def test_histogram_2d():
X = np.arange(100).reshape(-1, 2)
h = Histogram(bins=[5, 3])
h.fit(X)
assert h.ndim == 2
assert h.histogram_.shape[0] == 5 + 2
assert h.histogram_.shape[1] == 3 + 2
def test_histogram_2d():
X = np.arange(100).reshape(-1, 2)
h = Histogram(bins=[5, 3], random_state=1)
h.fit(X)
assert h.ndim == 2
assert h.histogram_.shape[0] == 5 + 2
assert h.histogram_.shape[1] == 3 + 2
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_histogram_sample_weight():
X = np.arange(11).reshape(-1, 1)
w = np.ones(len(X)) / len(X)
h1 = Histogram(bins=11)
h1.fit(X)
h2 = Histogram(bins=11)
h2.fit(X, sample_weight=w)
assert_array_almost_equal(h1.pdf([[0.0], [1.0], [10.0], [-0.5], [10.5]]),
h2.pdf([[0.0], [1.0], [10.0], [-0.5], [10.5]]))
assert_raises(ValueError, h1.fit, X, sample_weight=w[1:])
def test_histogram_variable_width():
X = np.arange(11).reshape(-1, 1)
h = Histogram(bins=11, variable_width=True)
h.fit(X)
assert_array_almost_equal(h.pdf([[1.0], [2.0], [8.0]]), [0.1, 0.1, 0.1])
h = Histogram(bins=3, variable_width=True)
h.fit(X)
integral = h.histogram_ * (h.edges_[0][1:] - h.edges_[0][:-1])
integral = integral[1:-1].sum()
assert_almost_equal(integral, 1.)
def test_histogram_sample_weight():
X = np.arange(11).reshape(-1, 1)
w = np.ones(len(X)) / len(X)
h1 = Histogram(bins=11)
h1.fit(X)
h2 = Histogram(bins=11)
h2.fit(X, sample_weight=w)
assert_array_almost_equal(
h1.pdf([[0.0], [1.0], [10.0], [-0.5], [10.5]]), h2.pdf([[0.0], [1.0], [10.0], [-0.5], [10.5]])
)
assert_raises(ValueError, h1.fit, X, sample_weight=w[1:])
def test_join_non_theano():
h0 = Histogram(interpolation="linear", bins=30)
h1 = Histogram(interpolation="linear", bins=30)
h2 = Histogram(interpolation="linear", bins=30)
h0.fit(Normal(mu=0).rvs(10000, random_state=0))
h1.fit(Normal(mu=1).rvs(10000, random_state=1))
h2.fit(Normal(mu=2).rvs(10000, random_state=2))
p = Join(components=[h0, h1, h2])
assert p.ndim == 3
assert len(p.parameters_) == 0
X = p.rvs(10000, random_state=1)
assert X.shape == (10000, 3)
assert np.abs(np.mean(X[:, 0]) - 0.) < 0.05
assert np.abs(np.mean(X[:, 1]) - 1.) < 0.05
assert np.abs(np.mean(X[:, 2]) - 2.) < 0.05
assert_array_almost_equal(-np.log(p.pdf(X)), p.nll(X))
def test_histogram():
X = np.arange(11).reshape(-1, 1)
h = Histogram(bins=11)
h.fit(X)
assert_array_almost_equal(h.pdf([[0.0], [1.0], [10.0], [-0.5], [10.5]]),
[0.1, 0.1, 0.1, 0., 0.])
assert_array_almost_equal(
h.nll([[0.0], [1.0], [10.0], [-0.5], [10.5]]),
-np.log(h.pdf([[0.0], [1.0], [10.0], [-0.5], [10.5]])))
X = h.rvs(10000, random_state=1)
assert np.abs(np.mean(X) - 5.0) < 0.05
assert X.min() >= 0.0
assert X.max() <= 10.0
def test_histogram():
X = np.arange(11).reshape(-1, 1)
h = Histogram(bins=11, random_state=1)
h.fit(X)
assert_array_almost_equal(h.pdf([[0.0], [1.0], [10.0], [-0.5], [10.5]]), [0.1, 0.1, 0.1, 0.0, 0.0])
assert_array_almost_equal(
h.nnlf([[0.0], [1.0], [10.0], [-0.5], [10.5]]), -np.log(h.pdf([[0.0], [1.0], [10.0], [-0.5], [10.5]]))
)
X = h.rvs(10000)
assert np.abs(np.mean(X) - 5.0) < 0.05
assert X.min() >= 0.0
assert X.max() <= 10.0
def test_join_non_theano():
h0 = Histogram(interpolation="linear", bins=30)
h1 = Histogram(interpolation="linear", bins=30)
h2 = Histogram(interpolation="linear", bins=30)
h0.fit(Normal(mu=0).rvs(10000, random_state=0))
h1.fit(Normal(mu=1).rvs(10000, random_state=1))
h2.fit(Normal(mu=2).rvs(10000, random_state=2))
p = Join(components=[h0, h1, h2])
assert p.ndim == 3
assert len(p.parameters_) == 0
X = p.rvs(10000, random_state=1)
assert X.shape == (10000, 3)
assert np.abs(np.mean(X[:, 0]) - 0.) < 0.05
assert np.abs(np.mean(X[:, 1]) - 1.) < 0.05
assert np.abs(np.mean(X[:, 2]) - 2.) < 0.05
assert_array_almost_equal(-np.log(p.pdf(X)), p.nll(X))
