def test_bayesian_mixture_predict_predict_proba():
# this is the same test as test_gaussian_mixture_predict_predict_proba()
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
for prior_type in PRIOR_TYPE:
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
Y = rand_data.Y
bgmm = BayesianGaussianMixture(
n_components=rand_data.n_components,
random_state=rng,
weight_concentration_prior_type=prior_type,
covariance_type=covar_type,
)
# Check a warning message arrive if we don't do fit
msg = ("This BayesianGaussianMixture instance is not fitted yet. "
"Call 'fit' with appropriate arguments before using this "
"estimator.")
with pytest.raises(NotFittedError, match=msg):
bgmm.predict(X)
bgmm.fit(X)
Y_pred = bgmm.predict(X)
Y_pred_proba = bgmm.predict_proba(X).argmax(axis=1)
assert_array_equal(Y_pred, Y_pred_proba)
assert adjusted_rand_score(Y, Y_pred) >= 0.95
def partition_data(self,args):
method, j = args
if method== "vi":
dp = BayesianGaussianMixture(n_components = self.K,weight_concentration_prior = self.alpha, max_iter=1,init_params='kmeans',weight_concentration_prior_type='dirichlet_process')
dp.fit(self.X[self.U[j]])
Z = dp.predict(self.X[self.U[j]]).astype(int)
Z_star = dp.predict(self.X_star).astype(int)
if method=="gmm":
Z,Z_star= self.uncollapsed_dp_partition_alt(j)
elif method=="kmean":
km = KMeans(n_clusters=self.K)
Z = km.fit_predict(self.X[self.U[j]]).astype(int)
Z_star = km.predict(self.X_star[self.U[j]]).astype(int)
else:
Z = np.random.choice(self.K,size = self.N_minibatch,replace=True)
Z_star = np.random.choice(np.unique(Z),size = self.N_star,replace=True)
le = LE()
le.fit(np.hstack((Z,Z_star)))
Z = le.transform(Z)
Z_star = le.transform(Z_star)
if (method=="vi"): #& (self.vi_partition):
Z_diff = np.setdiff1d(Z_star,Z)
if Z_diff.size > 0:
idx = np.hstack((np.where(Z_star==k) for k in Z_diff)).flatten()
unique_Z = np.unique(Z)
post_Z = dp.predict_proba(self.X_star[idx])[:,unique_Z]
Z_star[idx] = [np.random.choice(unique_Z,p = post_Z_i / post_Z_i.sum() ) for post_Z_i in post_Z]
assert(np.setdiff1d(Z_star,Z).size == 0)
return(Z,Z_star)
def fit_GMM(data,num_components):
gmm = GMM(n_components=num_components)
gmm.fit(data)
predicted_class = gmm.predict(data)
num_classes = np.unique(gmm.predict(data)).shape[0]
return gmm,predicted_class,num_classes
class VBEM(object):
def __init__(self,
n_components=1,
verbose=2,
verbose_interval=1,
Data=None):
'''
:param n_components: cluster number
:param verbose: whether to show training details
:param verbose_interval: showing training details interval
:param Data: dataset
'''
self.model = BayesianGaussianMixture(n_components=n_components,
verbose=verbose,
verbose_interval=verbose_interval)
self.n_components = n_components
if Data == None:
self.dataset = Dataset()
self.dataset.generate()
else:
self.dataset = Data
self.data = self.dataset.data
def train(self):
self.model.fit(self.data)
def show(self, n=None):
'''
show the result of trained model
:param n: just used for save files
:return: None
'''
plt.figure()
labels = self.model.predict(self.data)
plt.scatter(self.data[:, 0], self.data[:, 1], c=labels, s=15)
if n == None:
plt.show()
else:
plt.savefig('report/demo/vbem_%d_%d' % (n, 4))
def show_dis(self, dis=None):
'''
show the result of trained model
:param dis: just used for save files
:return: None
'''
plt.figure()
labels = self.model.predict(self.data)
plt.scatter(self.data[:, 0], self.data[:, 1], c=labels, s=15)
if dis == None:
plt.show()
else:
plt.savefig('report/demo/dis_vbem_%d_%d' % (dis, 3))
def extract_improved_cell_centroid(cell_subimg, cell_contour):
cell_subimg = skimage.filters.median(cell_subimg)
# Ensure exterior of cell is set to zero.
mask = np.zeros_like(cell_subimg)
cv2.drawContours(mask, [cell_contour], -1, 255, -1)
cell_subimg[mask == 0] = 0
#visualize('cell_subimg', cell_subimg)
