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 apply_sampling(X_data, Y_data, sampling, n_states, maxlen):
ratio = float(np.count_nonzero(Y_data == 1)) / \
float(np.count_nonzero(Y_data == 0))
X_data = np.reshape(X_data, (len(X_data), n_states * maxlen))
# 'Random over-sampling'
if sampling == 'OverSampler':
OS = OverSampler(ratio=ratio, verbose=True)
# 'Random under-sampling'
elif sampling == 'UnderSampler':
OS = UnderSampler(verbose=True)
# 'Tomek under-sampling'
elif sampling == 'TomekLinks':
OS = TomekLinks(verbose=True)
# Oversampling
elif sampling == 'SMOTE':
OS = SMOTE(ratio=1, verbose=True, kind='regular')
# Oversampling - Undersampling
elif sampling == 'SMOTETomek':
OS = SMOTETomek(ratio=ratio, verbose=True)
# Undersampling
elif sampling == 'OneSidedSelection':
OS = OneSidedSelection(verbose=True)
# Undersampling
elif sampling == 'CondensedNearestNeighbour':
OS = CondensedNearestNeighbour(verbose=True)
# Undersampling
elif sampling == 'NearMiss':
OS = NearMiss(version=1, verbose=True)
# Undersampling
elif sampling == 'NeighbourhoodCleaningRule':
OS = NeighbourhoodCleaningRule(verbose=True)
# ERROR: WRONG SAMPLER, TERMINATE
else:
print('Wrong sampling variable you have set... Exiting...')
sys.exit()
# print('shape ' + str(X.shape))
X_data, Y_data = OS.fit_transform(X_data, Y_data)
return X_data, Y_data
def condensed_nn(self):
CNN = CondensedNearestNeighbour(size_ngh=51, n_seeds_S=51, verbose=self.verbose)
cnnx, cnny = CNN.fit_transform(self.x, self.y)
print "Condensed NN Transformed"
return cnnx, cnny
TL = TomekLinks(verbose=verbose) tlx, tly = TL.fit_transform(x, y) # 'Clustering centroids' CC = ClusterCentroids(verbose=verbose) ccx, ccy = CC.fit_transform(x, y) # 'NearMiss-1' NM1 = NearMiss(version=1, verbose=verbose) nm1x, nm1y = NM1.fit_transform(x, y) # 'NearMiss-2' NM2 = NearMiss(version=2, verbose=verbose) nm2x, nm2y = NM2.fit_transform(x, y) # 'NearMiss-3' NM3 = NearMiss(version=3, verbose=verbose) nm3x, nm3y = NM3.fit_transform(x, y) # 'Condensed Nearest Neighbour' CNN = CondensedNearestNeighbour(size_ngh=51, n_seeds_S=51, verbose=verbose) cnnx, cnny = CNN.fit_transform(x, y) # 'One-Sided Selection' OSS = OneSidedSelection(size_ngh=51, n_seeds_S=51, verbose=verbose) ossx, ossy = OSS.fit_transform(x, y) # 'Neighboorhood Cleaning Rule' NCR = NeighbourhoodCleaningRule(size_ngh=51, verbose=verbose) ncrx, ncry = NCR.fit_transform(x, y) # Apply PCA to be able to visualise the results usx_vis = pca.transform(usx) tlx_vis = pca.transform(tlx) ccx_vis = pca.transform(ccx) nm1x_vis = pca.transform(nm1x) nm2x_vis = pca.transform(nm2x) nm3x_vis = pca.transform(nm3x)
