Question

在我的数据集（比如dat1）中，我有一个名为Campaign_Response的分类变量，其中包含值False和True。同样在同一个数据集中，我为Age变量创建了存储桶。这个age_bucket变量的值包括Teen，Adult和Senior。 现在我想通过Age_bucket变量计算广告系列响应率。我开始使用dplyr函数来解决这个问题：

dat1%>%group_by(Age_bucket)%>%summarize(ResponseRate= ???)

我有点陷入总结部分，因为Campaign_response是一个分类变量，我不知道如何继续这个。你能帮我看看年龄段的广告系列回复率吗？感谢您的所有帮助。感谢。

Answer 1

确保Campaign_Response是逻辑向量，然后使用

Linq

Answer 2

# data generation
exempleData <- data.frame(order = 1:100 ,age_group = sample(c("A1","A2","A3"),100 ,replace = T),Response = sample(c(T,F),100 ,replace = T))
#compute rates
library(plyr)
rate     <- ddply(exempleData, 
                      .(age_group),
                      summarise, 
                      yes_rate = length(Response[Response == T]) / length(Response),
                      .parallel = F )
# display rates
rate

Answer 3

或者如果你想要检查两者之间的步骤，你可以做这样的事情。

#some data made
Campaign_Resp <- c(T, F, T, T, F, T, F, T,F, T, T, F, T, F)
dat1 <- as.data.frame(Campaign_Resp)
Age <- c("Teen", "Teen", "Adult","Teen", "Adult","Adult", "Senior", "Teen", "Adult", "Adult", "Senior", "Adult", "Senior", "Senior")
dat1$Age <- Age

#transforming datatype
dat1$Campaign_Resp <- as.numeric(dat1$Campaign_Resp)

#using dplyr to count how many times a person inside a agegroup awnsered or not
dat2<- dat1%>%group_by(Age, Campaign_Resp) %>% summarise(Aantal= n())
dat3<- dat2 %>% spread(Campaign_Resp,value = Aantal)

#calculate non-responsive and responsive percentage
dat3$TOT <- dat3$`0`+ dat3$`1`
dat3$resp <- dat3$`1`/ dat3$TOT
dat3$nonresp <- dat3$`0`/ dat3$TOT

Answer 4

这个怎么样：

df <- data.frame(Campaign_Response = c(TRUE, FALSE, TRUE, FALSE, FALSE, TRUE), 
                 Age_Bucket = c("teen", "adult", "senior", "teen", "adult", "senior"))
df %>% 
   group_by(Age_Bucket, Campaign_Response) %>% 
   summarize(ResponseRate = n())

如果你想知道每个年龄组你有多少TRUE值，你可以这样做：

df %>% 
   group_by(Age_Bucket) %>% 
   summarize(ResponseRate= sum(Campaign_Response))

根据年龄组

4 个答案: