我正在尝试使用函数创建新变量,lapply
而不是使用循环在数据中正确工作。我曾经使用过 Stata,并且会使用类似于此处讨论的方法来解决此问题。
由于在 R 中以编程方式命名变量非常困难或至少很尴尬(而且您似乎不能使用 索引assign
),所以我将命名过程留到lapply
. 然后我使用for
循环在合并之前进行重命名,然后再次进行合并。有没有更有效的方法来做到这一点?我将如何更换循环?我应该进行某种重塑吗?
#Reproducible data
data <- data.frame("custID" = c(1:10, 1:20),
"v1" = rep(c("A", "B"), c(10,20)),
"v2" = c(30:21, 20:19, 1:3, 20:6), stringsAsFactors = TRUE)
#Function to analyze customer distribution for each category (v1)
pf <- function(cat, df) {
df <- df[df$v1 == cat,]
df <- df[order(-df$v2),]
#Divide the customers into top percents
nr <- nrow(df)
p10 <- round(nr * .10, 0)
cat("Number of people in the Top 10% :", p10, "\n")
p20 <- round(nr * .20, 0)
p11_20 <- p20-p10
cat("Number of people in the 11-20% :", p11_20, "\n")
#Keep only those customers in the top groups
df <- df[1:p20,]
#Create a variable to identify the percent group the customer is in
top_pct <- integer(length = p10 + p11_20)
#Identify those in each group
top_pct[1:p10] <- 10
top_pct[(p10+1):p20] <- 20
#Add this variable to the data frame
df$top_pct <- top_pct
#Keep only custID and the new variable
df <- subset(df, select = c(custID, top_pct))
return(df)
}
##Run the customer distribution function
v1Levels <- levels(data$v1)
res <- lapply(v1Levels, pf, df = data)
#Explore the results
summary(res)
# Length Class Mode
# [1,] 2 data.frame list
# [2,] 2 data.frame list
print(res)
# [[1]]
# custID top_pct
# 1 1 10
# 2 2 20
#
# [[2]]
# custID top_pct
# 11 1 10
# 16 6 10
# 12 2 20
# 17 7 20
##Merge the two data frames but with top_pct as a different variable for each category
#Change the new variable name
for(i in 1:length(res)) {
names(res[[i]])[2] <- paste0(v1Levels[i], "_top_pct")
}
#Merge the results
res_m <- res[[1]]
for(i in 2:length(res)) {
res_m <- merge(res_m, res[[i]], by = "custID", all = TRUE)
}
print(res_m)
# custID A_top_pct B_top_pct
# 1 1 10 10
# 2 2 20 20
# 3 6 NA 10
# 4 7 NA 20