def get_cascaded_sel_idx(high_th_year,
low_th_year,
feature_list,
set_feature,
sel_feature_num,
div_ratio=4):
high_risk_th = high_th_year * 365
low_risk_th = low_th_year * 365
high_risk_group, low_risk_group = helper.get_risk_group(
x, c, s, high_risk_th, low_risk_th)
#trn_x, trn_y, val_x, val_y = get_train_val(high_risk_group, low_risk_group)
trn_x, trn_y = helper.get_train(
high_risk_group,
low_risk_group,
is_categori_y=False,
seed=self.random_seed) #without validation set
if len(set_feature):
trn_x = trn_x[:, set_feature]
#val_x = val_x[:,set_feature]
feature_num = trn_x.shape[1]
if sel_feature_num == 0:
sel_gene_num = int(
max(sel_feature_num, feature_num / div_ratio))
else:
sel_gene_num = sel_feature_num
clf = RandomForestClassifier()
clf.fit(trn_x, trn_y)
f_scores = clf.feature_importances_
coef_idx_sort = np.argsort(f_scores)[::-1]
sel_idx = coef_idx_sort[:sel_gene_num]
return sel_idx
def get_cascaded_sel_idx(high_th_year,
low_th_year,
feature_list,
set_feature,
sel_feature_num,
div_ratio=4):
high_risk_th = high_th_year * 365
low_risk_th = low_th_year * 365
high_risk_group, low_risk_group = helper.get_risk_group(
x, c, s, high_risk_th, low_risk_th)
#trn_x, trn_y, val_x, val_y = get_train_val(high_risk_group, low_risk_group)
trn_x, trn_y = helper.get_train(
high_risk_group,
low_risk_group,
is_categori_y=False,
seed=self.random_seed) #without validation set
if len(set_feature):
trn_x = trn_x[:, set_feature]
#val_x = val_x[:,set_feature]
feature_num = trn_x.shape[1]
if sel_feature_num == 0:
sel_gene_num = int(
max(sel_feature_num, feature_num / div_ratio))
else:
sel_gene_num = sel_feature_num
sort_idx = trace_ratio.trace_ratio(trn_x, trn_y, mode='index')
sel_idx = sort_idx[:sel_gene_num]
return sel_idx
def get_sel_idx(high_th_year, low_th_year, feature_list, sel_feature_num):
high_risk_th = high_th_year*365
low_risk_th = low_th_year*365
high_risk_group, low_risk_group = helper.get_risk_group(x,c,s,high_risk_th,low_risk_th)
trn_x, trn_y = helper.get_train(high_risk_group, low_risk_group, is_categori_y=False, seed=self.random_seed)#without validation set
print('Into RFS fs...')
sort_idx = RFS.rfs(trn_x, trn_y, mode='index', verbose=True)
print('RFS fs done...')
return sort_idx[:sel_feature_num]
def get_sel_idx(high_th_year, low_th_year, feature_list, sel_feature_num):
high_risk_th = high_th_year*365
low_risk_th = low_th_year*365
high_risk_group, low_risk_group = helper.get_risk_group(x,c,s,high_risk_th,low_risk_th)
trn_x, trn_y, val_x, val_y = helper.get_train_val(high_risk_group, low_risk_group, is_categori_y=False, seed=self.random_seed)#with validation set
clf = xgb.XGBClassifier(seed=1, objective='binary:logistic')
clf.fit(trn_x, trn_y, eval_set=[(val_x, val_y)], verbose=False, eval_metric='auc', early_stopping_rounds=200)
f_scores = clf.feature_importances_
coef_idx_sort = np.argsort(f_scores)[::-1]
return coef_idx_sort[:sel_feature_num]
def get_sel_idx(high_th_year, low_th_year, feature_list,
sel_feature_num):
high_risk_th = high_th_year * 365
low_risk_th = low_th_year * 365
high_risk_group, low_risk_group = helper.get_risk_group(
x, c, s, high_risk_th, low_risk_th)
trn_x, trn_y = helper.get_train(
high_risk_group,
low_risk_group,
is_categori_y=False,
seed=self.random_seed) #without validation set
sort_idx = reliefF.reliefF(trn_x, trn_y, mode='index')
return sort_idx[:sel_feature_num]
def get_sel_idx(high_th_year, low_th_year, feature_list, sel_feature_num):
high_risk_th = high_th_year*365
low_risk_th = low_th_year*365
high_risk_group, low_risk_group = helper.get_risk_group(x,c,s,high_risk_th,low_risk_th)
trn_x, trn_y = helper.get_train(high_risk_group, low_risk_group, is_categori_y=False, seed=self.random_seed)#without validation set
svm_clf = svm.SVC(kernel='linear')
svm_clf.fit(trn_x, trn_y)
svm_coef = svm_clf.coef_
svm_coef = np.abs(np.mean(svm_coef, axis=0))
svm_coef_idx_sort = np.argsort(svm_coef)[::-1]
return svm_coef_idx_sort[:sel_feature_num]
def get_wx_sel_idx(high_th_year,
low_th_year,
feature_list,
set_feature,
sel_feature_num,
sel_op,
div_ratio=4):
high_risk_th = high_th_year * 365
low_risk_th = low_th_year * 365
high_risk_group, low_risk_group = helper.get_risk_group(
x, c, s, high_risk_th, low_risk_th)
trn_x, trn_y, val_x, val_y = helper.get_train_val(
high_risk_group,
low_risk_group,
is_categori_y=True,
seed=self.random_seed)
if len(set_feature):
trn_x = trn_x[:, set_feature]
val_x = val_x[:, set_feature]
feature_num = trn_x.shape[1]
if sel_feature_num == 0:
hp = WxHyperParameter(epochs=50,
learning_ratio=0.01,
batch_size=int(len(trn_x) / 4),
verbose=True)
sel_gene_num = int(
max(sel_feature_num, feature_num / div_ratio))
else:
hp = WxHyperParameter(epochs=50,
learning_ratio=0.001,
batch_size=int(len(trn_x) / 4),
verbose=True)
sel_gene_num = sel_feature_num
sel_idx, sel_genes, sel_weight, test_auc = DoFeatureSelectionWX(
trn_x,
trn_y,
val_x,
val_y,
val_x,
val_y,
feature_list,
hp,
n_sel=sel_gene_num,
sel_option=sel_op)
return sel_idx
def get_sel_idx(high_th_year, low_th_year, feature_list,
sel_feature_num):
high_risk_th = high_th_year * 365
low_risk_th = low_th_year * 365
high_risk_group, low_risk_group = helper.get_risk_group(
x, c, s, high_risk_th, low_risk_th)
trn_x, trn_y = helper.get_train(
high_risk_group,
low_risk_group,
is_categori_y=False,
seed=self.random_seed) #without validation set
clf = RandomForestClassifier()
clf.fit(trn_x, trn_y)
f_scores = clf.feature_importances_
coef_idx_sort = np.argsort(f_scores)[::-1]
return coef_idx_sort[:sel_feature_num]
def get_sel_idx(high_th_year, low_th_year, feature_list,
sel_feature_num):
high_risk_th = high_th_year * 365
low_risk_th = low_th_year * 365
high_risk_group, low_risk_group = helper.get_risk_group(
x, c, s, high_risk_th, low_risk_th)
trn_x, trn_y = helper.get_train(
high_risk_group,
low_risk_group,
is_categori_y=False,
seed=self.random_seed) #without validation set
W, _, _ = ll_l21.proximal_gradient_descent(trn_x,
trn_y,
z=0.01,
mode='raw')
sort_idx = feature_ranking(W)
return sort_idx[:sel_feature_num]
