feature_selection.py 文件源码

def pearson_between_feature_class(X,y,threshold):
    """
    Computes the Pearson Correlation between each feature and the target class and keeps the higlhy correlated features-class

    Keyword arguments:
    X -- The feature vectors
    y -- The target vector
    threshold -- Threshold value used to decide which features to keep (above the threshold)
    """

    if verbose:
        print '\nPerforming Feature Selection based on the correlation between each feature and class ...'

    feature_indexes=[]
    for i in xrange(len(X[0])):
        if abs(stats.pearsonr(X[:,i],y)[0])>threshold:
            feature_indexes+=[i]

    if len(feature_indexes)!=0:
        return X[:,feature_indexes],feature_indexes     #return selected features and original index features
    else:
        return X,feature_indexes