def test_io_seqgenerator_w_batches():
X = [numpy.random.randn(15, 8) for i in range(500)]
w = numpy.abs(numpy.random.randn(500))
data = SequenceGenerator(X, w)
w_ = numpy.concatenate([batch[1] for batch in data.batches()])
assert_almost_equal(w, w_)
def test_io_seqgenerator_wy_labeled():
X = [numpy.random.randn(15, 8) for i in range(500)]
y = [numpy.random.randint(6, size=15) for i in range(500)]
w = numpy.abs(numpy.random.randn(500))
idx = numpy.random.choice(500, size=100, replace=False)
for i in idx:
y[i] = None
data = SequenceGenerator(X, w, y)
X_ = numpy.concatenate([batch[0] for batch in data.labeled_batches()])
w_ = numpy.concatenate([batch[1] for batch in data.labeled_batches()])
y_ = numpy.concatenate([batch[2] for batch in data.labeled_batches()])
assert_true(len(X) > len(X_))
assert_true(len(w) > len(w_))
assert_true(len(y) > len(y_))
i = 0
for j in range(500):
if y[j] is not None:
assert_almost_equal(X[j], X_[i])
assert_almost_equal(w[j], w_[i])
assert_almost_equal(y[j], y_[i])
i += 1
def test_io_seqgenerator_w_symbol_batches():
X = [[numpy.random.choice(["A", "C", "G", "T"]) for i in range(18)]
for i in range(500)]
w = numpy.abs(numpy.random.randn(500))
data = SequenceGenerator(X, w)
w_ = numpy.concatenate([batch[1] for batch in data.batches()])
assert_almost_equal(w, w_)
def test_io_seqgenerator_y_batches():
X = [numpy.random.randn(15, 8) for i in range(500)]
y = [numpy.random.randint(6, size=15) for i in range(500)]
data = SequenceGenerator(X, y=y)
X_ = numpy.concatenate([batch[0] for batch in data.batches()])
y_ = numpy.concatenate([batch[2] for batch in data.batches()])
assert_array_equal(X, X_)
assert_almost_equal(y, y_)
def test_io_seqgenerator_y_symbol_batches():
X = [[numpy.random.choice(["A", "C", "G", "T"]) for i in range(18)]
for i in range(500)]
y = [numpy.random.randint(6, size=15) for i in range(500)]
data = SequenceGenerator(X, y=y)
X_ = numpy.concatenate([batch[0] for batch in data.batches()])
y_ = numpy.concatenate([batch[2] for batch in data.batches()])
assert_array_equal(X, X_)
assert_almost_equal(y, y_)
def test_io_seqgenerator_x_symbol_batches():
X = [[numpy.random.choice(["A", "C", "G", "T"]) for i in range(18)]
for i in range(500)]
w = numpy.ones(500)
data = SequenceGenerator(X)
X_ = numpy.concatenate([batch[0] for batch in data.batches()])
w_ = numpy.concatenate([batch[1] for batch in data.batches()])
assert_array_equal(X, X_)
assert_almost_equal(w, w_)
def test_io_seqgenerator_wy_batches():
X = [numpy.random.randn(15, 8) for i in range(500)]
y = [numpy.random.randint(6, size=15) for i in range(500)]
w = numpy.abs(numpy.random.randn(500))
data = SequenceGenerator(X, w, y)
X_ = numpy.concatenate([batch[0] for batch in data.batches()])
w_ = numpy.concatenate([batch[1] for batch in data.batches()])
y_ = numpy.concatenate([batch[2] for batch in data.batches()])
assert_almost_equal(X, X_)
assert_almost_equal(w, w_)
assert_almost_equal(y, y_)
def test_io_seqgenerator_wy_symbol_unlabeled():
X = [[numpy.random.choice(["A", "C", "G", "T"]) for i in range(18)]
for i in range(500)]
y = [numpy.random.randint(6, size=15) for i in range(500)]
w = numpy.abs(numpy.random.randn(500))
idx = numpy.random.choice(500, size=100, replace=False)
for i in idx:
y[i] = None
