I am looking to use R to generate a text file with one row that says “128, 128” and the next row is the 1st row from a data frame (with a comma between the two values). Then the third row is “128, 128” again, and the fourth row is the 2nd row from a data frame. The pattern continues for 1.7 million rows of the data frame.
Input data:
abol_cbol_sel <- setNames(data.frame(replicate(2, runif(20L))), c("abol", "cbol"))
> abol_cbol_sel
abol cbol
1 0.29636848 0.50432498
2 0.84140843 0.56122708
3 0.62139473 0.17974565
4 0.58794122 0.68818987
5 0.39900351 0.58141138
6 0.01508985 0.46200249
7 0.96268987 0.37889543
8 0.76299114 0.12223663
9 0.96278081 0.69597334
10 0.89542466 0.37967119
11 0.56731021 0.52199498
12 0.43678648 0.89333071
13 0.31440317 0.48038256
14 0.88831876 0.72405470
15 0.76464243 0.26287925
16 0.08912784 0.45741162
17 0.20423405 0.01003791
18 0.82469262 0.99269107
19 0.27169320 0.34495028
20 0.26738678 0.65987557
Expected output: For example, the first four rows of the text file would be:
128, 128
0.29636848, 0.50432498
128, 128
0.84140843, 0.56122708
I tried this code:
out <- (matrix(nrow=2, ncol=3569756))
for (i in 1: nrow(abol_cbol_sel)) {
out[1,]paste('128, 128', sep=",")
out[2,]paste(abol_cbol_sel[i])
}
write_lines(out, file="bol.txt", sep=",")
3
Here is one way with base R.
# Dummy data per your example
abol_cbol_sel <- setNames(data.frame(replicate(2, runif(20L))), c("abol", "cbol"))
> abol_cbol_sel
abol cbol
1 0.16075967 0.961929468
2 0.06670117 0.968577329
3 0.68362847 0.305907011
4 0.16850073 0.676103643
5 0.78666990 0.540069206
6 0.29216053 0.231236909
7 0.19106370 0.292454021
8 0.60435012 0.924734022
9 0.71236587 0.093686003
10 0.01240113 0.064305871
11 0.07158475 0.001502928
12 0.11337730 0.305517724
13 0.18248184 0.558679583
14 0.03304706 0.187489353
15 0.82306284 0.034983761
16 0.51861392 0.534777389
17 0.45777113 0.634643482
18 0.97615867 0.673790493
19 0.85063190 0.230844911
20 0.04825878 0.374013588
# Create the dataframe for the repeated values
df2 <- data.frame(abol = 128, cbol = 128)
# Receive the output
output1 <- list()
# Just create a mini matrix for each couplet of lines and add them to the list
for (i in 1:nrow(abol_cbol_sel)) {
output1[[i]] = matrix(c(df2, abol_cbol_sel[i,]), nrow = 2, byrow =T)
}
# Change the list of matrices into a matrix
del1 <- do.call(rbind, output1)
del1
[,1] [,2]
[1,] 128 128
[2,] 0.1607597 0.9619295
[3,] 128 128
[4,] 0.06670117 0.9685773
[5,] 128 128
[6,] 0.6836285 0.305907
[7,] 128 128
[8,] 0.1685007 0.6761036
[9,] 128 128
[10,] 0.7866699 0.5400692
[11,] 128 128
[12,] 0.2921605 0.2312369
[13,] 128 128
[14,] 0.1910637 0.292454
[15,] 128 128
[16,] 0.6043501 0.924734
[17,] 128 128
[18,] 0.7123659 0.093686
[19,] 128 128
[20,] 0.01240113 0.06430587
[21,] 128 128
[22,] 0.07158475 0.001502928
[23,] 128 128
[24,] 0.1133773 0.3055177
[25,] 128 128
[26,] 0.1824818 0.5586796
[27,] 128 128
[28,] 0.03304706 0.1874894
[29,] 128 128
[30,] 0.8230628 0.03498376
[31,] 128 128
[32,] 0.5186139 0.5347774
[33,] 128 128
[34,] 0.4577711 0.6346435
[35,] 128 128
[36,] 0.9761587 0.6737905
[37,] 128 128
[38,] 0.8506319 0.2308449
[39,] 128 128
[40,] 0.04825878 0.3740136
# Make it into a data frame if you want
del2 <- as.data.frame(del1)
# Write
readr::write_lines(del1, file = "bol.csv")
Here is a data.table approach (data.table provides a high-performance version of base R’s data.frame):
library(data.table)
abol_cbol_sel <- setNames(data.frame(replicate(2, runif(20L))), c("abol", "cbol"))
setDT(abol_cbol_sel)
abol_cbol_sel[, index := .I]
abol_cbol_sel <- rbindlist(list(data.table(index = seq_len(NROW(abol_cbol_sel)), abol = 128L, cbol = 128L), abol_cbol_sel), use.names=TRUE)
setorder(abol_cbol_sel, index)
abol_cbol_sel[, index := NULL]
head(abol_cbol_sel)
fwrite(abol_cbol_sel, file = "bol.txt")
browseURL("bol.txt")