def select_Z(dataset, OPTION_NZ):
from scipy.cluster.vq import kmeans as scipy_kmeans
np.random.seed(seed=149221)
Z, _ = scipy_kmeans(dataset.xtrain, OPTION_NZ)
return (Z)
def select_Z(dataset, OPTION_NZ):
from scipy.cluster.vq import kmeans as scipy_kmeans
np.random.seed(seed=149221)
Z, _ = scipy_kmeans(dataset.xtrain, OPTION_NZ)
return (Z)
def load_data(seed, ntrain, datasetName, num_inducing):
d = io.loadmat('benchmarks.mat')[datasetName][0, 0]
x, y = d[0], d[1]
y = np.where(y == 1, 1, 0) # data is stored as +-1, we use 1, 0
# split into train, test sets
np.random.seed(seed)
index = np.random.permutation(x.shape[0])
itrain, itest = index[:ntrain], index[ntrain:]
xtrain, xtest = x[itrain], x[itest]
ytrain, ytest = y[itrain], y[itest]
# normalize using training data mean, std
xmean, xstd = xtrain.mean(0), xtrain.std(0)
xstd = np.where(xstd > 1e-6, xstd, 1.)
xtrain, xtest = (xtrain-xmean)/xstd, (xtest-xmean)/xstd
Z, _ = scipy_kmeans(xtrain, num_inducing)
return dict(Xtrain=xtrain, Ytrain=ytrain, Xtest=xtest, Ytest=ytest, Z=Z)
def load_data(seed, ntrain, datasetName, num_inducing):
d = io.loadmat('benchmarks.mat')[datasetName][0, 0]
x, y = d[0], d[1]
y = np.where(y == 1, 1, 0) # data is stored as +-1, we use 1, 0
# split into train, test sets
np.random.seed(seed)
index = np.random.permutation(x.shape[0])
itrain, itest = index[:ntrain], index[ntrain:]
xtrain, xtest = x[itrain], x[itest]
ytrain, ytest = y[itrain], y[itest]
# normalize using training data mean, std
xmean, xstd = xtrain.mean(0), xtrain.std(0)
xstd = np.where(xstd > 1e-6, xstd, 1.)
xtrain, xtest = (xtrain - xmean) / xstd, (xtest - xmean) / xstd
Z, _ = scipy_kmeans(xtrain, num_inducing)
return dict(Xtrain=xtrain, Ytrain=ytrain, Xtest=xtest, Ytest=ytest, Z=Z)
f.close()
del f
d2 = datetime.now()
print "Loading time was: %d.%d" % ((d2-d1).seconds, (d2-d1).microseconds)
# -------------------------------
K = int(sys.argv[2])
print 'Starting clusterig method...'
d1 = datetime.now()
if len(sys.argv)>3 and '--scipy' in sys.argv:
print "Scipy kmeans"
centroids, labels = scipy_kmeans(m, K, minit='points')
else:
print "Opencv kmeans"
samples = cv.fromarray(m)
labels = cv.CreateMat(samples.height, 1, cv.CV_32SC1)
# crit = (cv.CV_TERMCRIT_EPS + cv.CV_TERMCRIT_ITER, 10, 1.0)
crit = (cv.CV_TERMCRIT_ITER, 10, 0)
cv.KMeans2(samples, K, labels, crit)
d2 = datetime.now()
print "Elapsed time for %d clusters: %d.%d" % (K, (d2-d1).seconds, (d2-d1).microseconds)
print 'Updating HDF file with results...'
d1 = datetime.now()
for i, cluster in enumerate(clusters):
print "Cluster", i, len(cluster.data_objects)
print "Silhouette score", cluster_evaluation.silhouette_score(clusters)
time_2 = time.time()
print time_2 - time_1, "seconds"
print
time_1 = time.time()
print "Scipy kmeans"
data_objects = data_objects.ix[:, 0:7].as_matrix()
codebook, distortion = scipy_kmeans(data_objects, k)
code, distortion = vq(data_objects, codebook)
for i in range(k):
print "Cluster", i, len(filter(lambda x:x==i, code))
print "Silhouette score", silhouette_score(data_objects, code)
time_2 = time.time()
print time_2 - time_1, "seconds"
