def split_train_test(test_size):
# choose a dataset with unbalanced class instances
#data = sklearn.datasets.fetch_mldata('segment')
data = sklearn.datasets.fetch_mldata('vehicle')
X = StandardScaler().fit_transform(data['data'])
target = np.unique(data['target'])
# mapping the targets to 0 to n_classes-1
y = np.array([np.where(target == i)[0][0] for i in data['target']])
X_trn, X_tst, y_trn, y_tst = \
train_test_split(X, y, test_size=test_size, stratify=y)
# making sure each class appears ones initially
init_y_ind = np.array(
[np.where(y_trn == i)[0][0] for i in range(len(target))])
y_ind = np.array([i for i in range(len(X_trn)) if i not in init_y_ind])
trn_ds = Dataset(
np.vstack((X_trn[init_y_ind], X_trn[y_ind])),
np.concatenate((y_trn[init_y_ind], [None] * (len(y_ind)))))
tst_ds = Dataset(X_tst, y_tst)
fully_labeled_trn_ds = Dataset(
np.vstack((X_trn[init_y_ind], X_trn[y_ind])),
np.concatenate((y_trn[init_y_ind], y_trn[y_ind])))
cost_matrix = 2000. * np.random.rand(len(target), len(target))
np.fill_diagonal(cost_matrix, 0)
print(trn_ds.get_entries()[0])
print(np.shape(fully_labeled_trn_ds.get_entries()))
return trn_ds, tst_ds, fully_labeled_trn_ds, cost_matrix
class UncertaintySampler(object):
def __init__(self, X, y, labs, n=2):
y = [yy if yy >= 0 else None for yy in y]
self.dataset = Dataset(X, y)
self.labs = labs
self.uc = UncertaintySampling(self.dataset,
method='lc',
model=LinearSVC())
self.n = n
def get_next(self):
print >> sys.stderr, 'get_next: start'
out = self.uc.make_query(n=self.n)
print >> sys.stderr, 'get_next: done'
return out
def set_label(self, idx, label):
print >> sys.stderr, 'set_label: start'
out = self.dataset.update(idx, label)
print >> sys.stderr, 'set_label: done'
return out
def get_data(self):
X, y = zip(*self.dataset.get_entries())
X, y = np.vstack(X), np.array(
[yy if yy is not None else -1 for yy in y])
return X, y
def n_hits(self):
labels = np.array(zip(*self.dataset.get_entries())[1])
return (labels == 1).sum()
def n_labeled(self):
return self.dataset.len_labeled()
def is_labeled(self, idx):
return idx in np.where(zip(*self.dataset.get_entries())[1])[0]
def save(self, outpath):
""" !! This should be updated to save in same format as simple_las """
X, y = self.get_data()
f = h5py.File(
'%s-%s-%s.h5' %
(outpath, 'uncertainty', datetime.now().strftime('%Y%m%d_%H%M%S')))
f['X'] = X
f['y'] = y
f['labs'] = self.labs
f.close()