def test_train(self, params='wm'):
b = bernoullimm.BernoulliMM(n_components=self.n_components)
b.weights_ = self.weights
b.means_ = self.means
b.log_odds_, b.log_inv_mean_sums_ = bernoullimm._compute_log_odds_inv_means_sums(
self.means)
# Create a training set by sampling from the predefined distribution.
X = b.sample(n_samples=100)
b = self.model(n_components=self.n_components,
random_state=rng,
n_iter=1,
init_params=params)
b.fit(X)
# Do one training iteration at a time so we can keep track of
# the log likelihood to make sure that it increases after each
# iteration.
trainll = []
for iter in range(5):
b.params = params
b.init_params = ''
b.fit(X)
trainll.append(self.score(b, X))
b.n_iter = 10
b.init_params = ''
b.params = params
b.fit(X) # finish fitting
delta_min = np.diff(trainll).min()
self.assertTrue(
delta_min > self.threshold,
"The min nll increase is %f which is lower than the admissible"
" threshold of %f. The likelihoods are %s." %
(delta_min, self.threshold, trainll))
def test_n_parameters():
"""Test that the right number of parameters is estimated"""
n_samples, n_dim, n_components = 7, 5, 2
X = (rng.rand(n_samples, n_dim) > .5).astype(np.uint8)
n_params = n_dim * n_components + n_components - 1
b = bernoullimm.BernoulliMM(n_components=n_components,
random_state=rng,
n_iter=1)
b.fit(X)
assert_true(b._n_parameters() == n_params)
def test_multiple_init():
"""Test that multiple inits performs at least as well as a single one"""
X = (rng.rand(30, 5) > .5).astype(np.uint8)
b = bernoullimm.BernoulliMM(n_components=2, random_state=rng, n_iter=5)
train1 = b.fit(X).score(X).sum()
b.n_init = 5
out_b = b.fit(X)
print(out_b.means_)
train2 = out_b.score(X).sum()
print("train2 = {0}, train1 = {1}".format(train2, train1))
assert_true(train2 >= train1 - 1.e-2)
def test_BernoulliMM_attributes():
n_components, n_features = 10, 4
b = bernoullimm.BernoulliMM(n_components, random_state=rng)
weights = rng.rand(n_components)
weights = weights / weights.sum()
means = np.clip(rng.rand(n_components, n_features), .01, .99)
log_inv_means = np.log(1 - means)
log_odds = np.log(means) - log_inv_means
log_inv_mean_sums = log_inv_means.sum(-1)
assert_true(b.n_components == n_components)
b.weights_ = weights
assert_array_almost_equal(b.weights_, weights)
b.means_ = means
assert_array_almost_equal(b.means_, means)
b.log_inv_means_ = log_inv_means
assert_array_almost_equal(b.log_inv_means_, log_inv_means)
b.log_odds_ = log_odds
assert_array_almost_equal(b.log_odds_, log_odds)
b.log_inv_mean_sums_ = log_inv_mean_sums
assert_array_almost_equal(b.log_inv_mean_sums_, log_inv_mean_sums)
def main(args):
"""
For each label and component constructed a positive and negative
training set and train a linear SVM to separate them
"""
config_d = configParserWrapper.load_settings(open(args.config, 'r'))
true_examples = []
false_examples = []
mean = 0
total = 0
num_less_than_eq = np.zeros(20)
all_X_patches = []
all_S_patches = []
for phn_id, (fl_edge, fl_spec) in enumerate(
itertools.izip(args.data, args.data_spec)):
if len(all_X_patches) > 100000: break
print phn_id
X = np.load(fl_edge)
X_shape = X.shape[1:]
S = np.load(fl_spec)
if args.do_exp_weighted_divergence:
S *= np.exp(S)
X_patches = []
S_patches = []
for i in xrange(len(X)):
if len(X_patches) > 1000: break
p_edge, p_spec = get_maximal_patches(
X[i], S[i], patch_radius=args.patch_radius)
X_patches.extend(p_edge)
S_patches.extend(p_spec)
num_new_patches = len(X_patches)
print phn_id, num_new_patches
all_X_patches.extend(X_patches)
all_S_patches.extend(S_patches)
X = np.array(all_X_patches)
S = np.array(all_S_patches)
data_shape = X.shape[1:]
X = X.reshape(X.shape[0], np.prod(data_shape))
bmm = bernoullimm.BernoulliMM(n_components=args.n_components,
n_init=20,
n_iter=500,
random_state=0,
verbose=args.v,
tol=1e-6)
bmm.fit(X)
# check above 30
use_means = bmm.predict_proba(X).sum(0) > 30
print use_means.sum()
try:
np.save(
args.save_parts,
bmm.means_.reshape(*((bmm.n_components, ) +
data_shape))[use_means])
except:
import pdb
pdb.set_trace()
S_shape = S.shape[1:]
S_clusters = bmm.cluster_underlying_data(
S.reshape(len(S), np.prod(S_shape)),
X).reshape(*((bmm.n_components, ) + S_shape))[use_means]
np.save(args.spec_save_parts, S_clusters)
ncols = int(np.sqrt(args.n_components))
nrows = int(np.ceil(args.n_components / ncols))
if args.viz_spec_parts is not None:
plt.close('all')
fig = plt.figure(1, (6, 6))
grid = ImageGrid(
fig,
111, # similar to subplot(111)
nrows_ncols=(nrows, ncols), # creates 2x2 grid of axes
axes_pad=0.001, # pad between axes in inch.
