save state: wrong idea for indices repartition

[epclust.git] / epclust / tests / testthat / test.de_serialize.R

diff --git a/epclust/tests/testthat/test.de_serialize.R b/epclust/tests/testthat/test.de_serialize.R
index 27e6d59..25f2c2b 100644 (file)
--- a/epclust/tests/testthat/test.de_serialize.R
+++ b/epclust/tests/testthat/test.de_serialize.R
@@ -1,65 +1,95 @@
 context("de_serialize")
 
-data_bin_file <<- "/tmp/epclust_test.bin"
-unlink(data_bin_file)
-
 test_that("serialization + getDataInFile retrieve original data / from matrix",
 {
-       #dataset 200 lignes / 30 columns
-       data_ascii = matrix(runif(200*30,-10,10),ncol=30)
+       data_bin_file = ".epclust_test_m.bin"
+       unlink(data_bin_file)
+
+       #dataset 200 cols / 30 rows
+       data_ascii = matrix(runif(200*30,-10,10),nrow=30)
        nbytes = 4 #lead to a precision of 1e-7 / 1e-8
        endian = "little"
 
        #Simulate serialization in one single call
-       serialize(data_ascii, data_bin_file, 500, ",", nbytes, endian)
+       binarize(data_ascii, data_bin_file, 500, ",", nbytes, endian)
        expect_equal(file.info(data_bin_file)$size, length(data_ascii)*nbytes+8)
        for (indices in list(c(1,3,5), 3:13, c(5,20,50), c(75,130:135), 196:200))
        {
                data_lines = getDataInFile(indices, data_bin_file, nbytes, endian)
-               expect_equal(data_lines, data_ascii[indices,], tolerance=1e-6)
+               expect_equal(data_lines, data_ascii[,indices], tolerance=1e-6)
        }
        unlink(data_bin_file)
 
        #...in several calls (last call complete, next call NULL)
        for (i in 1:20)
-               serialize(data_ascii[((i-1)*10+1):(i*10),], data_bin_file, 20, ",", nbytes, endian)
+               binarize(data_ascii[((i-1)*10+1):(i*10),], data_bin_file, 20, ",", nbytes, endian)
        expect_equal(file.info(data_bin_file)$size, length(data_ascii)*nbytes+8)
        for (indices in list(c(1,3,5), 3:13, c(5,20,50), c(75,130:135), 196:200))
        {
                data_lines = getDataInFile(indices, data_bin_file, nbytes, endian)
-               expect_equal(data_lines, data_ascii[indices,], tolerance=1e-6)
+               expect_equal(data_lines, data_ascii[,indices], tolerance=1e-6)
        }
        unlink(data_bin_file)
 })
 
+test_that("serialization + transform + getDataInFile retrieve original transforms",
+{
+       data_bin_file = ".epclust_test_t.bin"
+       unlink(data_bin_file)
+
+       #dataset 200 cols / 30 rows
+       data_ascii = matrix(runif(200*30,-10,10),nrow=30)
+       nbytes = 8
+       endian = "little"
+
+       binarize(data_ascii, data_bin_file, 500, ",", nbytes, endian)
+       # Serialize transformation (just compute range) into a new binary file
+       trans_bin_file = ".epclust_test_t_trans.bin"
+       unlink(trans_bin_file)
+       getSeries = function(inds) getDataInFile(inds, data_bin_file, nbytes, endian)
+       binarizeTransform(getSeries, function(series) apply(series, 2, range),
+               trans_bin_file, 250, nbytes, endian)
+       unlink(data_bin_file)
+       expect_equal(file.info(trans_bin_file)$size, 2*nrow(data_ascii)*nbytes+8)
+       for (indices in list(c(1,3,5), 3:13, c(5,20,50), c(75,130:135), 196:200))
+       {
+               trans_cols = getDataInFile(indices, trans_bin_file, nbytes, endian)
+               expect_equal(trans_cols, apply(data_ascii[indices,],2,range), tolerance=1e-6)
+       }
+       unlink(trans_bin_file)
+})
+
 test_that("serialization + getDataInFile retrieve original data / from connection",
 {
-       #dataset 300 lignes / 50 columns
+       data_bin_file = ".epclust_test_c.bin"
+       unlink(data_bin_file)
+
+       #dataset 300 cols / 50 rows
        data_csv = system.file("testdata","de_serialize.csv",package="epclust")
        nbytes = 8
        endian = "big"
-       data_ascii = as.matrix(read.csv(test_series, sep=";", header=FALSE)) #for ref
+       data_ascii = as.matrix(read.csv(data_csv, sep=";", header=FALSE)) #for ref
 
        #Simulate serialization in one single call
-       serialize(data_csv, data_bin_file, 350, ";", nbytes, endian)
+       binarize(data_csv, data_bin_file, 350, ";", nbytes, endian)
        expect_equal(file.info(data_bin_file)$size, 300*50*8+8)
        for (indices in list(c(1,3,5), 3:13, c(5,20,50), c(75,130:135), 196:200))
        {
                #HACK: as.matrix(as.data.frame( )) required to match (ref) data structure
-               data_lines = as.matrix(as.data.frame( getDataInFile(indices,data_bin_file,nbytes,endian) ))
-               expect_equal(data_lines, data_ascii[indices,])
+               data_cols = as.matrix(as.data.frame( getDataInFile(indices,data_bin_file,nbytes,endian) ))
+               expect_equal(data_cols, data_ascii[,indices])
        }
        unlink(data_bin_file)
 
        #...in several calls / chunks of 29 --> 29*10 + 10, incomplete last
        data_con = file(data_csv, "r")
-       serialize(data_con, data_bin_file, 29, ";", nbytes, endian)
+       binarize(data_con, data_bin_file, 29, ";", nbytes, endian)
        expect_equal(file.info(data_bin_file)$size, 300*50*8+8)
        for (indices in list(c(1,3,5), 3:13, c(5,20,50), c(75,130:135), 196:200))
        {
-               data_lines = as.matrix(as.data.frame( getDataInFile(indices,data_bin_file,nbytes,endian) ))
-               expect_equal(data_lines, data_ascii[indices,])
+               data_cols = as.matrix(as.data.frame( getDataInFile(indices,data_bin_file,nbytes,endian) ))
+               expect_equal(data_cols, data_ascii[,indices])
        }
        unlink(data_bin_file)
-       #close(data_con) --> done in serialize()
+       #close(data_con) --> done in binarize()
 })