def main_function(self):
"""
This function is the main function.
"""
# Load data and mask
data_all, label_all, self.orig_shape, self.mask_obj, self.mask_all = self._load_nii_and_gen_label(
)
# KFold Cross Validation
self.label_test_all = np.array([], dtype=np.int16)
train_index = np.array([], dtype=np.int16)
test_index = np.array([], dtype=np.int16)
self.decision = np.array([], dtype=np.int16)
self.prediction = np.array([], dtype=np.int16)
self.accuracy = np.array([], dtype=np.float16)
self.sensitivity = np.array([], dtype=np.float16)
self.specificity = np.array([], dtype=np.float16)
self.AUC = np.array([], dtype=np.float16)
self.coef = []
kf = KFold(n_splits=self.num_of_fold_outer,
shuffle=True,
random_state=0)
for i, (tr_ind, te_ind) in enumerate(kf.split(data_all)):
print(f'------{i+1}/{self.num_of_fold_outer}...------\n')
train_index = np.int16(np.append(train_index, tr_ind))
test_index = np.int16(np.append(test_index, te_ind))
feature_train = data_all[tr_ind, :]
label_train = label_all[tr_ind]
feature_test = data_all[te_ind, :]
label_test = label_all[te_ind]
self.label_test_all = np.int16(
np.append(self.label_test_all, label_test))
# Resampling training data
feature_train, label_train = self.re_sampling(
feature_train, label_train)
# data_preprocess
prep = elprep.Preprocessing(self.data_preprocess_method,
self.data_preprocess_level)
feature_train, feature_test = prep.data_preprocess(
feature_train, feature_test)
# dimension reduction using univariate feature selection
# feature_train, feature_test, mask_selected = self.dimReduction_filter(
# feature_train, label_train, feature_test, 0.05)
# Dimension reduction using PCA
if self.is_dim_reduction:
feature_train, feature_test, model_dim_reduction = self.dimReduction_PCA(
feature_train, feature_test, self.components)
print(
f'After dimension reduction, the feature number is {feature_train.shape[1]}'
)
else:
print('No dimension reduction perfromed\n')
print(f'The feature number is {feature_train.shape[1]}')
# Train: inner feature selection using RFECV
print('Training...\n')
model, weight = self.rfeCV_training(feature_train, label_train,
self.step,
self.num_fold_of_inner_rfeCV,
self.n_jobs)
if self.is_dim_reduction:
self.coef.append(model_dim_reduction.inverse_transform(weight))
else:
self.coef.append(weight)
# Testting
print('Testting...\n')
pred, dec = self.testing(model, feature_test)
self.prediction = np.append(self.prediction, np.array(pred))
self.decision = np.append(self.decision, np.array(dec))
# Evaluating classification performances
acc, sens, spec, auc = eval_performance(
label_test,
pred,
dec,
accuracy_kfold=None,
sensitivity_kfold=None,
specificity_kfold=None,
AUC_kfold=None,
verbose=1,
is_showfig=self.is_showfig_in_each_fold)
self.accuracy = np.append(self.accuracy, acc)
self.sensitivity = np.append(self.sensitivity, sens)
self.specificity = np.append(self.specificity, spec)
self.AUC = np.append(self.AUC, auc)
# Save results and fig to local path
self.save_results()
self._weight2nii(dimension_nii_data=(61, 73, 61))
self.save_fig()
print("--" * 10 + "Done!" + "--" * 10)
return self
def main_svc_rfe_cv(sel):
print('Training model and testing...\n')
# Load data
feature_550, label_550 = sel._load_data(sel.dataset_our_center_550)
feature_206, label_206 = sel._load_data(sel.dataset_206)
feature_COBRE, label_COBRE = sel._load_data(sel.data_COBRE)
feature_UCAL, label_UCAL = sel._load_data(sel.data_UCAL)
feature_all = [feature_550, feature_206, feature_COBRE, feature_UCAL]
label_all = [label_550, label_206, label_COBRE, label_UCAL]
# Leave one site CV
n_site = len(label_all)
name = ['550', '206', 'COBRE', 'UCLA']
sel.label_test_all = np.array([], dtype=np.int16)
sel.decision = np.array([], dtype=np.int16)
sel.prediction = np.array([], dtype=np.int16)
sel.accuracy = np.array([], dtype=np.float16)
sel.sensitivity = np.array([], dtype=np.float16)
sel.specificity = np.array([], dtype=np.float16)
sel.AUC = np.array([], dtype=np.float16)
sel.coef = []
for i in range(n_site):
print('-' * 40)
print(f'{i+1}/{n_site}: test dataset is {name[i]}...')
