def fcbf():
# http://featureselection.asu.edu/html/skfeature.function.information_theoretical_based.FCBF.html
before = datetime.datetime.now()
result = FCBF.fcbf(data, labels, mode="index", delta=0) # treshold je delta
after = datetime.datetime.now()
print("FCBF")
print(len(result))
print("cas: " + str(after - before))
print('\n')
if len(result) < len(header):
transform_and_save(result, "FCBF")
def execute(data, cols):
y = data['GroundTruth'].values
x_orig = data.drop(['GroundTruth'], axis=1)
x = x_orig.values
(idx, uncertainty_idx) = FCBF.fcbf(x, y, n_selected_features=len(cols))
headers = ["Name", "Score"]
values = sorted(zip(x_orig.columns[idx], uncertainty_idx),
key=lambda xi: xi[1] * -1)
return tabulate(values, headers, tablefmt="plain")
def _execute(data, cols):
y = data['GroundTruth'].values
x = data.drop(['GroundTruth'], axis=1).values
# split data into 10 folds
# ss = cross_validation.KFold(n_samples, n_folds=10, shuffle=True)
ss = model_selection.KFold(n_splits=10,
random_state=None,
shuffle=True)
# ss = cross_validate(svc, x, y, cv=10, scoring='accuracy')
# perform evaluation on classification task
num_fea = len(cols) # number of selected features
clf = svm.LinearSVC() # linear SVM
correct = 0
for train, test in ss.split(x, y):
# obtain the index of each feature on the training set
x_train = x[train]
y_train = y[train]
(idx, uncertainty_idx) = FCBF.fcbf(x_train,
y_train,
n_selected_features=num_fea)
# obtain the dataset on the selected features
features_idx = idx[0:num_fea]
features = x[:, features_idx]
# train a classification model with the selected features on the training dataset
clf.fit(features[train], y[train])
# predict the class labels of test data
y_predict = clf.predict(features[test])
# obtain the classification accuracy on the test data
acc = accuracy_score(y[test], y_predict)
correct = correct + acc
print(idx, train)
print(features_idx)
print(acc)
# output the average classification accuracy over all 10 folds
print('Accuracy:', 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 = 10 # number of selected features
clf = svm.LinearSVC() # linear SVM
correct = 0
for train, test in ss:
# obtain the index of each feature on the training set
idx = FCBF.fcbf(X[train], y[train], n_selected_features=num_fea)
# obtain the dataset on the selected features
features = X[:, idx[0:num_fea]]
# train a classification model with the selected features on the training dataset
clf.fit(features[train], y[train])
# predict the class labels of test data
y_predict = clf.predict(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 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 = 10 # number of selected features
clf = svm.LinearSVC() # linear SVM
correct = 0
for train, test in ss:
# obtain the index of each feature on the training set
idx = FCBF.fcbf(X[train], y[train], n_selected_features=num_fea)
# obtain the dataset on the selected features
features = X[:, idx[0:num_fea]]
# train a classification model with the selected features on the training dataset
clf.fit(features[train], y[train])
# predict the class labels of test data
y_predict = clf.predict(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 FBCF_featureSelection(x, y):
idx = FCBF.fcbf(x, y)
rank = feature_ranking(idx)
return rank
from sklearn.feature_selection import RFE from sklearn.svm import SVR bestFeat = SelectKBest() bestFeat.fit(train_X, train_Y) feat_scr = zip(feats, bestFeat.scores_) feat_scr = [f for f in feat_scr if not np.isnan(f[1])] sorted_fetas = sorted(feat_scr, key=lambda k: k[1], reverse=True) # estimator = SVR(kernel="linear") # selector = RFE(estimator, 5, step=1) # selector.fit(train_X, train_Y) # slow from sklearn.ensemble import GradientBoostingClassifier g_cls = GradientBoostingClassifier(n_estimators=10) g_cls.fit(train_X, train_Y) g_feats = g_cls.feature_importances_ g_feat_scr = zip(feats, g_feats) g_feat_scr = [f for f in g_feat_scr if not np.isnan(f[1])] g_sorted_fetas = sorted(g_feat_scr, key=lambda k: k[1], reverse=True) from skfeature.function.information_theoretical_based import FCBF, LCSI, MRMR, JMI score = FCBF.fcbf(train_X, train_Y) fcbf_sorted = [feats[i] for i in score] score = MRMR.mrmr(train_X, train_Y, n_selected_features=50) MRMR_sorted = [feats[i] for i in score] score = JMI.jmi(train_X, train_Y, n_selected_features=50) JMI_sorted = [feats[i] for i in score]
bestFeat.fit(train_X, train_Y) feat_scr = zip(feats,bestFeat.scores_) feat_scr = [f for f in feat_scr if not np.isnan(f[1])] sorted_fetas = sorted(feat_scr, key=lambda k:k[1], reverse=True) # estimator = SVR(kernel="linear") # selector = RFE(estimator, 5, step=1) # selector.fit(train_X, train_Y) # slow from sklearn.ensemble import GradientBoostingClassifier g_cls = GradientBoostingClassifier(n_estimators=10) g_cls.fit(train_X, train_Y) g_feats = g_cls.feature_importances_ g_feat_scr = zip(feats,g_feats) g_feat_scr = [f for f in g_feat_scr if not np.isnan(f[1])] g_sorted_fetas = sorted(g_feat_scr, key=lambda k:k[1], reverse=True) from skfeature.function.information_theoretical_based import FCBF, LCSI, MRMR, JMI score = FCBF.fcbf(train_X, train_Y) fcbf_sorted= [feats[i] for i in score] score = MRMR.mrmr(train_X, train_Y, n_selected_features = 50) MRMR_sorted= [feats[i] for i in score] score = JMI.jmi(train_X, train_Y, n_selected_features = 50) JMI_sorted= [feats[i] for i in score]