# 1D GMM.
X = cell_subimg[cell_subimg !=0 ].reshape(-1, 1)
gmm = BayesianGaussianMixture(n_components=10)
gmm.fit(X)
gpred_1d = gmm.predict(cell_subimg.reshape(-1, 1)).reshape(cell_subimg.shape).astype(np.uint8)
# Find maximum intensity label for 1D.
label_1d = np.argmax(gmm.means_)
# 3D GMM.
xvals = np.arange(cell_subimg.shape[0])
yvals = np.arange(cell_subimg.shape[1])
xx, yy = np.meshgrid(xvals, yvals)
S = np.vstack([xx.reshape(-1), yy.reshape(-1), cell_subimg.reshape(-1)]).T
#gmm = GaussianMixture(n_components=COMP)
gmm = BayesianGaussianMixture(n_components=3)
gmm.fit(S)
gpred_3d = gmm.predict(S).reshape(cell_subimg.shape)
# Find maximum intensity label for 3D.
label_3d = np.argmax(gmm.means_[:, 2])
P = np.zeros_like(cell_subimg)
P[np.logical_and(gpred_1d == label_1d, gpred_3d == label_3d)] = 1
# Now compute the centroid.
M = cv2.moments(P)
try:
cx = int(M['m10'] / M['m00'])
cy = int(M['m01'] / M['m00'])
# If unable to extract, choose the center of the bounding rectangle as the centroid.
except ZeroDivisionError:
x, y, w, h = cv2.boundingRect(cell_contour)
cx, cy = (x + w) // 2, (y + h) // 2
def plt_center():
plt.plot(cx, cy, 'ro')
return cx, cy
class Mixtures(object):
"""All mixture model algorithms are implemened here."""
def __init__(self, method, data, n_clusters=2, random_state=0):
"""
Initialize all the parameters.
method: Name of the algorithms (lower case joined by underscore)
data: Data (2D Matrix)
n_clusters: Number of clusters
random_state: Random initial state
"""
self.method = method
self.data = data
self.n_clusters = n_clusters
np.random.seed(random_state)
self.random_state = random_state
self.init_params = "kmeans"
self.cov = "full"
self.max_iter = 500
self.n_init = 5
self.weight_concentration_prior_type = "dirichlet_process"
return
def setup(self, **keywords):
"""
Setup the algorithms
"""
for key in keywords.keys():
setattr(self, key, keywords[key])
if self.method == "gmm": self.obj = GaussianMixture(n_components=self.n_clusters,
covariance_type=self.cov, max_iter=self.max_iter, random_state=self.random_state,
n_init=self.n_init, init_params=self.init_params)
if self.method == "bgmm": self.obj = BayesianGaussianMixture(n_components=self.n_clusters,
covariance_type=self.cov, max_iter=self.max_iter, random_state=self.random_state,
n_init=self.n_init, init_params=self.init_params,
weight_concentration_prior_type=self.weight_concentration_prior_type)
return
def run(self):
"""
Run the models
"""
if self.method == "gmm":
self.obj.fit(self.data)
setattr(self.obj, "labels_", self.obj.predict(self.data))
if self.method == "bgmm":
self.obj.fit(self.data)
setattr(self.obj, "labels_", self.obj.predict(self.data))
return
def __init__(self, **kwargs):
super().__init__(data_set=kwargs.pop('data_set', None), **kwargs)
self.clf_ = kwargs.get('clf', None)
if self.clf_ is None:
raise ValueError("missing required keyword-only argument 'clf'")
if not callable(getattr(self.clf_, 'fit', None)) or not callable(
(getattr(self.clf_, 'predict_proba', None))):
raise TypeError(
"'clf' must be an instance with the methods 'fit' and 'predict_proba'"
)
n_components = int(
kwargs.pop('n_components', np.min([20, len(self.data_set_)])))
if n_components < 0 or n_components > len(self.data_set_):
raise ValueError(
"'n_components' must be an integer in the interval [1, n_samples]"
)
# fit Gaussian mixture model for pre-clustering
gmm = BayesianGaussianMixture(n_components=n_components,
