我想在for循环上使用dplyr来总结每个独立变量（列）和目标变量。这是我的主要数据框：
contract_ID Asurion Variable_1 Variable_2 Variable_3
1 Y a c f
2 Y a d g
3 N b c g
4 N a d f
5 Y b c f
6 Y a d f
分组之后，我得到
a1 <- a %>%
group_by(Asurion,BhvrBnk_Donates_to_Env_Causes) %>%
summarise(counT=n_distinct(CONTRACT_ID)) %>%
mutate(perc=paste0(round(counT/sum(counT)*100,2),"%"))
Asurion Variable_1 CounT perc
Y a 3 75%
Y b 1 25%
N a 1 50%
N b 1 50%
我想对存在于我的数据框中的每个变量进行这种汇总，并且我想使用for循环来实现。如何获得理想的结果
这是我尝试使用的方法，但似乎不起作用。它用于学校项目，为此我需要使用for循环。请在这里帮助我
categorical <- colnames(a)###where categroical is the names of all columns in a
###I would like to have a for loop for every column in a and summarise in the following way. I would like to store each of the summarisations in a separate dataframe
for (i in categorical) {
a[[i]] <- a %>%
group_by(Asurion,get(i)) %>%
summarise(counT=n_distinct(CONTRACT_ID)) %>%
mutate(perc=paste0(round(counT/sum(counT)*100,2),"%"))
}
答案 0 :(得分：2)
您可能并不需要for loop来获得所需的东西。
df<-data.frame(contract_ID = 1:6,
Asurion = c("Y", "Y", "N", "N", "Y", "Y"),
Variable_1 = c("a", "a", "b", "a", "b","a"),
Variable_2 = c("c", "d", "c", "d", "c", "d"),
Variable_3 = c("f", "g", "g", "f", "f", "f"))
pct <- function(x) {
df %>%
group_by(Asurion, {{x}}) %>%
summarise(counT=n_distinct(contract_ID)) %>%
mutate(perc = paste0(round(counT/sum(counT)*100,2),"%"))
}
pct(Variable_1)
pct(Variable_2)
pct(Variable_3)
如果确实有很多变量，则可以使用诸如for loop或apply之类的方法来迭代最后一位。
这是一个选项：
categorical<- df[3:5]
a <- list()
j = 1
for (i in categorical) {
a[[j]] <- df %>%
group_by(Asurion, {{i}}) %>%
summarise(counT=n_distinct(contract_ID)) %>%
mutate(perc = paste0(round(counT/sum(counT)*100,2),"%"))
j = j + 1
}
a
[[1]]
# A tibble: 4 x 4
# Groups: Asurion [2]
Asurion `<fct>` counT perc
<fct> <fct> <int> <chr>
1 N a 1 50%
2 N b 1 50%
3 Y a 3 75%
4 Y b 1 25%
[[2]]
# A tibble: 4 x 4
# Groups: Asurion [2]
Asurion `<fct>` counT perc
<fct> <fct> <int> <chr>
1 N c 1 50%
2 N d 1 50%
3 Y c 2 50%
4 Y d 2 50%
[[3]]
# A tibble: 4 x 4
# Groups: Asurion [2]
Asurion `<fct>` counT perc
<fct> <fct> <int> <chr>
1 N f 1 50%
2 N g 1 50%
3 Y f 3 75%
4 Y g 1 25%
编辑
根据您的问题添加变量名称作为新的变量值，以识别group_by变量。
categorical<- df[3:5]
vnames <- colnames(categorical)
a <- list()
j = 1
for (i in categorical) {
a[[j]] <- df %>%
group_by(Asurion, {{i}}) %>%
summarise(counT=n_distinct(contract_ID)) %>%
mutate(perc = paste0(round(counT/sum(counT)*100,2),"%"))
a[[j]]$vnames = vnames[j]
j = j + 1
}
a
答案 1 :(得分：1)
Base R解决方案：
df2 <- data.frame(
reshape(df,
direction = "long",
varying = names(df)[!(names(df) %in% c("contract_ID", "Asurion"))],
v.names = "Val",
timevar = "Variable",
times = names(df)[!(names(df) %in% c("contract_ID", "Asurion"))]
),
row.names = NULL,
stringsAsFactors = F
)
# Count the unique contract ids within the specified group:
df2$CounT <- as.numeric(ave(df2$contract_ID,
paste(df2$Asurion, df2$Variable, df2$Val, sep = "_"),
