def imblearn_fit_var2d(self,
X,
X_3d,
y,
variables,
variables_3d,
random_state=42):
from Fuzzy_clustering.ver_tf2.Adasyn_var2d import ADASYN
flag = False
Std = 0.01
while (flag == False and Std <= 1):
try:
std = np.maximum(Std * np.std(y), 0.2)
yy = np.digitize(y,
np.arange(np.min(y), np.max(y), std),
right=True)
bins = np.arange(np.min(y), np.max(y), std)
bins = bins[(np.bincount(yy.ravel()) >= 2)[:-1]]
yy = np.digitize(y, bins, right=True)
# if Std==0.01 and np.max(yy)!=0:
# strategy = {cl:int(100*X.shape[0]/np.max(yy)) for cl in np.unique(yy)}
# else:
strategy = "auto"
if np.unique(yy).shape[0] == 1:
X2 = X
X_3d2 = X_3d
yy2 = y
return X2, X_3d2, yy2
if np.any(np.bincount(yy.ravel()) < 2):
for cl in np.where(np.bincount(yy.ravel()) < 2)[0]:
X = X[np.where(yy != cl)[0]]
X_3d = X_3d[np.where(yy != cl)[0]]
y = y[np.where(yy != cl)[0]]
yy = yy[np.where(yy != cl)[0]]
sm = ADASYN(sampling_strategy=strategy,
random_state=random_state,
variables=variables,
variables_3d=variables_3d,
n_neighbors=np.min(np.bincount(yy.ravel()) - 1),
n_jobs=self.n_jobs)
X2, X_3d2, yy2 = sm.fit_resample(X, X_3d, yy.ravel(),
y.ravel())
flag = True
except:
Std *= 10
if flag == True:
return X2, X_3d2, yy2
else:
return X, X_3d, y
def imblearn_fit_obsolete(self, X, y, random_state=42):
if self.model_type == {'pv', 'wind'}:
from Fuzzy_clustering.ver_tf2.imblearn.over_sampling import BorderlineSMOTE, SVMSMOTE, SMOTE, ADASYN
else:
from imblearn.over_sampling import BorderlineSMOTE, SVMSMOTE, SMOTE, ADASYN
flag = False
Std = 0.01
while (flag == False and Std <= 1):
try:
std = np.maximum(Std * np.std(y), 0.2)
yy = np.digitize(y,
np.arange(np.min(y), np.max(y), std),
right=True)
bins = np.arange(np.min(y), np.max(y), std)
bins = bins[(np.bincount(yy.ravel()) >= 2)[:-1]]
yy = np.digitize(y, bins, right=True)
# if Std==0.01 and np.max(yy)!=0:
# strategy = {cl:int(100*X.shape[0]/np.max(yy)) for cl in np.unique(yy)}
# else:
strategy = "auto"
if np.unique(yy).shape[0] == 1:
X2 = X
yy2 = y
return X2, yy2
if np.any(np.bincount(yy.ravel()) < 2):
for cl in np.where(np.bincount(yy.ravel()) < 2)[0]:
X = X[np.where(yy != cl)[0]]
y = y[np.where(yy != cl)[0]]
yy = yy[np.where(yy != cl)[0]]
if self.method == 'ADASYN':
sm = ADASYN(
sampling_strategy=strategy,
random_state=random_state,
n_neighbors=np.min(np.bincount(yy.ravel()) - 1),
n_jobs=self.n_jobs)
elif self.method == 'SVMSMOTE':
sm = SVMSMOTE(
sampling_strategy=strategy,
random_state=random_state,
k_neighbors=np.min(np.bincount(yy.ravel()) - 1),
m_neighbors=2 * np.min(np.bincount(yy.ravel()) - 1),
n_jobs=self.n_jobs)
else:
sm = BorderlineSMOTE(
sampling_strategy=strategy,
random_state=random_state,
k_neighbors=np.min(np.bincount(yy.ravel()) - 1),
m_neighbors=2 * np.min(np.bincount(yy.ravel()) - 1),
n_jobs=self.n_jobs)
try:
X2, yy2 = sm.fit_resample(X, yy.ravel())
except:
sm = SMOTE(sampling_strategy=strategy,
random_state=random_state,
k_neighbors=np.min(np.bincount(yy.ravel()) - 1),
n_jobs=self.n_jobs)
X2, yy2 = sm.fit_resample(X, yy.ravel())
X2 = X2[X.shape[0] + 1:]
X2[np.where(X2 < 0)] = 0
yy2 = yy2[X.shape[0] + 1:]
yy2 = bins[yy2 - 1]
flag = True
except:
Std *= 10
if flag == True:
return X2, yy2
else:
raise RuntimeError('Cannot make resampling ')