def try_covar(type_str, x_words):
clf = DPGMM(n_components=20, covariance_type=type_str, alpha=30, n_iter=1000)
clf.fit(x_data)
y_ = clf.predict(x_data)
print type_str
print_centers(x_words, y_, clf)
print
def train_dpgmm(X, n_components=3, covariance_type='diag', alpha=1.0,
random_state=None, thresh=None, tol=0.001, verbose=False,
min_covar=None, n_iter=10, params='wmc', init_params='wmc'):
"""
This function trains a Infinite Gaussian Mixture Model for clustering
:param X:
:param n_components:
:param covariance_type:
:param alpha:
:param random_state:
:param thresh:
:param tol:
:param verbose:
:param min_covar:
:param n_iter:
:param params:
:param init_params:
:return: a trained DPGMM clustering model
"""
model = DPGMM(n_components=n_components,
covariance_type=covariance_type,
alpha=alpha,
random_state=random_state,
thresh=thresh,
verbose=verbose,
min_covar=min_covar,
n_iter=n_iter,
params=params,
init_params=init_params)
model = model.fit(X)
return model
def fit_vel_profile_dpgmm(vel_profile, n_comps=5, dp=False):
"""
fit a velocity profile with DP-GMM
"""
N = 1000 # 1000 samples to fit
integral = np.sum(vel_profile)
#vel_profile is a 1D array, try to convert it to samples
t = np.linspace(0, 1, len(vel_profile))
data = np.array([])
for i in range(len(t)):
n_samples = vel_profile[i] / integral * N
if n_samples > 0:
#add samples
samples = np.ones(n_samples) * t[i]
#add noise
data = np.concatenate([data, samples])
fit_data = np.array([data]).transpose()
#fit Dirichlet-Process Gaussian Mixture Model,
#something wrong with the module? The clusters seem merged...
if dp:
model = DPGMM(n_components=n_comps, n_iter=1000, alpha=10)
else:
model = GMM(n_components=n_comps)
model.fit(fit_data)
return model
def Dirichlet(cluster_data, identification, iteration_number = 1):
print "In Dirichlet"
for i in range(0,iteration_number):
print "On iteration number ", i
dirichlet = DPGMM(n_components = len(cluster_data)).fit(cluster_data)
#paremeters= dirichlet.get_params #returns parameters of the algorithm as a whole from the fit
predict = dirichlet.predict(cluster_data)
n_clusters_ = len(set(predict)) - (1 if -1 in predict else 0)
print('Estimated number of clusters with Dirichlet: %d' % n_clusters_)
return _make_final_list(identification, predict)
def Dirichlet(cluster_data, identification, iteration_number=1):
print "In Dirichlet"
for i in range(0, iteration_number):
print "On iteration number ", i
dirichlet = DPGMM(n_components=len(cluster_data)).fit(cluster_data)
#paremeters= dirichlet.get_params #returns parameters of the algorithm as a whole from the fit
predict = dirichlet.predict(cluster_data)
n_clusters_ = len(set(predict)) - (1 if -1 in predict else 0)
print('Estimated number of clusters with Dirichlet: %d' % n_clusters_)
return _make_final_list(identification, predict)
def load_build_dpggm(dpggm_model_name, x_data):
if os.path.isfile(dpggm_model_name):
clf = load_dpggm(dpggm_model_name)
else:
clf = DPGMM(n_components=30, covariance_type='diag', alpha=5, n_iter=1000)
logging.info("Fitting with DPGMM")
clf.fit(x_data)
pickle.dump(clf, open(dpggm_model_name, 'wb'))
logging.info("Fitted")
print clf.converged_
return clf
def dpgmm(self, k=10, alpha=1.0):
self.h = DPGMM(n_components=k,
alpha=alpha,
random_state=self.random_seed).fit(self.X)
self.Y = self.h.predict(self.X)
self.k = k # this is the max number of components in dpgmm
self.centers = self.getCenters()
#TODO
# posterior = self.h.predict_proba( self.X[:5] )
# likelihood = self.h.score( self.X[:5] )
return self
def _fit_dpgmm(self, x):
# clustering
k = max(self.crange)
for r in xrange(self.repeats):
# info
if self.debug is True:
print '\t[%s][c:%d][r:%d]' % (self.clus_type, k, r + 1),
# fit and evaluate model
model_kwargs = {}
if 'alpha' in self.clus_kwargs:
model_kwargs.update(alpha=self.clus_kwargs['alpha'])
if 'conv_thresh' in self.clus_kwargs:
model_kwargs.update(thresh=self.clus_kwargs['conv_thresh'])
if 'max_iter' in self.clus_kwargs:
model_kwargs.update(n_iter=self.clus_kwargs['max_iter'])
model = DPGMM(n_components=k,
covariance_type=self.cvtype,
**model_kwargs)
model.fit(x)
self._labels[r] = model.predict(x)
self._parameters[r] = model.means_
self._ll[r] = model.score(x).sum()
# evaluate goodness of fit for this run
#self._gof[r] = self.gof(x, self._ll[r], k)
if self.gof_type == 'aic':
self._gof[r] = model.aic(x)
if self.gof_type == 'bic':
self._gof[r] = model.bic(x)
# debug
if self.debug is True:
print self._gof[r], model.n_components, model.weights_.shape[0]
def main():
if len(sys.argv) != 4:
print(__doc__)
return 1
infile = sys.argv[1]
N = int(sys.argv[2])
num_random = int(sys.argv[3])
print("Reading in", infile)
fullarr = np.loadtxt(fileinput.input(infile), delimiter = '\t')[:,:-7]
stds = np.apply_along_axis(np.std, 0, fullarr)[:,np.newaxis].T
means = np.apply_along_axis(np.mean, 0, fullarr)[:,np.newaxis].T
stds[stds == 0] = 1.0
num_lines = num_random
fullarr = fullarr[np.random.choice(fullarr.shape[0], num_lines, replace=True),:]
fullarr = (fullarr - means) / stds
output = ''
print("Parameter searching...")
igmm = None
best_score = -100000
best_alpha = -1
best_model = None
for alpha in [0.01,0.1,1,10]:
print("Learning infinite GMM with N={}, alpha={}".format(N, alpha))
output += "Learning infinite GMM with N={}, alpha={}\n".format(N, alpha)
igmm = DPGMM(covariance_type='diag', n_components=N, alpha=alpha, init_params='wmc')
igmm.fit(fullarr)
score = igmm.score(fullarr)
score = sum(score)/len(score)
print('{}: {} with {} clusters'.format(alpha, score, igmm.n_components))
output += '{}: {} with {} clusters\n'.format(alpha, score, igmm.n_components)
if score > best_score:
best_score = score
best_alpha = alpha
best_model = igmm
print('Best alpha={}, score={}'.format(best_alpha, best_score))
output += 'Best alpha={}, score={}\n'.format(best_alpha, best_score)
with open('parameter_search_results.txt', 'a+') as outf:
outf.write(output)
return 0
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 kmeans(self, k=2): self.h = KMeans(n_clusters = k, init = 'k-means++', n_init = 10, max_iter = 1000, tol = 0.00001, random_state = self.random_seed).fit( self.X ) self.Y = self.h.labels_ self.k = k self.centers = self.getCenters() return self
def affinity(self, k=2): # K is not used here self.h = AffinityPropagation(damping=0.75, preference=k, max_iter=200, convergence_iter=15, copy=True, affinity='euclidean').fit( self.X ) self.Y = self.h.labels_ self.k = k self.centers = self.getCenters() return self
def meanshift(self, k=2): # K is not used here self.h = MeanShift(bandwidth=None, seeds=None, bin_seeding=False, min_bin_freq=1, cluster_all=True).fit( self.X ) self.Y = self.h.labels_ self.k = k self.centers = self.getCenters() return self
def clustering_algorithm(lengths,
covs,
kmers,
algorithm='dirichlet',
K=300,
max_epoch=25,
t=0,
seed=None,
mu_pkl=None):
"""Clusters using given algorithm
Takes as argument cluster names, lengths, and coverage/kmer matrices.
