vectorizer.py 文件源码

def calculate_feature_correlation(instances):
    # calculate correlation by feature
    feature_correlation = []
    for i in range(instances.shape[1]):
        feature_vals_i = instances[:,i].transpose().toarray()[0]
        for j in range(i+1,instances.shape[1]):
            feature_vals_j = instances[:,j].transpose().toarray()[0]
            try:
                corr,p = stats.pearsonr(feature_vals_i,feature_vals_j)
                if math.isnan(corr):
                    corr = 0
            except:
                corr = 0
            feature_correlation.append([i,j,abs(corr),corr,p])
    return feature_correlation