题解 | #筛选某店铺最有价值用户中消费最多前5名#

import sys

for line in sys.stdin:
    a = line.split()
    print(int(a[0]) + int(a[1]))

import pandas as pd

df = pd.read_csv("sales.csv")

# df["R_Quartile"] = pd.qcut(df["recency"], 4, labels=["4", "3", "2", "1"]).astype(str)
# df["F_Quartile"] = pd.qcut(df["frequency"], 4, labels=["1", "2", "3", "4"]).astype(str)
# df["M_Quartile"] = pd.qcut(df["monetary"], 4, labels=["1", "2", "3", "4"]).astype(str)

a = pd.qcut(df["recency"], 4, labels=["4", "3", "2", "1"]).astype(str)
b = pd.qcut(df["frequency"], 4, labels=["1", "2", "3", "4"]).astype(str)
c = pd.qcut(df["monetary"], 4, labels=["1", "2", "3", "4"]).astype(str)

# df['RFMClass'] = df["R_Quartile"] + df["F_Quartile"] + df["M_Quartile"]
df['RFMClass'] = a + b + c
print(df[:5])
print()
index = df['RFMClass']=='444'
print(df[index].sort_values('monetary', ascending=False).reset_index(drop=True)[:5])

首先使用qcut对RFM列进行离散处理，然后，将其合并成为一列，这个地方我使用了a，b，c变量的目的是为了不想后面在把每个字段写一遍，为了偷个懒。