X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2Ftests%2Ftestthat%2Ftest.de_serialize.R;h=be49020e03b93f5fab51daa13170e64c6124b22e;hb=0486fbadb122cb4d78c5d9f248c29800a59eb24e;hp=8403e6d1273597277513364fe8d524133a43f763;hpb=492cd9e74a79cbcc0ecde55fa3071a44b7e463dc;p=epclust.git diff --git a/epclust/tests/testthat/test.de_serialize.R b/epclust/tests/testthat/test.de_serialize.R index 8403e6d..be49020 100644 --- a/epclust/tests/testthat/test.de_serialize.R +++ b/epclust/tests/testthat/test.de_serialize.R @@ -2,11 +2,11 @@ context("de_serialize") test_that("serialization + getDataInFile retrieve original data / from matrix", { - data_bin_file = "/tmp/epclust_test_m.bin" + data_bin_file = ".epclust_test_m.bin" unlink(data_bin_file) - #dataset 200 lignes / 30 columns - data_ascii = matrix(runif(200*30,-10,10),ncol=30) + #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" @@ -16,68 +16,69 @@ test_that("serialization + getDataInFile retrieve original data / from matrix", 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) - binarize(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)$size, length(data_ascii)*nbytes+8) for (indices in list(c(1,3,5), 3:13, c(5,20,50), c(75,130:135), 196:200)) { data_lines = getDataInFile(indices, data_bin_file, nbytes, endian) - expect_equal(data_lines, data_ascii[indices,], tolerance=1e-6) + expect_equal(data_lines, data_ascii[,indices], tolerance=1e-6) } unlink(data_bin_file) }) test_that("serialization + transform + getDataInFile retrieve original transforms", { - data_bin_file = "/tmp/epclust_test_t.bin" + data_bin_file = ".epclust_test_t.bin" unlink(data_bin_file) - #dataset 200 lignes / 30 columns - data_ascii = matrix(runif(200*30,-10,10),ncol=30) + #dataset 200 cols / 30 rows + data_ascii = matrix(runif(200*30,-10,10),nrow=30) nbytes = 8 endian = "little" binarize(data_ascii, data_bin_file, 500, ",", nbytes, endian) # Serialize transformation (just compute range) into a new binary file - trans_bin_file = "/tmp/epclust_test_t_trans.bin" + trans_bin_file = ".epclust_test_t_trans.bin" unlink(trans_bin_file) getSeries = function(inds) getDataInFile(inds, data_bin_file, nbytes, endian) - binarizeTransform(getSeries, function(series) t(apply(series, 1, range)), + binarizeTransform(getSeries, function(series) apply(series, 2, range), trans_bin_file, 250, nbytes, endian) unlink(data_bin_file) - expect_equal(file.info(trans_bin_file)$size, 2*nrow(data_ascii)*nbytes+8) + expect_equal(file.info(trans_bin_file)$size, 2*ncol(data_ascii)*nbytes+8) for (indices in list(c(1,3,5), 3:13, c(5,20,50), c(75,130:135), 196:200)) { - trans_lines = getDataInFile(indices, trans_bin_file, nbytes, endian) - expect_equal(trans_lines, t(apply(data_ascii[indices,],1,range)), tolerance=1e-6) + trans_cols = getDataInFile(indices, trans_bin_file, nbytes, endian) + expect_equal(trans_cols, apply(data_ascii[,indices],2,range), tolerance=1e-6) } unlink(trans_bin_file) }) test_that("serialization + getDataInFile retrieve original data / from connection", { - data_bin_file = "/tmp/epclust_test_c.bin" + data_bin_file = ".epclust_test_c.bin" unlink(data_bin_file) - #dataset 300 lignes / 50 columns + #dataset 300 cols / 50 rows data_csv = system.file("testdata","de_serialize.csv",package="epclust") nbytes = 8 endian = "big" - data_ascii = as.matrix(read.csv(data_csv, sep=";", header=FALSE)) #for ref + data_ascii = t( as.matrix(read.table(data_csv, sep=";", header=FALSE)) ) #for ref #Simulate serialization in one single call binarize(data_csv, data_bin_file, 350, ";", nbytes, endian) expect_equal(file.info(data_bin_file)$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 = getDataInFile(indices,data_bin_file,nbytes,endian) + #HACK: rows naming required to match (ref) data structure + rownames(data_cols) <- paste("V",seq_len(nrow(data_ascii)), sep="") + expect_equal(data_cols, data_ascii[,indices]) } unlink(data_bin_file) @@ -87,8 +88,9 @@ test_that("serialization + getDataInFile retrieve original data / from connectio 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 = getDataInFile(indices,data_bin_file,nbytes,endian) + rownames(data_cols) <- paste("V",seq_len(nrow(data_ascii)), sep="") + expect_equal(data_cols, data_ascii[,indices]) } unlink(data_bin_file) #close(data_con) --> done in binarize()