def test_rest(x, y):
print('Random under-sampling')
US = UnderSampler(verbose=verbose)
usx, usy = US.fit_transform(x, y)
print('Tomek links')
TL = TomekLinks(verbose=verbose)
tlx, tly = TL.fit_transform(x, y)
print('Clustering centroids')
CC = ClusterCentroids(verbose=verbose)
ccx, ccy = CC.fit_transform(x, y)
print('NearMiss-1')
NM1 = NearMiss(version=1, verbose=verbose)
nm1x, nm1y = NM1.fit_transform(x, y)
print('NearMiss-2')
NM2 = NearMiss(version=2, verbose=verbose)
nm2x, nm2y = NM2.fit_transform(x, y)
print('NearMiss-3')
NM3 = NearMiss(version=3, verbose=verbose)
nm3x, nm3y = NM3.fit_transform(x, y)
print('Neighboorhood Cleaning Rule')
NCR = NeighbourhoodCleaningRule(verbose=verbose)
ncrx, ncry = NCR.fit_transform(x, y)
print('Random over-sampling')
OS = OverSampler(verbose=verbose)
ox, oy = OS.fit_transform(x, y)
print('SMOTE Tomek links')
STK = SMOTETomek(verbose=verbose)
stkx, stky = STK.fit_transform(x, y)
print('SMOTE ENN')
SENN = SMOTEENN(verbose=verbose)
sennx, senny = SENN.fit_transform(x, y)
print('EasyEnsemble')
EE = EasyEnsemble(verbose=verbose)
eex, eey = EE.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 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 smote_tomek_links(self):
STK = SMOTETomek(ratio=self._ratio, verbose=self.verbose)
stkx, stky = STK.fit_transform(self.x, self.y)
return stkx, stky
usecols=[3, 4, 5, 6, 7])
y = pd.read_csv(tain_path,
header=None,
index_col=False,
names=colnames,
skiprows=[0],
usecols=[8])
y = y['violation'].values
# X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.333, random_state=0)
main_x = X.values
main_y = y
verbose = False
ratio = float(np.count_nonzero(y == 1)) / float(np.count_nonzero(y == 0))
# 'SMOTE Tomek links'
STK = SMOTETomek(ratio=ratio, verbose=verbose)
x, y = STK.fit_transform(main_x, main_y)
ratio = float(np.count_nonzero(y == 1)) / float(np.count_nonzero(y == 0))
X_train, X_test, y_train, y_test = train_test_split(x,
y,
test_size=.333,
random_state=0)
from sklearn.ensemble import RandomForestClassifier
from sklearn.cross_validation import cross_val_score
clf = RandomForestClassifier(n_estimators=10)
scores = cross_val_score(clf, X_test, y_test)
y_pred = clf.fit(X_train, y_train).predict(X_test)
osx, osy = OS.fit_transform(x, y)
# 'SMOTE'
smote = SMOTE(ratio=ratio, verbose=verbose, kind='regular')
smox, smoy = smote.fit_transform(x, y)
# 'SMOTE bordeline 1'
bsmote1 = SMOTE(ratio=ratio, verbose=verbose, kind='borderline1')
bs1x, bs1y = bsmote1.fit_transform(x, y)
# 'SMOTE bordeline 2'
bsmote2 = SMOTE(ratio=ratio, verbose=verbose, kind='borderline2')
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)
X = df.ix[:, attributes].values
y = df['true_label'].values
print(type(X))
print(type(y))
print("ratio before")
num_one = np.count_nonzero(y == 1)
num_zero = np.count_nonzero(y == 0)
ratio = float(num_zero) / float(num_one)
print(ratio)
#X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, train_size=0.8)
smote = SMOTETomek(ratio=90, verbose=False)
smox, smoy = smote.fit_transform(X, y)
print("ratio after")
num_one = np.count_nonzero(smoy == 1)
num_zero = np.count_nonzero(smoy == 0)
ratio = float(num_zero) / float(num_one)
print(ratio)
#clf = DecisionTreeClassifier()
#clf = SVC()
#clf = MultinomialNB()
clf = KNeighborsClassifier(n_neighbors=1)
#clf.fit(smox, smoy)
#predicted = clf.predict(X_test)
