Last active
November 9, 2018 04:01
-
-
Save djhocking/f743532d2d7bbd8d3ca745676cd80126 to your computer and use it in GitHub Desktop.
Subset and Save
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# make fake dataset | |
df <- data.frame(x = runif(100, 0, 1), y = rnorm(100, 10, 3), z = rpois(100, 10)) | |
# subset dataframe | |
df_sub <- df[which(df$x >= 0.75), ] | |
# subset using dplyr | |
library(dplyr) | |
df_sub2 <- df %>% | |
filter(x >= 0.75) | |
df_list <- list(sub1 = df_sub, sub2 = df_sub2) | |
# Create a new directory for output if it doesn't exist | |
if(!dir.exists("Output/Large")) dir.create("Output/Large", recursive = TRUE) | |
if(!dir.exists("Output/Small")) dir.create("Output/Small", recursive = TRUE) | |
# Save subset of data as csv to location based on size of subset | |
for(i in 1:length(df_list)) { | |
# currently will throw an error I think if the list is empty or has a blank space | |
if(ncol(df_list[[i]] >= 20) { | |
write.csv(df_sub, file = paste0("Output/Large/", names(df_list)[i], ".csv"), row.names = FALSE) | |
} else { | |
write.csv(df_sub, file = paste0("Output/Small/", names(df_list)[i], ".csv"), row.names = FALSE) | |
} | |
# save subset as RData | |
save(df_sub, file = "Output/subset1.RData") | |
# save subset 2 as RDS | |
saveRDS(df_sub2, file = "Output/subset2.rds") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment