print('Features H_0:{}'.format(t1 - t0))
# -----------------------------------------------------------------------------
# ------------------------------ H_1 ------------------------------------------
# -----------------------------------------------------------------------------
if adptative_feature == 'cder':
# ----------------------------------------------------------------------------
# ------------------------------ CDER ----------------------------------------
# ----------------------------------------------------------------------------
print('Begin CDER...')
t0 = time.time()
pc_train = multidim.PointCloud.from_multisample_multilabel(
X_train_1, F_train)
ct_train = CoverTree(pc_train)
cder = CDER(parsimonious=True)
cder.fit(ct_train)
cder_result = cder.gaussians
ellipses = []
for c in cder_result:
temp = {
key: c[key]
for key in ['mean', 'std', 'rotation', 'radius', 'entropy']
}
temp['std'] = 2 * temp['std']
#temp['std'] = np.array([temp['radius'], temp['radius']])
def adaptive_features(X_train, X_test, model, y_train, d=25):
if model == "gmm":
print('Begin GMM...')
start = time.time()
X_train_temp = np.vstack(X_train)
gmm_f_train = []
for i in range(len(X_train)):
gmm_f_train.append(y_train[i] * np.ones(len(X_train[i])))
gmm_f_train = np.concatenate(gmm_f_train)
gmm = mixture.BayesianGaussianMixture(n_components=d,
covariance_type='full',
max_iter=int(10e4)).fit(
X_train_temp, gmm_f_train)
ellipses = []
for i in range(len(gmm.means_)):
L, v = np.linalg.eig(gmm.covariances_[i])
temp = {
'mean': gmm.means_[i],
'std': np.sqrt(L),
'rotation': v.transpose(),
'radius': max(np.sqrt(L)),
'entropy': gmm.weights_[i]
}
temp['std'] = 3 * temp['std']
ellipses.append(temp)
X_train_features = ATS.get_all_features(X_train, ellipses,
ATS.f_ellipse)
X_test_features = ATS.get_all_features(X_test, ellipses, ATS.f_ellipse)
end = time.time()
print('Computing gmm features took (seconds):{}'.format(end - start))
elif model == "hdb":
print('Begin HDBSCAN...')
start = time.time()
X_train_temp = np.vstack(X_train)
clusterer = hdbscan.HDBSCAN()
clusterer.fit(X_train_temp)
num_clusters = clusterer.labels_.max()
ellipses = []
for i in range(num_clusters):
cluster_i = X_train_temp[clusterer.labels_ == i]
en = np.mean(clusterer.probabilities_[clusterer.labels_ == i])
mean = np.mean(cluster_i, axis=0)
cov_matrix = np.cov(cluster_i.transpose())
L, v = np.linalg.eig(cov_matrix)
temp = {
'mean': mean,
'std': np.sqrt(L),
'rotation': v.transpose(),
'radius': max(np.sqrt(L)),
'entropy': en
}
temp['std'] = 2 * temp['std']
ellipses.append(temp)
X_train_features = ATS.get_all_features(X_train, ellipses,
ATS.f_ellipse)
X_test_features = ATS.get_all_features(X_test, ellipses, ATS.f_ellipse)
end = time.time()
print('Computing hdbscan features took (seconds):{}'.format(end -
start))
elif model == "cder":
y_train_cder = y_train.copy()
print('Begin CDER...')
start = time.time()
pc_train = multidim.PointCloud.from_multisample_multilabel(
X_train, y_train_cder)
ct_train = CoverTree(pc_train)
cder = CDER(parsimonious=True)
cder.fit(ct_train)
cder_result = cder.gaussians
ellipses = []
for c in cder_result:
temp = {
key: c[key]
for key in ['mean', 'std', 'rotation', 'radius', 'entropy']
}
temp['std'] = 3 * temp['std']
ellipses.append(temp)
X_train_features = ATS.get_all_features(X_train, ellipses,
ATS.f_ellipse)
X_test_features = ATS.get_all_features(X_test, ellipses, ATS.f_ellipse)
end = time.time()
print('Computing features from H_1 took (seconds):{}'.format(end -
start))
else:
print("Not a valid model type")
return X_train_features, X_test_features
def adaptive_features(X_train, model, y_train, d=25):
if model == "gmm":
print('Begin GMM...')
start = time.time()
X_train_temp = np.vstack(X_train)
gmm_f_train = []
for i in range(len(X_train)):
gmm_f_train.append(y_train[i] * np.ones(len(X_train[i])))
gmm_f_train = np.concatenate(gmm_f_train)
gmm = mixture.BayesianGaussianMixture(n_components=d,
covariance_type='full',
max_iter=int(10e4)).fit(
X_train_temp, gmm_f_train)
ellipses = []
for i in range(len(gmm.means_)):
L, v = np.linalg.eig(gmm.covariances_[i])
temp = {
'mean': gmm.means_[i],
'std': np.sqrt(L),
'rotation': v.transpose(),
'radius': max(np.sqrt(L)),
'entropy': gmm.weights_[i]
}
temp['std'] = 3 * temp['std']
ellipses.append(temp)
X_train_features = ATS.get_all_features(X_train, ellipses,
ATS.f_ellipse)
end = time.time()
timing = end - start
elif model == "cder":
y_train_cder = y_train.copy()
print('Begin CDER...')
start = time.time()
pc_train = multidim.PointCloud.from_multisample_multilabel(
X_train, y_train_cder)
ct_train = CoverTree(pc_train)
cder = CDER(parsimonious=True)
cder.fit(ct_train)
cder_result = cder.gaussians
ellipses = []
for c in cder_result:
temp = {
key: c[key]
for key in ['mean', 'std', 'rotation', 'radius', 'entropy']
}
temp['std'] = 3 * temp['std']
ellipses.append(temp)
X_train_features = ATS.get_all_features(X_train, ellipses,
ATS.f_ellipse)
end = time.time()
timing = end - start
return timing