feature_train, label_train = feature_all.copy(), label_all.copy()
feature_test, label_test = feature_train.pop(i), label_train.pop(i)
sel.label_test_all = np.int16(
np.append(sel.label_test_all, label_test))
feature_train = np.concatenate(feature_train, axis=0)
label_train = np.concatenate(label_train, axis=0)
# Resampling training data
# feature_train, label_train = sel.re_sampling(feature_train, label_train)
# Normalization
prep = elprep.Preprocessing(
data_preprocess_method='StandardScaler',
data_preprocess_level='subject')
feature_train, feature_test = prep.data_preprocess(
feature_train, feature_test)
# Dimension reduction
if sel.is_dim_reduction:
feature_train, feature_test, model_dim_reduction = sel.dimReduction(
feature_train, feature_test, sel.components)
print(
f'After dimension reduction, the feature number is {feature_train.shape[1]}'
)
else:
print('No dimension reduction perfromed\n')
# Train and test
print('training and testing...\n')
model = sel.training(feature_train, label_train, sel.cv)
if sel.is_dim_reduction:
sel.coef.append(
model_dim_reduction.inverse_transform(
model.coef_)) # save coef
else:
sel.coef.append(model.coef_) # save coef
pred, dec = sel.testing(model, feature_test)
sel.prediction = np.append(sel.prediction, np.array(pred))
sel.decision = np.append(sel.decision, np.array(dec))
# Evaluating classification performances
acc, sens, spec, auc = eval_performance(label_test,
pred,
dec,
accuracy_kfold=None,
sensitivity_kfold=None,
specificity_kfold=None,
AUC_kfold=None,
verbose=1,
is_showfig=0)
sel.accuracy = np.append(sel.accuracy, acc)
sel.sensitivity = np.append(sel.sensitivity, sens)
sel.specificity = np.append(sel.specificity, spec)
sel.AUC = np.append(sel.AUC, auc)
print(f'performances = {acc, sens, spec,auc}')
return sel
def main_function(sel):
"""
The training data, validation data and test data are randomly splited
"""
print('Training model and testing...\n')
# load data
dataset_our_center_550 = np.load(sel.dataset_our_center_550)
dataset_206 = np.load(sel.dataset_206)
dataset_COBRE = np.load(sel.dataset_COBRE)
dataset_UCAL = np.load(sel.dataset_UCAL)
# Extracting features and label
features_our_center_550 = dataset_our_center_550[:, 2:]
features_206 = dataset_206[:, 2:]
features_COBRE = dataset_COBRE[:, 2:]
features_UCAL = dataset_UCAL[:, 2:]
label_our_center_550 = dataset_our_center_550[:, 1]
label_206 = dataset_206[:, 1]
label_COBRE = dataset_COBRE[:, 1]
label_UCAL = dataset_UCAL[:, 1]
# Generate training data and test data
data_all = np.concatenate(
[features_our_center_550, features_206, features_UCAL, features_COBRE], axis=0)
label_all = np.concatenate(
[label_our_center_550, label_206, label_UCAL, label_COBRE], axis=0)
# Unique ID
uid_our_center_550 = np.int32(dataset_our_center_550[:, 0])
uid_206 = np.int32(dataset_206[:, 0])
uid_all = np.concatenate([uid_our_center_550, uid_206,
np.zeros(len(label_UCAL, )) -1,
np.zeros(len(label_COBRE, )) -1], axis=0)
uid_all = np.int32(uid_all)
# KFold Cross Validation
sel.label_test_all = np.array([], dtype=np.int16)
train_index = np.array([], dtype=np.int16)
test_index = np.array([], dtype=np.int16)
sel.decision = np.array([], dtype=np.int16)
sel.prediction = np.array([], dtype=np.int16)
sel.accuracy = np.array([], dtype=np.float16)
sel.sensitivity = np.array([], dtype=np.float16)
sel.specificity = np.array([], dtype=np.float16)
sel.AUC = np.array([], dtype=np.float16)
sel.coef = []
kf = KFold(n_splits=sel.cv, shuffle=True, random_state=0)
for i, (tr_ind, te_ind) in enumerate(kf.split(data_all)):
print(f'------{i+1}/{sel.cv}...------\n')
train_index = np.int16(np.append(train_index, tr_ind))
test_index = np.int16(np.append(test_index, te_ind))
feature_train = data_all[tr_ind, :]
label_train = label_all[tr_ind]
feature_test = data_all[te_ind, :]
label_test = label_all[te_ind]
sel.label_test_all = np.int16(np.append(sel.label_test_all, label_test))
