自动分箱的代码实现（基于卡方）

def mc_chiMerge_final(df,var,target,max_groups=None,threshold=None):
  """
    df: 数据集
    var: 变量
    target: 标签
    max_groups: 最大分箱个数
    threshold: 卡方阈值
    """
    import numpy as np
    import pandas as pd

    
    def mc_chi2(arr): 
        #arr：频数统计表
        assert(arr.ndim==2)
        #计算每行频数
        R_N = arr.sum(axis=1)
        #每列总频数
        C_N = arr.sum(axis=0)
        #总频数
        N = arr.sum()
        #计算期望频数C_i*R_j/N
        E = np.ones(arr.shape) * C_N /N
        E = (E.T * R_N).T
        square = (arr-E)**2/E
        #期望频数为0时，无法作为除数，不计入卡方值
        square[E==0] = 0
        #卡方值
        v = square.sum()
        return v

    freq_tab = pd.crosstab(df[var],df[target])
    #转成numpy数组用于计算
    freq = freq_tab.values
    #初始分组切分点，每个变量值都是切分点；每组中只包含一个变量值.    
    #分组区间是左闭右开的，如cutoffs = [1,2,3]，则表示区间 [1,2) , [2,3) ,[3,3+)
    cutoffs = freq_tab.index.values
    #如果没有指定最大分组
    if max_groups is None:
        #如果没有指定卡方阈值，就以95%的置信度（自由度为类数目-1）设定阈值。
        if threshold is None:
            #类数目
            cls_num = freq.shape[-1]
            threshold = mc_chi2.isf(0.05,df= cls_num - 1)
            
    while True:
        minvalue = None
        minidx = None
        #从第1组开始，依次取两组计算卡方值，并判断是否小于当前最小卡方值
        for i in range(len(freq) - 1):
            v = mc_chi2(freq[i:i+2])
            if minvalue is None or minvalue>v: #小于当前最小卡方值，更新最小值
                minvalue = v
                minidx = i
                
        #如果最小卡方值小于阈值，则合并最小卡方值的相邻两组，并继续循环
        if(max_groups is not None and max_groups<len(freq)) or (threshold is not None and minvalue<threshold):
            #minidx后一行合并到minidx 
            tmp = freq[minidx] + freq[minidx+1]
            freq[minidx] = tmp
            #删除minidx最后一行
            freq = np.delete(freq,minidx+1,0)
            #删除对应的切分点
            cutoffs = np.delete(cutoffs,minidx+1,0)
        else:
            #最小卡方值不小于阈值，停止合并
            break
    
    
    def mc_valuegroup_1(x,cutoffs):
       
        num_groups = len(cutoffs)
        if pd.isna(x):
            return -999
        for i in range(1,num_groups):
            if cutoffs[i-1]<=x<cutoffs[i]:
                return i-1
        return len(cutoffs)-1
    
    #判断数值所属区间
    df["var_bin_count"] = df[var].apply(mc_valuegroup_1,args = (cutoffs,)) 
    
    #分组排序
    w1 = pd.DataFrame(df.groupby("var_bin_count").var_bin_count.count())
    w1["group_count"] = w1.index.values
    
    for i in range(0,len(cutoffs)):
        if i<len(cutoffs)-1:     
            w1.loc[i,"var_bin"] = "[" + str(cutoffs[w1.loc[i,"group_count"]]) + "," + str(cutoffs[w1.loc[i+1,"group_count"]]) + ")"
        else:
            w1.loc[i,"var_bin"] = "[" + str(cutoffs[w1.loc[i,"group_count"]]) + "," + "+" + ")"
    try:
        w1.loc[-999,"var_bin"] = w1.loc[-999,"group_count"]
    except KeyError:
        print('the feature nullvalue num is %d ' % (df[var].isnull().sum()))
        
    
    w1 = w1.sort_values(by = 'group_count')[["var_bin","var_bin_count"]]
    w2 = pd.crosstab(df["var_bin_count"],df[target]).sort_index()
    w3 = pd.merge(w1,w2,left_index = True ,right_index = True ,how = 'left')
    w4 = w3.rename(columns = {"var_bin":"分箱区间","var_bin_count":"总样本数",0:"正样本数",1:"负样本数"})
    
    #分布统计
    dt = w4
    dt["行占比"] = dt["总样本数"]/df.shape[0]
    dt["逾期率"] = dt["负样本数"]/dt["总样本数"]
    
    #woe&iv
    good_sum = sum(dt.正样本数)
    bad_sum = sum(dt.负样本数) 
    good_rate = dt.正样本数/sum(dt.正样本数)
    bad_rate = dt.负样本数/sum(dt.负样本数)
    rate = good_rate/bad_rate
    
    dt['woe'] = np.log(rate.astype('float'))
    dt['iv'] = (good_rate-bad_rate)*np.log(rate.astype('float')) #加上as.type
    dt = dt.replace({'woe': {np.inf: 0, -np.inf: 0},'iv': {np.inf: 0, -np.inf: 0}}) 
    
    #添加合计行
    dt1 = pd.DataFrame()
    dt1.loc[0,"分箱区间"] = "合计"
    dt1.loc[0,"总样本数"] = df[target].count()
    dt1.loc[0,"正样本数"] = df[df[target]==0][target].count()
    dt1.loc[0,"负样本数"] = df[df[target]==1][target].count()
    dt1.loc[0,"行占比"] = df[target].count()/df.shape[0]
    dt1.loc[0,"逾期率"] = dt1.loc[0,"负样本数"]/dt1.loc[0,"总样本数"]
    dt1.loc[0,"woe"] = "-"
    dt1.loc[0,"iv"] = "-"
    
    #修改列名顺序
    order = ['分箱区间', '总样本数', '正样本数', '负样本数', '行占比', '逾期率', 'woe', 'iv']
    dt = dt[order]
    dt1 = dt1[order]
    
    #汇总表
    dt_bin = dt.append(dt1)
    
    #修改序列号
    dt_bin.index = range(1,len(dt_bin)+1)
    
    #添加变量名
    dt_bin["变量名"] = var
    order = ['变量名','分箱区间', '总样本数', '正样本数', '负样本数', '行占比', '逾期率', 'woe', 'iv']
    dt_bin = dt_bin[order]
    
    #分箱后求和IV
    dt_bin.iloc[-1,-1] = dt_bin.loc[1:dt_bin.shape[0]-2,"iv"].sum()
    
    #指标有效性    
    dt_summary = pd.DataFrame()
    dt_summary.loc[0,"变量名"] = var
    dt_summary.loc[0,"覆盖率"] = (df.shape[0]-pd.isna(df[var]).sum())/df.shape[0]
    dt_summary.loc[0,"IV"] = dt_bin.loc[1:dt_bin.shape[0]-2,"iv"].sum()
    
    return dt_bin, dt_summary