"""
# create matrix for clustering
logging.info('Creating data matrix')
X = create_matrix(lengths, covs, kmers)
# project down dimension
logging.info('Performing dimensionality reduction')
X = reduce_dimensionality(X)
# do the clustering
logging.info('Starting clustering algorithm')
if algorithm == 'sk-gmm':
gmm = GMM(n_components=K, covariance_type='full', n_iter=500)
gmm.fit(X)
z = gmm.predict(X)
return z
elif algorithm == 'sk-dpgmm':
gmm = DPGMM(n_components=K, covariance_type='full', n_iter=500)
gmm.fit(X)
z = gmm.predict(X)
return z
elif algorithm == 'dirichlet':
n_data = X.shape[0]
mu_pred_dem, Sigma_pred_dem, asgn_dem, llik = dirichlet_em(
X.T, K=K, n_minibatch=n_data, max_epoch=max_epoch, seed=seed)
if mu_pkl:
with open(mu_pkl, 'wb') as f:
pickle.dump((mu_pred_dem, asgn_dem), f)
# further compress stuff
compressed_clusters = agglomerative(mu_pred_dem.T, t=t)
transl_dict = {i: c for i, c in enumerate(compressed_clusters)}
asign_dem_agg = np.array([transl_dict[i] for i in asgn_dem])
return asign_dem_agg
elif algorithm == 'ard':
n_data = X.shape[0]
_, _, asgn, _ = variational_em(X.T,
K=K,
n_minibatch=n_data,
max_epoch=max_epoch)
return asgn
else:
raise ValueError("Invalid algorithm name")
def _fit_dpgmm(self, x):
# clustering
k = max(self.crange)
for r in xrange(self.repeats):
# info
if self.debug is True:
print '\t[%s][c:%d][r:%d]' % (self.clus_type, k, r + 1),
# fit and evaluate model
model_kwargs = {}
if 'alpha' in self.clus_kwargs:
model_kwargs.update(alpha=self.clus_kwargs['alpha'])
if 'conv_thresh' in self.clus_kwargs:
model_kwargs.update(thresh=self.clus_kwargs['conv_thresh'])
if 'max_iter' in self.clus_kwargs:
model_kwargs.update(n_iter=self.clus_kwargs['max_iter'])
model = DPGMM(n_components=k, covariance_type=self.cvtype,
**model_kwargs)
model.fit(x)
self._labels[r] = model.predict(x)
self._parameters[r] = model.means_
self._ll[r] = model.score(x).sum()
# evaluate goodness of fit for this run
#self._gof[r] = self.gof(x, self._ll[r], k)
if self.gof_type == 'aic':
self._gof[r] = model.aic(x)
if self.gof_type == 'bic':
self._gof[r] = model.bic(x)
# debug
if self.debug is True:
print self._gof[r], model.n_components, model.weights_.shape[0]
def _Dirichlet(cluster_data, identification):
print "In Dirichlet"
for i in range(0, 3):
print "i is ", i
dirichlet = DPGMM(n_components=len(cluster_data)).fit(cluster_data)
#paremeters= dirichlet.get_params #returns parameters of the algorithm as a whole from the fit
predict = dirichlet.predict(cluster_data)
n_clusters_ = len(set(predict)) - (1 if -1 in predict else 0)
print('Estimated number of clusters with Dirichlet: %d' % n_clusters_)
final = []
for x in range(0, len(identification)):
final.append([identification[x], predict[x]])
print "this is what final sort of looked like"
print final[:3]
return final
def plot_num_iters_dpgmm(X, num_c, cv_type, alpha, max_iters, n_init):
bic = []
for iters in np.arange(1, max_iters):
best_bic = np.inf
for j in xrange(n_init):
dpgmm = DPGMM(n_components=comp, covariance_type=cv_type, \
alpha=a, n_iter=iters)
dpgmm.fit(X)
b = dpgmm.bic(X)
if b < best_bic:
best_bic = b
bic.append(best_bic)
fig, ax = plt.subplots(figsize=(10, 8))
ax.plot(np.arange(1, max_iters), bic)
ax.set_title('BIC vs. Number of Iterations DPGMM')
ax.set_xlabel('Number of iterations')
ax.set_ylabel('BIC score')
return fig
def _Dirichlet(cluster_data, identification):
print "In Dirichlet"
for i in range(0, 3):
print "i is ", i
dirichlet = DPGMM(n_components=len(cluster_data)).fit(cluster_data)
# paremeters= dirichlet.get_params #returns parameters of the algorithm as a whole from the fit
predict = dirichlet.predict(cluster_data)
n_clusters_ = len(set(predict)) - (1 if -1 in predict else 0)
print ("Estimated number of clusters with Dirichlet: %d" % n_clusters_)
final = []
for x in range(0, len(identification)):
final.append([identification[x], predict[x]])
print "this is what final sort of looked like"
print final[:3]
return final
def train_DPGMM(d, max_n_comp=100, max_n_iter=500):
'''Imports Data, Trains a DPGMM, Generates predictions testing'''
print "Training Model..."
gmm = DPGMM(max_n_comp, n_iter=max_n_iter)
start = timeit.default_timer()
gmm.fit(d)
end = timeit.default_timer()
print "Training completed in %f seconds" % (end-start)
print
print "Converged: "
print gmm.converged_
print
return gmm
def plot_alpha_dpgmm(X, num_c, cv_type, alphas, iters, n_init):
bic = []
for a in alphas:
best_bic = np.inf
for j in xrange(n_init):
dpgmm = DPGMM(n_components=num_c, covariance_type=cv_type, \
alpha=a, n_iter=iters)
dpgmm.fit(X)
b = dpgmm.bic(X)
if b < best_bic:
best_bic = b
bic.append(best_bic)
fig, ax = plt.subplots(figsize=(10, 8))
ax.plot(alphas, bic, 'bo-', lw=2)
ax.set_title('BIC vs. Alpha DPGMM')
ax.set_xlabel('Alpha')
ax.set_ylabel('BIC score')
return fig
def meanshift(self, k=2): # K is not used here
self.h = MeanShift(bandwidth=None,
seeds=None,
bin_seeding=False,
min_bin_freq=1,
cluster_all=True).fit(self.X)
self.Y = self.h.labels_
self.k = k
self.centers = self.getCenters()
return self
def gmm(self, k=2):
self.h = GMM(n_components=k, random_state=self.random_seed).fit(self.X)
self.Y = self.h.predict(self.X)
self.k = k
self.centers = self.getCenters()
#TODO
# posterior = self.h.predict_proba( self.X[:5] )
# likelihood = self.h.score( self.X[:5] )
return self
def gmm(self, k=2): self.h = GMM(n_components=k, random_state = self.random_seed).fit( self.X ) self.Y = self.h.predict( self.X ) self.k = k self.centers = self.getCenters() #TODO # posterior = self.h.predict_proba( self.X[:5] ) # likelihood = self.h.score( self.X[:5] ) return self
def dpgmm(self, k=10, alpha=1.0): self.h = DPGMM(n_components=k, alpha=alpha, random_state = self.random_seed).fit( self.X ) self.Y = self.h.predict( self.X ) self.k = k # this is the max number of components in dpgmm self.centers = self.getCenters() #TODO # posterior = self.h.predict_proba( self.X[:5] ) # likelihood = self.h.score( self.X[:5] ) return self
def kmeans(self, k=2):
self.h = KMeans(n_clusters=k,
init='k-means++',
n_init=10,
max_iter=1000,
tol=0.00001,
random_state=self.random_seed).fit(self.X)
self.Y = self.h.labels_
self.k = k
self.centers = self.getCenters()
return self
def affinity(self, k=2): # K is not used here
self.h = AffinityPropagation(damping=0.75,
preference=k,
max_iter=200,
convergence_iter=15,
copy=True,
affinity='euclidean').fit(self.X)
self.Y = self.h.labels_
self.k = k
self.centers = self.getCenters()
return self
def plot_GPLVM_data_cluster(results_dir, n_clusters=None, VB=False):
# Load relevant datasets
data_array = np.genfromtxt(os.path.join(results_dir, 'summary.csv'), delimiter=',')
X = (np.genfromtxt(os.path.join(results_dir, 'GPLVM-datasets-2.csv'), delimiter=','))
datasets = [line.rstrip('\n') for line in open(os.path.join(results_dir, 'datasets.csv'), 'r').readlines()]
methods = [line.rstrip('\n') for line in open(os.path.join(results_dir, 'methods.csv'), 'r').readlines()]
# Fit a mixture model
if n_clusters is None:
m = DPGMM()
elif VB:
m = VBGMM(alpha = 10, n_components=n_clusters)
else:
m = GMM(n_components=n_clusters, n_init=100)
m.fit(data_array.T)
clusters = m.predict(data_array.T)
# Plot
#clf()
figure(1)
pretty_scatter(X[:,0], X[:,1], clusters, 200*np.ones(X[:,0].shape), datasets)
xlabel('Dimension 1')
ylabel('Dimension 2')
if n_clusters is None:
title('CRP MoG')
elif VB:
title('%d clusters with VB' % n_clusters)
else:
title('%d clusters with EM' % n_clusters)
show()
def dpgmm_segmenter(factors, width=MEDIAN_WIDTH):
factors = median_filter(factors, size=(MEDIAN_WIDTH, 1), mode='mirror')
factors = pre.scale(factors, axis=1)
best_boundaries = [0, factors.shape[0] - 1]
best_n_types = 1
dpgmm = DPGMM(n_components=10, covariance_type='diag', alpha=10, n_iter=100)
dpgmm.fit(np.tile(factors, (10, 1)))
labels = dpgmm.predict(factors)
boundaries, labels = find_boundaries(labels, width)
if len(np.unique(labels)) > 1:
best_boundaries = boundaries
best_n_types = len(np.unique(labels))
if len(best_boundaries) < best_n_types + 1:
best_n_types = len(best_boundaries) - 1
best_labels = segment_labeling(factors, best_boundaries, c_method='kmeans', k=best_n_types)
best_boundaries = np.array(best_boundaries)
return best_boundaries, best_labels
def main():
if len(sys.argv) != 5:
print(__doc__)
return 1
infiles = glob(sys.argv[1])
outfile = sys.argv[2]
N = int(sys.argv[3])
alpha = float(sys.argv[4])
print("Reading in", len(infiles), "files")
fullarr = np.loadtxt(fileinput.input(infiles), delimiter = '\t')[:,:-7]
stds = np.apply_along_axis(np.std, 0, fullarr)[:,np.newaxis].T
means = np.apply_along_axis(np.mean, 0, fullarr)[:,np.newaxis].T
stds[stds == 0] = 1.0
num_lines = 10000
fullarr = fullarr[np.random.choice(fullarr.shape[0], num_lines, replace=True),:]
fullarr = (fullarr - means) / stds
print("Learning infinite GMM with N={}, alpha={}".format(N, alpha))
igmm = DPGMM(covariance_type='diag', n_components=N, alpha=alpha, init_params='wmc')
igmm.fit(fullarr)
print("Infinite GMM trained, saving")
with open(outfile + '_' + num_lines, 'wb') as out_model:
pickle.dump(igmm, out_model)
print("Score:", igmm.score(fullarr))
print("Num Components:", igmm.n_components)
return 0
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 get_best_dpgmm(X, num_c, cv_type, alpha, iters, n_init, rand_state=None):
best_bic = np.inf
bic_dpgmm = None
lbl_vec_dpgmm = np.zeros(X.shape[0])
prob_vec_dpgmm = np.zeros(X.shape[0])
log_prob_dpgmm = None
for i in xrange(n_init):
dpgmm = DPGMM(n_components=num_c, covariance_type=cv_type, \
alpha=alpha, random_state=rand_state)
dpgmm.fit(X)
b = dpgmm.bic(X)
if b < best_bic:
bic_dpgmm = b
lbl_vec = dpgmm.predict(X)
prob_vec = dpgmm.predict_proba(X)
log_prob_dpgmm = np.sum(dpgmm.score(X))
return [lbl_vec, prob_vec, bic_dpgmm, log_prob_dpgmm]
def main(method,cluster_num=30,alpha=.5):
f ='/Users/davidgreenfield/Downloads/features_csv_tmp.csv'
#f ='/Users/davidgreenfield/Downloads/features_f500.csv'
cols=range(1,4096)
feats =np.loadtxt(open(f,"rb"),delimiter=",",skiprows=1,usecols=(cols))
asins = np.loadtxt(open(f,"rb"),delimiter=",",skiprows=1,usecols=([0]),dtype=str)
if method == 'kmeans':
k_means=cluster.KMeans(n_clusters=cluster_num)
k_means.fit(feats)
y = k_means.labels_
if MAKE_GRAPH==1:
print "hello 1"
create_graph(k_means)
elif method == 'GMM_VB':
gmm_vb = VBGMM.fit(feats,n_components=50,alpha=.5)
y = gmm_vb.predict(feats)
cluster_no = len(np.unique(y))
elif method == 'GMM_DP':
gmm_dp = DPGMM(n_components=50,alpha=alpha)
gmm_dp.fit(feats)
y = gmm_dp.predict(feats)
cluster_no = len(np.unique(y))
clusters=[]
groups={}
data=load_data('./data/boots_aws.csv')
for i in range(0,cluster_num):
groups[i]=np.where(y==i)
ids=asins[groups[i]]
clusters.append(ids)
links=[data[x]['url'] for x in ids]
create_html(links,"templates/groups/group"+str(i)+".html")
output_clusters(clusters,"outputs/clusters.csv")
def test1():
print 'test1'
model = VDPGMM(T=10, alpha=1, max_iter=50)
X, Y = getXY('iris')
model.fit(X)
y = model.predict(X)
print 'VDPGMM'
print len(np.unique(y)), np.unique(y)
print[np.sum(y == label) for label in np.unique(y)]
from sklearn.mixture import DPGMM
model = DPGMM(n_components=10, alpha=1, n_iter=50)
model.fit(X)
y = model.predict(X)
print 'DPGMM'
print len(np.unique(y)), np.unique(y)
print[np.sum(y == label) for label in np.unique(y)]
def dpgmm_cluster(self, max_n_clusters=30, max_iter=300, verbose=False):
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=verbose,
verbose_interval=10) # init can be "kmeans" or "random"
dpgmm.fit(self.fet)
label = dpgmm.predict(self.fet)
self.clu.membership = label
self.clu.__construct__()
self.clu.emit('cluster')
return dpgmm
def select_model(model_key):
model = None
if model_key == 'b':
model = GradientBoostingClassifier()
elif model_key == 'svc':
model = SVC(probability=True, gamma='auto')
elif model_key == 'nusvc':
print 'selecting NuSVC'
model = NuSVC(probability=True)
elif model_key == 'r':
model = RandomForestClassifier(class_weight={'buy': 1, 'stay': .75})
elif model_key == 'e':
model = ExtraTreesClassifier()
elif model_key == 'nn':
model = KNeighborsClassifier()
elif model_key == 'gmm':
model = DPGMM()
return model, model_key
data_cluster_train = query_features(training, 15, 10, 23, data)
data_cluster_test = query_features(testing, 15, 10, 23, data)
data_cluster_train_ds = data_cluster_train
"""if you want clustering on the dissimilarity space uncomment
below and change accordingly"""
