def giniProc(X,y): # obtain the gini_index score of each feature score = gini_index.gini_index(X, y) # rank features in descending order according to score idx = gini_index.feature_ranking(score) return idx
def apply_impl(self, data):
# TODO: verify if is possible implement this with numpy
X, y = data.Xy
y = pd.Categorical(y).codes
self._score = gini_index.gini_index(X, y)
self._rank = gini_index.feature_ranking(self._score)
self._nro_features = math.ceil(self.ratio * X.shape[1])
return self.use_impl(data)
def test_gine_index(self):
X, y = self.DATA
f = FilterGiniIndex(ratio=0.5)
f.fit(X, y)
X_, y_ = f.transform(X, y)
score = gini_index.gini_index(X, y)
rank = gini_index.feature_ranking(score)
selected = rank[0:5]
assert f.fit(X, y) is f
assert np.array_equal(f.rank(), rank)
assert np.allclose(f.score(), score)
assert np.allclose(X_, X[:, selected])
assert np.array_equal(y_, y)
def main():
# load data
mat = scipy.io.loadmat('../data/colon.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 gini_index score of each feature
score = gini_index.gini_index(X[train], y[train])
# rank features in descending order according to score
idx = gini_index.feature_ranking(score)
# 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:', old_div(float(correct), 10))
def main():
# load data
mat = scipy.io.loadmat('../data/colon.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 gini_index score of each feature
score = gini_index.gini_index(X[train], y[train])
# rank features in descending order according to score
idx = gini_index.feature_ranking(score)
# 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 gini_index_FS(X_train, y_train):
score = gini_index.gini_index(X_train, y_train)
# rank features in descending order according to score
idx = gini_index.feature_ranking(score)
return (idx, score)