如何查找不同年龄组的信用卡持有人比例

Question

ACCOUNT表包含客户持有的帐户列表。客户可能拥有每种类型的多个帐户。该表的布局如下：

CUSTOMER_NUMBER CUSTOMER_AGE    ACCOUNT_NUMBER      ACCOUNT TYPE
123             27              A987                Home Loan
123             27              B6547               Credit Card
124             42              B7531               Credit Card

显示如何确定以下每个年龄段的信用卡客户比例：18 - 29,30 - 44,45 - 59,60 +。

输出应该如下所示：

Age Band    % with Credit Card
18-29   44.9%
30-44   41.2%
45-59   45.5%
60+ 43.0%

如何获得上表所示的预期结果，不同年龄组的百分比，即持有信用卡的人。

请帮我R代码

Answer 1

一个dplyr可能是：

df %>%
 group_by(grp = cut(CUSTOMER_AGE,
                  breaks = c(18, 29, 44, 59, Inf),
                  labels = c("18-29", "30-44", "45-59", "60+"),
                  right = FALSE)) %>%
 summarise(res = (length(ACCOUNT_TYPE[ACCOUNT_TYPE == "Credit_Card"])/n()*100))

  grp     res
  <fct> <dbl>
1 18-29    50
2 30-44   100

样本数据：

df <- read.table(text = "CUSTOMER_NUMBER CUSTOMER_AGE    ACCOUNT_NUMBER      ACCOUNT_TYPE
123             27              A987                Home_Loan
                 123             27              B6547               Credit_Card
                 124             42              B7531               Credit_Card", header = TRUE,
                 stringsAsFactors = FALSE)