Question

我有一个for loop，它在每次迭代后产生一个数据帧。我想将所有数据框附加在一起，但发现它很困难。以下就是我我正在尝试，请建议如何解决它：

d = NULL
for (i in 1:7) {

  # vector output
  model <- #some processing

  # add vector to a dataframe
  df <- data.frame(model)

}

df_total <- rbind(d,df)

Answer 1

不要在循环内完成。制作一个列表，然后将它们组合在循环之外。

datalist = list()

for (i in 1:5) {
    # ... make some data
    dat <- data.frame(x = rnorm(10), y = runif(10))
    dat$i <- i  # maybe you want to keep track of which iteration produced it?
    datalist[[i]] <- dat # add it to your list
}

big_data = do.call(rbind, datalist)
# or big_data <- dplyr::bind_rows(datalist)
# or big_data <- data.table::rbindlist(datalist)

这是一种更像R的做事方式。它也可以大大加快，特别是如果您使用dplyr::bind_rows或data.table::rbindlist进行数据帧的最终组合。

Answer 2

试试这个：

df_total = data.frame()
for (i in 1:7){

# vector output
model <- #some processing

# add vector to a dataframe
df <- data.frame(model)
df_total <- rbind(df_total,df)
}

Answer 3

再次maRtin是正确的，但要实现这一点，您必须从已经拥有至少一列的数据框开始

model <- #some processing
df <- data.frame(col1=model)

for (i in 2:17)
{
     model <- # some processing
     nextcol <-  data.frame(model)
     colnames(nextcol) <- c(paste("col", i, sep="")) # rename the comlum
     df <- cbind(df, nextcol)
}

Answer 4

在Coursera课程中，R编程简介，测试了这项技能。他们给所有学生332个单独的csv文件，并要求他们以编程方式组合几个文件来计算污染物的平均值。

这是我的解决方案：

  # create your empty dataframe so you can append to it.
  combined_df <- data.frame(Date=as.Date(character()),
                    Sulfate=double(),
                    Nitrate=double(),
                    ID=integer())
  # for loop for the range of documents to combine
  for(i in min(id): max(id)) {
    # using sprintf to add on leading zeros as the file names had leading zeros
    read <- read.csv(paste(getwd(),"/",directory, "/",sprintf("%03d", i),".csv", sep=""))
    # in your loop, add the files that you read to the combined_df
    combined_df <- rbind(combined_df, read)
  }

Answer 5

尝试使用rbindlist而不是rbind，因为它非常非常快。

示例：

library(data.table)

##### example 1: slow processing ######

table.1 <- data.frame(x = NA, y = NA)
time.taken <- 0
for( i in 1:100) {
  start.time = Sys.time()
  x <- rnorm(100)
  y <- x/2 +x/3
  z <- cbind.data.frame(x = x, y = y)

  table.1 <- rbind(table.1, z)
  end.time <- Sys.time()
  time.taken  <- (end.time - start.time) + time.taken

}
print(time.taken)
> Time difference of 0.1637917 secs

####example 2: faster processing #####

table.2 <- list()
t0 <- 0
for( i in 1:100) {
  s0 = Sys.time()
  x <- rnorm(100)
  y <- x/2 + x/3

  z <- cbind.data.frame(x = x, y = y)

  table.2[[i]] <- z

  e0 <- Sys.time()
  t0  <- (e0 - s0) + t0

}
s1 = Sys.time()
table.3 <- rbindlist(table.2)
e1 = Sys.time()

t1  <- (e1-s1) + t0
t1
> Time difference of 0.03064394 secs

Answer 6

以下一些tidyverse和自定义功能选项可能会根据您的需要起作用：

library(tidyverse)

# custom function to generate, filter, and mutate the data:
combine_dfs <- function(i){
 data_frame(x = rnorm(5), y = runif(5)) %>% 
    filter(x < y) %>% 
    mutate(x_plus_y = x + y) %>% 
    mutate(i = i)
}

df <- 1:5 %>% map_df(~combine_dfs(.))
df <- map_df(1:5, ~combine_dfs(.)) # both give the same results
> df %>% head()
# A tibble: 6 x 4
       x      y x_plus_y     i
   <dbl>  <dbl>    <dbl> <int>
1 -0.973 0.673    -0.300     1
2 -0.553 0.0463   -0.507     1
3  0.250 0.716     0.967     2
4 -0.745 0.0640   -0.681     2
5 -0.736 0.228    -0.508     2
6 -0.365 0.496     0.131     3

如果您有一个需要合并的文件目录，则可以执行类似的操作：

dir_path <- '/path/to/data/test_directory/'
list.files(dir_path)

combine_files <- function(path, file){
  read_csv(paste0(path, file)) %>% 
    filter(a < b) %>% 
    mutate(a_plus_b = a + b) %>% 
    mutate(file_name = file) 
}

df <- list.files(dir_path, '\\.csv$') %>% 
  map_df(~combine_files(dir_path, .))

# or if you have Excel files, using the readxl package:
combine_xl_files <- function(path, file){
  readxl::read_xlsx(paste0(path, file)) %>% 
    filter(a < b) %>% 
    mutate(a_plus_b = a + b) %>% 
    mutate(file_name = file) 
}

df <- list.files(dir_path, '\\.xlsx$') %>% 
  map_df(~combine_xl_files(dir_path, .))

Answer 7

对我来说，它非常简单。首先，我创建了一个空的data.frame，然后在每次迭代中都向其中添加了一列。这是我的代码：

df <- data.frame(modelForOneIteration)
for(i in 1:10){
  model <- # some processing
  df[,i] = model
}

Answer 8

x <- c(1:10) 

# empty data frame with variables ----

df <- data.frame(x1=character(),
                     y1=character())

for (i in x) {
  a1 <- c(x1 == paste0("The number is ",x[i]),y1 == paste0("This is another number ", x[i]))
  df <- rbind(df,a1)
}

names(df) <- c("st_column","nd_column")
View(df)

那可能是个好方法。...

在for循环中将数据帧附加在一起

8 个答案: