def em_clustering(data, nclust, maxiter, epsilon):
#Initialization of mean, covariance, and prior
n, d = data.shape
mu = np.zeros((nclust, d), dtype=float)
sigma = np.zeros((nclust, d, d), dtype=float)
for t in range(nclust): # assigning data points to the means
mu[t] = data[t]
sigma[t] = np.identity(d)
prior = np.asarray(np.repeat(1.0 / nclust, nclust),
dtype=float) #for each cluster one prior:
for i in range(maxiter):
mu_old = 1 * mu
W = EM.e_step(data, mu, sigma, prior, nclust) #calling E-step funct.
mu, sigma, prior = EM.m_step(data, W, mu, sigma,
nclust) # calling M-step funct.
#checking stopping criterion
temp = 0
for j in range(nclust):
temp = temp + np.sqrt(np.power((mu[j] - mu_old[j]), 2).sum())
temp = round(temp, 4)
if temp <= epsilon:
break
#print "Iteration number = %d, stopping criterion = %.4f" %(i+1,temp)
return mu, sigma, prior
def model_eval(dataFile, nclust, maxiter, epsilon):
#reading data: X- data, y- class att.
X, y = readingData.dataPrep(dataFile)
#training
start_time = time.time()
mu, sigma, prior = EM.em_clustering(X, nclust, maxiter, epsilon)
averageTraningTime = time.time() - start_time
#testing
W = EM.e_step(X, mu, sigma, prior, nclust)
accuracy = testing.test(y, W, X)
averageTraningTime = round(averageTraningTime, 3)
accuracy = int(round(accuracy * 100))
print(" Traning running time :%s seconds " % averageTraningTime)
print("accuracy:%s%%" % accuracy)