covariance_type='spherical',
max_iter=1000,
random_state=self.random_state_)
gmm.fit(self.data_set_.X_)
self.y_cluster_ = gmm.predict(self.data_set_.X_)
self.p_x_ = np.exp(gmm.score_samples(self.data_set_.X_))
def cluster(self,
dim,
method='dpgmm',
max_n_clusters=80,
max_iter=300,
refresh=True):
'''
dim is the dim index for clustering
'''
print('clustering DPGMM')
from sklearn.mixture import BayesianGaussianMixture as DPGMM
dpgmm = DPGMM(n_components=max_n_clusters,
covariance_type='full',
weight_concentration_prior=1e-3,
weight_concentration_prior_type='dirichlet_process',
init_params="kmeans",
max_iter=max_iter,
random_state=0,
verbose=1,
verbose_interval=10) # init can be "kmeans" or "random"
dpgmm.fit(self.fet[:, dim])
label = dpgmm.predict(self.fet[:, dim])
self.clu.membership = label
self.clu.__construct__()
self.clu.emit('cluster')
if refresh is True:
self.set_data(self.fet, self.clu)
return label
def bayesian_gaussian_mixture(self, n_components, weight_concentration_prior_type, weight_concentration_prior,
mean_precision_prior, n_init, max_iter, init_params):
'''Bayesian Gaussian Mixture clustering algorithm. Low value for weight_concentration_prior will put more
weight on a few components, high value will allow a larger number of components to be active in the mixture.'''
bgm = BayesianGaussianMixture(n_components=n_components,
weight_concentration_prior_type=weight_concentration_prior_type,
weight_concentration_prior=weight_concentration_prior,
mean_precision_prior=mean_precision_prior,
n_init=n_init,
max_iter=max_iter,
init_params=init_params)
bgm.fit(self.X)
self.labels = bgm.predict(self.X)
unique, counts = np.unique(self.labels, return_counts=True)
mydict = dict(zip(unique, counts))
print(mydict)
plt.bar(list(mydict.keys()), mydict.values(), color = 'g')
plt.ylabel("Number of skews")
plt.xlabel("Cluster")
plt.title(weight_concentration_prior_type)
plt.gcf().text(0.05, 0.05, "Parameters initialized using: "+init_params)
plt.gcf().text(0.05, 0.01, "Weight concentration prior: "+str(weight_concentration_prior))
plt.gcf().text(0.7, 0.05, "Mean precision prior: "+str(mean_precision_prior))
plt.gcf().text(0.7, 0.01, "Likelihood: "+str("%.2f"%bgm.lower_bound_))
#plt.show()
print("Weights: "+str(bgm.weights_))
print("Converged: "+str(bgm.converged_))
print("Number of iterations to reach convergence: "+str(bgm.n_iter_))
print("Lower bound value on likelihood: "+str(bgm.lower_bound_))
print("Bayesian Gaussian mixture complete")
class VBEM(object):
def __init__(self,
n_components=1,
verbose=2,
verbose_interval=1,
data=None):
self.model = BayesianGaussianMixture(n_components=n_components,
verbose=verbose,
verbose_interval=verbose_interval)
self.n_components = n_components
if data == None:
self.dataset = Dataset()
self.dataset.generate()
else:
self.dataset = data
self.data = self.dataset.data
def train(self):
self.model.fit(self.data)
def show(self, n=None):
plt.figure()
self.model.fit(self.data)
labels = self.model.predict(self.data)
plt.scatter(self.data[:, 0], self.data[:, 1], c=labels, s=10)
if n == None:
plt.show()
else:
plt.savefig('Pro2/vbem_%d_%d' % (n, 4))
def test_bayesian_mixture_predict_predict_proba():
# this is the same test as test_gaussian_mixture_predict_predict_proba()
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
for prior_type in PRIOR_TYPE:
