def test_regularisation():
# We train the GaussianMixture on degenerate data by defining two clusters
# of a 0 covariance.
rng = np.random.RandomState(0)
n_samples, n_features = 10, 5
X = np.vstack((np.ones(
(n_samples // 2, n_features)), np.zeros((n_samples // 2, n_features))))
for covar_type in COVARIANCE_TYPE:
gmm = GaussianMixture(n_components=n_samples,
reg_covar=0,
covariance_type=covar_type,
random_state=rng)
with warnings.catch_warnings():
warnings.simplefilter("ignore", RuntimeWarning)
assert_raise_message(
ValueError, "Fitting the mixture model failed because "
"some components have ill-defined empirical "
"covariance (for instance caused by "
"singleton or collapsed samples). Try to "
"decrease the number of components, or "
"increase reg_covar.", gmm.fit, X)
gmm.set_params(reg_covar=1e-6).fit(X)
def test_gaussian_mixture_fit_predict_n_init():
# Check that fit_predict is equivalent to fit.predict, when n_init > 1
X = np.random.RandomState(0).randn(1000, 5)
gm = GaussianMixture(n_components=5, n_init=5, random_state=0)
y_pred1 = gm.fit_predict(X)
y_pred2 = gm.predict(X)
assert_array_equal(y_pred1, y_pred2)
def test_gaussian_mixture_fit_predict_n_init():
# Check that fit_predict is equivalent to fit.predict, when n_init > 1
X = np.random.RandomState(0).randn(1000, 5)
gm = GaussianMixture(n_components=5, n_init=5, random_state=0)
y_pred1 = gm.fit_predict(X)
y_pred2 = gm.predict(X)
assert_array_equal(y_pred1, y_pred2)
def test_monotonic_likelihood():
# We check that each step of the EM without regularization improve
# monotonically the training set likelihood
rng = np.random.RandomState(0)
rand_data = RandomData(rng, scale=7)
n_components = rand_data.n_components
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
gmm = GaussianMixture(n_components=n_components,
covariance_type=covar_type, reg_covar=0,
warm_start=True, max_iter=1, random_state=rng,
tol=1e-7)
current_log_likelihood = -np.infty
with warnings.catch_warnings():
warnings.simplefilter("ignore", ConvergenceWarning)
# Do one training iteration at a time so we can make sure that the
# training log likelihood increases after each iteration.
for _ in range(600):
prev_log_likelihood = current_log_likelihood
try:
current_log_likelihood = gmm.fit(X).score(X)
except ConvergenceWarning:
pass
assert_greater_equal(current_log_likelihood,
prev_log_likelihood)
if gmm.converged_:
break
assert gmm.converged_
def test_score():
covar_type = 'full'
rng = np.random.RandomState(0)
rand_data = RandomData(rng, scale=7)
n_components = rand_data.n_components
X = rand_data.X[covar_type]
# Check the error message if we don't call fit
gmm1 = GaussianMixture(n_components=n_components,
n_init=1,
max_iter=1,
reg_covar=0,
random_state=rng,
covariance_type=covar_type)
assert_raise_message(
NotFittedError, "This GaussianMixture instance is not fitted "
"yet. Call 'fit' with appropriate arguments "
"before using this method.", gmm1.score, X)
# Check score value
with warnings.catch_warnings():
warnings.simplefilter("ignore", ConvergenceWarning)
gmm1.fit(X)
gmm_score = gmm1.score(X)
gmm_score_proba = gmm1.score_samples(X).mean()
assert_almost_equal(gmm_score, gmm_score_proba)
# Check if the score increase
gmm2 = GaussianMixture(n_components=n_components,
n_init=1,
reg_covar=0,
random_state=rng,
covariance_type=covar_type).fit(X)
assert_greater(gmm2.score(X), gmm1.score(X))
def create_mask(img, background_probability=0.75, use_triangle=False, use_otsu=False):
test_mask = None
if use_triangle:
test_mask = sitk.GetArrayFromImage(sitk.TriangleThreshold(img, 0, 1))
elif use_otsu:
test_mask = sitk.GetArrayFromImage(sitk.OtsuThreshold(img, 0, 1))
else:
if type(img) is sitk.SimpleITK.Image:
img = sitk.GetArrayFromImage(img)
gmix = GaussianMixture(n_components=3, covariance_type='full', init_params='kmeans', verbose=0)
gmix.fit(img.ravel().reshape(-1, 1))
covariances = gmix.covariances_
mean_background = gmix.means_.min()
covariance_background = covariances[np.where( gmix.means_ == mean_background ) ][0][0]
z_score = st.norm.ppf(background_probability)
threshold = z_score * np.sqrt(covariance_background) + mean_background
test_mask = (img > threshold)
eroded_im = morphology.opening(test_mask, selem=morphology.ball(2))
connected_comp = skimage.measure.label(eroded_im)
out = skimage.measure.regionprops(connected_comp)
area_max = 0.0
idx_max = 0
for i in range(len(out)):
if out[i].area > area_max:
area_max = out[i].area
idx_max = i+1
connected_comp[ connected_comp != idx_max ] = 0
mask = connected_comp
mask_sitk = sitk.GetImageFromArray(mask)
mask_sitk.CopyInformation(img)
return mask_sitk
def test_gaussian_mixture_estimate_log_prob_resp():
# test whether responsibilities are normalized
rng = np.random.RandomState(0)
rand_data = RandomData(rng, scale=5)
n_samples = rand_data.n_samples
n_features = rand_data.n_features
n_components = rand_data.n_components
X = rng.rand(n_samples, n_features)
for covar_type in COVARIANCE_TYPE:
weights = rand_data.weights
means = rand_data.means
precisions = rand_data.precisions[covar_type]
g = GaussianMixture(n_components=n_components,
random_state=rng,
weights_init=weights,
means_init=means,
precisions_init=precisions,
covariance_type=covar_type)
g.fit(X)
resp = g.predict_proba(X)
assert_array_almost_equal(resp.sum(axis=1), np.ones(n_samples))
assert_array_equal(g.weights_init, weights)
assert_array_equal(g.means_init, means)
assert_array_equal(g.precisions_init, precisions)
def test_monotonic_likelihood():
# We check that each step of the EM without regularization improve
# monotonically the training set likelihood
rng = np.random.RandomState(0)
rand_data = RandomData(rng, scale=7)
n_components = rand_data.n_components
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
gmm = GaussianMixture(n_components=n_components,
covariance_type=covar_type,
reg_covar=0,
warm_start=True,
max_iter=1,
random_state=rng,
tol=1e-7)
current_log_likelihood = -np.infty
with warnings.catch_warnings():
warnings.simplefilter("ignore", ConvergenceWarning)
