def select_feature(trainfilename, testfilename):
def returnTtest(X, y):
return tvalue
X_train, y_train, X_test, y_test = load_svmlight_files(
(trainfilename, testfilename), multilabel=True)
featureNum = X_train.get_shape()[1]
tvalue = ttest(X_train, y_train)
step = featureNum / 20
for i in range(1, 21):
selectNum = step * i
print "selecting", selectNum, "features"
selector = SelectKBest(returnTtest, k=selectNum)
X_train_new = selector.fit_transform(X_train, y_train)
X_test_new = selector.transform(X_test)
dump_svmlight_file(X_train_new,
y_train,
trainfilename + '_' + str(selectNum),
zero_based=False)
dump_svmlight_file(X_test_new,
y_test,
testfilename + '_' + str(selectNum),
zero_based=False)
def select_feature(trainfilename, testfilename):
def returnCHI(X, y):
return chivalue
X_train, y_train, X_test, y_test = load_svmlight_files((trainfilename, testfilename), multilabel=True)
featureNum = X_train.get_shape()[1]
chivalue = chi2(X_train, y_train)
step = featureNum / 20;
for i in range(1, 21):
selectNum = step * i
print "selecting", selectNum, "features"
selector = SelectKBest(chi2, k=selectNum)
X_train_new = selector.fit_transform(X_train, y_train)
X_test_new= selector.transform(X_test)
dump_svmlight_file(X_train_new, y_train, trainfilename + '_' + str(selectNum), zero_based = False)
dump_svmlight_file(X_test_new, y_test, testfilename + '_' + str(selectNum), zero_based = False)
def select_feature_multilabel(trainfilename, testfilename):
def returnIG(X, y):
return randval, p
X_train, y_train, X_test, y_test = load_svmlight_files((trainfilename, testfilename), multilabel=True)
featurenum = X_train.shape[1]
randval = randomValues(X_train, y_train)
p = np.ones((featurenum,1), int)
p.reshape(featurenum,1)
featureNum = X_train.get_shape()[1]
step = featureNum / 20;
for i in range(1, 21):
selectNum = step * i
print "selecting", selectNum, "features"
selector = SelectKBest(returnIG, k=selectNum)
X_train_new = selector.fit_transform(X_train, y_train)
X_test_new = selector.transform(X_test)
dump_svmlight_file(X_train_new, y_train, trainfilename + '_' + str(selectNum), zero_based = False)
dump_svmlight_file(X_test_new, y_test, testfilename + '_' + str(selectNum), zero_based = False)
