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 = []
# modelnames = ['KNN', 'LR', 'RFC', 'RFR', 'DTC', 'DTR', 'SVM', 'GBC', 'ABC', 'ABR']
modelnames = ['LR']
# in the same dataset and the same ratio of initial_label_rate,the number of split.
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(
# 'wdbc', 'clean1', 'ethn', , 'blood', 'breast-cancer-wisc'
datasetnames = ['australian']
# Different types of models, each type has many models with different parameters
# modelnames = ['KNN', 'LR', 'RFC', 'RFR', 'DTC', 'DTR', 'SVM', 'GBC', 'ABC', 'ABR']
modelnames = ['LR']
# in the same dataset and the same ratio of initial_label_rate,the number of split.
split_count = 30
# The number of unlabel data to select to generate the meta data.
num_xjselect = 30
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********************************************'
)
metadata = None
# run multiple split on the same dataset
# every time change the value of initial_label_rate
if datasetname in [
'echocardiogram', 'heart', 'heart-hungarian', 'heart-statlog',
'house', 'house-votes', 'spect', 'statlog-heart',
'vertebral-column-2clases'
QueryInstanceQUIRE, QueryRandom, QueryInstanceUncertainty, QureyExpectedErrorReduction, QueryInstanceLAL
from meta_data import DataSet
from QueryMetaData import QueryMetaData
dataset_path = './newdata/'
datasetnames = np.load('datasetname.npy')
# datasetname = 'echocardiogram'
# datasetname = 'australian'
# datasetname = 'blood'
# datasetname = 'texture'
datasetnames = ['tic-tac-toe']
for datasetname in datasetnames:
dt = DataSet(datasetname, dataset_path)
X = dt.X
y = dt.y.ravel()
y = np.asarray(y, dtype=int)
alibox = ToolBox(X=X,
y=y,
query_type='AllLabels',
saving_path='./experiment_result/')
# Split data
alibox.split_AL(test_ratio=0.3, initial_label_rate=0.05, split_count=5)
# Use the default Logistic Regression classifier
model = alibox.get_default_model()
rfr_meta = joblib.load('./newmetadata/rfr_p_regression_australian.joblib')
# rfc_meta = joblib.load('./newmetadata/rfc_p_classify_australian.joblib')
# lr_meta = joblib.load('./newmetadata/lr_p_classify_australian.joblib')
# Use the default Logistic Regression classifier
model = LogisticRegression(solver='lbfgs')
# model = RandomForestClassifier()
# model = SVC(gamma='auto')
for testdataset in testdatasetnames:
print('***********currently dataset is : ', testdataset)
lcdata_uncertainty_select_list = []
lcdata_random_select_list = []
# active learning
dt = DataSet(testdataset, dataset_path)
X = dt.X
y = dt.y.ravel()
y = np.asarray(y, dtype=int)
train_indexs, test_indexs, label_indexs, unlabel_indexs = split_load('./experiment_result/combination_classify/australian_lrmetadata_0.005/australian/')
alibox = ToolBox(X=X, y=y, query_type='AllLabels', saving_path=savefloder_path + testdataset +'/', train_idx=train_indexs, test_idx=test_indexs, label_idx=label_indexs, unlabel_idx=unlabel_indexs)
# Split data
# alibox.split_AL(test_ratio=test_ratio, initial_label_rate=initial_label_ratio, split_count=splitcount)
# alibox.
# The cost budget is 50 times querying
stopping_criterion = alibox.get_stopping_criterion('num_of_queries', query_num)
# datasetnames = ['echocardiogram', 'heart', 'heart-hungarian', 'heart-statlog', 'house',
# 'house-votes', 'spect', 'statlog-heart', 'vertebral-column-2clases']
datasetnames = ['australian']
# Different types of models, each type has many models with different parameters
# modelnames = ['KNN', 'LR', 'RFC', 'RFR', 'DTC', 'DTR', 'SVM', 'GBC', 'ABC', 'ABR']
modelnames = ['LR']
# in the same dataset and the same ratio of initial_label_rate,the number of split.
split_count = 10
# The number of unlabel data to select to generate the meta data.
num_xjselect = 20
# 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********************************************'
)
metadata = None
# run multiple split on the same dataset
# every time change the value of initial_label_rate
if datasetname in [
'echocardiogram', 'heart', 'heart-hungarian', 'heart-statlog',
'house', 'house-votes', 'spect', 'statlog-heart',
'vertebral-column-2clases'