# Do one training iteration at a time so we can make sure that the
# training log likelihood increases after each iteration.
for _ in range(600):
prev_log_likelihood = current_log_likelihood
try:
current_log_likelihood = gmm.fit(X).score(X)
except ConvergenceWarning:
pass
assert_greater_equal(current_log_likelihood,
prev_log_likelihood)
if gmm.converged_:
break
assert_true(gmm.converged_)
def macro_clusters(self, n_clusters, max_iters=1000, **kwargs):
data = np.concatenate([
m.sample(np.int32(np.ceil(m.n / 100))) for m in self.micro_clusters
])
gmm = GaussianMixture(n_components=n_clusters)
gmm.fit(data)
self.macro_centroids = gmm.means_
self.gmm_model = gmm
def test_gaussian_mixture_fit():
# recover the ground truth
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
n_features = rand_data.n_features
n_components = rand_data.n_components
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
g = GaussianMixture(n_components=n_components,
n_init=20,
reg_covar=0,
random_state=rng,
covariance_type=covar_type)
g.fit(X)
# needs more data to pass the test with rtol=1e-7
assert_allclose(np.sort(g.weights_),
np.sort(rand_data.weights),
rtol=0.1,
atol=1e-2)
arg_idx1 = g.means_[:, 0].argsort()
arg_idx2 = rand_data.means[:, 0].argsort()
assert_allclose(g.means_[arg_idx1],
rand_data.means[arg_idx2],
rtol=0.1,
atol=1e-2)
if covar_type == 'full':
prec_pred = g.precisions_
prec_test = rand_data.precisions['full']
elif covar_type == 'tied':
prec_pred = np.array([g.precisions_] * n_components)
prec_test = np.array([rand_data.precisions['tied']] * n_components)
elif covar_type == 'spherical':
prec_pred = np.array(
[np.eye(n_features) * c for c in g.precisions_])
prec_test = np.array([
np.eye(n_features) * c
for c in rand_data.precisions['spherical']
])
elif covar_type == 'diag':
prec_pred = np.array([np.diag(d) for d in g.precisions_])
prec_test = np.array(
[np.diag(d) for d in rand_data.precisions['diag']])
arg_idx1 = np.trace(prec_pred, axis1=1, axis2=2).argsort()
arg_idx2 = np.trace(prec_test, axis1=1, axis2=2).argsort()
for k, h in zip(arg_idx1, arg_idx2):
ecov = EmpiricalCovariance()
ecov.covariance_ = prec_test[h]
# the accuracy depends on the number of data and randomness, rng
assert_allclose(ecov.error_norm(prec_pred[k]), 0, atol=0.1)
def test_gaussian_mixture_n_parameters():
# Test that the right number of parameters is estimated
rng = np.random.RandomState(0)
n_samples, n_features, n_components = 50, 5, 2
X = rng.randn(n_samples, n_features)
n_params = {'spherical': 13, 'diag': 21, 'tied': 26, 'full': 41}
for cv_type in COVARIANCE_TYPE:
g = GaussianMixture(
n_components=n_components, covariance_type=cv_type,
random_state=rng).fit(X)
assert_equal(g._n_parameters(), n_params[cv_type])
def main():
#Import data from file
trainData, trainLabel = importTrainData()
testData, testLabel = importTestData()
#PCA procedure
#For train data
rawlowDivTrainData = []
pca = PCA(n_components=537)
#pca = PCA(n_components=537, whiten="True")
rawlowDivTrainData = pca.fit_transform(trainData)
#For test data which sum up to 10000
lowDivTestData = pca.fit_transform(testData)
#Classify manually, divide the data into 10 parts by labels
numTrainData = [[], [], [], [], [], [], [], [], [], []]
for i in range(60000):
numTrainData[trainLabel[i]].append(rawlowDivTrainData[i])
#Train Gmm for every mode/Each mode represent a number.
myGmms = []
#GMM procedure
for num in range(10):
print("GMM", num)
gmmClassifier = GaussianMixture(n_components=25,
init_params='kmeans',
max_iter=1000)
gmmClassifier.fit(numTrainData[num])
myGmms.append(gmmClassifier)