FUN = function(x){length(unique(x))}))
# Create the percentage of total counts:
df2$perc <- paste0(round((df2$CounT/as.numeric(ave(df2$Variable,
paste(df2$Variable, df2$Val, sep = "_"),
FUN = length))) * 100,2),"%")
# Allocate some memory for list of dataframes:
df_list <- vector("list", length(unique(df2$Variable)))
# Store the summary dataframes in the list:
df_list <- lapply(split(df2, df2$Variable),
function(x){x <- unique(x[,c(!(names(x) %in% c("id", "contract_ID")))])})
# Push the dataframes from the list into the global environment:
list2env(df_list, .GlobalEnv)
Tidyverse解决方案：
require(tidyverse)
# Allocate some memory for list of dataframes:
df_list <- vector("list", length(unique(names(df)[grepl("Variable_", names(df))])))
# Tidyverse summary:
df_list <-
df %>%
gather(Variable, Value, -contract_ID, -Asurion) %>%
group_by(Asurion, Variable, Value) %>%
mutate(CounT = length(unique(contract_ID))) %>%
ungroup() %>%
group_by(Variable, Value) %>%
mutate(perc = paste0(round((CounT/n()) * 100, 2), "%")) %>%
ungroup() %>%
select(-contract_ID) %>%
distinct() %>%
split(., .$Variable)
# Push the dataframes from the list into the global environment:
list2env(df_list, .GlobalEnv)
数据：
structure(list(contract_ID = 1:6, Asurion = c("Y", "Y", "N",
"N", "Y", "Y"), Variable_1 = c("a", "a", "b", "a", "b", "a"),
Variable_2 = c("c", "d", "c", "d", "c", "d"), Variable_3 = c("f",
"g", "g", "f", "f", "f")), class = "data.frame", row.names = c(NA,
-6L))
答案 2 :(得分：1)
这是一种tidyr和dplyr的方式，可根据您的问题生成结果列表：
library(tidyr)
library(dplyr)
DF%>%
add_count(Asurion, name = 'all_n')%>%
pivot_longer(cols = starts_with('Variable'))%>%
group_by(Asurion, name, value)%>%
summarize(CounT = n(),
perc = n() / first(all_n))%>%
ungroup()%>%
group_split(name, keep = F)
[[1]]
# A tibble: 4 x 4
Asurion value CounT perc
<fct> <fct> <int> <dbl>
1 N a 1 0.5
2 N b 1 0.5
3 Y a 3 0.75
4 Y b 1 0.25
[[2]]
# A tibble: 4 x 4
Asurion value CounT perc
<fct> <fct> <int> <dbl>
1 N c 1 0.5
2 N d 1 0.5
3 Y c 2 0.5
4 Y d 2 0.5
[[3]]
# A tibble: 4 x 4
Asurion value CounT perc
<fct> <fct> <int> <dbl>
1 N f 1 0.5
2 N g 1 0.5
3 Y f 3 0.75
4 Y g 1 0.25
还有一个更好地匹配预期输出的基本解决方案：
## base
lapply(grep('Variable', names(DF), value = T), # get vars starting with "Variable"
function(col_name){
t = table(DF[, c('Asurion', col_name)])
data.frame(prop.table(t, 1), CounT = c(t))
}
)
[[1]]
Asurion Variable_1 Freq CounT
1 N a 0.50 1
2 Y a 0.75 3
3 N b 0.50 1
4 Y b 0.25 1
[[2]]
Asurion Variable_2 Freq CounT
1 N c 0.5 1
2 Y c 0.5 2
3 N d 0.5 1
4 Y d 0.5 2
[[3]]
Asurion Variable_3 Freq CounT
1 N f 0.50 1
2 Y f 0.75 3
3 N g 0.50 1
4 Y g 0.25 1
每个@Zhiqiang Wang的数据：
DF<-data.frame(contract_ID = 1:6,
Asurion = c("Y", "Y", "N", "N", "Y", "Y"),
Variable_1 = c("a", "a", "b", "a", "b","a"),
Variable_2 = c("c", "d", "c", "d", "c", "d"),
Variable_3 = c("f", "g", "g", "f", "f", "f"))