卡方最优分箱

本文主要是介绍卡方最优分箱，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！

```python
def Chi2(df, total_col, bad_col,overallRate):'''#此函数计算卡方值:df dataFrame:total_col 每个值得总数量:bad_col 每个值的坏数据数量:overallRate 坏数据的占比: return 卡方值'''df2=df.copy()df2['expected']=df[total_col].apply(lambda x: x*overallRate)combined=list(zip(df2['expected'], df2[bad_col]))chi=[(i[0]-i[1])**2/i[0] for i in combined]chi2=sum(chi)return chi2

> #最大分箱数分箱 def ChiMerge_MaxInterval_Original(df, col, target,max_interval=5):
>     '''
>     : df dataframe
>     : col 要被分项的特征
>     ： target 目标值 0,1 值
>     : max_interval 最大箱数
>     ：return 箱体
>     '''
>     colLevels=set(df[col])
>     colLevels=sorted(list(colLevels))
>     N_distinct=len(colLevels)
>     if N_distinct <= max_interval:
>         print("the row is cann't be less than interval numbers")
>         return colLevels[:-1]
>     else:
>         total=df.groupby([col])[target].count()  #按分类特征分组，计算总数
>         total=pd.DataFrame({'total':total})      
>         bad=df.groupby([col])[target].sum()      #按分类特征分组，计算不良总数
>         bad=pd.DataFrame({'bad':bad})
>         regroup=total.merge(bad, left_index=True, right_index=True, how='left')
>         regroup.reset_index(level=0, inplace=True)  #自动重置索引，添加从0到n的索引值
>         N=sum(regroup['total'])
>         B=sum(regroup['bad'])
>         overallRate=B*1.0/N
>         groupIntervals=[[i] for i in colLevels]
>         groupNum=len(groupIntervals)
>         while(len(groupIntervals)>max_interval):
>             chisqList=[]
>             for interval in groupIntervals:
>                 df2=regroup.loc[regroup[col].isin(interval)]
>                 chisq=Chi2(df2,'total','bad',overallRate)
>                 chisqList.append(chisq)
>             min_position=chisqList.index(min(chisqList))
>             if min_position==0:
>                 combinedPosition=1
>             elif min_position==groupNum-1:
>                 combinedPosition=min_position-1
>             else:
>                 if chisqList[min_position-1]<=chisqList[min_position + 1]:
>                     combinedPosition=min_position-1
>                 else:
>                     combinedPosition=min_position+1
>             #合并箱体
>             groupIntervals[min_position]=groupIntervals[min_position]+groupIntervals[combinedPosition]
>             groupIntervals.remove(groupIntervals[combinedPosition])
>             groupNum=len(groupIntervals)
>         groupIntervals=[sorted(i) for i in groupIntervals]
>         print(groupIntervals)
>         cutOffPoints=[i[-1] for i in groupIntervals[:-1]]
>         return cutOffPoints

这篇关于卡方最优分箱的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！

---