#Validate
# We need to calculate all the total probability under each GMM, and choose the biggest one.
correctCount = 0
allProb = []
for num in range(10):
allProb.append(np.array(myGmms[num].score_samples(lowDivTestData)))
allProb = np.array(allProb)
#If the result seem strange, print the predict label
for i in range(10000):
predictLabel = 0
max = np.max(allProb[:, i])
for num in range(10):
if max == allProb[num, i]:
predictLabel = num
if predictLabel == testLabel[i]:
correctCount += 1
#Output
print("The correct rate is:", correctCount / 10000)
def test_gaussian_mixture_n_parameters():
# Test that the right number of parameters is estimated
rng = np.random.RandomState(0)
n_samples, n_features, n_components = 50, 5, 2
X = rng.randn(n_samples, n_features)
n_params = {'spherical': 13, 'diag': 21, 'tied': 26, 'full': 41}
for cv_type in COVARIANCE_TYPE:
g = GaussianMixture(n_components=n_components,
covariance_type=cv_type,
random_state=rng).fit(X)
assert_equal(g._n_parameters(), n_params[cv_type])
def test_init():
# We check that by increasing the n_init number we have a better solution
for random_state in range(25):
rand_data = RandomData(np.random.RandomState(random_state), scale=1)
n_components = rand_data.n_components
X = rand_data.X['full']
gmm1 = GaussianMixture(n_components=n_components, n_init=1,
max_iter=1, random_state=random_state).fit(X)
gmm2 = GaussianMixture(n_components=n_components, n_init=10,
max_iter=1, random_state=random_state).fit(X)
assert gmm2.lower_bound_ >= gmm1.lower_bound_
def test_multiple_init():
# Test that multiple inits does not much worse than a single one
rng = np.random.RandomState(0)
n_samples, n_features, n_components = 50, 5, 2
X = rng.randn(n_samples, n_features)
for cv_type in COVARIANCE_TYPE:
train1 = GaussianMixture(n_components=n_components,
covariance_type=cv_type,
random_state=rng).fit(X).score(X)
train2 = GaussianMixture(n_components=n_components,
covariance_type=cv_type,
random_state=rng, n_init=5).fit(X).score(X)
assert_greater_equal(train2, train1)
def test_score():
covar_type = 'full'
rng = np.random.RandomState(0)
rand_data = RandomData(rng, scale=7)
n_components = rand_data.n_components
X = rand_data.X[covar_type]
# Check the error message if we don't call fit
gmm1 = GaussianMixture(n_components=n_components, n_init=1,
max_iter=1, reg_covar=0, random_state=rng,
covariance_type=covar_type)
assert_raise_message(NotFittedError,
"This GaussianMixture instance is not fitted "
"yet. Call 'fit' with appropriate arguments "
"before using this method.", gmm1.score, X)
# Check score value
with warnings.catch_warnings():
warnings.simplefilter("ignore", ConvergenceWarning)
gmm1.fit(X)
gmm_score = gmm1.score(X)
gmm_score_proba = gmm1.score_samples(X).mean()
assert_almost_equal(gmm_score, gmm_score_proba)
# Check if the score increase
gmm2 = GaussianMixture(n_components=n_components, n_init=1, reg_covar=0,
random_state=rng,
covariance_type=covar_type).fit(X)
assert_greater(gmm2.score(X), gmm1.score(X))
def test_bic_1d_1component():
# Test all of the covariance_types return the same BIC score for
# 1-dimensional, 1 component fits.
rng = np.random.RandomState(0)
n_samples, n_dim, n_components = 100, 1, 1
X = rng.randn(n_samples, n_dim)
bic_full = GaussianMixture(n_components=n_components,
covariance_type='full',
random_state=rng).fit(X).bic(X)
for covariance_type in ['tied', 'diag', 'spherical']:
bic = GaussianMixture(n_components=n_components,
covariance_type=covariance_type,
random_state=rng).fit(X).bic(X)
assert_almost_equal(bic_full, bic)
def test_gaussian_mixture_verbose():
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
n_components = rand_data.n_components
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
g = GaussianMixture(n_components=n_components,
n_init=1,
reg_covar=0,
random_state=rng,
covariance_type=covar_type,
verbose=1)
h = GaussianMixture(n_components=n_components,
n_init=1,
reg_covar=0,
random_state=rng,
covariance_type=covar_type,
verbose=2)
old_stdout = sys.stdout
sys.stdout = StringIO()
try:
g.fit(X)
h.fit(X)
finally:
sys.stdout = old_stdout
def cluster(clusterType, vectors, y):
if (clusterType == "KMeans"):
kclusterer = KMeansClusterer(
NUM_CLUSTERS,
distance=nltk.cluster.util.cosine_distance,
repeats=25)
assigned_clusters = kclusterer.cluster(vectors, assign_clusters=True)
elif (clusterType == "GMM"):
GMM = GaussianMixture(n_components=NUM_CLUSTERS)
assigned_clusters = GMM.fit_predict(vectors)
elif (clusterType == "SVM"):
classifier = SVC(kernel='rbf', gamma='auto', random_state=0)
#cross-validation
assigned_clusters = cross_validation(classifier, vectors, y)
elif (clusterType == "T2VH"):
ret = hierarchical.ward_tree(vectors, n_clusters=NUM_CLUSTERS)
children = ret[0]
n_leaves = ret[2]
assigned_clusters = hierarchical._hc_cut(NUM_CLUSTERS, children,
n_leaves)
elif (clusterType == "RandomForest"):
classifier = RandomForestClassifier()
#cross-validation
assigned_clusters = cross_validation(classifier, vectors, y)
# classifier.fit(vectors, y)
# assigned_clusters=classifier.predict(vectors)
elif (clusterType == "DecisionTree"):
classifier = DecisionTreeClassifier()
#cross-validation
assigned_clusters = cross_validation(classifier, vectors, y)
# classifier.fit(vectors, y)
# assigned_clusters=classifier.predict(vectors)
elif (clusterType == "LogisticRegression"):
classifier = sklearn.linear_model.LogisticRegression()
#cross-validation
assigned_clusters = cross_validation(classifier, vectors, y)
# classifier.fit(vectors, y)
# assigned_clusters=classifier.predict(vectors)
else:
print(clusterType, " is not a predefined cluster type.")
return
return assigned_clusters
def test_sample():
rng = np.random.RandomState(0)
rand_data = RandomData(rng, scale=7, n_components=3)
n_features, n_components = rand_data.n_features, rand_data.n_components
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
gmm = GaussianMixture(n_components=n_components,
covariance_type=covar_type, random_state=rng)
# To sample we need that GaussianMixture is fitted
assert_raise_message(NotFittedError, "This GaussianMixture instance "
"is not fitted", gmm.sample, 0)
gmm.fit(X)
assert_raise_message(ValueError, "Invalid value for 'n_samples",
gmm.sample, 0)
# Just to make sure the class samples correctly
n_samples = 20000
X_s, y_s = gmm.sample(n_samples)
for k in range(n_components):
if covar_type == 'full':
assert_array_almost_equal(gmm.covariances_[k],
np.cov(X_s[y_s == k].T), decimal=1)
elif covar_type == 'tied':
assert_array_almost_equal(gmm.covariances_,
np.cov(X_s[y_s == k].T), decimal=1)
elif covar_type == 'diag':
assert_array_almost_equal(gmm.covariances_[k],
np.diag(np.cov(X_s[y_s == k].T)),
decimal=1)
else:
assert_array_almost_equal(
gmm.covariances_[k], np.var(X_s[y_s == k] - gmm.means_[k]),
decimal=1)
means_s = np.array([np.mean(X_s[y_s == k], 0)
for k in range(n_components)])
assert_array_almost_equal(gmm.means_, means_s, decimal=1)
# Check shapes of sampled data, see
# https://github.com/scikit-learn/scikit-learn/issues/7701
assert_equal(X_s.shape, (n_samples, n_features))
for sample_size in range(1, 100):
X_s, _ = gmm.sample(sample_size)
assert_equal(X_s.shape, (sample_size, n_features))
def spawn(self, sess, dataset, num_data=None):
"""
Run through the computational graph with a dataset
to create an agent
"""
# 1. Train the latent classifier
print('Step 1...')