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
Y = rand_data.Y
bgmm = BayesianGaussianMixture(
n_components=rand_data.n_components,
random_state=rng,
weight_concentration_prior_type=prior_type,
covariance_type=covar_type)
# Check a warning message arrive if we don't do fit
assert_raise_message(
NotFittedError, "This BayesianGaussianMixture instance"
" is not fitted yet. Call 'fit' with "
"appropriate arguments before using "
"this method.", bgmm.predict, X)
bgmm.fit(X)
Y_pred = bgmm.predict(X)
Y_pred_proba = bgmm.predict_proba(X).argmax(axis=1)
assert_array_equal(Y_pred, Y_pred_proba)
assert_greater_equal(adjusted_rand_score(Y, Y_pred), .95)
def recluster_node(dataset, node=None, idx=None, label=None, n_clusters=4):
selector = match_one(dataset, label=label, idx=idx, node=node)
# Get the node you want to recluster and flatten it
selected_data = dataset.select(selector).flatten(1)
if len(selected_data) >= 100:
cluster_on = tsne_time(selected_data, pcs=6, t_scale=2 * 60 * 60.0)
else:
cluster_on = PCA(
n_components=min(6, len(selected_data))).fit_transform(
selected_data.waveforms)
n_clusters = min(n_clusters, len(cluster_on))
weight = np.array([node.count for node in selected_data.nodes])
# kmeans = KMeans(n_clusters=n_clusters).fit(cluster_on, sample_weight=weight)
# labels = kmeans.predict(cluster_on, sample_weight=weight)
if len(cluster_on) < 2:
labels = np.arange(len(cluster_on))
else:
gmm = BayesianGaussianMixture(n_components=n_clusters).fit(cluster_on)
labels = gmm.predict(cluster_on)
reclustered = selected_data.cluster(labels)
new_dataset = dataset.select(np.logical_not(selector), child=False)
return add_nodes(new_dataset, *reclustered.nodes)
def do_bgm(self, n_components=6, seed=42):
"""Bayesian Gaussian Mixture.
Infer the effective number of components in a Gaussian Mixture Model via variational Bayesian estimation.
n_effective_componenents < n_components if the model sets some weights close to 0.
Args:
n_components (int): Number of components in GMM.
seed (int): Random seed.
Returns:
bgm_output (dict): Labels and probabilities.
"""
np.random.seed(seed)
bgm = BayesianGaussianMixture(n_components=n_components, covariance_type='full', weight_concentration_prior=1e-2, weight_concentration_prior_type='dirichlet_process', mean_precision_prior=1e-2, init_params='random', max_iter=100, random_state=seed)
bgm.fit(self.X)
bgm_labels = bgm.predict(self.X)
bgm_prob = bgm.predict_proba(self.X)[:,0]
bgm_output = {'bgm_labels': bgm_labels, 'bgm_prob': bgm_prob}
return bgm_output
def airmass_labels(z, P, T, H2O, O3, n_airmass=5, labels=None):
cH2O = mf2mol_cum(H2O, P, T)
cO3 = mf2mol_cum(O3, P, T)
T_surf = T[:, z < 3].mean(axis=1)
T_grad = np.diff(T[:, z < 6], axis=1).mean(axis=1)
H2O_tot = cH2O[:, -1]
O3_tot = cO3[:, -1]
f = lambda x: (x - x.mean()) / x.std()
features = np.vstack((f(T_surf), f(T_grad), f(H2O_tot), f(O3_tot))).T
if labels is None:
pdf = BayesianGaussianMixture(n_components=n_airmass,
covariance_type='full',
max_iter=25000)
pdf.fit(features)
labels = pdf.predict(features)
plt.figure()
for ii in range(n_airmass):
ix = labels == ii
plt.subplot(1, 3, 1)
plt.plot(T_surf[ix], H2O_tot[ix], '.')
plt.xlabel('Mean T (z<3km) [K]')
plt.ylabel('Total H2O [mol]')
plt.subplot(1, 3, 2)
plt.plot(T_surf[ix], 1e6 * O3_tot[ix], '.')
plt.xlabel('Mean T (z<3km) [K]')
plt.ylabel('Total O3 [µmol]')
plt.subplot(1, 3, 3)
plt.plot(H2O_tot[ix], 1e6 * O3_tot[ix], '.')
