def trainNormalization(self):
assert len(self.labels) >= 2
if self.type == TYPE_TWOCLASS or self.type == TYPE_MULTICLASS:
# Learn the classes
n_classes = 0
self.class_map = {}
for label in self.labels:
if not self.class_map.has_key(label):
self.class_map[label] = n_classes
n_classes += 1
if self.type == TYPE_MULTICLASS:
assert n_classes >= 2
if self.type == TYPE_TWOCLASS:
assert n_classes == 2
self.class_inv = {}
for key, value in self.class_map.iteritems():
self.class_inv[value] = key
new_labels = []
for each in self.labels:
new_labels.append(self.class_map[each])
self.labels = new_labels
if self.type == TYPE_REGRESSION:
self.reg_mean = mean(self.labels)
self.reg_std = std(self.labels)
new_labels = []
for each in self.labels:
new_labels.append((each - self.reg_mean) / self.reg_std)
self.labels = new_labels
#test length
shape = self.vectors[0].shape
assert len(shape) == 1
for each in self.vectors:
assert shape == each.shape
#crate a data matrix
data = array(self.vectors, 'd')
if self.norm == NORM_AUTO:
self.norm = NORM_VALUE
if data.shape[1] > 128:
self.norm = NORM_PCA
#Setup value normalization
if self.norm == NORM_VALUE:
self.dmean = data.mean(axis=0)
self.dstd = data.std(axis=0)
self.vectors = (data - self.dmean) / self.dstd
elif self.norm == NORM_PCA:
self.pca = PCA()
for vec in self.vectors:
self.pca.addFeature(vec)
if self.pca_basis > 1:
self.pca.train(drop_front=self.pca_drop, number=self.pca_basis)
else:
self.pca.train(drop_front=self.pca_drop, energy=self.pca_basis)
new_vectors = []
for each in self.vectors:
new_vectors.append(self.pca.project(each, whiten=True))
self.vectors = array(new_vectors, 'd')
