def gmmClustering(X, k = 2, maxiter = 3):
my_io.startLog(__name__)
logger = logging.getLogger(__name__)
X, r = kmeans.kmeansClustering(X, 2, 1)
(N, D) = np.shape(X)
pi_k_old = [np.divide(len(np.where(r==kth)[0]), float(N))
for kth in range(k) ]
# mu_old = compute_muk(X, k, r)
cova_old, mu_old = compute_cova(k, X, r)
for i in range(maxiter):
#if i==1:
# pdb.set_trace()
logger.info('ite: %d loss: %f',i,
loss(X, mu_old, pi_k_old, cova_old) )
p = gmm_Esteps(X, pi_k_old, k, cova_old, mu_old)
mu_new, cova_new, pi_k_new = gmm_Msteps(mu_old, X, p)
pi_k_old = pi_k_new
mu_old = mu_new
cova_old = cova_new
#matplotlib.cm=get_cmap("jet")
cm = plt.get_cmap('jet')
ax = plt.gca()
# colors = ['r' if i==0 else 'g' for i in ?]
#colors = 'r'
#ax.scatter(X[:,0], X[:,1], c=colors,alpha=0.8)
# plt.show()
for j in range(N):
likehood = p[1][j]
color = cm(likehood)
plt.plot(X[j,0], X[j,1] ,"o", color=color)
plt.show()
for j in range(N):
likehood = p[0][j]
color = cm(likehood)
plt.plot(X[j,0], X[j,1] ,"o", color=color)
plt.show()
from __future__ import absolute_import
import argparse
import numpy as np
import kmeans as km
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument("--verbosity", help="increase output verbosity")
args = parser.parse_args()
# data = load_data("../data/data.txt")
data = np.load("data/clusterable_data.npy")
clusters, centroids = km.kmeansClustering(data,
k=6,
iter=20,
verbose=args.verbosity)
plot_data(data)
plot_clusters(clusters, centroids)
def pre_kmeans(X,k): # X can be unnorlized, which will be done in kmeans (normalizeX, r) = kmeans.kmeansClustering(X,k) return normalizeX, r