plt.xlabel('Total H2O [mol]')
plt.ylabel('Total O3 [µmol]')
return labels
def test_bayesian_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 = BayesianGaussianMixture(n_components=5, n_init=10, random_state=0)
y_pred1 = gm.fit_predict(X)
y_pred2 = gm.predict(X)
assert_array_equal(y_pred1, y_pred2)
class VBEM(object):
def __init__(self, n_components=5, dataset=None):
self.model = BayesianGaussianMixture(n_components=n_components,
max_iter=10000)
self.n_components = n_components
self.class_num = dataset.class_num
self.data_num = dataset.data_num
self.data = dataset.data
self.label = dataset.label
self.bestVBEM_k = 0
self.model.fit(self.data)
def draw(self):
label = self.model.predict(self.data)
self.bestVBEM_k = max(label) + 1
data_2d = pd.DataFrame(self.data, columns=['x', 'y'])
label_2d = pd.DataFrame(label, columns=['label'])
label_names = np.unique(label)
colors = [
plt.cm.tab10(i / float(len(label_names)))
for i in range(len(label_names))
]
tmp_2d = pd.concat([data_2d, label_2d], axis=1)
plt.figure()
for i, label in enumerate(label_names):
plt.scatter(tmp_2d.loc[tmp_2d.label == label].x,
tmp_2d.loc[tmp_2d.label == label].y,
s=5,
cmap=colors[i],
alpha=0.5)
plt.title('Best GMM with VBEM_' + str(self.class_num) + '_' +
str(self.data_num))
plt.savefig('res/GMM_VBEM_' + str(self.class_num) + '_' +
str(self.data_num) + '.jpg')
def test_bayesian_mixture_fit_predict_n_init():
# Check that fit_predict is equivalent to fit.predict, when n_init > 1
X = np.random.RandomState(0).randn(50, 5)
gm = BayesianGaussianMixture(n_components=5, n_init=10, random_state=0)
y_pred1 = gm.fit_predict(X)
y_pred2 = gm.predict(X)
assert_array_equal(y_pred1, y_pred2)
def test_bayesian_mixture_predict_predict_proba():
# this is the same test as test_gaussian_mixture_predict_predict_proba()
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
for prior_type in PRIOR_TYPE:
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
Y = rand_data.Y
bgmm = BayesianGaussianMixture(
n_components=rand_data.n_components,
random_state=rng,
weight_concentration_prior_type=prior_type,
covariance_type=covar_type)
# Check a warning message arrive if we don't do fit
assert_raise_message(NotFittedError,
"This BayesianGaussianMixture instance"
" is not fitted yet. Call 'fit' with "
"appropriate arguments before using "
"this method.", bgmm.predict, X)
bgmm.fit(X)
Y_pred = bgmm.predict(X)
Y_pred_proba = bgmm.predict_proba(X).argmax(axis=1)
assert_array_equal(Y_pred, Y_pred_proba)
assert_greater_equal(adjusted_rand_score(Y, Y_pred), .95)
def genotype(cnvays):
result = []
n_com = 10 if cnvays.shape[1] >= 10 else cnvays.shape[1]
n_init = 3
for cnvay in cnvays:
cnv = [[x] for x in cnvay]
dpgmm = BayesianGaussianMixture(
n_components=n_com,
n_init=n_init,
max_iter=10000,
weight_concentration_prior_type='dirichlet_process').fit(cnv)
labels = dpgmm.predict(cnv)
normed_ay = np.arange(0, np.max(cnvay) + 0.5, 0.5)
swlabels = {}
for rawlabel in np.unique(labels):
swlabels[rawlabel] = normed_ay[np.argmin(
np.abs(normed_ay - np.median(cnvay[labels == rawlabel])))]
newlabels = [swlabels[x] for x in labels]
gtlabes = {0: 'dd', 0.5: 'Ad', 1: 'AA', 1.5: 'AB', 2: 'BB', 2.5: 'BC'}
finalline = [gtlabes.get(x, 'M') for x in newlabels]
if len(np.unique(finalline)) > 1:
sc = silhouette_score(cnv, finalline,
metric='euclidean') # silhouette_score
chs = calinski_harabaz_score(cnv, labels) # calinski_harabaz_score
else:
sc = np.nan
chs = np.nan
llh = dpgmm.score(
cnv) # Log likelihood of the Gaussian mixture given X
finalline += [sc, chs, llh]
result.append(finalline)
return result
def predict_cp_interval(self, n_components = 30):
'''
Estimates the (phenotypical) levels of observed amplitudes, regardless of order. Consequently, each
observed time-point is classified. Between each transition from one inferred level to another one, a
change-point with uniform distirbution is inferred.
