def test_CNN(x, y):
print('Condensed Nearest Neighbour')
CNN = CondensedNearestNeighbour(verbose=verbose)
cnnx, cnny = CNN.fit_transform(x, y)
print('One-Sided Selection')
OSS = OneSidedSelection(verbose=verbose)
ossx, ossy = OSS.fit_transform(x, y)
print('BalanceCascade')
BS = BalanceCascade(verbose=verbose)
bsx, bsy = BS.fit_transform(x, y)
def sampling():
verbose = False
y = np.bincount(target_train1)
print y
ratio = float(y[2]) / float(y[1])
# 'Random over-sampling'
OS = OverSampler(ratio=ratio, verbose=verbose)
osx, osy = OS.fit_transform(data_train1, target_train1)
random_methods(osx,osy)
# 'SMOTE'
smote = SMOTE(ratio=ratio, verbose=verbose, kind='regular')
smox, smoy = smote.fit_transform(data_train1, target_train1)
random_methods(smox,smoy)
# 'SMOTE bordeline 1'
bsmote1 = SMOTE(ratio=ratio, verbose=verbose, kind='borderline1')
bs1x, bs1y = bsmote1.fit_transform(data_train, target_train)
random_methods(bs1x,bs1y)
# 'SMOTE bordeline 2'
bsmote2 = SMOTE(ratio=ratio, verbose=verbose, kind='borderline2')
bs2x, bs2y = bsmote2.fit_transform(data_train1, target_train1)
random_methods(bs2x,bs2y)
# 'SMOTE SVM'
svm_args={'class_weight' : 'auto'}
svmsmote = SMOTE(ratio=ratio, verbose=verbose, kind='svm', **svm_args)
svsx, svsy = svmsmote.fit_transform(data_train1, target_train1)
random_methods(svsx,svsy)
# 'SMOTE Tomek links'
STK = SMOTETomek(ratio=ratio, verbose=verbose)
stkx, stky = STK.fit_transform(data_train1, target_train1)
random_methods(stkx,stky)
# 'SMOTE ENN'
SENN = SMOTEENN(ratio=ratio, verbose=verbose)
ennx, enny = SENN.fit_transform(data_train1, target_train1)
random_methods(ennx,enny)
# 'EasyEnsemble'
EE = EasyEnsemble(verbose=verbose)
eex, eey = EE.fit_transform(data_train1, target_train1)
random_methods(eex,eey)
# 'BalanceCascade'
BS = BalanceCascade(verbose=verbose)
bsx, bsy = BS.fit_transform(data_train1, target_train1)
random_methods(bsx,bsy)
def balance_cascade(sel):
BS = BalanceCascade(verbose=self.verbose)
bsx, bsy = BS.fit_transform(self.x, self.y)
return bsx, bsy
bs2x, bs2y = bsmote2.fit_transform(x, y)
# 'SMOTE SVM'
svm_args={'class_weight' : 'auto'}
svmsmote = SMOTE(ratio=ratio, verbose=verbose, kind='svm', **svm_args)
svsx, svsy = svmsmote.fit_transform(x, y)
# 'SMOTE Tomek links'
STK = SMOTETomek(ratio=ratio, verbose=verbose)
stkx, stky = STK.fit_transform(x, y)
# 'SMOTE ENN'
SENN = SMOTEENN(ratio=ratio, verbose=verbose)
ennx, enny = SENN.fit_transform(x, y)
# 'EasyEnsemble'
EE = EasyEnsemble(verbose=verbose)
eex, eey = EE.fit_transform(x, y)
# 'BalanceCascade'
BS = BalanceCascade(verbose=verbose)
bsx, bsy = BS.fit_transform(x, y)
# Apply PCA to be able to visualise the results
osx_vis = pca.transform(osx)
smox_vis = pca.transform(smox)
bs1x_vis = pca.transform(bs1x)
bs2x_vis = pca.transform(bs2x)
svsx_vis = pca.transform(svsx)
stkx_vis = pca.transform(stkx)
ennx_vis = pca.transform(ennx)
# Project each subset of the ensemble
eex_vis = []
for e in eex:
eex_vis.append(pca.transform(e))