def ll_l21_FS(X_train, y, train_index):
Y = construct_label_matrix_pan(y)
Y_train = Y[train_index]
Weight, obj, value_gamma = ll_l21.proximal_gradient_descent(X_train,
Y[train_index],
0.1,
verbose=False)
#print("weight ",Weight)
idx = feature_ranking(Weight)
return (idx, Weight)
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]
Y = construct_label_matrix_pan(y)
n_samples, n_features = X.shape # number of samples and number of features
X = X[:200]
Y = Y[:200]
# split data into 10 folds
# ss = cross_validation.KFold(n_samples, n_folds=10, shuffle=True)
ss = KFold(n_splits=10)
# perform evaluation on classification task
num_fea = 100 # number of selected features
clf = svm.LinearSVC() # linear SVM
correct = 0
for train, test in ss.split(X):
# obtain the feature weight matrix
Weight, obj, value_gamma = ll_l21.proximal_gradient_descent(
X[train], Y[train], 0.1, verbose=False)
# sort the feature scores in an ascending order according to the feature scores
idx = feature_ranking(Weight)
# 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 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]
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]
Y = construct_label_matrix_pan(y)
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 feature weight matrix
Weight, obj, value_gamma = ll_l21.proximal_gradient_descent(X[train], Y[train], 0.1, verbose=False)
# sort the feature scores in an ascending order according to the feature scores
idx = feature_ranking(Weight)
# 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 fit(self, X, y):
idx = []
if self.tp == 'ITB':
if self.name == 'MRMR':
idx = MRMR.mrmr(X,
y,
n_selected_features=self.params['num_feats'])
elif self.tp == 'filter':
if self.name == 'Relief':
score = reliefF.reliefF(X, y, k=self.params['k'])
idx = reliefF.feature_ranking(score)
if self.name == 'Fisher':
# obtain the score of each feature on the training set
score = fisher_score.fisher_score(X, y)
# rank features in descending order according to score
idx = fisher_score.feature_ranking(score)
if self.name == 'MI':
idx = np.argsort(
mutual_info_classif(
X, y, n_neighbors=self.params['n_neighbors']))[::-1]
elif self.tp == 'wrapper':
model_fit = self.model.fit(X, y)
model = SelectFromModel(model_fit, prefit=True)
idx = model.get_support(indices=True)
elif self.tp == 'SLB':
# one-hot-encode on target
y = construct_label_matrix(y)
if self.name == 'SMBA':
scba = fs.SCBA(data=X,
alpha=self.params['alpha'],
norm_type=self.params['norm_type'],
verbose=self.params['verbose'],
thr=self.params['thr'],
max_iter=self.params['max_iter'],
affine=self.params['affine'],
normalize=self.params['normalize'],
step=self.params['step'],
PCA=self.params['PCA'],
GPU=self.params['GPU'],
device=self.params['device'])
nrmInd, sInd, repInd, _ = scba.admm()
if self.params['type_indices'] == 'nrmInd':
idx = nrmInd
elif self.params['type_indices'] == 'repInd':
idx = repInd
else:
idx = sInd
if self.name == 'RFS':
W = RFS.rfs(X, y, gamma=self.params['gamma'])
idx = feature_ranking(W)
if self.name == 'll_l21':
# obtain the feature weight matrix
W, _, _ = ll_l21.proximal_gradient_descent(X,
y,
z=self.params['z'],
verbose=False)
# sort the feature scores in an ascending order according to the feature scores
idx = feature_ranking(W)
if self.name == 'ls_l21':
# obtain the feature weight matrix
W, _, _ = ls_l21.proximal_gradient_descent(X,
y,
z=self.params['z'],
verbose=False)
# sort the feature scores in an ascending order according to the feature scores
idx = feature_ranking(W)
if self.name == 'LASSO':
LASSO = Lasso(alpha=self.params['alpha'], positive=True)
y_pred_lasso = LASSO.fit(X, y)
if y_pred_lasso.coef_.ndim == 1:
coeff = y_pred_lasso.coef_
else:
coeff = np.asarray(y_pred_lasso.coef_[0, :])
idx = np.argsort(-coeff)
if self.name == 'EN': # elastic net L1
enet = ElasticNet(alpha=self.params['alpha'],
l1_ratio=1,
positive=True)
y_pred_enet = enet.fit(X, y)