# resampling training data
# feature_train, label_train = sel.re_sampling(feature_train, label_train)
# normalization
prep = elprep.Preprocessing(data_preprocess_method='StandardScaler', data_preprocess_level='subject')
feature_train, feature_test = prep.data_preprocess(feature_train, feature_test)
# dimension reduction
if sel.is_dim_reduction:
feature_train, feature_test, model_dim_reduction = sel.dimReduction(
feature_train, feature_test, sel.components)
print(f'After dimension reduction, the feature number is {feature_train.shape[1]}')
else:
print('No dimension reduction perfromed\n')
# train
print('training and testing...\n')
# model, weight = rfeCV(feature_train, label_train, step=0.2, cv=3, n_jobs=-1, permutation=0)
model = sel.training(feature_train, label_train)
coef = model.coef_
# coef = weight
# Weight
if sel.is_dim_reduction:
sel.coef.append(model_dim_reduction.inverse_transform(coef)) # save coef
else:
sel.coef.append(coef) # save coef
# test
pred, dec = sel.testing(model, feature_test)
sel.prediction = np.append(sel.prediction, np.array(pred))
sel.decision = np.append(sel.decision, np.array(dec))
# Evaluating classification performances
acc, sens, spec, auc = eval_performance(label_test, pred, dec,
accuracy_kfold=None, sensitivity_kfold=None, specificity_kfold=None, AUC_kfold=None,
verbose=1, is_showfig=0)
sel.accuracy = np.append(sel.accuracy, acc)
sel.sensitivity = np.append(sel.sensitivity, sens)
sel.specificity = np.append(sel.specificity, spec)
sel.AUC = np.append(sel.AUC, auc)
uid_all_sorted = np.int32(uid_all[test_index])
sel.special_result = np.concatenate(
[uid_all_sorted, sel.label_test_all, sel.decision, sel.prediction], axis=0).reshape(4, -1).T
print('Done!')
return sel
def main_function(self):
"""
"""
print('Training model and testing...\n')
# load data and mask
data_all, label_all, self.orig_shape, self.mask_obj, self.mask_all = self._load_nii_and_gen_label(
)
# KFold Cross Validation
self.label_test_all = np.array([], dtype=np.int16)
train_index = np.array([], dtype=np.int16)
test_index = np.array([], dtype=np.int16)
self.decision = np.array([], dtype=np.int16)
self.prediction = np.array([], dtype=np.int16)
self.accuracy = np.array([], dtype=np.float16)
self.sensitivity = np.array([], dtype=np.float16)
self.specificity = np.array([], dtype=np.float16)
self.AUC = np.array([], dtype=np.float16)
self.coef = []
kf = KFold(n_splits=self.num_of_kfold, shuffle=True, random_state=0)
for i, (tr_ind, te_ind) in enumerate(kf.split(data_all)):
print(f'------{i+1}/{self.num_of_kfold}...------\n')
train_index = np.int16(np.append(train_index, tr_ind))
test_index = np.int16(np.append(test_index, te_ind))
feature_train = data_all[tr_ind, :]
label_train = label_all[tr_ind]
feature_test = data_all[te_ind, :]
label_test = label_all[te_ind]
self.label_test_all = np.int16(
np.append(self.label_test_all, label_test))
# Resampling training data
feature_train, label_train = self.re_sampling(
feature_train, label_train)
# data_preprocess
feature_train, feature_test = elprep.Preprocessing(
).data_preprocess(feature_train, feature_test,
self.data_preprocess_method,
self.data_preprocess_level)
# Dimension reduction using PCA
if self.is_dim_reduction:
feature_train, feature_test, model_dim_reduction = self.dimReduction_PCA(
feature_train, feature_test, self.components)
print(
f'After dimension reduction, the feature number is {feature_train.shape[1]}'
)
else:
print('No dimension reduction perfromed\n')
print(f'The feature number is {feature_train.shape[1]}')
# Feature selection
if self.is_feature_selection:
feature_train, feature_test, mask, n_features_origin = self.feature_selection_relief(
feature_train, label_train, feature_test,
self.n_features_to_select)
# Train and test
print('training and testing...\n')
model = self.training(feature_train, label_train)
