def test_mixin_composition():
# Check composed expressions as parameters
a = theano.shared(0.0)
b = theano.shared(-1.0)
mu = a + b - 1.0
sigma = T.abs_(a * b)
p = Normal(mu=mu, sigma=sigma)
assert a in p.parameters_
assert b in p.parameters_
# Compose parameters with observed variables
a = theano.shared(1.0)
b = theano.shared(0.0)
y = T.dmatrix(name="y")
p = Normal(mu=a * y + b)
assert len(p.parameters_) == 3
assert a in p.parameters_
assert b in p.parameters_
assert p.sigma in p.parameters_
assert p.mu not in p.parameters_
assert len(p.observeds_) == 1
assert y in p.observeds_
# Check signatures
data_X = np.random.rand(10, 1)
data_y = np.random.rand(10, 1)
p.pdf(X=data_X, y=data_y)
p.cdf(X=data_X, y=data_y)
p.rvs(10, y=data_y)
# Check error
a = theano.shared(1.0)
b = theano.shared(0.0)
y = T.dmatrix() # y must be named
assert_raises(ValueError, Normal, mu=a * y + b)
def test_likelihood_free_mixture():
p1 = Normal(random_state=1)
p2 = Normal(mu=2.0, random_state=1)
h1 = Histogram(bins=50).fit(p1.rvs(10000))
h2 = Histogram(bins=50).fit(p2.rvs(10000))
m1 = Mixture(components=[p1, p2])
m2 = Mixture(components=[h1, h2])
# Check whether pdf, nnlf and cdf have been overriden
assert isinstance(m1.pdf, theano.compile.function_module.Function)
assert isinstance(m1.nnlf, theano.compile.function_module.Function)
assert isinstance(m1.cdf, theano.compile.function_module.Function)
assert isinstance(m2.pdf, types.MethodType)
assert isinstance(m2.nnlf, types.MethodType)
assert isinstance(m2.cdf, types.MethodType)
# Compare pdfs
rng = check_random_state(1)
X = rng.rand(100, 1) * 10 - 5
assert np.mean(np.abs(m1.pdf(X) - m2.pdf(X))) < 0.05
# Test sampling
X = m2.rvs(10)
assert X.shape == (10, 1)
# Check errors
assert_raises(NotImplementedError, m2.fit, X)
def check_classifier_ratio(clf, method, cv):
# Passing distributions directly
p0 = Normal(mu=0.0)
p1 = Normal(mu=0.1)
ratio = ClassifierRatio(CalibratedClassifierCV(base_estimator=clf,
method=method,
cv=cv))
ratio.fit(numerator=p0, denominator=p1, n_samples=10000)
reals = np.linspace(-1, 1, num=100).reshape(-1, 1)
assert ratio.score(reals, p0.pdf(reals) / p1.pdf(reals)) > -0.1
assert np.mean(np.abs(np.log(ratio.predict(reals)) -
ratio.predict(reals, log=True))) < 0.01
# Passing X, y only
X = np.vstack((p0.rvs(5000), p1.rvs(5000)))
y = np.zeros(10000, dtype=np.int)
y[5000:] = 1
ratio = ClassifierRatio(CalibratedClassifierCV(base_estimator=clf,
method=method,
cv=cv))
ratio.fit(X=X, y=y)
reals = np.linspace(-1, 1, num=100).reshape(-1, 1)
assert ratio.score(reals, p0.pdf(reals) / p1.pdf(reals)) > -0.1
assert np.mean(np.abs(np.log(ratio.predict(reals)) -
ratio.predict(reals, log=True))) < 0.01
def test_mixin_composition():
# Check composed expressions as parameters
a = theano.shared(0.0)
b = theano.shared(-1.0)
mu = a + b - 1.0
sigma = T.abs_(a * b)
p = Normal(mu=mu, sigma=sigma)
assert a in p.parameters_
assert b in p.parameters_
# Compose parameters with observed variables
a = theano.shared(1.0)
b = theano.shared(0.0)
y = T.dmatrix(name="y")
p = Normal(mu=a * y + b)
assert len(p.parameters_) == 3
assert a in p.parameters_
assert b in p.parameters_
assert p.sigma in p.parameters_
assert p.mu not in p.parameters_
assert len(p.observeds_) == 1
assert y in p.observeds_
# Check signatures
data_X = np.random.rand(10, 1)
data_y = np.random.rand(10, 1)
p.pdf(X=data_X, y=data_y)
p.cdf(X=data_X, y=data_y)
p.rvs(10, y=data_y)
# Check error
a = theano.shared(1.0)
b = theano.shared(0.0)
y = T.dmatrix() # y must be named
assert_raises(ValueError, Normal, mu=a * y + b)
def check_classifier_ratio(clf, method, cv):
# Passing distributions directly
p0 = Normal(mu=0.0)
p1 = Normal(mu=0.1)
ratio = ClassifierRatio(
CalibratedClassifierCV(base_estimator=clf, method=method, cv=cv))
