Select specified rows when importing CSV

Question

I have a large CSV file, and I want to import only certain lines, if so. First I create the indexes of the rows to be imported, then I want to pass the names of these rows to sqldf and return the full records for the specified rows.

#create the random rows ids that will be sampled
library(dplyr)
#range for the values
index<-c(1:20)
index<-as.data.frame(as.matrix(index))
#number of values to be returned
number<-5
ids<-sample_n(index,number)

#sample the data
library(sqldf)
#filepath
f<-file("/Users/.../filename.csv")
#select data    
df<-sqldf("select * from f")

How to import a series of lines from a CSV file by specifying line numbers?

Answer 1

Try this example:

library(sqldf)

#dummy csv 
write.csv(data.frame(myid=1:10,var=runif(10)),"temp.csv")

#define ids
ids <- c(1,3,4)
ids <- paste(ids,collapse = ",")

f <- file("temp.csv")

#query with subset
fn$sqldf("select *
          from f
          where myid in ($ids)",
          file.format = list(header = TRUE, sep = ","))

#output
#     X myid       var
# 1 "1"    1 0.2310945
# 2 "3"    3 0.8825055
# 3 "4"    4 0.6655517

close(f)

Answer 2

maybe something like this ... base R

# dummy csv 
write.csv( data.frame( myid=1:10, var=runif(10) ),"temp.csv")

# define ids
ids <- c(1,3,4)

# reading from line 3 to 4 / reading 2 lines
read.table("temp.csv", header=T, sep=",", skip=2, nrows=2)

##   X2 X2.1 X0.406697876984254
## 1  3    3          0.6199803
## 2  4    4          0.0271722


# selctive line retrieval function 
dummy <- function(file, ids){
  tmp <- 
    mapply(
      read.table, 
      skip=ids, 
      MoreArgs= list(nrows=1, file=file, sep=",") ,
      SIMPLIFY = FALSE
    )
  tmp_df <- do.call(rbind.data.frame, tmp)
  names(tmp_df) <- names(read.table("temp.csv", header=T, sep=",",nrows=1))
  return(tmp_df)
}

# et voila
dummy("temp.csv", ids)

##   X myid       var
## 1 1    1 0.9040861
## 2 3    3 0.6027502
## 3 4    4 0.6829611