def _fit_dpgmm(self, x):
# clustering
k = max(self.crange)
for r in xrange(self.repeats):
# info
if self.debug is True:
print '\t[%s][c:%d][r:%d]' % (self.clus_type, k, r + 1),
# fit and evaluate model
model_kwargs = {}
if 'alpha' in self.clus_kwargs:
model_kwargs.update(alpha=self.clus_kwargs['alpha'])
if 'conv_thresh' in self.clus_kwargs:
model_kwargs.update(thresh=self.clus_kwargs['conv_thresh'])
if 'max_iter' in self.clus_kwargs:
model_kwargs.update(n_iter=self.clus_kwargs['max_iter'])
model = DPGMM(n_components=k, covariance_type=self.cvtype,
**model_kwargs)
model.fit(x)
self._labels[r] = model.predict(x)
self._parameters[r] = model.means_
self._ll[r] = model.score(x).sum()
# evaluate goodness of fit for this run
#self._gof[r] = self.gof(x, self._ll[r], k)
if self.gof_type == 'aic':
self._gof[r] = model.aic(x)
if self.gof_type == 'bic':
self._gof[r] = model.bic(x)
# debug
if self.debug is True:
print self._gof[r], model.n_components, model.weights_.shape[0]
def _fit_dpgmm(self, x):
# clustering
k = max(self.crange)
for r in xrange(self.repeats):
# info
if self.debug is True:
print '\t[%s][c:%d][r:%d]' % (self.clus_type, k, r + 1),
# fit and evaluate model
model_kwargs = {}
if 'alpha' in self.clus_kwargs:
model_kwargs.update(alpha=self.clus_kwargs['alpha'])
if 'conv_thresh' in self.clus_kwargs:
model_kwargs.update(thresh=self.clus_kwargs['conv_thresh'])
if 'max_iter' in self.clus_kwargs:
model_kwargs.update(n_iter=self.clus_kwargs['max_iter'])
model = DPGMM(n_components=k,
covariance_type=self.cvtype,
**model_kwargs)
model.fit(x)
self._labels[r] = model.predict(x)
self._parameters[r] = model.means_
self._ll[r] = model.score(x).sum()
# evaluate goodness of fit for this run
#self._gof[r] = self.gof(x, self._ll[r], k)
if self.gof_type == 'aic':
self._gof[r] = model.aic(x)
if self.gof_type == 'bic':
self._gof[r] = model.bic(x)
# debug
if self.debug is True:
print self._gof[r], model.n_components, model.weights_.shape[0]
def main():
if len(sys.argv) != 4:
print(__doc__)
return 1
infile = sys.argv[1]
N = int(sys.argv[2])
num_random = int(sys.argv[3])
print("Reading in", infile)
fullarr = np.loadtxt(fileinput.input(infile), delimiter = '\t')[:,:-7]
stds = np.apply_along_axis(np.std, 0, fullarr)[:,np.newaxis].T
means = np.apply_along_axis(np.mean, 0, fullarr)[:,np.newaxis].T
stds[stds == 0] = 1.0
num_lines = num_random
fullarr = fullarr[np.random.choice(fullarr.shape[0], num_lines, replace=True),:]
fullarr = (fullarr - means) / stds
output = ''
print("Parameter searching...")
igmm = None
best_score = -100000
best_alpha = -1
best_model = None
for alpha in [0.01,0.1,1,10]:
print("Learning infinite GMM with N={}, alpha={}".format(N, alpha))
output += "Learning infinite GMM with N={}, alpha={}\n".format(N, alpha)
igmm = DPGMM(covariance_type='diag', n_components=N, alpha=alpha, init_params='wmc')
igmm.fit(fullarr)
score = igmm.score(fullarr)
score = sum(score)/len(score)
print('{}: {} with {} clusters'.format(alpha, score, igmm.n_components))
output += '{}: {} with {} clusters\n'.format(alpha, score, igmm.n_components)
if score > best_score:
best_score = score
best_alpha = alpha
best_model = igmm
print('Best alpha={}, score={}'.format(best_alpha, best_score))
output += 'Best alpha={}, score={}\n'.format(best_alpha, best_score)
with open('parameter_search_results.txt', 'a+') as outf:
outf.write(output)
return 0
def get_best_dpgmm(X, num_c, cv_type, alpha, iters, n_init, rand_state=None):
best_bic = np.inf
bic_dpgmm = None
lbl_vec_dpgmm = np.zeros(X.shape[0])
prob_vec_dpgmm = np.zeros(X.shape[0])
log_prob_dpgmm = None
for i in xrange(n_init):
dpgmm = DPGMM(n_components=num_c, covariance_type=cv_type, \
alpha=alpha, random_state=rand_state)
dpgmm.fit(X)
b = dpgmm.bic(X)
if b < best_bic:
bic_dpgmm = b
lbl_vec = dpgmm.predict(X)
prob_vec = dpgmm.predict_proba(X)
log_prob_dpgmm = np.sum(dpgmm.score(X))
return [lbl_vec, prob_vec, bic_dpgmm, log_prob_dpgmm]
def main():
if len(sys.argv) != 5:
print(__doc__)
return 1
infiles = glob(sys.argv[1])
outfile = sys.argv[2]
N = int(sys.argv[3])
alpha = float(sys.argv[4])
print("Reading in", len(infiles), "files")
fullarr = np.loadtxt(fileinput.input(infiles), delimiter = '\t')[:,:-7]
stds = np.apply_along_axis(np.std, 0, fullarr)[:,np.newaxis].T
means = np.apply_along_axis(np.mean, 0, fullarr)[:,np.newaxis].T
stds[stds == 0] = 1.0
num_lines = 10000
fullarr = fullarr[np.random.choice(fullarr.shape[0], num_lines, replace=True),:]
fullarr = (fullarr - means) / stds
print("Learning infinite GMM with N={}, alpha={}".format(N, alpha))
igmm = DPGMM(covariance_type='diag', n_components=N, alpha=alpha, init_params='wmc')
igmm.fit(fullarr)
print("Infinite GMM trained, saving")
with open(outfile + '_' + num_lines, 'wb') as out_model:
pickle.dump(igmm, out_model)
print("Score:", igmm.score(fullarr))
print("Num Components:", igmm.n_components)
return 0