:param n_components: maximum number of components of the mixture model (default is 30)
'''
logging.warn("Predicting CP intervals")
state_mix = BayesianGaussianMixture(
n_components,
n_init = 10,
weight_concentration_prior_type = 'dirichlet_distribution',
verbose = 1,
max_iter = 500,
tol=1e-12
)
observed = self.observation[~np.isnan(self.observation)].reshape(-1, 1)
state_mix.fit(observed)
classified = deepcopy(self.observation)
predicted = state_mix.predict(classified[~np.isnan(classified)].reshape(-1, 1))
classified[~np.isnan(classified)] = predicted
last = None
begin = 0
for i, c in enumerate(classified):
if not np.isnan(c):
last = c
begin = i
break
segments = []
for i in range(begin, classified.shape[0]):
if not np.isnan(classified[i]):
if classified[i] != last:
s = np.max(np.argwhere(~np.isnan(classified[0:i-1])))
segments.append((s, i))
last = classified[i]
begin = i
# calculate uniform distribution parameters
result = []
for segment in segments:
a = segment[0]
b = segment[1]
distro = {
'begin': a,
'end': b
}
result.append(distro)
result = pd.DataFrame(result)
return result, state_mix
def clusteringBayGaussMixt(X, y, nclusters, paramlist):
bgm = BayesianGaussianMixture(n_components=nclusters, covariance_type='full', tol=0.001, reg_covar=1e-06, max_iter=100, n_init=1,\
init_params='kmeans', weight_concentration_prior_type='dirichlet_process', weight_concentration_prior=None,\
mean_precision_prior=None, mean_prior=None, degrees_of_freedom_prior=None, covariance_prior=None, \
random_state=None, warm_start=False, verbose=0, verbose_interval=10)
bgm.fit(X, y)
labels = bgm.predict(X)
return labels
def convert_to_deciles(y, n=10, gmm=False):
"""
By default converts to deciles, can be changed based on choice of n.
"""
if gmm:
# this is experimental
bgm = BayesianGaussianMixture(n_components=10)
bgm.fit(y.reshape(-1, 1))
return bgm.predict(y.reshape(-1, 1))
return np.array(pd.cut(y, n, labels=range(n)))
def bayesian_gaussian_mixture(latent):
gauss_mix = BayesianGaussianMixture(
n_components=N_COMPONENTS,
covariance_type=COVARIANCE_TYPE,
weight_concentration_prior_type=WEIGHT_CONCENTRATION_PRIOR_TYPE,
weight_concentration_prior=WEIGHT_CONCENTRATION_PRIOR,
max_iter=MAX_ITER,
verbose=VERBOSE).fit(latent)
labels = gauss_mix.predict(latent)
return labels
def getBayesianGaussian(filename, targetname):
# use Bayesian Gaussian model on tsne
matrix = tsne(filename)
# fit the model
model = BayesianGaussianMixture(n_components=8).fit(matrix)
label = model.predict(matrix)
print(label)
# generate graph
getTsne(filename, targetname, label)
def cluster_embeddings(
self,
cluster_method,
num_clusters,
use_decomposed,
additional_params={"random_state": 0},
):
"""
@param cluster_method clustering method, one of {KMeans, Spectral, GaussianMix, BayesGaussMix}
@param num_clusters number of clusters
@param use_decomposed boolean, whether to use decomposed or raw representations
@param additional_params {param_name: value} of parameters accepted by the sklearn clustering function.
Cannot include n_components.
Predicts cluster assignments for data points on raw or decomposed embedding representations.
