feature_selection.py 文件源码

def rfe_selection(X,y,n_features):
    """
    Performs the Recursive Feature Elimination method and selects the top ranking features

    Keyword arguments:
    X -- The feature vectors
    y -- The target vector
    n_features -- n best ranked features
    """

    if verbose:
        print '\nPerforming Feature Selection based on the Recursive Feature Elimination method ...'

    clf=RandomForestClassifierWithCoef(n_estimators=10,n_jobs=-1)
    fs= RFE(clf, n_features, step=1)
    fs= fs.fit(X,y)
    ranks=fs.ranking_

    feature_indexes=[]
    for i in xrange(len(ranks)):
        if ranks[i]==1:
            feature_indexes+=[i]

    return X[:,feature_indexes[0:n_features]],feature_indexes[0:n_features]     #return selected features and original index features