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 _sample_values(X, y, method=None, ratio=1, verbose=False):
"""Perform any kind of sampling(over and under).
Parameters
----------
X : array, shape = [n_samples, n_features]
Data.
y : array, shape = [n_samples]
Target.
method : str, optional default: None
Over or under smapling method.
ratio: float
Unbalanced class ratio.
Returns
-------
X, y : tuple
Sampled X and y.
"""
if method == 'SMOTE':
sampler = SMOTE(ratio=ratio, verbose=verbose)
elif method == 'SMOTEENN':
ratio = ratio * 0.3
sampler = SMOTEENN(ratio=ratio, verbose=verbose)
elif method == 'random_over_sample':
sampler = OverSampler(ratio=ratio, verbose=verbose)
elif method == 'random_under_sample':
sampler = UnderSampler(verbose=verbose)
elif method == 'TomekLinks':
sampler = TomekLinks(verbose=verbose)
return sampler.fit_transform(X, y)
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 ENN'
SENN = SMOTEENN(ratio=ratio, verbose=verbose)
x, y = SENN.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)