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 trace():
before = datetime.datetime.now()
result = trace_ratio.trace_ratio(data, labels, mode="index", n_selected_features=treshold)
after = datetime.datetime.now()
print("Trace ratio")
# result = result[:treshold]
print(len(result))
print("cas: " + str(after - before))
print('\n')
if len(result) < len(header):
transform_and_save(result, "Trace_ratio")
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
feature_num = trn_x.shape[1]
sort_idx = trace_ratio.trace_ratio(trn_x, trn_y, mode='index')
return sort_idx[:sel_feature_num]
def test_trace_ratio():
from sklearn.datasets import make_classification
X, y = make_classification(n_samples=200,
n_features=20,
n_informative=5,
n_redundant=5,
n_classes=2)
X = X.astype(float)
n_samples, n_features = X.shape # number of samples and number of features
num_fea = 5
#parameters = {
# "select_top_k__n_selected_features": [num_fea]
#}
assert (trace_ratio.trace_ratio(X, y, n_selected_features=5), True)
def main():
# load data
mat = scipy.io.loadmat('../data/COIL20.mat')
X = mat['X'] # data
X = X.astype(float)
y = mat['Y'] # label
y = y[:, 0]
n_samples, n_features = X.shape # number of samples and number of features
# split data into 10 folds
ss = cross_validation.KFold(n_samples, n_folds=10, shuffle=True)
# perform evaluation on classification task
num_fea = 100 # number of selected features
clf = svm.LinearSVC() # linear SVM
correct = 0
for train, test in ss:
# obtain the index of selected features
idx, feature_score, subset_score = trace_ratio.trace_ratio(
X[train], y[train], num_fea, style='fisher')
# obtain the dataset on the selected features
selected_features = X[:, idx[0:num_fea]]
# train a classification model with the selected features on the training dataset
clf.fit(selected_features[train], y[train])
# predict the class labels of test data
y_predict = clf.predict(selected_features[test])
# obtain the classification accuracy on the test data
acc = accuracy_score(y[test], y_predict)
correct = correct + acc
# output the average classification accuracy over all 10 folds
print('Accuracy:', float(correct) / 10)
def trace_ratio_FS(X, train_index, y_train):
_, k = X.shape
feature_idx, feature_score, subset_score = trace_ratio.trace_ratio(
X[train_index], y_train, k, style='fisher')
return (feature_idx, feature_score)
elif fsMethod == 'JMI':
featSelected, J_CMI, MIfy = jmi(X_dis,Y,n_selected_features=maxNumSelFeatures)
elif fsMethod == 'MRMR':
featSelected, J_CMI, MIfy = mrmr(X_dis,Y,n_selected_features=maxNumSelFeatures)
elif fsMethod == 'MIM':
featSelected, J_CMI, MIfy = mim(X_dis,Y,n_selected_features=maxNumSelFeatures)
elif fsMethod == 'MRI':
featSelected = mri(X_dis,Y,n_selected_features=maxNumSelFeatures)
elif fsMethod == 'MIFS':
featSelected, J_CMI, MIfy = mifs(X_dis,Y,n_selected_features=maxNumSelFeatures,beta=1)
elif fsMethod == 'CIFE':
featSelected, J_CMI, MIfy = cife(X_dis,Y,n_selected_features=maxNumSelFeatures)
elif fsMethod == 'CMIM':
featSelected, J_CMI, MIfy = cmim(X_dis,Y,n_selected_features=maxNumSelFeatures)
elif fsMethod == 'trace_ratio':
featSelected, feature_score, subset_score = trace_ratio(X_dis,Y,n_selected_features=maxNumSelFeatures)
else:
print('The feature selection method %s is not supported' %fsMethod)
assert(False)
time1 = time.time()
filename = "results/sel_features/selFeatures_%s_dataset_%s.csv" %(fsMethod,datName)
if fsMethod == 'VMIrm' or fsMethod == 'VMIgm' or fsMethod == 'VMIin' \
or fsMethod == 'JMIrm' or fsMethod == 'MRMRrm' or fsMethod == 'RMRMRrm':
featSelected = genfromtxt(filename, delimiter=',',dtype=int)
print(featSelected)
else:
fileSaving(filename, featSelected, 'w')
print('Features selected by %s on dataset %s:' % (fsMethod, datName))
print(featSelected)
def trace(train, test, K):
idx, _, _ = trace_ratio.trace_ratio(train[0], train[1], K, style='fisher')
return idx
