z[ii] = initial_sample[ii]
data[k, :] = z
file = 'High_IR_Data/shuttle-2_vs_5.dat'
name = file.split('.')[0]
print(name)
RD.Initialize_Data(file)
print('Number of Positive: ', RD.Num_positive)
print('Number of Negative: ', RD.Num_negative)
nominal_feature = []
data = RD.get_feature()
num_samples = data.shape[0]
num_features = data.shape[1]
num_bins = 100
bounds = np.zeros((num_bins + 1, num_features))
for i in range(num_features):
if i not in nominal_feature:
bounds[:, i] = np.histogram(data[:, i], bins=num_bins)[1]
nf = RD.get_negative_feature()
transfer(nf, bounds, num_features, nominal_feature)
pf = RD.get_positive_feature()
transfer(pf, bounds, num_features, nominal_feature)
bayes = BayesianNetwork.from_samples(nf, algorithm='chow-liu')
pt = bayes.log_probability(nf).sum()
Num_Cross_Folders = 5
G_Mean = np.linspace(0, 0, Num_Cross_Folders)
Sensitivity = np.linspace(0, 0, Num_Cross_Folders)
Specificity = np.linspace(0, 0, Num_Cross_Folders)
G_Mean_GAN = np.linspace(0, 0, Num_Cross_Folders)
Sensitivity_GAN = np.linspace(0, 0, Num_Cross_Folders)
Specificity_GAN = np.linspace(0, 0, Num_Cross_Folders)
for j in range(Num_Cross_Folders):
# dir_train = "glass1-5-fold/glass1-5-" + str(j+1) + "tra.dat"
# dir_test = "glass1-5-fold/glass1-5-" + str(j+1) + "tst.dat"
dir_train = "page-blocks0-5-fold/page-blocks0-5-" + str(j + 1) + "tra.dat"
dir_test = "page-blocks0-5-fold/page-blocks0-5-" + str(j + 1) + "tst.dat"
RD.Initialize_Data(dir_train)
Train_Feature = RD.get_feature()
Train_Label = RD.get_label()
Train_Label = Train_Label.ravel()
print(Train_Feature.shape)
print(Train_Label.size)
# clf = svm.SVC(C=1, kernel='rbf', gamma= 0.2)
# clf.fit(Train_Feature, Train_Label)
Feature_samples = RD.get_positive_feature()
G = GAN_Build(Feature_samples)
Sudo_Samples = Over_Sampling(G, RD.Num_negative - RD.Num_positive, 6)
print(Sudo_Samples[0])
print(Sudo_Samples[-1])
Train_Feature = np.concatenate((Train_Feature, Sudo_Samples))
print(Train_Feature[0])