dataset_string = sess.run(dataset.repeat(1000).batch(self.batch_size).make_one_shot_iterator().string_handle())
try:
while True:
sess.run(self.latent_train_step, feed_dict={self.handle: dataset_string})
except tf.errors.OutOfRangeError:
pass
# 2. Train the GMM
print('Step 2...')
dataset_string = sess.run(dataset.batch(num_data).make_one_shot_iterator().string_handle())
_, z_mean, _, _ = sess.run(self.iterator.get_next(), feed_dict={self.handle: dataset_string})
gmm = GaussianMixture(n_components=self.num_pattern, covariance_type='full').fit(z_mean)
means_ = gmm.means_.astype(np.float32)
scales_ = self.scale_to_unconstrained.forward(np.linalg.cholesky(gmm.covariances_).astype(np.float32))
sess.run([self.means.assign(means_), self.scales_unconstrained.assign(scales_)], feed_dict={self.handle: dataset_string})
# 3. Compute S_labels_patterns
print('Step 3...')
S_label_pattern_ = sess.run(self.S_label_pattern)
patterns = (means_, gmm.covariances_)
return Agent(sess, patterns, S_label_pattern_)
def test_convergence_detected_with_warm_start():
# We check that convergence is detected when warm_start=True
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
n_components = rand_data.n_components
X = rand_data.X['full']
for max_iter in (1, 2, 50):
gmm = GaussianMixture(n_components=n_components, warm_start=True,
max_iter=max_iter, random_state=rng)
for _ in range(100):
gmm.fit(X)
if gmm.converged_:
break
assert gmm.converged_
assert max_iter >= gmm.n_iter_
def test_convergence_detected_with_warm_start():
# We check that convergence is detected when warm_start=True
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
n_components = rand_data.n_components
X = rand_data.X['full']
for max_iter in (1, 2, 50):
gmm = GaussianMixture(n_components=n_components, warm_start=True,
max_iter=max_iter, random_state=rng)
for _ in range(100):
gmm.fit(X)
if gmm.converged_:
break
assert gmm.converged_
assert max_iter >= gmm.n_iter_
def test_gaussian_mixture_fit():
# recover the ground truth
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
n_features = rand_data.n_features
n_components = rand_data.n_components
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
g = GaussianMixture(n_components=n_components, n_init=20,
reg_covar=0, random_state=rng,
covariance_type=covar_type)
g.fit(X)
# needs more data to pass the test with rtol=1e-7
assert_allclose(np.sort(g.weights_), np.sort(rand_data.weights),
rtol=0.1, atol=1e-2)
arg_idx1 = g.means_[:, 0].argsort()
arg_idx2 = rand_data.means[:, 0].argsort()
assert_allclose(g.means_[arg_idx1], rand_data.means[arg_idx2],
rtol=0.1, atol=1e-2)
if covar_type == 'full':
prec_pred = g.precisions_
prec_test = rand_data.precisions['full']
elif covar_type == 'tied':
prec_pred = np.array([g.precisions_] * n_components)
prec_test = np.array([rand_data.precisions['tied']] * n_components)
elif covar_type == 'spherical':
prec_pred = np.array([np.eye(n_features) * c
for c in g.precisions_])
prec_test = np.array([np.eye(n_features) * c for c in
rand_data.precisions['spherical']])
elif covar_type == 'diag':
prec_pred = np.array([np.diag(d) for d in g.precisions_])
prec_test = np.array([np.diag(d) for d in
rand_data.precisions['diag']])
arg_idx1 = np.trace(prec_pred, axis1=1, axis2=2).argsort()
arg_idx2 = np.trace(prec_test, axis1=1, axis2=2).argsort()
for k, h in zip(arg_idx1, arg_idx2):
ecov = EmpiricalCovariance()
ecov.covariance_ = prec_test[h]
# the accuracy depends on the number of data and randomness, rng
assert_allclose(ecov.error_norm(prec_pred[k]), 0, atol=0.1)
def test_score_samples():
covar_type = 'full'
rng = np.random.RandomState(0)
rand_data = RandomData(rng, scale=7)
n_components = rand_data.n_components
X = rand_data.X[covar_type]
# Check the error message if we don't call fit
gmm = GaussianMixture(n_components=n_components, n_init=1, reg_covar=0,
random_state=rng, covariance_type=covar_type)
assert_raise_message(NotFittedError,
"This GaussianMixture instance is not fitted "
"yet. Call 'fit' with appropriate arguments "
"before using this method.", gmm.score_samples, X)
gmm_score_samples = gmm.fit(X).score_samples(X)
assert_equal(gmm_score_samples.shape[0], rand_data.n_samples)
def test_score_samples():
covar_type = 'full'
rng = np.random.RandomState(0)
rand_data = RandomData(rng, scale=7)
n_components = rand_data.n_components
X = rand_data.X[covar_type]
# Check the error message if we don't call fit
gmm = GaussianMixture(n_components=n_components, n_init=1, reg_covar=0,
random_state=rng, covariance_type=covar_type)
assert_raise_message(NotFittedError,
"This GaussianMixture instance is not fitted "
"yet. Call 'fit' with appropriate arguments "
"before using this method.", gmm.score_samples, X)
gmm_score_samples = gmm.fit(X).score_samples(X)
assert_equal(gmm_score_samples.shape[0], rand_data.n_samples)
def test_gaussian_mixture_fit_predict():
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
Y = rand_data.Y
g = GaussianMixture(n_components=rand_data.n_components,
random_state=rng, weights_init=rand_data.weights,
means_init=rand_data.means,
precisions_init=rand_data.precisions[covar_type],
covariance_type=covar_type)
# check if fit_predict(X) is equivalent to fit(X).predict(X)
f = copy.deepcopy(g)
