创建包含范围的列

Question

我的数据集是Churn_Modeling：Churn_Modeling

我希望创建一个名为c_rating的列，其范围如下：(<500 -=“非常差”，500-600=“差”，601-660=“一般”，661- 780 =“好”，>= 780-“优秀”)。

library(tidyverse)
library(reticulate)
library(readxl)
library(modelr)
library(ggplot2)
library(dplyr)

churn <- read.csv("Churn_Modeling.csv")

churn$CreditScore <- as.numeric(churn$CreditScore)
class(churn$CreditScore)

churn$c_rating <- cut(churn$CreditScore, c(-Inf, 500, 600, 601, 660, 661, 780, Inf),
                      levels=c('<=500', '500-600', '601-660', '661-780', '>780'))

churn$c_rating

我的输出并没有像我想的那样创建一个列c_rating。有什么想法吗？

Answer 1

使用mutate()和case_when()。

library(tidyverse)

churn <- read.csv("Churn_Modeling.csv")
churn<-churn %>% mutate(c_rating=case_when(CreditScore<500~"very poor", 
                                           CreditScore>=500 & CreditScore<=600~"poor", 
                                           CreditScore>=601 & CreditScore<=660~"fair", 
                                           CreditScore>=661 & CreditScore<=780~"good", 
                                           CreditScore> 780 ~ "excellent"))

Answer 2

Nicolas Ratto的回答非常好。另一种方法是首先创建一个用户定义的函数，然后使用lapply()。下面是一个例子。

churn <- read.csv("Churn_Modeling.csv")

churn$CreditScore <- as.numeric(churn$CreditScore)

C_Rating = function(score){
  if (score < 500) 
    rating = "Very Poor"
  else if (score >= 500 & score <= 600)
    rating = "Poor"
  else if (score >= 601 & score <= 660)
    rating = "Fair"
  else if(score >= 661 & score <= 780)
    rating = "Good"
  else
    rating = "Excellent"
  
  return(rating)

}

churn$c_rating = churn$CreditScore %>% lapply(C_Rating)