vectorizer.py 文件源码

def calculate_ordinal_correlation_feature_labels(instances,labels):
    # calculate correlation by feature
    feature_correlation = []
    for i in range(instances.shape[1]):
        feature_vals = instances[:,i].transpose().toarray()[0]
        try:
            corr,p = stats.pearsonr(feature_vals,labels)
            if math.isnan(corr):
                corr = 0
        except:
            corr = 0
        feature_correlation.append([i,abs(corr),corr,p])
    sorted_feature_correlation = sorted(feature_correlation,key=lambda k : k[1],reverse=True)
    return sorted_feature_correlation