# print 'Calculating dissimilarity space for training queries...'
# data_cluster_train_ds = sc.pdist(data_cluster_train, 'euclidean')
# data_cluster_train_ds = sc.squareform(data_cluster_train_ds)
# # plt.figure(1)
# # plt.imshow(data_cluster_train_ds)
# # plt.colorbar()
# # plt.title('Initial dissimilarity')
print 'Training a Dirichlet Process Gaussian Mixture model...'
dpgmm = DPGMM(alpha=1.0, n_iter=100, n_components=50)
dpgmm.fit(data_cluster_train_ds)
prediction = dpgmm.predict(data_cluster_train_ds)
clusters = np.unique(prediction)
print 'Found %i clusters!' % clusters.shape[0]
print clusters
"""create the reordered input data according to the clusters
it is only needed if you want to visuallize the clustering
afterwards"""
#data_cluster = np.zeros((1, data_cluster_train.shape[1]))
# each cluster is a list of lists that contains the indices
# of the queries for each cluster
each_cluster = []
for i in xrange(clusters.shape[0]):
axes[2].set_title('Normed(dB Feature)')
axes[0].imshow(feats,
aspect='auto', origin='low', interpolation='nearest',
cmap=plt.cm.plasma)
axes[1].imshow(feats_log,
aspect='auto', origin='low', interpolation='nearest',
cmap=plt.cm.plasma)
axes[2].imshow(feats_log_normed,
aspect='auto', origin='low', interpolation='nearest',
cmap=plt.cm.plasma)
fig.tight_layout()
# Clustering with DP-GMM
n_components = 32
dpgmm = DPGMM(n_components=n_components, tol=1e-3, n_iter=32, alpha=1000,
covariance_type='diag', verbose=True)
dpgmm.fit(feats_log.T)
preds_proba = dpgmm.predict_proba(feats_log.T)
preds = np.argmax(preds_proba, axis=1)
np.unique(preds)
# resynthesis by sampling from clusters
resynthesis = dpgmm.means_[preds.astype(int), :]
fig, axes = plt.subplots(4, 1, figsize=(18, 8))
axes[0].set_title(feature)
axes[1].set_title('Prediction Probability')
axes[2].set_title('Resynthesis')
axes[3].set_title('Max(Prediction Probability)')
axes[0].imshow(feats_log,
aspect='auto', origin='low', interpolation='nearest',
def __init__(self, cluster_method=2, cluter_tag=False, train_path=None, event_info_path=None, city_id=None):
self.loss_choice = 0 # 0:reg; 1:pairwise ranking
self.ndim = 20
self.tr_method = 0 # 0:SGD1; 1:SGD2
self.cluster_method = cluster_method # 0:DPGMM; 1:GMM; 2:K-means
self.n_components = 20
self.city_id = city_id
# SGD
self.niters1 = 10
self.lr1 = 0.01
self.lambda1 = 0.001
self.neg_num1 = 5
self.beta1 = 1
self.alpha1 = 1
self.ins_weight = [self.beta1, self.alpha1]
pois = []
if cluter_tag == True:
events = set([entry[1] for entry in csv.reader(open(train_path, "r"))])
for entry in csv.reader(open(event_info_path, "r")):
event = entry[0]
if event in events:
poi = map(float, entry[3].split(" "))
pois.append(poi)
if not checkGeoScope(poi, self.city_id):
print 'Invalic location'
sys.exit(1)
if self.cluster_method == 0:
cluster = DPGMM(n_components=500,
covariance_type='diag',
alpha=1,
n_iter=50)
cluster.fit(pois)
centers = removeDup(cluster.means_)
outputCenterforVis(centers)
self.n_components = len(centers)
cluster_fd = open(settings["DPGMM_CLUSTER"], "wb")
pickle.dump([centers, None], cluster_fd)
self.model_path = settings["GEOMF"]
outputCenterforVis(centers)
elif self.cluster_method == 1:
cluster = GMM(n_components = self.n_components,
covariance_type='diag',
min_covar=1e-7,
n_init=10,
random_state=0,
n_iter=100)
cluster.fit(pois)
outputCenterforVis(cluster.means_)
labels = deterClusterRel(pois, cluster.means_)
#showNumInEachCluster(labels, self.n_components)
dis_variances = calDisVariance(self.n_components, labels, pois)
dis_variances = smoothVar(dis_variances)
covars = smoothVar(cluster.covars_)
cluster_fd = open(settings["GMM_CLUSTER"], "wb")
pickle.dump([cluster.means_, covars, dis_variances], cluster_fd)
elif self.cluster_method == 2:
cluster = KMeans(n_clusters = self.n_components,
max_iter=300,
init='k-means++')
cluster.fit(pois)
means, variances= calCenterCov(self.n_components, cluster.labels_, pois)
outputCenterforVis(means)
dis_variances = calDisVariance(self.n_components, cluster.labels_, pois)
variances = smoothVar(variances)
dis_variances = smoothVar(dis_variances)
cluster_fd = open(settings["KMEANS_CLUSTER"], "wb")
pickle.dump([means, variances, dis_variances], cluster_fd)
else:
print 'Invalid choice of clustering method'
sys.exit(1)
feature_idx.append(i[1])
#print 'feature num', len(feature_idx)
#fn = fn[:, feature_idx]
#X = StandardScaler().fit_transform(fn)
fold = 3
kf = StratifiedKFold(label, n_folds=fold, shuffle=True)
#kf = KFold(len(label), n_folds=fold, shuffle=True)
clf = RFC(n_estimators=100, criterion='entropy')
rounds = 1
acc_sum = [[] for i in range(fold)]
for train, test in kf:
train_fn = fn[train]
#n_class = len(np.unique(label[train]))
d = DPGMM(n_components=50, covariance_type='spherical',alpha=10)
d.fit(train_fn)
#print 'mixture mean', d.means_
preds = d.predict(train_fn)
print '# of M by DP', len(np.unique(preds))
acc_sum[0].append(ARI(label[train], preds))
#acc_sum[0].append(SS(train_fn, preds))
#n_class = len(np.unique(preds))
n_class = 32
g = GMM(n_components=n_class, covariance_type='spherical', init_params='wmc', n_iter=100)
g.fit(train_fn)
#g.means_ = np.array([x_train[y_train == i].mean(axis=0) for i in np.unique(y_train)])
preds = g.predict(train_fn)
#prob = np.sort(g.predict_proba(train_fd))
acc_sum[1].append(ARI(label[train], preds))
def run_all_classifiers(X_train, X_test, y_train, y_test, print_output_scores_to_csv=False, output_scores_csv_file_suffix='', print_only_table=False):
"""
The list of all classifiers was generated by running the following commented code.
Args:
a_X_train, a_X_test, a_y_train, a_y_test: The train and tests datasets.
a_print_output_scores_to_csv: If True the Precision, Recall, F1-Score and Support for both classes will
be printed to a file with the current date and time.
a_output_scores_csv_file_suffix: Suffix to be added to the csv file just before the .csv extension. Normally
describing the run that is being performed.
Returns:
dataset: Returns output scores dataset.
