def __kfold_prob_tp_fp(self, X, y, n_folds=2):
# if isinstance(X, csr_matrix) and isinstance(y, np.ndarray):
# X=X.toarray()
# elif isinstance(X, np.ndarray) and isinstance(y, np.ndarray):
# if len(y.shape)==1:
# y=MultiLabelBinarizer(classes=self.classes).fit_transform([[y_p] for y_p in y])
# elif len(y.shape)==2:
# pass
if isinstance(y, list):
y = np.asarray(y)
try:
with open(
self.prefix + self.dir_name + '/' + str(n_folds) +
'FCV_prob.pickle', 'rb') as f:
[tp_av, fp_av] = pickle.load(f)
except:
kf = KFold(y.shape[0], n_folds=n_folds)
TP_avr = []
FP_avr = []
for train_index, test_index in kf:
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]
model = self.model
model = model.fit(X_train, y_train)
y_predict = model.predict(X_test)
y_prob_predict = model.predict_proba(X_test)
TP = []
FP = []
if len(y.shape) == 1:
y_predict = MultiLabelBinarizer(
classes=self.classes).fit_transform(
[[y_p] for y_p in y_predict])
elif len(y.shape) == 2:
pass
for class_ind, class_prob in zip(y_predict.transpose(),
y_prob_predict.transpose()):
TP_class = []
FP_class = []
for ind, prob in zip(class_ind, class_prob):
if ind == 1: TP_class.append(prob)
elif ind == 0: FP_class.append(prob)
TP.append(np.sum(TP_class) / len(class_ind))
FP.append(np.sum(FP_class) / len(class_ind))
TP_avr.append(TP)
FP_avr.append(FP)
tp_av, fp_av = np.average(TP_avr, axis=0), np.average(FP_avr,
axis=0)
with open(
self.prefix + self.dir_name + '/' + str(n_folds) +
'FCV_prob.pickle', 'wb') as f:
pickle.dump([tp_av, fp_av], f)
f.close()
#print('tp, fp by prob', tp_av, fp_av)
return [tp_av, fp_av]
def __kfold_prob_tp_fp(self, X, y, n_folds=2):
# if isinstance(X, csr_matrix) and isinstance(y, np.ndarray):
# X=X.toarray()
# elif isinstance(X, np.ndarray) and isinstance(y, np.ndarray):
# if len(y.shape)==1:
# y=MultiLabelBinarizer(classes=self.classes).fit_transform([[y_p] for y_p in y])
# elif len(y.shape)==2:
# pass
if isinstance(y, list):
y = np.asarray(y)
try:
with open(self.prefix + self.dir_name + "/" + str(n_folds) + "FCV_prob.pickle", "rb") as f:
[tp_av, fp_av] = pickle.load(f)
except:
kf = KFold(y.shape[0], n_folds=n_folds)
TP_avr = []
FP_avr = []
for train_index, test_index in kf:
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]
model = self.model
model = model.fit(X_train, y_train)
y_predict = model.predict(X_test)
y_prob_predict = model.predict_proba(X_test)
TP = []
FP = []
if len(y.shape) == 1:
y_predict = MultiLabelBinarizer(classes=self.classes).fit_transform([[y_p] for y_p in y_predict])
elif len(y.shape) == 2:
pass
for class_ind, class_prob in zip(y_predict.transpose(), y_prob_predict.transpose()):
TP_class = []
FP_class = []
for ind, prob in zip(class_ind, class_prob):
if ind == 1:
TP_class.append(prob)
elif ind == 0:
FP_class.append(prob)
TP.append(np.sum(TP_class) / len(class_ind))
FP.append(np.sum(FP_class) / len(class_ind))
TP_avr.append(TP)
FP_avr.append(FP)
tp_av, fp_av = np.average(TP_avr, axis=0), np.average(FP_avr, axis=0)
with open(self.prefix + self.dir_name + "/" + str(n_folds) + "FCV_prob.pickle", "wb") as f:
pickle.dump([tp_av, fp_av], f)
f.close()
# print('tp, fp by prob', tp_av, fp_av)
return [tp_av, fp_av]