"""
self.cluster_method = cluster_method
self.num_clusters = num_clusters
if use_decomposed:
vec_df = self.decomposed_embedding_representation
else:
vec_df = self.embedding_representation
if self.cluster_method == "KMeans":
self.predicted_labels = KMeans(
n_clusters=self.num_clusters, **additional_params
).fit_predict(vec_df)
if self.cluster_method == "Spectral":
self.predicted_labels = SpectralClustering(
n_clusters=self.num_clusters,
affinity="cosine",
assign_labels="discretize",
**additional_params,
).fit_predict(vec_df)
if self.cluster_method == "GaussianMix":
gm_model = GaussianMixture(
n_components=self.num_clusters, **additional_params
).fit(vec_df)
self.predicted_labels = gm_model.predict(vec_df)
if self.cluster_method == "BayesGaussMix":
bgm_model = BayesianGaussianMixture(
n_components=self.num_clusters, **additional_params
).fit(vec_df)
self.predicted_labels = bgm_model.predict(vec_df)
self.num_clusters = len(
set(self.predicted_labels)
) # set num_clusters to actual num components
def embed_mixture_variational(xmaps_np,
n_components,
):
sample_by_feature = np.vstack([np_map.flatten()
for dtag, np_map
in xmaps_np.items()
]
)
# mixture = BayesianGaussianMixture()
begin = time.time()
pca = PCA(n_components=50)
sample_by_feature_pca = pca.fit_transform(sample_by_feature)
print("shape is: {}".format(sample_by_feature_pca.shape))
mixture = BayesianGaussianMixture(n_components,
covariance_type="spherical",
verbose=10,
verbose_interval=2,
)
mixture.fit(sample_by_feature_pca)
finish = time.time()
print(mixture)
print("Finished in {}".format(finish - begin))
print(mixture.predict(sample_by_feature_pca))
print(mixture.weights_)
clusters = mixture.predict(sample_by_feature_pca)
probabilities = mixture.score_samples(sample_by_feature_pca)
return mixture, pca, clusters, probabilities
def split_units(self, n_clusters):
"""Splits recovered spikes per units into clusters."""
self.n_clusters = n_clusters
if self.cid is None:
self.cid = []
for i in tqdm(range(self.n_unit), 'Splitting Units'):
f = self.features[i]
f = f.reshape([f.shape[0], self.n_feat * self.n_main_chan])
clustering = BayesianGaussianMixture(
n_components=n_clusters, max_iter=500)
clustering.fit(f)
self.cid.append(clustering.predict(f))
return self.cid
def bayesian_gaussian_mixture(vector: np.array, n: int, BIC_calculate = False):
if BIC_calculate == True:
np.random.seed(140597)
mask = np.random.choice([False, True], len(vector), p=[0.70, 0.30])
model_train = BayesianGaussianMixture(n_components=n, covariance_type='full').fit(vector[~mask])
validation_score = model_train.score(vector[mask])
train_score = model_train.score(vector[~mask])
return validation_score, train_score
else:
np.random.seed(140597)
mask = np.random.choice([False, True], len(vector), p=[0.70, 0.30])
dpgmm = BayesianGaussianMixture(n_components=n, covariance_type='full', max_iter=900, tol=1e-4).fit(vector[~mask])
cluster_label = dpgmm.predict(vector)
return cluster_label
def _dpgmm(fet, n_comp=8, max_iter=400):
from sklearn.mixture import BayesianGaussianMixture as DPGMM
dpgmm = DPGMM(n_components=n_comp,
covariance_type='full',
weight_concentration_prior=1e-3,
weight_concentration_prior_type='dirichlet_process',
init_params="kmeans",
max_iter=100,
random_state=0,
verbose=0,
verbose_interval=10) # init can be "kmeans" or "random"
dpgmm.fit(fet)
label = dpgmm.predict(fet)
return label
def gmm_hyper(hyper_image, features, n_clusters):
"""
"""
gmm = BayesianGaussianMixture(n_components=n_clusters,
covariance_type='spherical').fit(features)
labels = gmm.predict(features)
label_image = labels.reshape(hyper_image.shape[:-1])
gmm_spectra = average_spectra(hyper_image, labels)
score = calinski_harabaz_score(features, label_image.ravel())
return label_image, gmm_spectra, score
def run_BayesianGaussianMixture(Y, K):
"""
For K-means clustering
Input
-----
Y: the expression matrix
K: number of clusters
return
-----
clusters assigned to each cell.