"""
assert isinstance(X_train, pd.core.frame.DataFrame)
assert isinstance(X_test, pd.core.frame.DataFrame)
assert isinstance(y_train, pd.core.frame.Series)
assert isinstance(y_test, pd.core.frame.Series)
assert isinstance(print_output_scores_to_csv, bool)
assert isinstance(output_scores_csv_file_suffix, object)
import time
# https://stackoverflow.com/questions/42160313/how-to-list-all-classification-regression-clustering-algorithms-in-scikit-learn
#from sklearn.utils.testing import all_estimators
#estimators = all_estimators()
#for name, class_ in estimators:
# log_print(name)
from sklearn.calibration import CalibratedClassifierCV
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
from sklearn.ensemble import AdaBoostClassifier
from sklearn.ensemble import BaggingClassifier
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.gaussian_process import GaussianProcessClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.linear_model import LogisticRegressionCV
from sklearn.linear_model import SGDClassifier
from sklearn.mixture import BayesianGaussianMixture
from sklearn.mixture import DPGMM
from sklearn.mixture import GaussianMixture
from sklearn.mixture import GMM
from sklearn.mixture import VBGMM
from sklearn.naive_bayes import BernoulliNB
from sklearn.naive_bayes import GaussianNB
from sklearn.neighbors import KNeighborsClassifier
from sklearn.neural_network import MLPClassifier
from sklearn.semi_supervised import LabelPropagation
from sklearn.semi_supervised import LabelSpreading
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
#from xgboost import XGBClassifier
models = []
models.append(('AdaBoostClassifier', AdaBoostClassifier()))
models.append(('BaggingClassifier', BaggingClassifier()))
models.append(('BayesianGaussianMixture', BayesianGaussianMixture()))
models.append(('BernoulliNB', BernoulliNB()))
models.append(('CalibratedClassifierCV', CalibratedClassifierCV()))
models.append(('DPGMM', DPGMM()))
models.append(('DecisionTreeClassifier', DecisionTreeClassifier(random_state=SEED)))
models.append(('ExtraTreesClassifier', ExtraTreesClassifier(random_state=SEED)))
models.append(('GMM', GMM()))
models.append(('GaussianMixture', GaussianMixture()))
models.append(('GaussianNB', GaussianNB()))
models.append(('GaussianProcessClassifier', GaussianProcessClassifier()))
models.append(('GradientBoostingClassifier', GradientBoostingClassifier()))
models.append(('KNeighborsClassifier', KNeighborsClassifier()))
models.append(('LabelPropagation', LabelPropagation()))
models.append(('LabelSpreading', LabelSpreading()))
models.append(('LinearDiscriminantAnalysis', LinearDiscriminantAnalysis()))
models.append(('LogisticRegression', LogisticRegression()))
models.append(('LogisticRegressionCV', LogisticRegressionCV()))
models.append(('MLPClassifier', MLPClassifier()))
#models.append(('MultinomialNB', MultinomialNB()))
#models.append(('NuSVC', NuSVC()))
models.append(('QuadraticDiscriminantAnalysis', QuadraticDiscriminantAnalysis()))
models.append(('RandomForestClassifier', RandomForestClassifier(random_state=SEED)))
models.append(('SGDClassifier', SGDClassifier()))
models.append(('SVC', SVC()))
models.append(('VBGMM', VBGMM()))
#models.append(('XGBClassifier', XGBClassifier()))
output_scores_df = fit_predict_plot(X_train, X_test, y_train, y_test, models, print_only_table)
if print_output_scores_to_csv:
output_scores_df.to_csv(time.strftime('output_scores' + str(output_scores_csv_file_suffix) + '.csv')
return output_scores_df
def run_all_classifiers(X_train, X_test, y_train, y_test, print_details=True):
"""
Run all classifiers of sklearn
Args:
X_train, X_test, y_train, y_test: The train and tests datasets.
print_details: if true, print details of all models and save csv table ;
if false, print only table with summary of the models
Returns:
dataset: Returns output scores dataset.
"""
assert isinstance(X_train, pd.core.frame.DataFrame)
assert isinstance(X_test, pd.core.frame.DataFrame)
assert isinstance(y_train, pd.core.frame.Series)
assert isinstance(y_test, pd.core.frame.Series)
assert isinstance(print_details, bool)
log_method_execution_time(log_funcname())
from sklearn.utils.testing import all_estimators
import sklearn.metrics
import time
from src.util.acq_util import RANDOM_SEED
# https://stackoverflow.com/questions/42160313/how-to-list-all-classification-regression-clustering-algorithms-in-scikit-learn
#from xgboost import XGBClassifier
#models.append(('XGBClassifier', XGBClassifier()))
models = all_estimators(type_filter='classifier')
output_scores_dataset = pd.DataFrame(index=['Precision 0', 'Recall 0', 'F1-Score 0', 'Support 0',
'Precision 1', 'Recall 1', 'F1-Score 1', 'Support 1'],
columns=list(zip(*models))[0])
for name, model in models:
if print_details is True:
print('------------------------------------------------------------------------------')
print(name)
print('------------------------------------------------------------------------------')
if (name == 'MultinomialNB' or name == 'NuSVC' or name == 'RadiusNeighborsClassifier' or name == 'GaussianProcessClassifier'):
continue
model = model()
if 'random_state' in model.get_params():
model.random_state = SEED
#Fitting the model.
model.fit(X_train, y_train)
#Measuring accuracy.
y_train_pred = model.predict(X_train)
y_test_pred = model.predict(X_test)
output_scores_dataset = class_compute_accuracy(y_train, y_train_pred, output_scores_dataset,
['Accuracy on the train set', name], print_details)
output_scores_dataset = class_compute_accuracy(y_test, y_test_pred, output_scores_dataset,
['Accuracy on the test set', name], print_details)
#Plotting confusion matrix.
output_scores_dataset = class_compute_plot_confusion_matrix(y_test, y_test_pred, output_scores_dataset, name, print_details)
#Showing classification report.
if print_details is True:
print(sklearn.metrics.classification_report(y_test, y_test_pred))
# Printing scores to output dataset.
output_scores_dataset = class_compute_recall_precision_f1(y_test, y_test_pred, output_scores_dataset, name)
# Can use idxmax with axis=1 to find the column with the greatest value on each row.
output_scores_dataset['Max Value'] = output_scores_dataset.apply(max, axis=1)
#output_scores_dataset['Max Classifier'] = output_scores_dataset.idxmax(axis=1)
if print_details is True:
output_scores_dataset.to_csv('output_scores' + '.csv')
return output_scores_dataset
def train_test_split_for_classification(dataset, label, test_size, random_state=SEED):
"""
Selects X and y, considering that y has been renamed to label.
"""
from sklearn.model_selection import train_test_split
assert isinstance(dataset, pd.core.frame.DataFrame)
assert isinstance(test_size, float)
assert isinstance(random_state, int)
X = dataset.loc[:, dataset.columns != label]
y = dataset[g_label]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_size, random_state=random_state, stratify=y)
log_print('X_train: {}'.format(X_train.shape))
log_print('y_train: {}'.format(y_train.shape))
log_print('X_test: {}'.format(X_test.shape))
log_print('y_test: {}'.format(y_test.shape))
return(X_train, X_test, y_train, y_test)
# In[4]:
train_dataset = train.values
X = train_dataset[:, 2:]
y = train_dataset[:, 1]
y = y.astype('int')
test_dataset = test.values
X_test = test_dataset[:, 2:]
print(type(X_test))
print('X.shape, y.shape, X_test.shape', X.shape, y.shape, X_test.shape)
# In[5]:
df = pd.DataFrame({"SK_ID_CURR": df['SK_ID_CURR']})
print('dirichlet process gaussian mixture begins****************')
dpgmm = DPGMM(n_components=3)
print('fitting****************')
dpgmm_train = dpgmm.fit(X, y)
print('predicting on train****************')
dpgmm_X_prediction = dpgmm.predict_proba(X)[:, 1]
print('predicting on test****************')
dpgmm_X_test_prediction = dpgmm.predict_proba(X_test)[:, 1]
tr_te_concatenated = np.concatenate(
[dpgmm_X_prediction, dpgmm_X_test_prediction])
df['dirichlet_process_gaussian_mixture'] = tr_te_concatenated
print('final tr_te shape', df.shape)
print(df.head())
df.to_csv('dirichlet_process_gaussian_mixture_tr_te.csv', index=False)
class DPGMMClusterModel(BaseEstimator, TransformerMixin):
def __init__(self, w2v_model=None, n_components=None, no_above=0.9, no_below=8, dataname="", stoplist=None,
dictionary=None, recluster_thresh=1000, alpha=5):
self.w2v_model = w2v_model
self.no_above = no_above
self.no_below = no_below
self.alpha = alpha
self.n_components = n_components
self.n_sub_components = int(n_components / 2)
self.stoplist = stoplist
self.dataname = dataname
self.dictionary = dictionary
self.dpgmm = None
self.scaler = None
self.cluster_info = None
# a list of sub-clusterer
self.feature_crd = {}
self.subdpgmms = []
self.reclustered = []
self.recluster_thresh = recluster_thresh
def should_cluster_word(self, word):
return (word in self.dictionary.token2id) and (len(word) > 1) and \
(self.w2v_model is None or word in self.w2v_model) and \
(self.stoplist is None or word not in self.stoplist)
# constructs a dictionary and a DPGMM model on 9000 middle frequency words from X
# X is a sequence of texts
def fit(self, X, y=None):
# either consturct a dictionary from X, trim it
if self.dictionary is None:
self.dictionary = corpora.Dictionary(X)
# or use an existing dictionary and trim the given set of words
self.dictionary.filter_extremes(no_below=self.no_below, no_above=self.no_above, keep_n=9000)
if self.w2v_model is None:
w2v_corpus = [[word for word in text if self.should_cluster_word(word)] for text in X]
self.w2v_model = w2v_models.build_word2vec(w2v_corpus, size=100, window=10, min_count=self.no_below,
dataname=self.dataname+"_dpgmm")
word_list = np.array([word for word in self.dictionary.token2id.iterkeys() if self.should_cluster_word(word)])
