def test_small_sparse_partial_fit():
for sparse in [csc_matrix, csr_matrix]:
X_sparse = sparse(Xdigits[:100])
X = Xdigits[:100].copy()
rbm1 = BernoulliRBM(n_components=64, learning_rate=0.1,
batch_size=10, random_state=9)
rbm2 = BernoulliRBM(n_components=64, learning_rate=0.1,
batch_size=10, random_state=9)
rbm1.partial_fit(X_sparse)
rbm2.partial_fit(X)
assert_almost_equal(rbm1.score_samples(X).mean(),
rbm2.score_samples(X).mean(),
decimal=0)
def test_fit():
X = Xdigits.copy()
rbm = BernoulliRBM(n_components=64, learning_rate=0.1,
batch_size=10, n_iter=7, random_state=9)
rbm.fit(X)
print rbm.get_components()
assert_almost_equal(rbm.score_samples(X).mean(), -21., decimal=0)
# in-place tricks shouldn't have modified X
assert_array_equal(X, Xdigits)
def test_score_samples():
"""Test score_samples (pseudo-likelihood) method."""
# Assert that pseudo-likelihood is computed without clipping.
# See Fabian's blog, http://bit.ly/1iYefRk
rng = np.random.RandomState(42)
X = np.vstack([np.zeros(1000), np.ones(1000)])
rbm1 = BernoulliRBM(n_components=10, batch_size=2,
n_iter=10, random_state=rng)
rbm1.fit(X)
assert_true((rbm1.score_samples(X) < -300).all())
# Sparse vs. dense should not affect the output. Also test sparse input
# validation.
rbm1.random_state = 42
d_score = rbm1.score_samples(X)
rbm1.random_state = 42
s_score = rbm1.score_samples(lil_matrix(X))
assert_almost_equal(d_score, s_score)
# Test numerical stability (#2785): would previously generate infinities
# and crash with an exception.
with np.errstate(under='ignore'):
rbm1.score_samples(np.arange(1000) * 100)
def test_partial_fit():
X = Xdigits.copy()
n = 7
rbm = BernoulliRBM(n_components=64, learning_rate=0.1,
batch_size=10, random_state=9)
n_samples = X.shape[0]
n_batches = int(np.ceil(float(n_samples) / rbm.batch_size))
batch_slices = np.array_split(X, n_batches)
for i in range(n):
for batch in batch_slices:
rbm.partial_fit(batch)
assert_almost_equal(rbm.score_samples(X).mean(), -21., decimal=0)
assert_array_equal(X, Xdigits)