根据美国数据库营销研究所Arthur Hughes的研究，客户数据库中有3个神奇的要素，这3个要素构成了数据分析最好的指标：
最近一次消费 (Recency)
消费频率 (Frequency)
消费金额 (Monetary)
–来源百度百科
Recency：最近一次消费，意指上一次购买距离现在的时间，一般按照天进行计算
Frequency：消费频率是顾客在限定的期间内所购买的次数，时间范围需要自己设定
Monetary：指的是一段时间（通常是1年）内的消费金额
实例：
#定义相关函数 #三个指标的分值函数 def Recency(x): if x>=0 and x<5: return 5 elif x>=5 and x<15: return 4 elif x>=15 and x<30: return 3 elif x>=30 and x<90: return 2 elif x>=90: return 1 def Frequency(x): if x>=0 and x<10: return 1 elif x>=10 and x<30: return 2 elif x>=30 and x<50: return 3 elif x>=50 and x<100: return 4 elif x>=100: return 5 def Monetory(x): if x>=0 and x<300: return 1 elif x>=300 and x<1000: return 2 elif x>=1000 and x<3000: return 3 elif x>=3000 and x<10000: return 4 elif x>=1000: return 5 #判断函数 def judge(x): if x>avg: return 1 else: return 0 #定义RFM函数 def RFM(x): if x.iloc[0]==1 and x.iloc[1]==1 and x.iloc[2]==1: return "重要价值客户" elif x.iloc[0]==1 and x.iloc[1]==1 and x.iloc[2]==0: return "重要潜力客户" elif x.iloc[0]==1 and x.iloc[1]==0 and x.iloc[2]==1: return "重要发展客户" elif x.iloc[0]==1 and x.iloc[1]==0 and x.iloc[2]==0: return "新客户" elif x.iloc[0]==0 and x.iloc[1]==1 and x.iloc[2]==1: return "重要保持客户" elif x.iloc[0]==0 and x.iloc[1]==1 and x.iloc[2]==0: return "一般客户" elif x.iloc[0]==0 and x.iloc[1]==0 and x.iloc[2]==1: return "重要挽回客户" elif x.iloc[0]==0 and x.iloc[1]==0 and x.iloc[2]==0: return "流失客户" #分值转化 data["R-SCORE"] = data["R"].apply(Recency) data["F-SCORE"] = data["F"].apply(Frequency) data["M-SCORE"] = data["M"].apply(Monetory) #查看分组情况，用来查看分组的分布是否合理 grouped_r=data["R-SCORE"].groupby(data["R-SCORE"]).count() grouped_f=data["F-SCORE"].groupby(data["F-SCORE"]).count() grouped_m=data["M-SCORE"].groupby(data["M-SCORE"]).count() #计算查看平均值 avg_r = data["R-SCORE"].mean() avg_f = data["F-SCORE"].mean() avg_m = data["M-SCORE"].mean() display(avg_r,avg_f,avg_m) #也可以用pandas_profiling进行数据预览 import pandas_profiling pandas_profiling.ProfileReport(data) #0-1分类 for avg in [avg_r,avg_f,avg_m]: if avg==avg_r: data["R-SCORE是否大于均值"] = data["R-SCORE"].apply(judge) elif avg==avg_f: data["F-SCORE是否大于均值"] = data["F-SCORE"].apply(judge) elif avg==avg_m: data["M-SCORE是否大于均值"] = data["M-SCORE"].apply(judge) #打标签 data["RFM"] = data[["R-SCORE是否大于均值","F-SCORE是否大于均值","M-SCORE是否大于均值"]].apply(RFM,axis=1) data.head() #数据汇总 result = data.groupby("RFM").agg({"RFM":"count"}) #数据展示 from pyecharts import options as opts from pyecharts.charts import TreeMap data = [ {"value": int(result['RFM'][0]), "name": result['RFM'].index[0]}, {"value": int(result['RFM'][1]), "name": result['RFM'].index[1]}, {"value": int(result['RFM'][2]), "name": result['RFM'].index[2]}, {"value": int(result['RFM'][3]), "name": result['RFM'].index[3]}, {"value": int(result['RFM'][4]), "name": result['RFM'].index[4]}, {"value": int(result['RFM'][5]), "name": result['RFM'].index[5]}, {"value": int(result['RFM'][6]), "name": result['RFM'].index[6]}, {"value": int(result['RFM'][7]), "name": result['RFM'].index[7]}, ] c = ( TreeMap() .add("RFM模型", data ,label_opts= opts.LabelOpts(font_size= 12,position = "inside")) .set_global_opts(title_opts=opts.TitleOpts(title="")) ) c.render_notebook()