)
for i in xrange(S_clusters.shape[0]):
try:
grid[i].imshow(S_clusters[i],
cmap=cm.binary,
interpolation='nearest')
grid[i].spines['bottom'].set_color('red')
grid[i].spines['top'].set_color('red')
grid[i].spines['left'].set_color('red')
grid[i].spines['right'].set_color('red')
for a in grid[i].axis.values():
a.toggle(all=False)
except:
import pdb
pdb.set_trace()
for i in xrange(S_clusters.shape[0], nrows * ncols):
try:
grid[i].spines['bottom'].set_color('red')
except:
import pdb
pdb.set_trace()
grid[i].spines['top'].set_color('red')
grid[i].spines['left'].set_color('red')
grid[i].spines['right'].set_color('red')
for a in grid[i].axis.values():
a.toggle(all=False)
plt.savefig('%s' % args.viz_spec_parts, bbox_inches='tight')
def main(args):
"""
For each label and component constructed a positive and negative
training set and train a linear SVM to separate them
"""
config_d = configParserWrapper.load_settings(open(args.config,'r'))
true_examples = []
false_examples = []
mean = 0
total = 0
num_less_than_eq = np.zeros(20)
fls = np.loadtxt(args.fls_txt, dtype=str)
all_X_patches = []
all_S_patches = []
htemp, dhtemp, ddhtemp, tttemp = fb.hermite_window(
args.winsize,
args.num_tapers,
args.win_half_time_support)
run_transform = lambda x, winlength : esp.get_spectrogram_features(x,
16000,
winlength,
80,
2**(int(np.ceil(np.log2(winlength)))),
4000,
7,
)
X_patches = []
S_patches = []
for fl_id, fl_path in enumerate(fls):
if len(X_patches) > 100000: break
S = run_transform(wavfile.read(fl_path)[1], args.winsize)
# spectrogram(,
# 16000,
# 3200,
# args.winsize,
# 2**int(np.ceil(np.log2(args.winsize))),
# 2,
# htemp)
if args.do_exp_weighted_divergence:
Sold = S.copy()
S *=np.exp(S)
X = get_edge_features_use_config(S.T,config_d['EDGES'])
cur_X_patches, cur_S_patches = get_maximal_patches(X,S,patch_radius=2)
X_patches.extend(cur_X_patches)
S_patches.extend(cur_S_patches)
num_new_patches = len(X_patches)
X = np.array(X_patches)
S = np.array(S_patches)
data_shape = X.shape[1:]
X = X.reshape(X.shape[0],np.prod(data_shape))
bmm = bernoullimm.BernoulliMM(n_components=args.n_components,
n_init= 50,
n_iter= 500,
random_state=0,
verbose=args.v, tol=1e-6)
bmm.fit(X)
# check above 30
use_means = bmm.predict_proba(X).sum(0) > 30
print use_means.sum()
try:
np.save(args.save_parts,bmm.means_.reshape(*( (bmm.n_components,)+data_shape))[use_means])
except:
import pdb; pdb.set_trace()
S_shape = S.shape[1:]
import pdb; pdb.set_trace()
S_clusters = bmm.cluster_underlying_data(S.reshape(len(S),np.prod(S_shape)),X).reshape(
*( (bmm.n_components,) + S_shape))[use_means]
np.save(args.spec_save_parts,S_clusters)
ncols = int(np.sqrt(args.n_components))
nrows = int(np.ceil(args.n_components/ncols))
if args.viz_spec_parts is not None:
plt.close('all')
fig = plt.figure(1, (6, 6))
grid = ImageGrid(fig, 111, # similar to subplot(111)
nrows_ncols = (nrows,ncols ), # creates 2x2 grid of axes
axes_pad=0.001, # pad between axes in inch.
)
for i in xrange(S_clusters.shape[0]):
try:
grid[i].imshow(S_clusters[i],cmap=cm.binary,interpolation='nearest')
grid[i].spines['bottom'].set_color('red')
grid[i].spines['top'].set_color('red')
grid[i].spines['left'].set_color('red')
grid[i].spines['right'].set_color('red')
for a in grid[i].axis.values():
a.toggle(all=False)
except:
import pdb; pdb.set_trace()
for i in xrange(S_clusters.shape[0],nrows*ncols):
try:
grid[i].spines['bottom'].set_color('red')
except: import pdb; pdb.set_trace()
grid[i].spines['top'].set_color('red')
grid[i].spines['left'].set_color('red')
grid[i].spines['right'].set_color('red')
for a in grid[i].axis.values():
a.toggle(all=False)
plt.savefig('%s' % args.viz_spec_parts
,bbox_inches='tight')