Read file tps and split data

Function to read tps file:

read.tps = function(data) {
      a = readLines(data)
      LM = grep("LM", a)
      ID.ind = grep("ID", a)  
      images = basename(gsub("(IMAGE=)(.*)", "\\2", a[ID.ind - 1]))

      skip = LM
      nrows = as.numeric(gsub("(LM=)([0-9])", "\\2", grep("LM", a, value=T)))
      l = length(LM)

      landmarks = vector("list", l)

      for (i in 1:l) {
        landmarks[i] = list(data.frame(
            read.table(file=data, header=F, skip=LM[i],
                       nrows=nrows[i], col.names=c("X", "Y")),
            IMAGE = images[i],
            ID = read.table(file=data, header=F, skip=ID.ind[i]-1, 
                            nrows=1, sep="=", col.names="ID")[2,],
            Scale = read.table(file=data, header=F, skip=ID.ind[i],
                                nrows=1, sep="=")[,2]))
      }
      do.call(rbind, landmarks)
  }

Try with a sample tps file from the dataset:

setwd("C:/Users/Admin/Documents/Intern/Intern")
X = read.tps("sample.TPS")
head(X)

##      X   Y                     IMAGE ID    Scale
## 1 1158 816 F_ST03_06.22.11_LT_01.tif 0  0.001562
## 2 1463 753 F_ST03_06.22.11_LT_01.tif 0  0.001562
## 3 1583 669 F_ST03_06.22.11_LT_01.tif 0  0.001562
## 4 1636 606 F_ST03_06.22.11_LT_01.tif 0  0.001562
## 5 1655 544 F_ST03_06.22.11_LT_01.tif 0  0.001562
## 6 1593 474 F_ST03_06.22.11_LT_01.tif 0  0.001562

A sample file contains 16 coordinates of many sand fly’s right wings,hence, split them into each csv with respect to each wing: 1. Test to split a csv file:

  data1 <- sample(X[1:16,])
  write.csv(data1,file="1.csv")

Each file .csv will contain the landmark coordinates of a wing.

  Y = read.csv("1.csv")
  print(Y)

##    X.1    Scale ID   Y    X                     IMAGE
## 1    1 0.001562  0 816 1158 F_ST03_06.22.11_LT_01.tif
## 2    2 0.001562  0 753 1463 F_ST03_06.22.11_LT_01.tif
## 3    3 0.001562  0 669 1583 F_ST03_06.22.11_LT_01.tif
## 4    4 0.001562  0 606 1636 F_ST03_06.22.11_LT_01.tif
## 5    5 0.001562  0 544 1655 F_ST03_06.22.11_LT_01.tif
## 6    6 0.001562  0 474 1593 F_ST03_06.22.11_LT_01.tif
## 7    7 0.001562  0 403 1470 F_ST03_06.22.11_LT_01.tif
## 8    8 0.001562  0 344 1299 F_ST03_06.22.11_LT_01.tif
## 9    9 0.001562  0 303 1144 F_ST03_06.22.11_LT_01.tif
## 10  10 0.001562  0 517  848 F_ST03_06.22.11_LT_01.tif
## 11  11 0.001562  0 665  807 F_ST03_06.22.11_LT_01.tif
## 12  12 0.001562  0 722 1035 F_ST03_06.22.11_LT_01.tif
## 13  13 0.001562  0 573  504 F_ST03_06.22.11_LT_01.tif
## 14  14 0.001562  0 602  545 F_ST03_06.22.11_LT_01.tif
## 15  15 0.001562  0 631  541 F_ST03_06.22.11_LT_01.tif
## 16  16 0.001562  0 708  470 F_ST03_06.22.11_LT_01.tif

To get all the data seperated, use loop function:

  check = 0
  checkpoint = 1
  for( i in 1:nrow(X)){
    if ((i %% 16) == 0){
      # print(i)
      check = check +1
      temp <- sample(X[checkpoint:i,])
      # print(temp)
      write.csv(temp,file <- paste(toString(check),".csv"))
      temp <- data.frame(matrix(ncol = 5,nrow = 16))
      checkpoint = i+1
    }
  }

374 files.csv are extracted from sample. Each file contains 16 landmark coordinates of a wing.

Read file tps and split data

Hong Hanh

April 7, 2017