Y_pred1 = f.fit(X).predict(X)
Y_pred2 = g.fit_predict(X)
assert_array_equal(Y_pred1, Y_pred2)
assert_greater(adjusted_rand_score(Y, Y_pred2), .95)
def test_gaussian_mixture_fit_predict():
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
Y = rand_data.Y
g = GaussianMixture(n_components=rand_data.n_components,
random_state=rng, weights_init=rand_data.weights,
means_init=rand_data.means,
precisions_init=rand_data.precisions[covar_type],
covariance_type=covar_type)
# check if fit_predict(X) is equivalent to fit(X).predict(X)
f = copy.deepcopy(g)
Y_pred1 = f.fit(X).predict(X)
Y_pred2 = g.fit_predict(X)
assert_array_equal(Y_pred1, Y_pred2)
assert_greater(adjusted_rand_score(Y, Y_pred2), .95)
def test_gaussian_mixture_fit_best_params():
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
n_components = rand_data.n_components
n_init = 10
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
g = GaussianMixture(n_components=n_components, n_init=1, reg_covar=0,
random_state=rng, covariance_type=covar_type)
ll = []
for _ in range(n_init):
g.fit(X)
ll.append(g.score(X))
ll = np.array(ll)
g_best = GaussianMixture(n_components=n_components,
n_init=n_init, reg_covar=0, random_state=rng,
covariance_type=covar_type)
g_best.fit(X)
assert_almost_equal(ll.min(), g_best.score(X))
def test_property():
rng = np.random.RandomState(0)
rand_data = RandomData(rng, scale=7)
n_components = rand_data.n_components
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
gmm = GaussianMixture(n_components=n_components,
covariance_type=covar_type, random_state=rng,
n_init=5)
gmm.fit(X)
if covar_type == 'full':
for prec, covar in zip(gmm.precisions_, gmm.covariances_):
assert_array_almost_equal(linalg.inv(prec), covar)
elif covar_type == 'tied':
assert_array_almost_equal(linalg.inv(gmm.precisions_),
gmm.covariances_)
else:
assert_array_almost_equal(gmm.precisions_, 1. / gmm.covariances_)
def test_property():
rng = np.random.RandomState(0)
rand_data = RandomData(rng, scale=7)
n_components = rand_data.n_components
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
gmm = GaussianMixture(n_components=n_components,
covariance_type=covar_type, random_state=rng,
n_init=5)
gmm.fit(X)
if covar_type == 'full':
for prec, covar in zip(gmm.precisions_, gmm.covariances_):
assert_array_almost_equal(linalg.inv(prec), covar)
elif covar_type == 'tied':
assert_array_almost_equal(linalg.inv(gmm.precisions_),
gmm.covariances_)
else:
assert_array_almost_equal(gmm.precisions_, 1. / gmm.covariances_)
def test_check_means():
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
n_components, n_features = rand_data.n_components, rand_data.n_features
X = rand_data.X['full']
g = GaussianMixture(n_components=n_components)
# Check means bad shape
means_bad_shape = rng.rand(n_components + 1, n_features)
g.means_init = means_bad_shape
assert_raise_message(ValueError,
"The parameter 'means' should have the shape of ",
g.fit, X)
# Check good means matrix
means = rand_data.means
g.means_init = means
g.fit(X)
assert_array_equal(means, g.means_init)
class ScikitLL(LikelihoodEvaluator):
"""
Fastest Single Core Version so far!
"""
def __init__(self, Xpoints, numMixtures):
super().__init__(Xpoints, numMixtures)
self.evaluator = GaussianMixture(numMixtures, 'diag')
self.Xpoints = Xpoints
self.evaluator.fit(Xpoints)
def __str__(self):
return "SciKit's learn implementation Implementation"
def loglikelihood(self, means, diagCovs, weights):
self.evaluator.weights_ = weights
self.evaluator.covariances_ = diagCovs
self.evaluator.means_ = means
self.evaluator.precisions_cholesky_ = _compute_precision_cholesky(
diagCovs, "diag")
return self.numPoints * np.sum(self.evaluator.score(self.Xpoints))
def _initialize_from_json(self, data):
self.name = data["name"]
self.spatial_coefs = np.array(data["spatial_coeffs"])
self.knots = np.array(data["knots"])
self.n_canonical_frames = data["n_canonical_frames"]
self.time_function = np.array(list(range(self.n_canonical_frames)))
self.motion_spline = MotionSpline(self.spatial_coefs,
self.time_function, self.knots, None)
self.gmm = GaussianMixture(n_components=1, covariance_type='full')
#self.gmm.fit([0])
if "skeleton" in data:
self.animated_joints = data["skeleton"]["animated_joints"]
def fuse(self, agent1, agent2):
gmm = GaussianMixture(n_components=self.num_pattern).fit(np.concatenate((agent1.patterns[0], agent2.patterns[0])))
s1 = agent1.S_label_pattern
s2 = agent2.S_label_pattern
idx1 = gmm.predict(agent1.patterns[0])
idx2 = gmm.predict(agent2.patterns[0])
s = np.ones((self.num_pattern, 10))
for j in range(self.num_pattern):
i1 = np.argwhere(idx1 == j)[:, 0]
for i in i1:
s[j, :] *= s1[i, :]
i2 = np.argwhere(idx2 == j)[:, 0]
for i in i2:
s[j, :] *= s2[i, :]
normalization_const = np.sum(s, axis=1, keepdims=True)
# normalization_const = np.reshape(normalization_const, (self.num_pattern, 10))
normalization_const = np.tile(normalization_const, (1, 10))
s /= normalization_const
return Agent(agent1.sess, (gmm.means_, gmm.covariances_), s)
def get_3d_grid_gmm(subdivisions: Tuple[int, int, int] = (5, 5, 5),
variance: float = 0.04) -> GaussianMixture:
"""
Compute the weight, mean and covariance of a gmm placed on a 3D grid