ratio.fit(numerator=p0, denominator=p1, n_samples=10000)
reals = np.linspace(-1, 1, num=100).reshape(-1, 1)
assert ratio.score(reals, p0.pdf(reals) / p1.pdf(reals)) > -0.1
assert np.mean(
np.abs(np.log(ratio.predict(reals)) -
ratio.predict(reals, log=True))) < 0.01
# Passing X, y only
X = np.vstack((p0.rvs(5000), p1.rvs(5000)))
y = np.zeros(10000, dtype=np.int)
y[5000:] = 1
ratio = ClassifierRatio(
CalibratedClassifierCV(base_estimator=clf, method=method, cv=cv))
ratio.fit(X=X, y=y)
reals = np.linspace(-1, 1, num=100).reshape(-1, 1)
assert ratio.score(reals, p0.pdf(reals) / p1.pdf(reals)) > -0.1
assert np.mean(
np.abs(np.log(ratio.predict(reals)) -
ratio.predict(reals, log=True))) < 0.01
def test_likelihood_free_mixture():
p1 = Normal(random_state=1)
p2 = Normal(mu=2.0, random_state=1)
h1 = Histogram(bins=50).fit(p1.rvs(10000))
h2 = Histogram(bins=50).fit(p2.rvs(10000))
m1 = Mixture(components=[p1, p2])
m2 = Mixture(components=[h1, h2])
# Check whether pdf, nnlf and cdf have been overriden
assert isinstance(m1.pdf, theano.compile.function_module.Function)
assert isinstance(m1.nnlf, theano.compile.function_module.Function)
assert isinstance(m1.cdf, theano.compile.function_module.Function)
assert isinstance(m2.pdf, types.MethodType)
assert isinstance(m2.nnlf, types.MethodType)
assert isinstance(m2.cdf, types.MethodType)
# Compare pdfs
rng = check_random_state(1)
X = rng.rand(100, 1) * 10 - 5
assert np.mean(np.abs(m1.pdf(X) - m2.pdf(X))) < 0.05
# Test sampling
X = m2.rvs(10)
assert X.shape == (10, 1)
# Check errors
assert_raises(NotImplementedError, m2.fit, X)
def test_linear_transform_1d():
p0 = Normal()
pt = LinearTransform(p0, A=np.array([[0.5]]))
X0 = p0.rvs(10, random_state=0)
Xt = pt.rvs(10, random_state=0)
assert X0.shape == Xt.shape
assert_array_equal(X0 * 0.5, Xt)
assert_array_equal(p0.pdf(X0), pt.pdf(Xt))
assert_array_equal(p0.nll(X0), pt.nll(Xt))
def test_linear_transform_1d():
p0 = Normal()
pt = LinearTransform(p0, A=np.array([[0.5]]))
X0 = p0.rvs(10, random_state=0)
Xt = pt.rvs(10, random_state=0)
assert X0.shape == Xt.shape
assert_array_equal(X0 * 0.5, Xt)
assert_array_equal(p0.pdf(X0), pt.pdf(Xt))
assert_array_equal(p0.nll(X0), pt.nll(Xt))
def test_parameterized_regressor():
mu = theano.shared(0)
p = Normal(mu=mu)
X = p.rvs(100)
y = p.pdf(X).astype(np.float32)
tf = ParameterStacker(params=[mu])
clf = ParameterizedRegressor(DecisionTreeRegressor(), params=[mu])
clf.fit(tf.transform(X), y)
assert clf.n_features_ == 1
assert_array_almost_equal(y, clf.predict(tf.transform(X)), decimal=3)
def test_kde():
# Test API
p = Normal(random_state=1)
X = p.rvs(10000)
k = KernelDensity()
k.fit(X)
reals = np.linspace(-3, 3).reshape(-1, 1)
assert np.mean(np.abs(p.pdf(reals) - k.pdf(reals))) < 0.05
assert np.mean(np.abs(p.nnlf(reals) - k.nnlf(reals))) < 0.05
# Test sampling
X = k.rvs(10000)
assert np.abs(np.mean(X)) < 0.05
def test_parameter_stacker():
mu = theano.shared(0)
sigma = theano.shared(1)
p = Normal(mu=mu, sigma=sigma)
X = p.rvs(10)
tf = ParameterStacker(params=[mu, sigma])
Xt = tf.transform(X)
assert Xt.shape == (10, 1+2)
assert_array_almost_equal(Xt[:, 1], np.zeros(10))
assert_array_almost_equal(Xt[:, 2], np.ones(10))
mu.set_value(1)
Xt = tf.transform(X)
assert_array_almost_equal(Xt[:, 1], np.ones(10))
def check_rvs(mu, sigma, random_state):
p = Normal(mu=mu, sigma=sigma)
samples = p.rvs(10000, random_state=random_state)
assert np.abs(np.mean(samples) - mu) <= 0.05
assert np.abs(np.std(samples) - sigma) <= 0.05
def check_rvs(mu, sigma, random_state):
p = Normal(mu=mu, sigma=sigma)
samples = p.rvs(10000, random_state=random_state)
assert np.abs(np.mean(samples) - mu) <= 0.05
assert np.abs(np.std(samples) - sigma) <= 0.05
