我有一个数据框“my_data”,其中包含6列:
group1.members group2.members group3.members price price.2 price.3
1 1 1 800 877 334
1 2 1 850 877 334
2 2 1 859 877 334
3 1 1 859 877 334
3 1 2 870 877 334
2 2 2 870 877 334
2 3 2 870 877 334
1 3 3 880 877 334
我想通过ROW总结my_data的“价格”列到几个单独的数据框中,在每个不同的“group.member”列上使用group_by。看来,group_by不允许这样做?
这就是我的想法:
my_data <- as.data.frame(data)
num_of_years <- c(1,2,3)
for(i in 1:length(num_of_years)){
price_means <- my_data %>% group_by(my_data[i]) %>%
select(-value) %>%
summarise_each(funs(mean(., na.rm=TRUE))) %>%
ungroup
assign(paste("PriceMeans",i,sep=""),price_means, envir = .GlobalEnv)
}
换句话说:
编辑:我的解决方案:
for(i in 1:length(my_groups)){
# construct the group to select
current.group <- my_groups[i]
current.group <- paste0("memb_", current.group)
# construct the groups to exclude
groups.to.drop <- my_groups[-i]
groups.to.drop <- paste0("memb_", groups.to.drop)
# Get Means
Means <- data %>% group_by_(as.name(current.group)) %>%
select(- c(ID, get(groups.to.drop))) %>%
summarise_each(funs(mean(., na.rm = TRUE)))
Means <- Means[,-1:-(length(my_groups)-1)]
Means <- as.list(Means)
assign(x = paste0("Means_",i),
value = Means,
envir = parent.env(new.env())
}
答案 0 :(得分:1)
我绝不是dplyr
专家,但这似乎完成了你想要做的事情:
for (i in 1:length(num_of_years)){
var1 <- names(my_data)[[i]]
var2 <- c(var1)
price_means <- my_data %>%
select(eval(i), price, price.2, price.3) %>%
group_by_(var2) %>%
summarise_each(funs(mean(., na.rm=TRUE))) %>%
ungroup()
assign(paste("PriceMeans",i,sep=""),price_means, envir = .GlobalEnv)
}