def main():
# load MATLAB data
mat = scipy.io.loadmat('../data/COIL20.mat')
X = mat['X'] # data
y = mat['Y'] # label
y = y[:, 0]
n_samples, n_features = X.shape
X = X.astype(float)
Y = construct_label_matrix(y)
# split data
cv = cross_validation.KFold(n_samples, n_folds=10, shuffle=True)
# evaluation
n_selected_features = 100
clf = svm.LinearSVC()
correct = 0
for train, test in cv:
W = RFS.erfs(X[train, :], Y[train, :], gamma=0.1, verbose=True)
idx = feature_ranking(W)
X_selected = X[:, idx[0:n_selected_features]]
clf.fit(X_selected[train, :], y[train])
y_predict = clf.predict(X_selected[test, :])
acc = accuracy_score(y[test], y_predict)
print acc
correct = correct + acc
print 'ACC', float(correct)/10
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]
kwargs = {"metric": "euclidean", "neighbor_mode": "knn", "weight_mode": "heat_kernel", "k": 5, 't': 1}
W = construct_W.construct_W(X, **kwargs)
# NDFS feature selection
W = NDFS.ndfs(X, W=W, n_clusters=20, verbose=False)
idx = feature_ranking(W)
# evaluation
n_selected_features = 100
X_selected = X[:, idx[0:n_selected_features]]
ari, nmi, acc = evaluation(X_selected=X_selected, n_clusters=20, y=y)
print 'ARI:', ari
print 'NMI:', nmi
print 'ACC:', acc