data = SequenceGenerator(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(len(X) > len(X_))
assert_true(len(w) > len(w_))
i = 0
for j in range(500):
if y[j] is None:
assert_array_equal(X[j], X_[i])
assert_almost_equal(w[j], w_[i])
i += 1
def test_io_seqgenerator_shape():
X = [numpy.random.randn(15, 8) for i in range(500)]
data = SequenceGenerator(X)
assert_array_equal(data.shape, (len(X), 8))
def test_io_seqgenerator_symbol_shape():
X = [[numpy.random.choice(['A', 'C', 'G', 'T']) for j in range(15)]
for i in range(500)]
data = SequenceGenerator(X)
assert_array_equal(data.shape, (len(X), 1))
def _initDists(self, X, distribution=MultivariateGaussianDistribution):
technique = "R_MV-GMM" # mixture of multivariate gaussain distribution
if (technique == "GMM"):
# gaussian mixture model
#// uvgd = NormalDistribution.from_samples(X)
#// gmm = GeneralMixtureModel([uvgd.copy() for _ in range(self.nmix)])
gmm = GeneralMixtureModel.from_samples(
distributions=[NormalDistribution for _ in range(self.nmix)],
X=X)
dists = [gmm.copy() for _ in range(self.statesNumber)]
elif (technique == "MV-GMM"):
# multivariate gaussian mixture model
#// mvgd = MultivariateGaussianDistribution.from_samples(X)
#// gmm = GeneralMixtureModel([mvgd.copy() for _ in range(self.nmix)])
gmm = GeneralMixtureModel.from_samples(distributions=[
MultivariateGaussianDistribution for _ in range(self.nmix)
],
X=X,
n_components=3)
dists = [gmm.copy() for _ in range(self.statesNumber)]
elif (technique == "MVG"):
self._initkmeans(X=X, numClasses=self.statesNumber)
dists = [
MultivariateGaussianDistribution.from_samples(X=X[y == i])
for i in range(self.statesNumber)
]
elif (technique == "R_GMM"):
# random gaussian mixture model
randNormal = lambda: NormalDistribution(np.random.randint(1, 10), 1
)
randGMM = lambda: GeneralMixtureModel(
[randNormal() for _ in range(self.nmix)])
dists = [randGMM() for _ in range(self.statesNumber)]
elif (technique == "R_MV-GMM"):
# random multivariate gaussian mixture model
randGMM = lambda: GeneralMixtureModel(
[randMVG() for _ in range(self.nmix)])
dists = [randGMM() for _ in range(self.statesNumber)]
return dists
#* not completed:
#! GMM-HMM-k
y = self._initkmeans(X, self.statesNumber)
# list(map(print, y))
return [
GeneralMixtureModel.from_samples(distribution,
X=X[y == i],
n_components=self.nmix)
for i in range(self.statesNumber)
]
#! Kmeans init
if not isinstance(X, BaseGenerator):
data_generator = SequenceGenerator(X, None, None)
else:
data_generator = X
initialization_batch_size = len(data_generator)
X_ = []
data = data_generator.batches()
for i in range(initialization_batch_size):
batch = next(data)
X_.extend(batch[0])
X_concat = np.concatenate(X_)
if X_concat.ndim == 1:
X_concat = X_concat.reshape(X_concat.shape[0], 1)
n, d = X_concat.shape
clf = Kmeans(self.statesNumber, init="kmeans++",
n_init=1) # init should be one of
clf.fit(X_concat, max_iterations=None, batches_per_epoch=None)
y = clf.predict(X_concat)
if callable(distribution):
if d == 1:
dists = [
distribution.from_samples(X_concat[y == i][:, 0])
for i in range(self.statesNumber)
]
elif distribution.blank().d > 1:
dists = [
distribution.from_samples(X_concat[y == i])
for i in range(self.statesNumber)
]
else:
print("error")
return dists