"""
gmm = BayesianGaussianMixture(K, max_iter=1000)
gmm.fit(Y)
return gmm.predict(Y)
def Bayesian_gmm_inference(self, data: Union[pd.DataFrame, np.ndarray],
**params) -> None:
"""
Bayesian inference of parameters by the EM algorithms of sklearn,
accept only DataFrame with numerical data, please do the feature engineering before enter the Dataframe
:param data: Set of data to do the inference
:return: None
"""
Bayesian_gmm = BayesianGaussianMixture(**params)
Bayesian_gmm.fit(data)
self.means = Bayesian_gmm.means_
self.precision = Bayesian_gmm.precisions_
self.weight = Bayesian_gmm.weights_
self.label = Bayesian_gmm.predict(data)
self.data = data
self.nrb_comp = Bayesian_gmm.n_components
ax1_min, ax1_max, ax2_min, ax2_max = plt.axis()
plt.xlim((x1_min, x1_max))
plt.ylim((x2_min, x2_max))
plt.title('GMM', fontsize=15)
plt.grid(b=True, ls=':', color='#606060')
# DPGMM
dpgmm = BayesianGaussianMixture(n_components=n_components, covariance_type='full', max_iter=1000, n_init=5,
weight_concentration_prior_type='dirichlet_process', weight_concentration_prior=0.1)
dpgmm.fit(x)
centers = dpgmm.means_
covs = dpgmm.covariances_
print('DPGMM均值 = \n', centers)
print('DPGMM方差 = \n', covs)
y_hat = dpgmm.predict(x)
print(y_hat)
ax = plt.subplot(212)
grid_hat = dpgmm.predict(grid_test)
grid_hat = grid_hat.reshape(x1.shape)
plt.pcolormesh(x1, x2, grid_hat, cmap=cm)
plt.scatter(x[:, 0], x[:, 1], s=20, c=y, cmap=cm, marker='o', edgecolors='#202020')
for i, cc in enumerate(zip(centers, covs)):
if i not in y_hat:
continue
center, cov = cc
value, vector = sp.linalg.eigh(cov)
width, height = value[0], value[1]
v = vector[0] / sp.linalg.norm(vector[0])
appl = 'WHE' # Create vector with P and Q values and plot them P = d[appl].P[init:end].values Q = d[appl].Q[init:end].values X = np.transpose([P, Q]) plt.plot(d[appl].P[init:end], d[appl].Q[init:end],'o', alpha=0.1) # Normalize X sscl = StandardScaler().fit(X) X = sscl.transform(X) # Apply clusterer bgm = BayesianGaussianMixture(n_components=33, covariance_type='full', weight_concentration_prior_type='dirichlet_distribution', random_state=42).fit(X) y_pred = bgm.predict(X) # Plot clusters with X unnormalized X = sscl.inverse_transform(X) plt.figure() plt.scatter(X[:,0],X[:,1], color=colors[y_pred]) means = sscl.inverse_transform(bgm.means_) medians = get_medians(X, y_pred) # plt.plot(means[:,0],means[:,1],'kx') plt.plot(medians[:,0],medians[:,1],'kx') # TODO: Compare mean with ground truth plt.figure() plt.plot(P) P_pred = means[y_pred][:,0]
data_thr.rateC, data_thr.rateCA]
scaler = StandardScaler()
X = scaler.fit_transform(X)
# 1 corresponds to data_thr.rate and 4=5-1 to data_thr.rateC
w = w / np.sqrt(scaler.var_[1:])
# w = np.exp(-np.exp(3 * w.mean(axis=1)))
w = 1. / w.mean(axis=1) ** 2
Html_file = open("gmm_sklearn_files/gmm3_sklearn.html", "w")
gmm = BayesianGaussianMixture(n_components=3, alpha_prior=0.1, beta_prior=1,
n_init=5)
gmm.fit(X) # , weights=w) not implemented in sklearn yet
preds = gmm.predict(X)
probs = gmm.predict_proba(X)
data_thr['preds'] = pd.Series(preds).astype("category")
color_key = ["red", "blue", "yellow", "grey", "black", "purple", "pink",
"brown", "green", "orange"] # Spectral9
color_key = color_key[:len(set(preds))+1]
covs = gmm.covariances_
means = gmm.means_
# transform cov for non-standardizeed data:
covs = np.array([np.dot(np.diag(np.sqrt(scaler.var_)),
np.dot(covs[j], np.diag(np.sqrt(scaler.var_))))
for j in range(covs.shape[0])])