if y_pred_enet.coef_.ndim == 1:
coeff = y_pred_enet.coef_
else:
coeff = np.asarray(y_pred_enet.coef_[0, :])
idx = np.argsort(-coeff)
return idx
def main():
# load data
# mat = scipy.io.loadmat('../data/COIL20.mat')
# X = mat['X'] # data
# X = X.astype(float)
# y = mat['Y'] # label
# print(y)
# print(y.shape)
# y = y[:, 0]
# print(y)
# print(y.shape)
sequence_name = 'D3'
feature_model_num = 0
img_feature_path = '/usr/luopengting/shareHoldersWithGPU_a/luopengting/workplace/python/pytorch/breast_cancer_lymph/data/' \
+ sequence_name + '/model_' + str(feature_model_num) + '_img_feature.txt'
img_label_path = '/usr/luopengting/shareHoldersWithGPU_a/luopengting/workplace/python/pytorch/breast_cancer_lymph/data/' \
+ sequence_name + '/labels.txt'
train = pd.read_csv(img_feature_path, sep=' ', header=None)
train_labels = pd.read_csv(img_label_path, sep='\t', header=None)
X_train = train.as_matrix(columns=None)
y_train = train_labels.as_matrix(columns=None)
# y.astype(int)
y_train = y_train[:, 0]
# print(y)
ss = KFold(n_splits=5)
# perform kmeans clustering based on the selected features and repeats 20 times
nmi_total = 0
acc_total = 0
for train, test in ss.split(X_train):
X = X_train[train]
y = y_train[train]
# obtain the feature weight matrix
Weight, obj, value_gamma = ll_l21.proximal_gradient_descent(
X, y, 0.1, verbose=False)
# sort the feature scores in an ascending order according to the feature scores
idx = feature_ranking(Weight)
# perform evaluation on clustering task
num_fea = 100 # number of selected features
# obtain the dataset on the selected features
selected_features = X[:, idx[0:num_fea]]
classifier = LogisticRegression(penalty='l2',
dual=False,
tol=0.0001,
C=1.0,
fit_intercept=True,
intercept_scaling=1,
class_weight='balanced',
random_state=None,
solver='liblinear',
max_iter=100,
multi_class='ovr',
verbose=0,
warm_start=False,
n_jobs=1)
classifier.fit(selected_features, y)
X_test = X_train[test]
X_test = X_test[:, idx[0:num_fea]]
Y_test = y_train[test]
Y_pred = classifier.predict(X_test)
from sklearn.metrics import confusion_matrix
confusion_matrix = confusion_matrix(Y_test, Y_pred)
print(confusion_matrix)
def fit(self, X, y):
if self.name == 'LASSO':
# print self.params['alpha']
LASSO = Lasso(alpha=self.params['alpha'], positive=True)
y_pred_lasso = LASSO.fit(X, y)
if y_pred_lasso.coef_.ndim == 1:
coeff = y_pred_lasso.coef_
else:
coeff = np.asarray(y_pred_lasso.coef_[0, :])
idx = np.argsort(-coeff)
if self.name == 'EN': # elastic net L1
# alpha = self.params['alpha']
# alpha = .9 - ((self.params['alpha'] - 1.0) * (1 - 0.1)) / ((50 - 1) + 0.1)
# print alpha
enet = ElasticNet(alpha=self.params['alpha'],
l1_ratio=1,
positive=True)
y_pred_enet = enet.fit(X, y)
# if y_pred_enet.coef_
if y_pred_enet.coef_.ndim == 1:
coeff = y_pred_enet.coef_
else:
coeff = np.asarray(y_pred_enet.coef_[0, :])
idx = np.argsort(-coeff)
if self.name == 'RFS':
W = RFS.rfs(X,
construct_label_matrix(y),
gamma=self.params['gamma'])
idx = feature_ranking(W)
if self.name == 'll_l21':
# obtain the feature weight matrix
W, _, _ = ll_l21.proximal_gradient_descent(
X,
construct_label_matrix(y),
z=self.params['z'],
verbose=False)
# sort the feature scores in an ascending order according to the feature scores
idx = feature_ranking(W)
if self.name == 'ls_l21':
# obtain the feature weight matrix
W, _, _ = ls_l21.proximal_gradient_descent(
X,
construct_label_matrix(y),
z=self.params['z'],
verbose=False)
# sort the feature scores in an ascending order according to the feature scores
idx = feature_ranking(W)
if self.tp == 'ITB':
if self.name == 'MRMR':
idx = MRMR.mrmr(X,
y,
n_selected_features=self.params['num_feats'])
if self.name == 'Relief':
score = reliefF.reliefF(X, y, k=self.params['k'])
idx = reliefF.feature_ranking(score)
if self.name == 'MI':
idx = np.argsort(
mutual_info_classif(
X, y, n_neighbors=self.params['n_neighbors']))[::-1]
return idx