def SelectLabeled(self, labeled_data_x, labeled_data_y, unlabeled_data_x):
# just append train data to labeled data
labeled_x = np.concatenate((self.init_labeled_data_x, labeled_data_x)) \
if len(labeled_data_x) > 0 else self.init_labeled_data_x
labeled_y = np.concatenate((self.init_labeled_data_y, labeled_data_y)) \
if len(labeled_data_x) > 0 else self.init_labeled_data_y
#
# create model to predict with confidence and credibility
model = ClassifierAdapter(
DecisionTreeClassifier(random_state=config.random_state,
min_samples_leaf=config.min_samples_leaf))
nc = ClassifierNc(model, MarginErrFunc())
model_icp = IcpClassifier(nc, smoothing=True)
model_icp.fit(labeled_x, labeled_y)
model_icp.calibrate(self.calibration_data_x, self.calibration_data_y)
s = model_icp.predict_conf(unlabeled_data_x)
print(s)
#
# selection method
labeled_ind = [
i for i, a in enumerate(s)
if a[1] > config.confidence and a[2] > config.credibility
]
unlabeled_ind = [
i for i, a in enumerate(s)
if a[1] < config.confidence or a[2] < config.credibility
]
labeled_unlabeled_x, labeled_unlabeled_y, unlabeled_data_x = \
np.take(unlabeled_data_x, labeled_ind, axis=0), np.take(s.T, labeled_ind), np.take(unlabeled_data_x,
unlabeled_ind, axis=0)
#
return labeled_unlabeled_x, labeled_unlabeled_y, unlabeled_data_x
def test_confidence_credibility(self):
data = load_iris()
x, y = data.data, data.target
for i, y_ in enumerate(np.unique(y)):
y[y == y_] = i
n_instances = y.size
idx = np.random.permutation(n_instances)
train_idx = idx[:int(n_instances / 3)]
cal_idx = idx[int(n_instances / 3):2 * int(n_instances / 3)]
test_idx = idx[2 * int(n_instances / 3):]
nc = ClassifierNc(ClassifierAdapter(RandomForestClassifier()))
icp = IcpClassifier(nc)
icp.fit(x[train_idx, :], y[train_idx])
icp.calibrate(x[cal_idx, :], y[cal_idx])
print(
pd.DataFrame(icp.predict_conf(x[test_idx, :]),
columns=["Label", "Confidence", "Credibility"]))
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import load_iris
from nonconformist.base import ClassifierAdapter
from nonconformist.icp import IcpClassifier
from nonconformist.nc import ClassifierNc
data = load_iris()
x, y = data.data, data.target
for i, y_ in enumerate(np.unique(y)):
y[y == y_] = i
n_instances = y.size
idx = np.random.permutation(n_instances)
train_idx = idx[:int(n_instances / 3)]
cal_idx = idx[int(n_instances / 3):2 * int(n_instances / 3)]
test_idx = idx[2 * int(n_instances / 3):]
nc = ClassifierNc(ClassifierAdapter(RandomForestClassifier()))
icp = IcpClassifier(nc)
icp.fit(x[train_idx, :], y[train_idx])
icp.calibrate(x[cal_idx, :], y[cal_idx])
print(
pd.DataFrame(icp.predict_conf(x[test_idx, :]),
columns=["Label", "Confidence", "Credibility"]))
import pandas as pd from sklearn.ensemble import RandomForestClassifier from sklearn.datasets import load_iris from nonconformist.base import ClassifierAdapter from nonconformist.icp import IcpClassifier from nonconformist.nc import ClassifierNc data = load_iris() x, y = data.data, data.target for i, y_ in enumerate(np.unique(y)): y[y == y_] = i n_instances = y.size idx = np.random.permutation(n_instances) train_idx = idx[:int(n_instances / 3)] cal_idx = idx[int(n_instances / 3):2 * int(n_instances / 3)] test_idx = idx[2 * int(n_instances / 3):] nc = ClassifierNc(ClassifierAdapter(RandomForestClassifier())) icp = IcpClassifier(nc) icp.fit(x[train_idx, :], y[train_idx]) icp.calibrate(x[cal_idx, :], y[cal_idx]) print(pd.DataFrame(icp.predict_conf(x[test_idx, :]), columns=['Label', 'Confidence', 'Credibility']))
