题解 | #筛选某店铺最有价值用户中消费最多前5名#

import pandas as pd 
df = pd.read_csv('sales.csv')
# 定义评分函数  
def score_feature(series, reverse=False):  
    # 计算四分位数 Series方法 用于计算序列中数据的分位数 
    q1 = series.quantile(0.25)  
    q2 = series.quantile(0.50)  
    q3 = series.quantile(0.75)  
      
    # 定义评分函数  
    if reverse == False: 
        scores = [4 if x <= q1 else  
                   3 if x <= q2 else  
                   2 if x <= q3 else  
                   1 for x in series]  
    else:  
        scores = [4 if x >= q3 else  
                   3 if x >= q2 else  
                   2 if x >= q1 else  
                   1 for x in series]  
      
    return scores  
  
# 对每个特征进行评分  
df['R_Quartile'] = score_feature(df['recency'])
df['F_Quartile'] = score_feature(df['frequency'], reverse=True)  
df['M_Quartile'] = score_feature(df['monetary'], reverse=True)  
df['RFMClass'] = df['R_Quartile'].astype(str) + df['F_Quartile'].astype(str) + df['M_Quartile'].astype(str)
#df['RFMClass'] = df.apply(lambda row: str(row['R_Quartile']) + str(row['F_Quartile']) + str(row['M_Quartile']), axis=1)
show_row = ['user_id','recency','frequency','monetary','RFMClass']
print(df[show_row].head())
cond = df['RFMClass'] = '444'
df1 = df[df[cond]].sort_values(by = 'monetary',ascending=False)
print(df[show_row].head())