DA46. 某店铺用户消费特征评分
描述
现有某店铺会员消费情况sales.csv。包含以下字段：
请你分别对每个用户的每个消费特征进行评分。
请你对每个用户销售情况的每个特征进行评分，分值为1-4分。对于recency特征，值越小越好。对于frequency和monetary值越大越好。请分别将对应的数据进行四等分并评分，如对于recency：
对于frequency和monetary则方法刚好相反。
要求给所有数据进行评分，并输出前5行。以上数据的输出结果如下：
Python 3 解法, 执行用时: 783ms, 内存消耗: 524288KB, 提交时间: 2022-07-16
import pandas as pd
sales = pd.read_csv('sales.csv')
sales['monetary'] = sales['monetary'].astype('float')
sales['R_Quartile'] = pd.qcut(sales['recency'],[0,0.25,0.5,0.75,1],
labels=['4','3','2','1']).astype('int')
sales['F_Quartile'] = pd.qcut(sales['frequency'],[0,0.25,0.5,0.75,1],
labels=['1','2','3','4']).astype('int')
sales['M_Quartile'] = pd.qcut(sales['monetary'],[0,0.25,0.5,0.75,1],
labels=['1','2','3','4']).astype('int')
print(sales.head())
Python 3 解法, 执行用时: 803ms, 内存消耗: 524288KB, 提交时间: 2022-07-15
import pandas as pd
sales = pd.read_csv('sales.csv')
sales['R_Quartile'] = pd.qcut(sales['recency'], [0, 0.25, 0.5, 0.75, 1],["4", "3", "2", "1"]).astype("int")
sales['F_Quartile'] = pd.qcut(sales['frequency'], [0, 0.25, 0.5, 0.75, 1],["1", "2", "3", "4"]).astype("int")
sales['M_Quartile'] = pd.qcut(sales['monetary'], [0, 0.25, 0.5, 0.75, 1],["1", "2", "3", "4"]).astype("int")
print(sales.head())
Python 3 解法, 执行用时: 803ms, 内存消耗: 524288KB, 提交时间: 2022-06-30
import pandas as pd
sales = pd.read_csv('sales.csv')
def deal(x,name):
if name == 'recency':
if x <= dict_list[0][name]:
return 4
elif x > dict_list[0][name] and x <= dict_list[1][name]:
return 3
elif x > dict_list[1][name] and x <= dict_list[2][name]:
return 2
else:
return 1
else:
if x <= dict_list[0][name]:
return 1
elif x > dict_list[0][name] and x <= dict_list[1][name]:
return 2
elif x > dict_list[1][name] and x <= dict_list[2][name]:
return 3
else:
return 4
sales_quantile = sales.quantile([.25,.50,.75])
dict_list = sales_quantile.to_dict('records')
sales['R_Quartile'] = sales['recency'].apply(lambda x : deal(x,'recency')).astype('int')
sales['F_Quartile'] = sales['frequency'].apply(lambda x : deal(x,'frequency')).astype('int')
sales['M_Quartile'] = sales['monetary'].apply(lambda x : deal(x,'monetary')).astype('int')
print(sales.head(5))
Python 3 解法, 执行用时: 806ms, 内存消耗: 524288KB, 提交时间: 2022-07-09
import pandas as pd
sales = pd.read_csv('sales.csv')
def deal(x,name):
if name == 'recency':
if x <= dict_list[0][name]:
return 4
elif x > dict_list[0][name] and x <= dict_list[1][name]:
return 3
elif x > dict_list[1][name] and x <= dict_list[2][name]:
return 2
else:
return 1
else:
if x <= dict_list[0][name]:
return 1
elif x > dict_list[0][name] and x <= dict_list[1][name]:
return 2
elif x > dict_list[1][name] and x <= dict_list[2][name]:
return 3
else:
return 4
sales_quantile = sales.quantile([.25,.50,.75])
dict_list = sales_quantile.to_dict('records')#此处的'records'是参数，转化后是list形式的字典
sales['R_Quartile'] = sales['recency'].apply(lambda x : deal(x,'recency')).astype('int')
sales['F_Quartile'] = sales['frequency'].apply(lambda x : deal(x,'frequency')).astype('int')
sales['M_Quartile'] = sales['monetary'].apply(lambda x : deal(x,'monetary')).astype('int')
print(sales.head(5))
Python 3 解法, 执行用时: 811ms, 内存消耗: 524288KB, 提交时间: 2022-07-15
import pandas as pd
sales = pd.read_csv('sales.csv')
sales['monetary']=sales['monetary'].astype('float')
a=sales['recency'].quantile([0.25,0.5,0.75]).values
b=sales['frequency'].quantile([0.25,0.5,0.75]).values
c=sales['monetary'].quantile([0.25,0.5,0.75]).values
def col_recency(x):
x=float(x)
if x<=a[0]: return 4
elif a[0]<x<=a[1]:return 3
elif a[1]<x<=a[2]:return 2
else: return 1
def col_frequency(x):
x=float(x)
if x<=b[0]: return 1
elif b[0]<x<=b[1]:return 2
elif b[1]<x<=b[2]:return 3
else: return 4
def col_monetary(x):
x=float(x)
if x<=c[0]: return 1
elif c[0]<x<=c[1]:return 2
elif c[1]<x<=c[2]:return 3
else: return 4
sales['R_Quartile']=sales['recency'].apply(col_recency)
sales['F_Quartile']=sales['frequency'].apply(col_frequency)
sales['M_Quartile']=sales['monetary'].apply(col_monetary)
print(sales.head(5))