def data_objects_fusion(obj1, obj2):
# Initialize data with parameters form top
obj = Data(splits=config['SPLITS'], holdout=config['HOLDOUT'])
# simply merge all
obj.Xs_train = merge_nparr(obj1.Xs_train, obj2.Xs_train)
obj.Xs_val = merge_nparr(obj1.Xs_val, obj2.Xs_val)
obj.ys_train = merge_nparr(obj1.ys_train, obj2.ys_train)
obj.ys_val = merge_nparr(obj1.ys_val, obj2.ys_val)
if config['HOLDOUT']:
obj.X_train_holdout = np.concatenate(
(obj1.X_train_holdout, obj2.X_train_holdout), axis=None)
obj.X_test_holdout = np.concatenate(
(obj1.X_test_holdout, obj2.X_test_holdout), axis=None)
obj.y_train_holdout = np.concatenate(
(obj1.y_train_holdout, obj2.y_train_holdout), axis=None)
obj.y_test_holdout = np.concatenate(
(obj1.y_test_holdout, obj2.y_test_holdout), axis=None)
return obj
def kfold_holdout(X, y, groups, splits, holdout):
group_kfold = GroupKFold(n_splits=splits)
group_kfold.get_n_splits(X, y, groups)
d_obj = Data(splits=splits, holdout=holdout)
for train_index, test_index in group_kfold.split(X, y, groups):
# inplace shuffeling
shuffle(train_index)
shuffle(test_index)
# generate folds
if holdout == True:
if d_obj.X_test_holdout is None:
# first folds are for test only
d_obj.X_train_holdout, d_obj.X_test_holdout = X[
train_index], X[test_index]
d_obj.y_train_holdout, d_obj.y_test_holdout = y[
train_index], y[test_index]
store_test_index = test_index
else:
# holdout idx if re-occuring in train
train_index = [
x for x in train_index if x not in store_test_index
]
d_obj.Xs_train.append(X[train_index])
d_obj.Xs_val.append(X[test_index])
d_obj.ys_train.append(y[train_index])
d_obj.ys_val.append(y[test_index])
elif holdout == False:
d_obj.Xs_train.append(X[train_index])
d_obj.Xs_val.append(X[test_index])
d_obj.ys_train.append(y[train_index])
d_obj.ys_val.append(y[test_index])
else:
print("Something is wrong here")
exit()
return d_obj