# This was reclustering clause - I need to re-write this
# else:
# # note the double loop here!!
# word_list = np.array([word for text in X for word in text if self.should_cluster_word(word)])
# construct a list of words to cluster
# remove rare and frequent words
# remove words of length 1
# remove stopwords
vec_list = [self.w2v_model[word] for word in word_list]
logging.info("DPGMM received %i words" % len(vec_list))
# save word representations
filename = "w2v_vocab_%s_%.1f_%.0f.lcsv" % (self.dataname, self.no_above, self.no_below)
io.save_words_representations(filename, word_list, vec_list)
self.scaler = StandardScaler()
vecs = self.scaler.fit_transform(np.array(vec_list))
self.dpgmm = DPGMM(n_components=self.n_components, covariance_type='diag', alpha=self.alpha,
n_iter=1000, tol=0.0001)
self.dpgmm.fit(vecs)
logging.info("DPGMM converged: %s" % self.dpgmm.converged_)
# save information about found clusters
self.cluster_info = []
y_ = self.dpgmm.predict(vecs)
for i, cluster_center in enumerate(self.dpgmm.means_):
cluster_words = word_list[y_ == i]
cluster_size = len(cluster_words)
if cluster_size > self.recluster_thresh and self.recluster_thresh > 0:
logging.info("DPGMM: reclustering %i words for cluster %i" % (len(cluster_words), i))
sub_dpgmm = DPGMMClusterModel(w2v_model=self.w2v_model,
n_components=self.n_sub_components,
dictionary=self.dictionary,
dataname="%s-%i" % (self.dataname, i), stoplist=self.stoplist)
# recluster words. Note the double array
sub_dpgmm.fit([cluster_words])
self.subdpgmms.append(sub_dpgmm)
self.reclustered.append(i)
if cluster_size > 0:
#cluster_center_original = self.scaler.inverse_transform(cluster_center)
#similar_words = self.w2v_model.most_similar_cosmul(positive=[cluster_center_original], topn=cluster_size)
#central_words = [word for word, _ in similar_words if word in cluster_words]
central_words = cluster_words[0:10]
else:
central_words = []
self.cluster_info.append({'cnt': i, 'size': cluster_size, 'words': central_words})
filename = "clusters_%s_%i_%.1f_%.0f.txt" % (self.dataname, self.n_components, self.no_above, self.no_below)
io.save_cluster_info(filename, self.cluster_info)
# setting up the coordinates for the features
self.feature_crd = {'global': range(0, self.n_components),
'reclustered': [i for i in range(0, self.n_components + self.n_sub_components*len(self.reclustered))
if i not in self.reclustered]}
return self
# calculate cluster counts for one text
def clusterize(self, text):
word_list = [word for word in text if self.should_cluster_word(word)]
vec_list = np.array([self.w2v_model[word] for word in word_list])
bincounts = np.zeros((self.n_components+self.n_sub_components*len(self.reclustered),))
if len(vec_list) > 0:
# assign words to clusters
predictions = self.dpgmm.predict(self.scaler.transform(np.array(vec_list)))
global_bincount = np.bincount(predictions, minlength=self.n_components)
# re-assign words in large clusters
bincounts[0:self.n_components] = global_bincount #reshape((1,len(global_bincount)))
start = self.n_components
for i, subdpgmm in zip(self.reclustered, self.subdpgmms):
# if words in respective clusters exists - recluster them
vecs_torecluster = vec_list[predictions == i]
if len(vecs_torecluster) > 0:
predictions = subdpgmm.dpgmm.predict(subdpgmm.scaler.transform(np.array(vecs_torecluster)))
bincounts[start:start+subdpgmm.dpgmm.n_components] = \
np.bincount(predictions, minlength=subdpgmm.dpgmm.n_components) #.reshape((1, subdpgmm.n_components))
start += subdpgmm.dpgmm.n_components
# erase the count inthe global counts
# returns a vector of cluster bin counts: [ global, reclustered1, reclustered2, ...]
return bincounts.reshape((1, len(bincounts)))
# for a text, constructs a bincount of clusters present in the sentence
# X is a list of texts. One text is one string! Not tokenized
def transform(self, X):
# Text pre-processing
x_clean = [tu.normalize_punctuation(text).split() for text in X]
logging.info("DPGGM: Text prepocessed")
# Vectorize using W2V model
if self.dpgmm is not None:
logging.info("Vectorizing a corpus")
size = self.w2v_model.layer1_size
if len(X) > 0:
vecs = np.concatenate([self.clusterize(z) for z in x_clean], axis=0)
else:
vecs = np.zeros(size).reshape((1, size))
logging.info("DPGMM: returning pre-processed data of shape %s" % (vecs.shape, ))
else:
logging.info("W2V Averaged: no model was provided.")
vecs = np.zeros((len(X), 1))
return vecs
class Clustering:
def __init__(self, X, scale=False, features=None):
self.random_seed = 12345 # set to None for random
self.X = X
self.k = None
self.centers = None
self.h = None
self.Y = None
self.scaler = None
self.ids = None
# Visualize().plot( zip(*self.X) ) # FOR DEBUG
# Reduce the number of features
if features is not None:
if isinstance( features, (int, float) ):
variances = VarianceThreshold().fit(self.X).variances_
self.ids = sorted(range(len(variances)), key=lambda i: variances[i])[-int(features):] # indexes of the top n_features values in variances
elif type(features) in [list,tuple]:
self.ids = features
self.X = self.reduceFeatures(self.X)
print("Selected features", self.ids, "on a total of", len(X[0])) # FOR DEBUG
# Visualize().plot( zip(*self.X) ) # FOR DEBUG
if scale:
self.scaler = StandardScaler() # MinMaxScaler() can also be used instead of StandardScaler()
self.X = self.scaler.fit_transform(self.X)
#---------------------------------------
def reduceFeatures(self, X):
if self.ids is None:
return X
else:
return [ [v for iv,v in enumerate(x) if iv in self.ids] for x in X ]
#---------------------------------------
def affinity(self, k=2): # K is not used here
self.h = AffinityPropagation(damping=0.75, preference=k, max_iter=200, convergence_iter=15, copy=True, affinity='euclidean').fit( self.X )
self.Y = self.h.labels_
self.k = k
self.centers = self.getCenters()
return self
#---------------------------------------
def meanshift(self, k=2): # K is not used here
self.h = MeanShift(bandwidth=None, seeds=None, bin_seeding=False, min_bin_freq=1, cluster_all=True).fit( self.X )
self.Y = self.h.labels_
self.k = k
self.centers = self.getCenters()
return self
#---------------------------------------
def kmeans(self, k=2):
self.h = KMeans(n_clusters = k, init = 'k-means++', n_init = 10, max_iter = 1000, tol = 0.00001, random_state = self.random_seed).fit( self.X )
self.Y = self.h.labels_
self.k = k
self.centers = self.getCenters()
return self
#---------------------------------------
def gmm(self, k=2):
self.h = GMM(n_components=k, random_state = self.random_seed).fit( self.X )
self.Y = self.h.predict( self.X )
self.k = k
self.centers = self.getCenters()
#TODO
# posterior = self.h.predict_proba( self.X[:5] )
# likelihood = self.h.score( self.X[:5] )
return self
#---------------------------------------
''' Dirichlet Process is as likely to start a new cluster for a point as it is to add that point to a cluster with alpha elements (0<alpha<inf).
A higher alpha means more clusters, as the expected number of clusters is alpha*log(N)'''
def dpgmm(self, k=10, alpha=1.0):
self.h = DPGMM(n_components=k, alpha=alpha, random_state = self.random_seed).fit( self.X )
self.Y = self.h.predict( self.X )
self.k = k # this is the max number of components in dpgmm
self.centers = self.getCenters()
#TODO
# posterior = self.h.predict_proba( self.X[:5] )
# likelihood = self.h.score( self.X[:5] )
return self
#---------------------------------------
def done(self):
if self.h is None:
print("Clustering is not yet done !")
return False
else:
return True
#---------------------------------------
def getCenters(self):
if not self.done(): return
try:
return self.h.cluster_centers_
# If the clustering has no centers, compute them based on clusters
except AttributeError:
unique_labels = np.unique(self.Y)
clusters = { ul:[] for ul in unique_labels }
for i in range( len(self.X) ):
clusters[ self.Y[i] ].append( self.X[i] )
centers = []
for label in clusters:
centers.append( [np.mean(col) for col in list(zip(* clusters[label] )) ] )
return centers
#---------------------------------------
def predict(self, x):
if not self.done(): return
x_processed = x
x_processed = self.reduceFeatures([x_processed])[0]
x_processed = x_processed if self.scaler is None else self.scaler.transform(x_processed)
return self.h.predict(x_processed)[0]
#---------------------------------------
def predictAll(self, X):
if not self.done(): return
X_processed = X
X_processed = self.reduceFeatures(X_processed)
X_processed = X_processed if self.scaler is None else self.scaler.transform(X_processed)
return list(self.h.predict(X_processed))
#---------------------------------------
def quality(self, X=None):
if not self.done(): return
if X is None: # if X not provided then use the training data and resulting labels
X = self.X
Y = self.Y
else: # if X is provided then use it with the predicted labels (clusters)
Y = self.predictAll(X)
indexs = range(len(X)); shuffle(indexs)
X = np.array([ X[i] for i in indexs[:5000] ])
Y = np.array([ Y[i] for i in indexs[:5000] ])
if len(set(Y)) < 2: return 0. # FIXME
return silhouette_score(X, Y, metric='euclidean')
#---------------------------------------
def plot(self, fig=None):
if not self.done(): return
viz = Visualize()
if len(self.X[0]) > 3:
X = viz.PCA_Transform( list(zip(*self.X)) )
else:
X = self.X
unique_labels = np.unique(self.Y)
clusters = { ul:[] for ul in unique_labels }
for i in range( len(X) ):
clusters[ self.Y[i] ].append( X[i] )
centers_for_plot = [] # Not the real centers because dimension was reduced using PCA
for label in clusters:
centers_for_plot.append( [np.mean(col) for col in list(zip(* clusters[label] )) ] )
viz.do_plot(list(zip(*centers_for_plot)), marker='o', color='m')
viz.plot_groups(clusters, fig)
X_unlabeled = extract_unlabeled_chunkrange(unlabeled_datafile, opts.size)
chunk_sizes = extract_chunk_sizes(unlabeled_datafile)
# Extract some of the dataset from the datafile
# X_labeled, labels = extract_labeled_chunkrange(labeled_datafile, opts.size)
# done, close h5 files
#labeled_datafile.close()
unlabeled_datafile.close()
for chunks in np.arange(1, opts.size, step = 3):
# Sample the specified number of points from X_unlabeled
size = np.cumsum(chunk_sizes[:chunks])[-1]
# Fit a Dirichlet process mixture of Gaussians using up to ten components
dpgmm = DPGMM(n_components=10, alpha=10.0, covariance_type='full')
indices = np.arange(X_unlabeled.shape[0])
np.random.shuffle(indices)
X = X_unlabeled[indices[:size],]
print("fitting a model with", size, "data points")
with timeit():
dpgmm.fit(X)
print("Done!")
