vectorizer.py 文件源码

def return_correlations(instances, labels):
    feature_correlation = {}
    nplabels = numpy.array(labels)
    for i in range(instances.shape[1]):
        feature_vals = instances[:,i].toarray()
        corr,p = stats.pearsonr(feature_vals,nplabels)
        feature_correlation[i] = [corr,p]
    return feature_correlation[i]