:param subdivisions: 2 element list of number of subdivisions of the 3D space in each axes to form the grid
:param variance: scalar for spherical gmm.p
:return gmm: gmm: instance of sklearn GaussianMixture (GMM) object Gauassian mixture model
"""
n_gaussians = np.prod(np.array(subdivisions))
step = [
1.0 / (subdivisions[0]), 1.0 / (subdivisions[1]),
1.0 / (subdivisions[2])
]
means = np.mgrid[step[0] - 1:1.0 - step[0]:complex(0, subdivisions[0]),
step[1] - 1:1.0 - step[1]:complex(0, subdivisions[1]),
step[2] - 1:1.0 - step[2]:complex(0, subdivisions[2])]
means = np.reshape(means, [3, -1]).T
covariances = variance * np.ones_like(means)
weights = (1.0 / n_gaussians) * np.ones(n_gaussians)
gmm = GaussianMixture(n_components=n_gaussians, covariance_type='diag')
gmm.weights_ = weights
gmm.covariances_ = covariances
gmm.means_ = means
gmm.precisions_cholesky_ = _compute_precision_cholesky(covariances, 'diag')
return gmm
def test_check_precisions():
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
n_components, n_features = rand_data.n_components, rand_data.n_features
# Define the bad precisions for each covariance_type
precisions_bad_shape = {
'full': np.ones((n_components + 1, n_features, n_features)),
'tied': np.ones((n_features + 1, n_features + 1)),
'diag': np.ones((n_components + 1, n_features)),
'spherical': np.ones((n_components + 1))
}
# Define not positive-definite precisions
precisions_not_pos = np.ones((n_components, n_features, n_features))
precisions_not_pos[0] = np.eye(n_features)
precisions_not_pos[0, 0, 0] = -1.
precisions_not_positive = {
'full': precisions_not_pos,
'tied': precisions_not_pos[0],
'diag': -1. * np.ones((n_components, n_features)),
'spherical': -1. * np.ones(n_components)
}
not_positive_errors = {
'full': 'symmetric, positive-definite',
'tied': 'symmetric, positive-definite',
'diag': 'positive',
'spherical': 'positive'
}
for covar_type in COVARIANCE_TYPE:
X = RandomData(rng).X[covar_type]
g = GaussianMixture(n_components=n_components,
covariance_type=covar_type,
random_state=rng)
# Check precisions with bad shapes
g.precisions_init = precisions_bad_shape[covar_type]
assert_raise_message(
ValueError, "The parameter '%s precision' should have "
"the shape of" % covar_type, g.fit, X)
# Check not positive precisions
g.precisions_init = precisions_not_positive[covar_type]
assert_raise_message(
ValueError, "'%s precision' should be %s" %
(covar_type, not_positive_errors[covar_type]), g.fit, X)
# Check the correct init of precisions_init
g.precisions_init = rand_data.precisions[covar_type]
g.fit(X)
assert_array_equal(rand_data.precisions[covar_type], g.precisions_init)
def test_sample():
rng = np.random.RandomState(0)
rand_data = RandomData(rng, scale=7)
n_features, n_components = rand_data.n_features, rand_data.n_components
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
gmm = GaussianMixture(n_components=n_components,
covariance_type=covar_type, random_state=rng)
# To sample we need that GaussianMixture is fitted
assert_raise_message(NotFittedError, "This GaussianMixture instance "
"is not fitted", gmm.sample, 0)
gmm.fit(X)
assert_raise_message(ValueError, "Invalid value for 'n_samples",
gmm.sample, 0)
# Just to make sure the class samples correctly
X_s, y_s = gmm.sample(20000)
for k in range(n_features):
if covar_type == 'full':
assert_array_almost_equal(gmm.covariances_[k],
np.cov(X_s[y_s == k].T), decimal=1)
elif covar_type == 'tied':
assert_array_almost_equal(gmm.covariances_,
np.cov(X_s[y_s == k].T), decimal=1)
elif covar_type == 'diag':
assert_array_almost_equal(gmm.covariances_[k],
np.diag(np.cov(X_s[y_s == k].T)),
decimal=1)
else:
assert_array_almost_equal(
gmm.covariances_[k], np.var(X_s[y_s == k] - gmm.means_[k]),
decimal=1)
means_s = np.array([np.mean(X_s[y_s == k], 0)
for k in range(n_features)])
assert_array_almost_equal(gmm.means_, means_s, decimal=1)
def test_check_weights():
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
n_components = rand_data.n_components
X = rand_data.X['full']
g = GaussianMixture(n_components=n_components)
# Check bad shape
weights_bad_shape = rng.rand(n_components, 1)
g.weights_init = weights_bad_shape
assert_raise_message(ValueError,
"The parameter 'weights' should have the shape of "
"(%d,), "
"but got %s" % (n_components,
str(weights_bad_shape.shape)),
g.fit, X)
# Check bad range
weights_bad_range = rng.rand(n_components) + 1
g.weights_init = weights_bad_range
assert_raise_message(ValueError,
"The parameter 'weights' should be in the range "
"[0, 1], but got max value %.5f, min value %.5f"
% (np.min(weights_bad_range),
np.max(weights_bad_range)),
g.fit, X)
# Check bad normalization
weights_bad_norm = rng.rand(n_components)
weights_bad_norm = weights_bad_norm / (weights_bad_norm.sum() + 1)
g.weights_init = weights_bad_norm
assert_raise_message(ValueError,
"The parameter 'weights' should be normalized, "
"but got sum(weights) = %.5f"
% np.sum(weights_bad_norm),
g.fit, X)
# Check good weights matrix
weights = rand_data.weights
g = GaussianMixture(weights_init=weights, n_components=n_components)
g.fit(X)
assert_array_equal(weights, g.weights_init)
def test_regularisation():