print("AIC for this model & data: ", dpgmm.aic(X))
print("BIC for this model & data: ", dpgmm.bic(X))
Y_hat = dpgmm.predict(X)
print ("Model assigned points to", np.max(Y_hat), "components")
# How can I best check this out?
data_cluster_test = query_features(testing, 15, 10, 23, data)
data_cluster_train_ds = data_cluster_train
"""if you want clustering on the dissimilarity space uncomment
below and change accordingly"""
# print 'Calculating dissimilarity space for training queries...'
# data_cluster_train_ds = sc.pdist(data_cluster_train, 'euclidean')
# data_cluster_train_ds = sc.squareform(data_cluster_train_ds)
# # plt.figure(1)
# # plt.imshow(data_cluster_train_ds)
# # plt.colorbar()
# # plt.title('Initial dissimilarity')
print 'Training a Dirichlet Process Gaussian Mixture model...'
dpgmm = DPGMM(alpha=1.0, n_iter=100, n_components=50)
dpgmm.fit(data_cluster_train_ds)
prediction = dpgmm.predict(data_cluster_train_ds)
clusters = np.unique(prediction)
print 'Found %i clusters!' % clusters.shape[0]
print clusters
"""create the reordered input data according to the clusters
it is only needed if you want to visuallize the clustering
afterwards"""
#data_cluster = np.zeros((1, data_cluster_train.shape[1]))
# each cluster is a list of lists that contains the indices
# of the queries for each cluster
each_cluster = []
# print(pca.n_components_) # print(pca.explained_variance_ratio_[0:3]) print(pca.reconstruction_err_) fig = plt.figure(figsize=(20, 20)) ax = fig.add_subplot(111, projection='3d') plt.scatter(datat[:, 0], datat[:, 1], zs=datat[:, 2], c=labels, marker='o') plt.show() plt.close() #km = KMeans(n_clusters=5) km = DPGMM(n_components=7, covariance_type='tied') clabels = km.fit_predict(datat) # for ex, lab in zip(exid, clabels): # print(ex, lab) fig = plt.figure(figsize=(20, 20)) ax = fig.add_subplot(111, projection='3d') plt.scatter(datat[:, 0], datat[:, 1], zs=datat[:, 2], c=clabels, marker='o') plt.show() plt.close()
def fit(self, X, y=None):
# either consturct a dictionary from X, trim it
if self.dictionary is None:
self.dictionary = corpora.Dictionary(X)
# or use an existing dictionary and trim the given set of words
self.dictionary.filter_extremes(no_below=self.no_below, no_above=self.no_above, keep_n=9000)
if self.w2v_model is None:
w2v_corpus = [[word for word in text if self.should_cluster_word(word)] for text in X]
self.w2v_model = w2v_models.build_word2vec(w2v_corpus, size=100, window=10, min_count=self.no_below,
dataname=self.dataname+"_dpgmm")
word_list = np.array([word for word in self.dictionary.token2id.iterkeys() if self.should_cluster_word(word)])
# This was reclustering clause - I need to re-write this
# else:
# # note the double loop here!!
# word_list = np.array([word for text in X for word in text if self.should_cluster_word(word)])
# construct a list of words to cluster
# remove rare and frequent words
# remove words of length 1
# remove stopwords
vec_list = [self.w2v_model[word] for word in word_list]
logging.info("DPGMM received %i words" % len(vec_list))
# save word representations
filename = "w2v_vocab_%s_%.1f_%.0f.lcsv" % (self.dataname, self.no_above, self.no_below)
io.save_words_representations(filename, word_list, vec_list)
self.scaler = StandardScaler()
vecs = self.scaler.fit_transform(np.array(vec_list))
self.dpgmm = DPGMM(n_components=self.n_components, covariance_type='diag', alpha=self.alpha,
n_iter=1000, tol=0.0001)
self.dpgmm.fit(vecs)
logging.info("DPGMM converged: %s" % self.dpgmm.converged_)
# save information about found clusters
self.cluster_info = []
y_ = self.dpgmm.predict(vecs)
for i, cluster_center in enumerate(self.dpgmm.means_):
cluster_words = word_list[y_ == i]
cluster_size = len(cluster_words)
if cluster_size > self.recluster_thresh and self.recluster_thresh > 0:
logging.info("DPGMM: reclustering %i words for cluster %i" % (len(cluster_words), i))
sub_dpgmm = DPGMMClusterModel(w2v_model=self.w2v_model,
n_components=self.n_sub_components,
dictionary=self.dictionary,
dataname="%s-%i" % (self.dataname, i), stoplist=self.stoplist)
# recluster words. Note the double array
sub_dpgmm.fit([cluster_words])
self.subdpgmms.append(sub_dpgmm)
self.reclustered.append(i)
if cluster_size > 0:
#cluster_center_original = self.scaler.inverse_transform(cluster_center)
#similar_words = self.w2v_model.most_similar_cosmul(positive=[cluster_center_original], topn=cluster_size)
#central_words = [word for word, _ in similar_words if word in cluster_words]
central_words = cluster_words[0:10]
else:
central_words = []
self.cluster_info.append({'cnt': i, 'size': cluster_size, 'words': central_words})
filename = "clusters_%s_%i_%.1f_%.0f.txt" % (self.dataname, self.n_components, self.no_above, self.no_below)
io.save_cluster_info(filename, self.cluster_info)
# setting up the coordinates for the features
self.feature_crd = {'global': range(0, self.n_components),
'reclustered': [i for i in range(0, self.n_components + self.n_sub_components*len(self.reclustered))
if i not in self.reclustered]}
return self
def _st_smooth(self,
var_idx,
x_v,
y_v=None,
n_component=1,
thresh_hold=0.3,
dp=False):
mixture_dist = []
for task_idx in range(self.num_task):
if y_v is not None:
mean = self.params_mean[task_idx][var_idx][x_v][y_v]
var = self.transform_var(
self.params_var[task_idx][var_idx][x_v][y_v])
else:
mean = self.params_mean[task_idx][var_idx][x_v]
var = self.transform_var(
self.params_var[task_idx][var_idx][x_v])
mixture_dist.append({'kwargs': {'loc': mean, 'scale': var}})
alpha = 0.3
alpha_list = [(1 - alpha) / (self.num_task - 1)] * (self.num_task - 1)
alpha_list.append(alpha)
sample = create_mixture(mixture_dist, alpha_list=alpha_list)
if dp:
gmm = DPGMM(max_iter=1000,
n_components=n_component,
covariance_type='spherical')
else:
gmm = GMM(max_iter=500,
n_components=n_component,
covariance_type='spherical')
gmm.fit(sample)
new_idx_list = []
for task_idx in range(self.num_task):
if y_v is not None:
predict_probability = gmm.predict_proba(
np.array(
self.params_mean[task_idx][var_idx][x_v][y_v]).reshape(
-1, 1))
else:
predict_probability = gmm.predict_proba(
np.array(self.params_mean[task_idx][var_idx][x_v]).reshape(
-1, 1))
f_ = True
while f_:
if gmm.weights_[np.argmax(predict_probability)] > thresh_hold:
new_idx = np.argmax(predict_probability)
f_ = False
else:
predict_probability[0][np.argmax(
predict_probability)] = 0.0
#self.num_merged_params += 1
if new_idx in new_idx_list:
self.num_merged_params += 1
new_idx_list.append(new_idx)
if y_v is not None:
self.params_mean[task_idx][var_idx][x_v][y_v] = gmm.means_[
new_idx]
self.params_var[task_idx][var_idx][x_v][
y_v] = self.retransform_var(gmm.covariances_[new_idx])
else:
self.params_mean[task_idx][var_idx][x_v] = gmm.means_[new_idx]
self.params_var[task_idx][var_idx][x_v] = self.retransform_var(
gmm.covariances_[new_idx])
"""
def fit_dirichlet_gmm_to_points(points,
n_components,
mdl,
ps=[],
num_iter=100,
covariance_type='full',
mass_multiplier=1.0):
"""fit a GMM to some points. Will return core::Gaussians.
