numpy.concatenate([batch[0] for batch in data.batches()])
w_ = numpy.concatenate([batch[1] for batch in data.batches()])
assert_almost_equal(X, X_)
assert_almost_equal(w, w_)
data = DataGenerator(X, batch_size=1)
X_ = numpy.concatenate([batch[0] for batch in data.batches()])
w_ = numpy.concatenate([batch[1] for batch in data.batches()])
assert_almost_equal(X, X_)
assert_almost_equal(w, w_)
data = DataGenerator(X, batch_size=506)
X_ = numpy.concatenate([batch[0] for batch in data.batches()])
w_ = numpy.concatenate([batch[1] for batch in data.batches()])
assert_almost_equal(X, X_)
assert_almost_equal(w, w_)
def test_io_datagenerator_classes():
X = numpy.random.randn(500, 13)
y = numpy.random.randint(5, size=500)
data = DataGenerator(X, y=y)
assert_array_equal(data.classes, [0, 1, 2, 3, 4])
def test_io_datagenerator_classes_fail():
X = numpy.random.randn(500, 13)
data = DataGenerator(X)
assert_raises(ValueError, lambda data: data.classes, data)
def test_io_datagenerator_shape():
X = numpy.random.randn(500, 13)
data = DataGenerator(X)
assert_array_equal(data.shape, X.shape)