# We train the GaussianMixture on degenerate data by defining two clusters
# of a 0 covariance.
rng = np.random.RandomState(0)
n_samples, n_features = 10, 5
X = np.vstack((np.ones((n_samples // 2, n_features)),
np.zeros((n_samples // 2, n_features))))
for covar_type in COVARIANCE_TYPE:
gmm = GaussianMixture(n_components=n_samples, reg_covar=0,
covariance_type=covar_type, random_state=rng)
with warnings.catch_warnings():
warnings.simplefilter("ignore", RuntimeWarning)
assert_raise_message(ValueError,
"The algorithm has diverged because of too "
"few samples per components. "
"Try to decrease the number of components, "
"or increase reg_covar.", gmm.fit, X)
gmm.set_params(reg_covar=1e-6).fit(X)
def test_check_covariances():
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
n_components, n_features = rand_data.n_components, rand_data.n_features
# Define the bad covariances for each covariance_type
covariances_bad_shape = {
'full': rng.rand(n_components + 1, n_features, n_features),
'tied': rng.rand(n_features + 1, n_features + 1),
'diag': rng.rand(n_components + 1, n_features),
'spherical': rng.rand(n_components + 1)}
# Define not positive-definite covariances
covariances_not_pos = rng.rand(n_components, n_features, n_features)
covariances_not_pos[0] = np.eye(n_features)
covariances_not_pos[0, 0, 0] = -1.
covariances_not_positive = {
'full': covariances_not_pos,
'tied': covariances_not_pos[0],
'diag': -1. * np.ones((n_components, n_features)),
'spherical': -1. * np.ones(n_components)}
not_positive_errors = {
'full': 'symmetric, positive-definite',
'tied': 'symmetric, positive-definite',
'diag': 'positive',
'spherical': 'positive'}
for cov_type in ['full', 'tied', 'diag', 'spherical']:
X = rand_data.X[cov_type]
g = GaussianMixture(n_components=n_components,
covariance_type=cov_type)
# Check covariance with bad shapes
g.covariances_init = covariances_bad_shape[cov_type]
assert_raise_message(ValueError,
"The parameter '%s covariance' should have "
"the shape of" % cov_type,
g.fit, X)
# Check not positive covariances
g.covariances_init = covariances_not_positive[cov_type]
assert_raise_message(ValueError,
"'%s covariance' should be %s"
% (cov_type, not_positive_errors[cov_type]),
g.fit, X)
# Check the correct init of covariances_init
g.covariances_init = rand_data.covariances[cov_type]
g.fit(X)
assert_array_equal(rand_data.covariances[cov_type], g.covariances_init)
def test_gaussian_mixture_estimate_log_prob_resp():
# test whether responsibilities are normalized
rng = np.random.RandomState(0)
rand_data = RandomData(rng, scale=5)
n_samples = rand_data.n_samples
n_features = rand_data.n_features
n_components = rand_data.n_components
X = rng.rand(n_samples, n_features)
for covar_type in COVARIANCE_TYPE:
weights = rand_data.weights
means = rand_data.means
precisions = rand_data.precisions[covar_type]
g = GaussianMixture(n_components=n_components, random_state=rng,
weights_init=weights, means_init=means,
precisions_init=precisions,
covariance_type=covar_type)
g.fit(X)
resp = g.predict_proba(X)
assert_array_almost_equal(resp.sum(axis=1), np.ones(n_samples))
assert_array_equal(g.weights_init, weights)
assert_array_equal(g.means_init, means)
assert_array_equal(g.precisions_init, precisions)
def test_gaussian_mixture_predict_predict_proba():
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
Y = rand_data.Y
g = GaussianMixture(n_components=rand_data.n_components,
random_state=rng, weights_init=rand_data.weights,
means_init=rand_data.means,
precisions_init=rand_data.precisions[covar_type],
covariance_type=covar_type)
# Check a warning message arrive if we don't do fit
assert_raise_message(NotFittedError,
"This GaussianMixture instance is not fitted "
"yet. Call 'fit' with appropriate arguments "
"before using this method.", g.predict, X)
g.fit(X)
Y_pred = g.predict(X)
Y_pred_proba = g.predict_proba(X).argmax(axis=1)
assert_array_equal(Y_pred, Y_pred_proba)
assert_greater(adjusted_rand_score(Y, Y_pred), .95)
def test_regularisation():
# We train the GaussianMixture on degenerate data by defining two clusters
# of a 0 covariance.
rng = np.random.RandomState(0)
n_samples, n_features = 10, 5
X = np.vstack((np.ones((n_samples // 2, n_features)),
np.zeros((n_samples // 2, n_features))))
for covar_type in COVARIANCE_TYPE:
gmm = GaussianMixture(n_components=n_samples, reg_covar=0,
covariance_type=covar_type, random_state=rng)
with warnings.catch_warnings():
warnings.simplefilter("ignore", RuntimeWarning)
assert_raise_message(ValueError,
"Fitting the mixture model failed because "
"some components have ill-defined empirical "
"covariance (for instance caused by "
"singleton or collapsed samples). Try to "
"decrease the number of components, or "
"increase reg_covar.", gmm.fit, X)
gmm.set_params(reg_covar=1e-6).fit(X)
def test_check_precisions():
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
n_components, n_features = rand_data.n_components, rand_data.n_features
# Define the bad precisions for each covariance_type
precisions_bad_shape = {
'full': np.ones((n_components + 1, n_features, n_features)),
'tied': np.ones((n_features + 1, n_features + 1)),
'diag': np.ones((n_components + 1, n_features)),
'spherical': np.ones((n_components + 1))}
# Define not positive-definite precisions
precisions_not_pos = np.ones((n_components, n_features, n_features))
precisions_not_pos[0] = np.eye(n_features)
precisions_not_pos[0, 0, 0] = -1.