if no particles are provided, they will be created
points: list of coordinates (python)
n_components: number of gaussians to create
mdl: IMP Model
ps: list of particles to be decorated. if empty, will add
num_iter: number of EM iterations
covariance_type: covar type for the gaussians. options: 'full', 'diagonal', 'spherical'
init_centers: initial coordinates of the GMM
force_radii: fix the radii (spheres only)
force_weight: fix the weights
mass_multiplier: multiply the weights of all the gaussians by this value
"""
new_sklearn = True
try:
from sklearn.mixture import BayesianGaussianMixture
except ImportError:
from sklearn.mixture import DPGMM
new_sklearn = False
### create and fit GMM
print('using dirichlet prior')
if new_sklearn:
gmm = BayesianGaussianMixture(
weight_concentration_prior_type='dirichlet_process',
n_components=n_components, max_iter=num_iter,
covariance_type=covariance_type)
else:
gmm = DPGMM(n_components=n_components, n_iter=num_iter,
covariance_type=covariance_type)
gmm.fit(points)
#print('>>> GMM score',gmm.score(points))
#print gmm.covars_
#print gmm.weights_
#print gmm.means_
### convert format to core::Gaussian
if not new_sklearn:
gmm.precisions_ = gmm.precs_
for ng in range(n_components):
invcovar=gmm.precisions_[ng]
covar=np.linalg.inv(invcovar)
if covar.size==3:
covar=np.diag(covar).tolist()
else:
covar=covar.tolist()
center=list(gmm.means_[ng])
weight=mass_multiplier*gmm.weights_[ng]
if ng>=len(ps):
ps.append(IMP.Particle(mdl))
shape=IMP.algebra.get_gaussian_from_covariance(covar,IMP.algebra.Vector3D(center))
g=IMP.core.Gaussian.setup_particle(ps[ng],shape)
IMP.atom.Mass.setup_particle(ps[ng],weight)
IMP.core.XYZR.setup_particle(ps[ng],sqrt(max(g.get_variances())))
aspect='auto',
origin='low',
interpolation='nearest',
cmap=plt.cm.plasma)
axes[2].imshow(feats_log_normed,
aspect='auto',
origin='low',
interpolation='nearest',
cmap=plt.cm.plasma)
fig.tight_layout()
# Clustering with DP-GMM
n_components = 32
dpgmm = DPGMM(n_components=n_components,
tol=1e-3,
n_iter=32,
alpha=1000,
covariance_type='diag',
verbose=True)
dpgmm.fit(feats_log.T)
preds_proba = dpgmm.predict_proba(feats_log.T)
preds = np.argmax(preds_proba, axis=1)
np.unique(preds)
# resynthesis by sampling from clusters
resynthesis = dpgmm.means_[preds.astype(int), :]
fig, axes = plt.subplots(4, 1, figsize=(18, 8))
axes[0].set_title(feature)
axes[1].set_title('Prediction Probability')
axes[2].set_title('Resynthesis')
axes[3].set_title('Max(Prediction Probability)')
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis, QuadraticDiscriminantAnalysis
from sklearn.mixture import GMM, DPGMM, BayesianGaussianMixture, VBGMM
from sklearn.svm import NuSVC, SVC
# Useful for seeing all sklearn estimators that have `predict_prob` attribute
estimators = all_estimators()
for name, class_ in estimators:
if hasattr(class_, 'predict_proba'):
print(name)
# Now pick and choose the ones you like
estimators = {
AdaBoostClassifier(): 'AdaBoost',
BayesianGaussianMixture(): 'BayesianGaussianMixture',
BernoulliNB(): 'BernoulliNB',
DPGMM(): 'DPGMM',
ExtraTreesClassifier(): 'ExtraTreesClassifier',
GMM(): 'GMM',
GaussianNB(): 'GaussianNB',
GaussianProcessClassifier(): 'GaussianProcessClassifier',
GradientBoostingClassifier(): 'GradientBoostingClassifier',
KNeighborsClassifier(): 'KNeighborsClassifier',
LabelPropagation(): 'LabelPropagation',
LabelSpreading(): 'LabelSpreading',
LinearDiscriminantAnalysis(): 'LinearDiscriminantAnalysis',
LogisticRegression(): 'LogisticRegression',
MLPClassifier(): 'MLPClassifier',
NuSVC(): 'NuSVC',
QuadraticDiscriminantAnalysis(): 'QuadraticDiscriminantAnalysis',
RandomForestClassifier(): 'RandomForestClassifier',
SGDClassifier(): 'SGDClassifier',
def dpgmm_simple(X, init_numC, random_state):
model = DPGMM(n_components = init_numC, n_iter=100, tol=0.000001, random_state=random_state)
model.fit(X)
y = model.predict(X)
cluster_num = len(np.unique(y))
return cluster_num, y
class Clustering:
def __init__(self, X, scale=False, features=None):
self.random_seed = 12345 # set to None for random
self.X = X
self.k = None
self.centers = None
self.h = None
self.Y = None
self.scaler = None
self.ids = None
# Visualize().plot( zip(*self.X) ) # FOR DEBUG
# Reduce the number of features
if features is not None:
if isinstance(features, (int, float)):
variances = VarianceThreshold().fit(self.X).variances_
self.ids = sorted(
range(len(variances)), key=lambda i: variances[i]
)[-int(features
):] # indexes of the top n_features values in variances
elif type(features) in [list, tuple]:
self.ids = features
self.X = self.reduceFeatures(self.X)
print("Selected features", self.ids, "on a total of",
len(X[0])) # FOR DEBUG
# Visualize().plot( zip(*self.X) ) # FOR DEBUG
if scale:
self.scaler = StandardScaler(
) # MinMaxScaler() can also be used instead of StandardScaler()
self.X = self.scaler.fit_transform(self.X)
#---------------------------------------
def reduceFeatures(self, X):
if self.ids is None:
return X
else:
return [[v for iv, v in enumerate(x) if iv in self.ids] for x in X]
#---------------------------------------
def affinity(self, k=2): # K is not used here
self.h = AffinityPropagation(damping=0.75,
preference=k,
max_iter=200,
convergence_iter=15,
copy=True,
affinity='euclidean').fit(self.X)
self.Y = self.h.labels_
self.k = k
self.centers = self.getCenters()
return self
#---------------------------------------
def meanshift(self, k=2): # K is not used here
self.h = MeanShift(bandwidth=None,
seeds=None,
bin_seeding=False,
min_bin_freq=1,
cluster_all=True).fit(self.X)
self.Y = self.h.labels_
self.k = k
self.centers = self.getCenters()
return self
#---------------------------------------
def kmeans(self, k=2):
self.h = KMeans(n_clusters=k,
init='k-means++',
n_init=10,
max_iter=1000,
tol=0.00001,
random_state=self.random_seed).fit(self.X)
self.Y = self.h.labels_
self.k = k
self.centers = self.getCenters()
return self
#---------------------------------------
def gmm(self, k=2):
self.h = GMM(n_components=k, random_state=self.random_seed).fit(self.X)
self.Y = self.h.predict(self.X)
self.k = k
self.centers = self.getCenters()
#TODO
# posterior = self.h.predict_proba( self.X[:5] )
# likelihood = self.h.score( self.X[:5] )
return self
#---------------------------------------
''' Dirichlet Process is as likely to start a new cluster for a point as it is to add that point to a cluster with alpha elements (0<alpha<inf).
A higher alpha means more clusters, as the expected number of clusters is alpha*log(N)'''
def dpgmm(self, k=10, alpha=1.0):
self.h = DPGMM(n_components=k,
alpha=alpha,
random_state=self.random_seed).fit(self.X)
self.Y = self.h.predict(self.X)
self.k = k # this is the max number of components in dpgmm
self.centers = self.getCenters()
#TODO
# posterior = self.h.predict_proba( self.X[:5] )
# likelihood = self.h.score( self.X[:5] )
return self
#---------------------------------------
def done(self):
if self.h is None:
print("Clustering is not yet done !")
return False
else:
return True
#---------------------------------------
def getCenters(self):
if not self.done(): return
try:
return self.h.cluster_centers_
# If the clustering has no centers, compute them based on clusters
except AttributeError:
unique_labels = np.unique(self.Y)
clusters = {ul: [] for ul in unique_labels}
for i in range(len(self.X)):
clusters[self.Y[i]].append(self.X[i])
centers = []
for label in clusters:
centers.append(
[np.mean(col) for col in list(zip(*clusters[label]))])
return centers
#---------------------------------------
def predict(self, x):
if not self.done(): return
x_processed = x
x_processed = self.reduceFeatures([x_processed])[0]
x_processed = x_processed if self.scaler is None else self.scaler.transform(
x_processed)
return self.h.predict(x_processed)[0]
#---------------------------------------
def predictAll(self, X):
if not self.done(): return
X_processed = X
X_processed = self.reduceFeatures(X_processed)
X_processed = X_processed if self.scaler is None else self.scaler.transform(
X_processed)
return list(self.h.predict(X_processed))
#---------------------------------------
def quality(self, X=None):
if not self.done(): return
if X is None: # if X not provided then use the training data and resulting labels
X = self.X
Y = self.Y
else: # if X is provided then use it with the predicted labels (clusters)
Y = self.predictAll(X)
indexs = range(len(X))
shuffle(indexs)
X = np.array([X[i] for i in indexs[:5000]])
Y = np.array([Y[i] for i in indexs[:5000]])
if len(set(Y)) < 2: return 0. # FIXME
return silhouette_score(X, Y, metric='euclidean')
#---------------------------------------
def plot(self, fig=None):
if not self.done(): return
viz = Visualize()
if len(self.X[0]) > 3:
X = viz.PCA_Transform(list(zip(*self.X)))
else:
X = self.X
unique_labels = np.unique(self.Y)
clusters = {ul: [] for ul in unique_labels}
for i in range(len(X)):
clusters[self.Y[i]].append(X[i])
centers_for_plot = [
] # Not the real centers because dimension was reduced using PCA
for label in clusters:
centers_for_plot.append(
[np.mean(col) for col in list(zip(*clusters[label]))])
viz.do_plot(list(zip(*centers_for_plot)), marker='o', color='m')
viz.plot_groups(clusters, fig)
