def test_cluster_perfect_center(self):
centroids = np.zeros((self.cluster_count,dna.DNA.kmer_hash_count))
centroids[0,:] = multinomial.fit_nonzero_parameters([self.contigs[0],self.contigs[1]])
centroids[1,:] = multinomial.fit_nonzero_parameters([self.contigs[2],self.contigs[3]])
correct_clusters = kmeans._expectation(self.contigs,multinomial.log_probabilities,centroids)
self.params["centroids"] = centroids
(clusters, clust_prob,new_centroids) = kmeans._clustering(self.cluster_count, self.max_iter, self.run, self.epsilon, self.verbose, multinomial.log_probabilities, multinomial.fit_nonzero_parameters, **self.params)
assert_equal(kmeans._evaluate_clustering(multinomial.log_probabilities, correct_clusters, centroids),clust_prob)
def test_generate_kplusplus_centroids10000(self):
centroids = kmeans._generate_kplusplus(self.contigs,multinomial.log_probabilities,multinomial.fit_nonzero_parameters,self.cluster_count,dna.DNA.kmer_hash_count,self.rs)
print>>sys.stderr, centroids.shape
print>>sys.stderr, len(self.contigs)
print>>sys.stderr, self.cluster_count
self.params["centroids"] = centroids
(clusters,clust_prob,new_centroids) = kmeans._clustering(self.cluster_count,self.max_iter, self.run, self.epsilon, self.verbose, multinomial.log_probabilities,multinomial.fit_nonzero_parameters,**self.params)
assert_equal(len(centroids), self.cluster_count)
assert_equal(len(centroids[0]),dna.DNA.kmer_hash_count )
assert_equal(np.sum(centroids,axis=1).all(),1)
def test_generate_kplusplus_centroids(self):
centroids = kmeans._generate_kplusplus(self.contigs,multinomial.log_probabilities, multinomial.fit_nonzero_parameters,self.cluster_count,dna.DNA.kmer_hash_count,self.rs)
assert_equal(len(centroids), self.cluster_count)
assert_equal(len(centroids[0]),dna.DNA.kmer_hash_count )
assert_equal(np.sum(centroids,axis=1).all(),1)
correct_centroids = np.zeros((self.cluster_count,dna.DNA.kmer_hash_count))
correct_centroids[0,:] = multinomial.fit_nonzero_parameters([self.contigs[0], self.contigs[1]])
correct_centroids[1,:] = multinomial.fit_nonzero_parameters([self.contigs[2], self.contigs[3]])
correct_clusters = kmeans._expectation(self.contigs,multinomial.log_probabilities,correct_centroids)
correct_clust_prob = kmeans._evaluate_clustering(multinomial.log_probabilities, correct_clusters,correct_centroids)
self.params["centroids"] = correct_centroids
(clusters, clust_prob,new_centroids) = kmeans._clustering(self.cluster_count, self.max_iter, self.run, self.epsilon, self.verbose, multinomial.log_probabilities, multinomial.fit_nonzero_parameters, **self.params)
print clust_prob
assert_almost_equal(0, min(np.abs(clust_prob - np.array([-1659.9510320847476, -1652.322663414292, -1658.28785337, -1665.52431153]))))
def _clustering_XXXXX_NOT_USED(cluster_count, max_iter, run, epsilon, verbose, log_probabilities_func, fit_nonzero_parameters_func, **kwargs):
contigs = kwargs["contigs"]
p = kwargs["centroids"]
if 'model_coverage' in kwargs and kwargs['model_coverage'] is not None:
print >> sys.stderr, "Model coverage in em"
sys.exit(-1)
if not np.any(p):
clustering,_, p = kmeans._clustering(cluster_count, max_iter=3, run=run, epsilon=epsilon, verbose=verbose, log_probabilities_func=log_probabilities_func, fit_nonzero_parameters_func=fit_nonzero_parameters_func, **kwargs)
n = np.array([len(cluster) for cluster in clustering])
exp_log_qs, max_log_qs = _get_exp_log_qs(contigs,log_probabilities_func,p)
z = _expectation(contigs,n,exp_log_qs)
prev_prob,_,_ = _evaluate_clustering(contigs, log_probabilities_func, p, z)
else:
print >> sys.stderr, "Not implemented for EM to start with fixed p (centroids)"
sys.exit(-1)
if verbose:
_log_current_status(contigs,prev_prob,p,z,run)
prob_diff = np.inf
prev_prob = -np.inf
iteration = 0
while(max_iter - iteration > 0 and prob_diff >= epsilon):
z = _expectation(contigs,n,exp_log_qs)
p = _maximization(contigs,fit_nonzero_parameters_func,z)
curr_prob, exp_log_qs, max_log_qs = _evaluate_clustering(contigs,log_probabilities_func,p,z)
n = np.sum(z,axis=0,keepdims=True)
prob_diff = curr_prob - prev_prob
if verbose:
_log_current_status(contigs,curr_prob,p,z,run)
(curr_prob,prev_prob) = (prev_prob,curr_prob)
iteration += 1
#Change back so curr_prob represents the highest probability
(curr_prob,prev_prob) = (prev_prob,curr_prob)
print >> sys.stderr, "EM iterations: {0}, difference: {1}".format(iteration, prob_diff)
if prob_diff < 0:
print >> sys.stderr, "EM got worse, diff: {0}".format(prob_diff)
return (clustering, curr_prob, p)
