def __init__(self,
X,
y,
cb_classifier,
label_inds_5=None,
unlabel_inds_5=None,
modelOutput_5=None):
self.X = X
self.y = y
self.cb_classifier = cb_classifier
dt = DataSet('au', X=X, y=y)
self.distacne = dt.get_distance()
_, self.cluster_center_index = dt.get_cluster_center()
self.flag = False
if label_inds_5 is not None:
if unlabel_inds_5 is not None:
if modelOutput_5 is not None:
self.label_inds_5 = label_inds_5
self.unlabel_inds_5 = unlabel_inds_5
self.modelOutput_5 = modelOutput_5
self.flag = True
if self.flag is False:
self.label_inds_5 = []
self.unlabel_inds_5 = []
self.modelOutput_5 = []
split_count = [30, 50, 70, 90]
# The number of unlabel data to select to generate the meta data.
num_xjselect = 30
diff_five_round = 20
n_labelleds = np.arange(2, 100, 2)
# first choose a dataset
for datasetname in datasetnames:
dataset = DataSet(datasetname, dataset_path)
X = dataset.X
y = dataset.y
distacne = dataset.get_distance()
_, cluster_center_index = dataset.get_cluster_center()
print(
datasetname +
' DataSet currently being processed********************************************'
)
# run multiple split on the same dataset
# every time change the value of initial_label_rate
for split_c in split_count:
for n_labelled in n_labelleds:
metadata = None
# trains, tests, label_inds, unlabel_inds = dataset.split_data_by_nlabelled(n_labelled, test_ratio=0.6, split_count=split_count, saving_path='./n_labelled_split_info')
trains, tests, label_inds, unlabel_inds = dataset.split_data_by_nlabelled_fulldataset(
n_labelled, test_ratio=0.5, split_count=split_c)
for t in range(split_c):
meta_data = cal_meta_data_sequence(
X, y, distacne, cluster_center_index, modelnames,