width, height = value[0], value[1]
v = vector[0] / sp.linalg.norm(vector[0])
angle = 180* np.arctan(v[1] / v[0]) / np.pi
e = Ellipse(xy=center, width=width, height=height,
angle=angle, color='m', alpha=0.5, clip_box = ax.bbox)
ax.add_artist(e)
ax1_min, ax1_max, ax2_min, ax2_max = plt.axis()
plt.xlim((x1_min, x1_max))
plt.ylim((x2_min, x2_max))
plt.title(u'GMM', fontsize=20)
plt.grid(True)
# DPGMM
n_components = 3
dpgmm = DPGMM(n_components=n_components, alpha=1, covariance_type='full', random_state=0)
dpgmm.fit(x)
centers = dpgmm.means_
covs = dpgmm._get_covars()
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=30, c=y, cmap=cm, marker='o')
for i, cc in enumerate(zip(centers, covs)):
plt.figure()
plt.subplot(1, 2, 1)
plt.imshow(img)
plt.title('Original Image')
if K.image_dim_ordering() == "th":
img = np.moveaxis(
img.reshape((1, img.shape[0], img.shape[1], img.shape[2])), -1, 1)
img = vgg16.preprocess_input(img.astype('float32'))
""" Scaling activations to fit random initialization scheme"""
actvs = get_activations(model, layer, img).squeeze()
actvs /= np.max(actvs) * 0.1
""" Clustering with dirichlet process Gaussian Mixture Model"""
dpgmm = DPGMM(n_components=50,
alpha=1,
verbose=2,
tol=0.01,
n_iter=250,
min_covar=1e-6)
#dpgmm = BayesianGaussianMixture(n_components=50, covariance_type="diag", reg_covar = 1e-6,
# weight_concentration_prior_type="dirichlet_process",
# weight_concentration_prior=1, verbose=2,
# tol=0.01, max_iter=250, init_params='random',
# mean_precision_prior=actvs.std(),
# mean_prior=np.repeat(actvs.max()/5,actvs.shape[0]))
dpgmm.fit(
np.transpose(actvs.reshape(actvs.shape[0],
actvs.shape[1] * actvs.shape[2])))
labels = dpgmm.predict(
np.transpose(actvs.reshape(actvs.shape[0],
actvs.shape[1] * actvs.shape[2])))
def plotClustering(fullpath, order=1, sr=4, cutoff=.1, n_singv=3,
feature='chroma', dim_red='SVD', round_to=0, normalize=1,
scale=1, length=4, clustering='KMEANS'):
feat = {}
print ('Analyzing {} with feature {}, order {}, sr {}, cutoff {}, '
'n_singv {}, scale {} normalize {}, round_to {}'.format(
fullpath, feature, order, sr, cutoff, n_singv, scale, normalize,
round_to))
# extract filename, filepath and beat aligned feature
filename, file_ext = os.path.splitext(fullpath)
# extract filter and apply pre-processing
feat[feature], beat_times = extractFeature(
filename, file_ext, feature, scale, round_to, normalize,
beat_sync=True, save=True)
feat['LPF'] = lpf(feat[feature], cutoff, sr, order)
feat[dim_red] = dim_red_fn(dim_red, feat[feature], n_singv)
feat['{}(LPF)'.format(dim_red)] = dim_red_fn(
dim_red, feat['LPF'], n_singv)
feat['LPF({})'.format(dim_red)] = lpf(feat[dim_red], cutoff, sr, order)
feat['{}-LPF'.format(feature)] = feat[feature] - feat['LPF']
feat['LPF({}-LPF)'.format(feature)] = lpf(
feat['{}-LPF'.format(feature)], cutoff, sr, order)
feat['{}(LPF({}-LPF))'.format(dim_red, feature)] = dim_red_fn(dim_red,
feat['LPF({}-LPF)'.format(feature)], n_singv)
# create vars for plotting
ts = np.arange(0, len(feat[feature]))
step_size = max(1, int(len(ts) * .01))
fig = plt.figure(figsize=(98, 64))
fig.suptitle('feature {} order {}, cutoff {}, sr {}'.format(
feature, order, cutoff, sr))
gs = mpl.gridspec.GridSpec(12, 4, width_ratios=[1, 1, 1, 1])
i = 0
print "\tPlot data and pre-processing"
for name in (feature,
'{}-LPF'.format(feature),
'{}(LPF)'.format(dim_red),
'LPF({})'.format(dim_red),
'LPF({}-LPF)'.format(feature),
'{}(LPF({}-LPF))'.format(dim_red, feature)):
data = feat[name]
data_wide = np.array([feat[name][m:m+length, :]
for m in xrange(len(feat[name])-length)])
data_wide = data_wide.reshape(
data_wide.shape[0], data_wide.shape[1]*data_wide.shape[2])
# build codebook using kmeans or DP-GMM
if clustering == 'KMEANS':
K_MIN, K_MAX = 2, 16
KM = [KMeans(n_clusters=l, init='k-means++').fit(data_wide)
for l in xrange(K_MIN, K_MAX+1)]
# compute scores to assess fit
scores_bic = [computeBic(KM[x], data_wide) for x in xrange(len(KM))]
scores_inertia = [KM[x].inertia_ for x in xrange(len(KM))]
scores_silhouette = [silhouette_score(data_wide, KM[x].labels_,
metric='euclidean')
for x in xrange(len(KM))]
# get best clusters
idx_best_bic = findElbow(np.dstack(
(xrange(K_MIN, K_MAX+1), scores_bic))[0])
idx_best_inertia = findElbow(np.dstack(
(xrange(K_MIN, K_MAX+1), scores_inertia))[0])
idx_best_silhouette = findElbow(np.dstack(
(xrange(K_MIN, K_MAX+1), scores_silhouette))[0])
idx_best = int(np.median(
(idx_best_bic, idx_best_inertia, idx_best_silhouette))) + 1
# get clusters and cluster allocations given best K
k_best = idx_best + K_MIN
centroids = KM[idx_best].cluster_centers_
centroid_idx = KM[idx_best].labels_
elif clustering == 'DPGMM':
n_components = 12
dpgmm = DPGMM(
n_components=n_components, tol=1e-3, n_iter=32, alpha=1000,
covariance_type='diag', verbose=True)
dpgmm.fit(data_wide)
# compute scores to assess fit
scores_bic = dpgmm.bic(data_wide)
scores_silhouette = [silhouette_score(data_wide, centroids,
metric='euclidean')]
scores_silhouette = [0.0]
# get clusters and cluster allocations given best K
k_best = dpgmm.means_.shape[0]
centroids = dpgmm.means_
centroid_idx = np.argmax(dpgmm.predict_proba(data_wide), axis=1)
# plot data
if data.shape[1] == 3:
data = data.reshape(1, data.shape[0], data.shape[1])
else:
data = data.T
ax = fig.add_subplot(gs[i, :])
ax.set_title(name)
ax.imshow(data,
interpolation='nearest',
origin='low',
aspect='auto',
cmap=plt.cm.Oranges)
xlabels = ["{}:{}".format(int(x / 60), int(x % 60))
for x in beat_times[::step_size]]
ax.set_xticks(ts[::step_size])
ax.set_xticklabels(xlabels, rotation=60)
ax.grid(False)
# plot clustering on raw feature
changes = np.hstack(([True], centroid_idx[:-1] != centroid_idx[1:]))
for c in xrange(changes.shape[0]-1):
if changes[c] and changes[c+1]:
changes[c] = False
ax_twin = ax.twiny()
ax_twin.set_xlim(ax.get_xlim())
ax_twin.set_xticks(np.argwhere(changes)[:, 0])
ax_twin.set_xticklabels(centroid_idx[changes])
ax_twin.grid(False)
# plot codebook (centroids)
ax = fig.add_subplot(gs[i+1, 0])
ax.set_title(name)
if centroids.shape[1] == 3:
centroids = centroids.reshape(
1, centroids.shape[0], centroids.shape[1])
elif centroids.shape[1] == n_singv * length:
centroids = centroids.reshape(
1, centroids.shape[0]*length, centroids.shape[1]/length)
else:
centroids = centroids.reshape(
centroids.shape[0] * length,
centroids.shape[1] / length).T
ax.imshow(centroids,
interpolation='nearest',
origin='low',
aspect='auto',
cmap=plt.cm.Oranges)
ax.set_xticks(xrange(0, centroids.shape[1], 4))
ax.set_xticklabels(xrange(k_best))
ax.grid(False)
# plot elbow curve
c = 1
for k, v, idx in (('BIC', scores_bic, idx_best_bic),
('INERTIA', scores_inertia, idx_best_inertia),
('SILHOUETTE', scores_silhouette, idx_best_silhouette)
):
ax = fig.add_subplot(gs[i+1, c])
ax.set_title('{}, {} best K {}'.format(name, k, idx+K_MIN))
ax.plot(xrange(K_MIN, K_MAX+1), v, 'b*-')
ax.set_xlim((K_MIN, K_MAX+1))
ax.set_xlabel('Number of clusters')
ax.set_ylabel('Score')
ax.grid(True)
ax.axvline(idx+K_MIN, color='r')
c += 1
i += 2
"""
if 'SVD' in name:
# scikit-image clustering
segments_slic = slic(
data, n_segments=10, compactness=10, sigma=1)
segments_quickshift = quickshift(
data, kernel_size=3, max_dist=6, ratio=0.5)
ax = fig.add_subplot(gs[k, 0])
ax.set_title('{} with quickshift'.format(name))
ax.imshow(mark_boundaries(data, segments_quickshift, mode='outer'),
interpolation='nearest',
origin='low',
aspect='auto',
cmap=plt.cm.Oranges)
ax.set_xticks(ts[::step_size])
ax.set_xticklabels(beat_times[::step_size], rotation=60)
ax.grid(False)
ax = fig.add_subplot(gs[k, 1])
ax.set_title('{} with slic'.format(name))
ax.imshow(mark_boundaries(data, segments_slic, mode='outer'),
interpolation='nearest',
origin='low',
aspect='auto',
cmap=plt.cm.Oranges)
ax.set_xticks(ts[::step_size])
ax.set_xticklabels(beat_times[::step_size], rotation=60)
ax.grid(False)
k += 1
"""
plt.tight_layout()
plt.savefig("{}_clustering_{}_{}_r_{}_n_{}_s_{}_l_{}_{}.png".format(
filename, feature, cutoff, round_to, normalize, scale, length, dim_red))
# save with large size
plt.savefig("{}_clustering_{}_{}_r_{}_n_{}_s_{}_l_{}_{}.png".format(
filename, feature, cutoff, round_to, normalize, scale, length, dim_red))
# save with smaller size
fig.set_figwidth(36)
fig.set_figheight(24)
plt.tight_layout()
plt.savefig("{}_clustering_{}_{}_r_{}_n_{}_s_{}_l_{}_{}_small.png".format(
filename, feature, cutoff, round_to, normalize, scale, length, dim_red))
plt.close(fig)
X = ds.data
Y = ds.target
return X, Y
def test1():
print 'test1'
model = VDPGMM(T = 10, alpha = 1, max_iter = 50)
X, Y = getXY('iris')
model.fit(X)
y = model.predict(X)
print 'VDPGMM'
print len(np.unique(y)), np.unique(y)
print [np.sum(y == label) for label in np.unique(y)]
from sklearn.mixture import DPGMM
model = DPGMM(n_components = 10, alpha = 1, n_iter = 50)
model.fit(X)
y = model.predict(X)
print 'DPGMM'
print len(np.unique(y)), np.unique(y)
print [np.sum(y == label) for label in np.unique(y)]
def test2():
print 'test2'
np.random.seed(1)
X = np.concatenate((2 + np.random.randn(100, 2), 5 + np.random.randn(100, 2), 10 + np.random.randn(100, 2)))
T = 10
model = VDPGMM(T=T, alpha=.5, max_iter=100, thresh=1e-5)
model.fit(X)
plt.clf()