precisions_not_positive = {
'full': precisions_not_pos,
'tied': precisions_not_pos[0],
'diag': np.full((n_components, n_features), -1.),
'spherical': np.full(n_components, -1.)}
not_positive_errors = {
'full': 'symmetric, positive-definite',
'tied': 'symmetric, positive-definite',
'diag': 'positive',
'spherical': 'positive'}
for covar_type in COVARIANCE_TYPE:
X = RandomData(rng).X[covar_type]
g = GaussianMixture(n_components=n_components,
covariance_type=covar_type,
random_state=rng)
# Check precisions with bad shapes
g.precisions_init = precisions_bad_shape[covar_type]
assert_raise_message(ValueError,
"The parameter '%s precision' should have "
"the shape of" % covar_type,
g.fit, X)
# Check not positive precisions
g.precisions_init = precisions_not_positive[covar_type]
assert_raise_message(ValueError,
"'%s precision' should be %s"
% (covar_type, not_positive_errors[covar_type]),
g.fit, X)
# Check the correct init of precisions_init
g.precisions_init = rand_data.precisions[covar_type]
g.fit(X)
assert_array_equal(rand_data.precisions[covar_type], g.precisions_init)
def test_gaussian_mixture_fit_best_params():
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
n_components = rand_data.n_components
n_init = 10
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
g = GaussianMixture(n_components=n_components, n_init=1, reg_covar=0,
random_state=rng, covariance_type=covar_type)
ll = []
for _ in range(n_init):
g.fit(X)
ll.append(g.score(X))
ll = np.array(ll)
g_best = GaussianMixture(n_components=n_components,
n_init=n_init, reg_covar=0, random_state=rng,
covariance_type=covar_type)
g_best.fit(X)
assert_almost_equal(ll.min(), g_best.score(X))
def test_gaussian_mixture_aic_bic():
# Test the aic and bic criteria
rng = np.random.RandomState(0)
n_samples, n_features, n_components = 50, 3, 2
X = rng.randn(n_samples, n_features)
# standard gaussian entropy
sgh = 0.5 * (fast_logdet(np.cov(X.T, bias=1)) +
n_features * (1 + np.log(2 * np.pi)))
for cv_type in COVARIANCE_TYPE:
g = GaussianMixture(
n_components=n_components, covariance_type=cv_type,
random_state=rng, max_iter=200)
g.fit(X)
aic = 2 * n_samples * sgh + 2 * g._n_parameters()
bic = (2 * n_samples * sgh +
np.log(n_samples) * g._n_parameters())
bound = n_features / np.sqrt(n_samples)
assert (g.aic(X) - aic) / n_samples < bound
assert (g.bic(X) - bic) / n_samples < bound
def test_gaussian_mixture_verbose():
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
n_components = rand_data.n_components
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
g = GaussianMixture(n_components=n_components, n_init=1, reg_covar=0,
random_state=rng, covariance_type=covar_type,
verbose=1)
h = GaussianMixture(n_components=n_components, n_init=1, reg_covar=0,
random_state=rng, covariance_type=covar_type,
verbose=2)
old_stdout = sys.stdout
sys.stdout = StringIO()
try:
g.fit(X)
h.fit(X)
finally:
sys.stdout = old_stdout
def test_warm_start():
random_state = 0
rng = np.random.RandomState(random_state)
n_samples, n_features, n_components = 500, 2, 2
X = rng.rand(n_samples, n_features)
# Assert the warm_start give the same result for the same number of iter
g = GaussianMixture(n_components=n_components, n_init=1, max_iter=2,
reg_covar=0, random_state=random_state,
warm_start=False)
h = GaussianMixture(n_components=n_components, n_init=1, max_iter=1,
reg_covar=0, random_state=random_state,
warm_start=True)
with warnings.catch_warnings():
warnings.simplefilter("ignore", ConvergenceWarning)
g.fit(X)
score1 = h.fit(X).score(X)
score2 = h.fit(X).score(X)
assert_almost_equal(g.weights_, h.weights_)
assert_almost_equal(g.means_, h.means_)
assert_almost_equal(g.precisions_, h.precisions_)
assert_greater(score2, score1)
# Assert that by using warm_start we can converge to a good solution
g = GaussianMixture(n_components=n_components, n_init=1,
max_iter=5, reg_covar=0, random_state=random_state,
warm_start=False, tol=1e-6)
h = GaussianMixture(n_components=n_components, n_init=1,
max_iter=5, reg_covar=0, random_state=random_state,
warm_start=True, tol=1e-6)
with warnings.catch_warnings():
warnings.simplefilter("ignore", ConvergenceWarning)
g.fit(X)
h.fit(X).fit(X)
assert_true(not g.converged_)
assert_true(h.converged_)
def test_warm_start(seed):
random_state = seed
rng = np.random.RandomState(random_state)
n_samples, n_features, n_components = 500, 2, 2
X = rng.rand(n_samples, n_features)
# Assert the warm_start give the same result for the same number of iter
g = GaussianMixture(n_components=n_components, n_init=1, max_iter=2,
reg_covar=0, random_state=random_state,
warm_start=False)
h = GaussianMixture(n_components=n_components, n_init=1, max_iter=1,
reg_covar=0, random_state=random_state,
warm_start=True)
g.fit(X)
score1 = h.fit(X).score(X)
score2 = h.fit(X).score(X)
assert_almost_equal(g.weights_, h.weights_)
assert_almost_equal(g.means_, h.means_)
assert_almost_equal(g.precisions_, h.precisions_)
assert score2 > score1
# Assert that by using warm_start we can converge to a good solution
g = GaussianMixture(n_components=n_components, n_init=1,
max_iter=5, reg_covar=0, random_state=random_state,
warm_start=False, tol=1e-6)
h = GaussianMixture(n_components=n_components, n_init=1,
max_iter=5, reg_covar=0, random_state=random_state,
warm_start=True, tol=1e-6)
g.fit(X)
assert not g.converged_
h.fit(X)
# depending on the data there is large variability in the number of
# refit necessary to converge due to the complete randomness of the
# data
for _ in range(1000):
h.fit(X)
if h.converged_:
break
assert h.converged_
