聚合R中多个输入文件的输出

Question

Right now I have the R code below. It reads in data that looks like this:

track_id    day hour    month   year    rate    gate_id pres_inter  vmax_inter
9   10  0   7   1   9.6451E-06  2   97809   23.545
9   10  0   7   1   9.6451E-06  17  100170  13.843
10  3   6   7   1   9.6451E-06  2   96662   31.568
13  22  12  8   1   9.6451E-06  1   94449   48.466
13  22  12  8   1   9.6451E-06  17  96749   30.55
16  13  0   8   1   9.6451E-06  4   98702   19.205
16  13  0   8   1   9.6451E-06  16  98585   18.143
19  27  6   9   1   9.6451E-06  9   98838   20.053
19  27  6   9   1   9.6451E-06  17  99221   17.677
30  13  12  6   2   9.6451E-06  2   97876   27.687
30  13  12  6   2   9.6451E-06  16  99842   18.163
32  20  18  6   2   9.6451E-06  1   99307   17.527


##################################################################
# Input / Output variables
##################################################################
for (N in (59:96)){
  if (N < 10){
#     TrackID <- "000$N"
     TrackID <- paste("000",N, sep="")
  }
  else{
#     TrackID <- "00$N"
     TrackID <- paste("00",N, sep="")
  }
  print(TrackID)

# For 2010_08_24 trackset
#  fname_in <- paste('input/2010_08_24/intersections_track_calibrated_jma_from1951_',TrackID,'.csv', sep="")
#  fname_out <- paste('output/2010_08_24/tracks_crossing_regional_polygon_',TrackID,'.csv', sep="")
# For 2012_05_01 trackset
  fname_in <- paste('input/2012_05_01/intersections_track_param_',TrackID,'.csv', sep="")
  fname_out <- paste('output/2012_05_01/tracks_crossing_regional_polygon_',TrackID,'.csv', sep="")
  fname_out2 <- paste('output/2012_05_01/GateID_',TrackID,'.csv', sep="")

#######################################################################
# we read the gate crossing track date
  cat('reading the crosstat output file', fname_in, '\n')
  header <- read.table(fname_in, nrows=1)
  track <- read.table(fname_in, sep=',', skip=1)
  colnames(track) <- c("ID", "day", "month", "year", "hour", "rate", "gate_id", "pres_inter", "vmax_inter")

#  track_id=track[,1]
#  pres_inter=track[,15]

# Function to select maximum surge by stormID 
  ByTrack <- ddply(track, "ID", function(x) x[which.max(x$vmax_inter),])
  ByGate <- count(track, vars="gate_id")

# Write the output file with a single record per storm                     
  cat('Writing the full output file', fname_out, '\n')
  write.table(ByTrack, fname_out, col.names=T, row.names=F, sep = ',')

# Write the output file with a single record per storm                     
   cat('Writing the full output file', fname_out2, '\n')
   write.table(ByGate, fname_out2, col.names=T, row.names=F, sep = ',')
}

My output for the final section of code is a file the groups by GateID and outputs the frequency of occurrence. It looks like this:

gate_id freq
1   935
2   2096
3   1363
4   963
5   167
6   17
7   43
8   62
9   208
10  267
11  64
12  162
13  178
14  632
15  807
16  2003
17  838
18  293

The thing is that I output a file that looks just like this for 96 different input files. Instead of outputting 96 separate files, I'd like to calculate these aggregations per input file, and then sum the frequency across all 96 inputs and print out one SINGLE output file. Can anyone help?

Thanks, K

Answer 1

You are going to need to do something like the function below. This would grab all the .csv files in one directory, so that directory would have to have only the files you want to analyze in it.

myFun <- function(out.file = "mydata") {
files <- list.files(pattern = "\\.(csv|CSV)$")
# Use this next line if you are going use the file name as a variable/output etc
files.noext <- substr(basename(files), 1, nchar(basename(files)) - 4)

for (i in 1:length(files)) {
    temp <- read.csv(files[i], header = FALSE)
    # YOUR CODE HERE
    # Use the code you have already written but operate on files[i] or temp
    # Save the important stuff into one data frame that grows
    # Think carefully ahead of time what structure makes the  most sense
    }

datafile <- paste(out.file, ".csv", sep = "")
write.csv(yourDataFrame, file = datafile)
}