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 

#1-导入数据
data = pd.read_csv('sales.csv')
#2-三个特征
data['R'] = pd.qcut(data['recency'], [0, 0.25, 0.5, 0.75, 1], ['4', '3', '2', '1']).astype('str')
data['F'] = pd.qcut(data['frequency'], [0, 0.25, 0.5, 0.75, 1], ['1', '2', '3', '4']).astype('str')
data['M'] = pd.qcut(data['monetary'], [0, 0.25, 0.5, 0.75, 1], ['1', '2', '3', '4']).astype('str')
#3-构建新列
data['RFMClass'] = data['R']+data['F']+data['M']
#4-取子集
df = data[['user_id', 'recency', 'frequency', 'monetary', 'RFMClass']]
#5-输出结果一
print(df.head(n = 5))
print('\n')
#6-从评分为“444”的用户中筛选销售总金额最高的前5位
df_value = df[df['RFMClass'] == '444'].sort_values('monetary', ascending = False).reset_index()
#7-输出结果二
print(df_value.head(n = 5))