# Get weight
if self.is_feature_selection:
coef = np.zeros([
n_features_origin,
])
coef[mask] = model.coef_
else:
coef = model.coef_
if self.is_dim_reduction:
self.coef.append(model_dim_reduction.inverse_transform(coef))
else:
self.coef.append(coef)
pred, dec = self.testing(model, feature_test)
self.prediction = np.append(self.prediction, np.array(pred))
self.decision = np.append(self.decision, np.array(dec))
# Evaluating classification performances
acc, sens, spec, auc = eval_performance(
label_test,
pred,
dec,
accuracy_kfold=None,
sensitivity_kfold=None,
specificity_kfold=None,
AUC_kfold=None,
verbose=1,
is_showfig=self.is_showfig_in_each_fold)
self.accuracy = np.append(self.accuracy, acc)
self.sensitivity = np.append(self.sensitivity, sens)
self.specificity = np.append(self.specificity, spec)
self.AUC = np.append(self.AUC, auc)
# Save results and fig to local path
self.save_results()
self._weight2nii(dimension_nii_data=(61, 73, 61))
self.save_fig()
print("--" * 10 + "Done!" + "--" * 10)
return self
def main_function(sel):
"""
The training data, validation data and test data are randomly splited
"""
print('training model and testing...\n')
# load data
data = np.load(sel.data )
# Extracting features and label
features_our_center_550 = data [:,2:]
label_our_center_550 = data [:,1]
# Generate training data and test data
data_all = features_our_center_550
label_all = label_our_center_550
# Unique ID
# KFold Cross Validation
sel.label_test_all = np.array([], dtype=np.int16)
train_index = np.array([], dtype=np.int16)
test_index = np.array([], dtype=np.int16)
sel.decision = np.array([], dtype=np.int16)
sel.prediction = np.array([], dtype=np.int16)
sel.accuracy = np.array([], dtype=np.float16)
sel.sensitivity = np.array([], dtype=np.float16)
sel.specificity = np.array([], dtype=np.float16)
sel.AUC = np.array([], dtype=np.float16)
sel.coef = []
kf = KFold(n_splits=sel.cv, shuffle=True, random_state=0)
for i, (tr_ind , te_ind) in enumerate(kf.split(data_all)):
print(f'------{i+1}/{sel.cv}...------\n')
train_index = np.int16(np.append(train_index, tr_ind))
test_index = np.int16(np.append(test_index, te_ind))
feature_train = data_all[tr_ind,:]
label_train = label_all[tr_ind]
feature_test = data_all[te_ind,:]
label_test = label_all[te_ind]
sel.label_test_all = np.int16(np.append(sel.label_test_all, label_test))
# resampling training data
# feature_train, label_train = sel.re_sampling(feature_train, label_train)
# normalization
prep = elprep.Preprocessing(data_preprocess_method='StandardScaler', data_preprocess_level='subject')
feature_train, feature_test = prep.data_preprocess(feature_train, feature_test)
# dimension reduction
if sel.is_dim_reduction:
feature_train,feature_test, model_dim_reduction= sel.dimReduction(feature_train, feature_test, sel.components)
print(f'After dimension reduction, the feature number is {feature_train.shape[1]}')
else:
print('No dimension reduction perfromed\n')
# train and test
print('training and testing...\n')
model = sel.training(feature_train,label_train)
weight = model.coef_
if sel.is_dim_reduction:
sel.coef.append(model_dim_reduction.inverse_transform(weight)) # save coef
else:
sel.coef.append(weight) # save coef
pred, dec = sel.testing(model,feature_test)
sel.prediction = np.append(sel.prediction, np.array(pred))
sel.decision = np.append(sel.decision, np.array(dec))
# Evaluating classification performances
acc, sens, spec, auc = eval_performance(label_test, pred, dec,
accuracy_kfold=None, sensitivity_kfold=None, specificity_kfold=None, AUC_kfold=None,
verbose=1, is_showfig=0)
sel.accuracy = np.append(sel.accuracy,acc)
sel.sensitivity = np.append(sel.sensitivity,sens)
sel.specificity = np.append(sel.specificity,spec)
sel.AUC = np.append(sel.AUC,auc)
sel.special_result = np.concatenate([sel.label_test_all, sel.decision, sel.prediction], axis=0).reshape(3, -1).T
print('Done!')
return sel