KNN_predict计算方差的问题

[Edward-hb]

            这里的i在计算方差的时候是没有变化的计算的方差没有遍历所有的。



            i = 0
	for p in self.labeled_hudongList:  # 预先计算存储各分量相似度
		if p.title == item.title:	# 如果训练集已经有，直接返回label
			return p.label
		title_simi.append(self.get_title_simi(p, item))
		openTypeList_simi.append(self.get_openTypeList_simi(p, item))
		baseInfoKeyList_simi.append(self.get_baseInfoKeyList_simi(p, item))
		baseInfoValueList_simi.append(self.get_baseInfoValueList_simi(p, item))
		
		mean[0] += title_simi[i]
		mean[1] += openTypeList_simi[i]
		
		mean[2] += baseInfoKeyList_simi[i]
		maxx[2] = max(maxx[2],baseInfoKeyList_simi[i])
		minn[2] = min(minn[2],baseInfoKeyList_simi[i])
		
		mean[3] += baseInfoValueList_simi[i]
		maxx[3] = max(maxx[3],baseInfoValueList_simi[i])
		minn[3] = min(minn[3],baseInfoValueList_simi[i])
		
		i += 1
	
	for i in range(4):
		mean[i] /= len(self.labeled_hudongList)
	
	for p in self.labeled_hudongList: # 计算方差
		var[0] += (title_simi[i]-mean[0])*(title_simi[i]-mean[0])
		var[1] += (openTypeList_simi[i]-mean[1])*(openTypeList_simi[i]-mean[1])
		var[2] += (baseInfoKeyList_simi[i]-mean[2])*(baseInfoKeyList_simi[i]-mean[2])
		var[3] += (baseInfoValueList_simi[i]-mean[3])*(baseInfoValueList_simi[i]-mean[3])

修改为：

我这里修改了变量名所以和源码略有不同
for i in range(len(self.labeled_hudongList)):
title_simi[i] = (title_simi[i] - mean[0]) / stand[0]
openTypeList_simi[i] = (openTypeList_simi[i] - mean[1]) / stand[1]
baseInfoKeyList_simi[i] = (baseInfoKeyList_simi[i] - mean[2]) / stand[2]
baseInfoValueList_simi[i] = (baseInfoValueList_simi[i] - mean[3]) / stand[3]