Append data frames together in a for loop

Question

I have a for loop which produces a data frame after each iteration. I want to append all data frames together but finding it difficult. Following is what I am

Answer 1

You should try this:

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 2

Here are some tidyverse and custom function options that might work depending on your needs:

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

You could do something similar if you had a directory of files that needed to be combined:

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 3

In the Coursera course, an Introduction to R Programming, this skill was tested. They gave all the students 332 separate csv files and asked them to programmatically combined several of the files to calculate the mean value of the pollutant.

This was my solution:

  # 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 4

Don't do it inside the loop. Make a list, then combine them outside the loop.

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)

This is a much more R-like way to do things. It can also be substantially faster, especially if you use dplyr::bind_rows or data.table::rbindlist for the final combining of data frames.

Answer 5

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)

that might be a good way to do so....

Answer 6

Try to use rbindlist approach over rbind as it's very, very fast.

Example:

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