def fit(self, data, iterations):
prior, muu, sig = kmean_init.EM_init(data, self.nbmixtures_states)
self.prior, self.muu, self.sig = em.EM(data,
prior,
muu,
sig,
iterate=iterations)
help='Verbose mode (Styles Matrices + probZ)')
args = parser.parse_args()
data = init_from_file(args.train_data, 0, not args.r, args.t or args.n)
# Uncomment to confirm correctness of Q and gradQ
# check_gradient(data)
# Run the naive (baseline) algorithm
if args.n:
print naive(data)
# Train our model
else:
start = time()
EM(data)
elapsed = time() - start
print "Completed training in %d minutes and %d seconds\n" % (
elapsed / 60, elapsed % 60)
if args.v: data.outputResults()
if args.t:
if args.p: acc, ce = data.permutedAcc()
else:
acc = data.std_percent_correct()
ce = data.std_cross_entropy()
print "Percent Correct: " + str(acc * 100) + "%"
print "Cross Entropy: " + str(ce)
# Run multiple trials of a test
if __name__ == '__main__':
np.random.seed()
accuracies = []
cross_entropies = []
times = []
steps = []
for sim in range(50): # Run 50 simulations
data = init_from_file("Tests/SinkhornAnalysis/data/%d.txt" % sim, 0,
True, True)
start = time()
num_steps = EM(data)
elapsed = time() - start
times.append(elapsed)
steps.append(num_steps)
print("Simulation %d:" % sim)
print("Number of EM Steps: %d" % num_steps)
print("Elapsed Time: %d minutes, %d seconds" %
(elapsed / 60, elapsed % 60))
acc, ce = data.permutedAcc()
print "Accuracy: %.2f %% | %.2f CE\n" % (acc * 100, ce)
accuracies.append(acc)
cross_entropies.append(ce)
average_acc = 100 * sum(accuracies) / len(accuracies)
def fit(self, data):
self.data = data
Priors, Mu, Sigma = EM_init(data, self.numbefOfStates)
self.Priors, self.Mu, self.Sigma, self.Pix = EM(
data, Priors, Mu, Sigma)
import Logistic import EM # logistic=Logistic.Logistic(50,1,2,1,2,10,2,10,2) # logistic.run() # logistic=Logistic.Logistic(50,1,2,1,2,3,4,3,4) # logistic.run() em = EM.EM() em.run()
def fit(self, data):
self.D = np.shape(data)[1]
self.priors, self.mu, self.sigma, self.coefficients, self.y_sigma, self.ll = EM(data, self.number_of_components)
# -*- coding: utf-8 -*-
"""
Author: VincentGum
"""
import pandas as pd
import numpy as np
import EM
data = pd.read_csv('data/Q2Q3_input.csv')
data.pop('user_id')
# set the initial clusters' centers like this
c1 = np.array([1, 1, 1, 1, 1, 1])
c2 = np.array([0, 0, 0, 0, 0, 0])
c_init = [c1, c2]
em = EM.EM(data.values, c_init)
em.train()
print(em.SSE)
