# HG changeset patch # User ethevenot # Date 1519814864 18000 # Node ID 9590fac86f633c9d74c0291a3b9713722a4c7a46 # Parent 80a38d36f9466197f54559ee2645a860a2914dca planemo upload for repository https://github.com/workflow4metabolomics/checkformat.git commit 46e92656192f2714265cc525b283c7cbb87b9093 diff -r 80a38d36f946 -r 9590fac86f63 checkformat_config.xml --- a/checkformat_config.xml Thu Jan 11 10:24:56 2018 -0500 +++ b/checkformat_config.xml Wed Feb 28 05:47:44 2018 -0500 @@ -2,7 +2,7 @@ Checking/formatting the sample and variable names of the dataMatrix, sampleMetadata, and variableMetadata files - r-batch + r-batch diff -r 80a38d36f946 -r 9590fac86f63 checkformat_script.R --- a/checkformat_script.R Thu Jan 11 10:24:56 2018 -0500 +++ b/checkformat_script.R Wed Feb 28 05:47:44 2018 -0500 @@ -82,20 +82,24 @@ if(nrow(datMN) != nrow(samDF)) { if(nrow(datMN) > nrow(samDF)) { print(setdiff(rownames(datMN), rownames(samDF))) - stop("The sample names above from dataMatrix were not found in sampleMetadata") + stop("The sample names above from dataMatrix were not found in sampleMetadata", + call. = FALSE) } else { print(setdiff(rownames(samDF), rownames(datMN))) - stop("The sample names above from sampleMetadata were not found in dataMatrix") + stop("The sample names above from sampleMetadata were not found in dataMatrix", + call. = FALSE) } } if(ncol(datMN) != nrow(varDF)) { if(ncol(datMN) > nrow(varDF)) { print(setdiff(colnames(datMN), rownames(varDF))) - stop("The variable names above from dataMatrix were not found in variableMetadata") + stop("The variable names above from dataMatrix were not found in variableMetadata", + call. = FALSE) } else { print(setdiff(rownames(varDF), colnames(datMN))) - stop("The variable names above from variableMetadata were not found in dataMatrix") + stop("The variable names above from variableMetadata were not found in dataMatrix", + call. = FALSE) } } @@ -181,191 +185,3 @@ } ## end of checkAndReadF - - - - ## if(!identical(rownames(datMN), rownames(samDF))) { - ## ## checking sample names - - ## chkL <- FALSE - - ## datSamDifVc <- setdiff(rownames(datMN), rownames(samDF)) - - ## if(length(datSamDifVc)) { - ## cat("\nThe following samples were found in the dataMatrix column names but not in the sampleMetadata row names:\n", sep="") - ## print(cbind.data.frame(col = as.numeric(sapply(datSamDifVc, function(samC) which(rownames(datMN) == samC))), - ## name = datSamDifVc)) - ## } - - ## samDatDifVc <- setdiff(rownames(samDF), rownames(datMN)) - - ## if(length(samDatDifVc)) { - ## cat("\n\nThe following samples were found in the sampleMetadata row names but not in the dataMatrix column names:\n", sep="") - ## print(cbind.data.frame(row = as.numeric(sapply(samDatDifVc, function(samC) which(rownames(samDF) == samC))), - ## name = samDatDifVc)) - ## } - - ## if(nrow(datMN) != nrow(samDF)) { - ## cat("\n\nThe dataMatrix has ", nrow(datMN), " columns (ie samples) whereas the sampleMetadata has ", nrow(samDF), " rows\n", sep="") - ## } else if(identical(gsub("^X", "", rownames(datMN)), rownames(samDF))) { - ## cat("\n\nThe dataMatrix column names start with an 'X' but not the sampleMetadata row names\n", sep="") - ## } else if(identical(gsub("^X", "", rownames(samDF)), rownames(datMN))) { - ## cat("\n\nThe sampleMetadata row names start with an 'X' but not the dataMatrix column names\n", sep="") - ## } else if(identical(sort(rownames(datMN)), sort(rownames(samDF)))) { - ## cat("\n\nThe dataMatrix column names and the sampleMetadata row names are not in the same order:\n", sep="") - ## print(cbind.data.frame(indice = 1:nrow(datMN), - ## dataMatrix_columnnames=rownames(datMN), - ## sampleMetadata_rownames=rownames(samDF))[rownames(datMN) != rownames(samDF), , drop = FALSE]) - ## } else { - ## cat("\n\nThe dataMatrix column names and the sampleMetadata row names are not identical:\n", sep="") - ## print(cbind.data.frame(indice = 1:nrow(datMN), - ## dataMatrix_columnnames=rownames(datMN), - ## sampleMetadata_rownames=rownames(samDF))[rownames(datMN) != rownames(samDF), , drop = FALSE]) - ## } - - ## } - ## datRowVc <- rownames(datMN) - ## datRowMakVc <- make.names(datRowVc, unique = TRUE) - ## if(datRowMakVc != datRowVc) { - ## rownames(datMN) <- datRowMakVc - ## cat("\n\nMessage: The sample names of the dataMatrix have been converted to the standard R format\n") - ## } - - ## datColVc <- colnames(datMN) - ## datColMakVc <- make.names(datColVc, unique = TRUE) - ## if(datColMakVc != datColVc) { - ## colnames(datMN) <- datColMakVc - ## cat("\n\nMessage: The variable names of the dataMatrix have been converted to the standard R format\n") - ## } - - ## samRowVc <- rownames(datMN) - ## samRowMakVc <- make.names(samRowVc, unique = TRUE) - ## if(samRowMakVc != samRowVc) { - ## rownames(datMN) <- samRowMakVc - ## cat("\n\nMessage: The sample names of the sampleMetadata have been converted to the standard R format\n") - ## } - - ## datRowVc <- rownames(datMN) - ## datRowMakVc <- make.names(datRowVc, unique = TRUE) - ## if(datRowMakVc != datRowVc) { - ## rownames(datMN) <- datRowMakVc - ## cat("\n\nMessage: The sample names of the dataMatrix have been converted to the standard R format\n") - ## } - - ## } - - ## checking names (optional) - - - - - ## datRowMakVc <- make.names(datRowVc, unique = TRUE) - ## if(datRowMakVc != datRowVc) { - ## if(makNamL) { - ## rownames(datMN) <- datRowMakVc - ## cat("\n\nMessage: The sample names of the dataMatrix have been converted to the standard R format; select the make names argument to convert them\n") - ## } else { - ## cat("\n\nWarning: Some of the sample names of the dataMatrix are not in the standard R format; select the make names argument to convert them\n") - ## } - - ## if(makNamL) { - - ## rownames(datMN) <- make.names(rownames(datMN), unique = TRUE) - ## colnames(datMN) <- make.names(colnames(datMN), unique = TRUE) - ## rownames(samDF) <- make.names(rownames(samDF), unique = TRUE) - ## rownames(varDF) <- make.names(rownames(varDF), unique = TRUE) - - ## } - ## checking sample names - - ## if(nrow(datMN) == nrow(samDF)) { - - - - ## } - - ## chkL <- FALSE - - ## datSamDifVc <- setdiff(rownames(datMN), rownames(samDF)) - - ## if(length(datSamDifVc)) { - ## cat("\nThe following samples were found in the dataMatrix column names but not in the sampleMetadata row names:\n", sep="") - ## print(cbind.data.frame(col = as.numeric(sapply(datSamDifVc, function(samC) which(rownames(datMN) == samC))), - ## name = datSamDifVc)) - ## } - - ## samDatDifVc <- setdiff(rownames(samDF), rownames(datMN)) - - ## if(length(samDatDifVc)) { - ## cat("\n\nThe following samples were found in the sampleMetadata row names but not in the dataMatrix column names:\n", sep="") - ## print(cbind.data.frame(row = as.numeric(sapply(samDatDifVc, function(samC) which(rownames(samDF) == samC))), - ## name = samDatDifVc)) - ## } - - ## if(nrow(datMN) != nrow(samDF)) { - ## cat("\n\nThe dataMatrix has ", nrow(datMN), " columns (ie samples) whereas the sampleMetadata has ", nrow(samDF), " rows\n", sep="") - ## } else if(identical(gsub("^X", "", rownames(datMN)), rownames(samDF))) { - ## cat("\n\nThe dataMatrix column names start with an 'X' but not the sampleMetadata row names\n", sep="") - ## } else if(identical(gsub("^X", "", rownames(samDF)), rownames(datMN))) { - ## cat("\n\nThe sampleMetadata row names start with an 'X' but not the dataMatrix column names\n", sep="") - ## } else if(identical(sort(rownames(datMN)), sort(rownames(samDF)))) { - ## cat("\n\nThe dataMatrix column names and the sampleMetadata row names are not in the same order:\n", sep="") - ## print(cbind.data.frame(indice = 1:nrow(datMN), - ## dataMatrix_columnnames=rownames(datMN), - ## sampleMetadata_rownames=rownames(samDF))[rownames(datMN) != rownames(samDF), , drop = FALSE]) - ## } else { - ## cat("\n\nThe dataMatrix column names and the sampleMetadata row names are not identical:\n", sep="") - ## print(cbind.data.frame(indice = 1:nrow(datMN), - ## dataMatrix_columnnames=rownames(datMN), - ## sampleMetadata_rownames=rownames(samDF))[rownames(datMN) != rownames(samDF), , drop = FALSE]) - ## } - - ## } - - - ## if(!identical(colnames(datMN), rownames(varDF))) { - ## ## checking variable names - - ## chkL <- FALSE - - ## datVarDifVc <- setdiff(colnames(datMN), rownames(varDF)) - - ## if(length(datVarDifVc)) { - ## cat("\nThe following variables were found in the dataMatrix row names but not in the variableMetadata row names:\n", sep="") - ## print(cbind.data.frame(row = as.numeric(sapply(datVarDifVc, function(varC) which(colnames(datMN) == varC))), - ## name = datVarDifVc)) - - ## } - - ## varDatDifVc <- setdiff(rownames(varDF), colnames(datMN)) - - ## if(length(varDatDifVc)) { - ## cat("\n\nThe following variables were found in the variableMetadata row names but not in the dataMatrix row names:\n", sep="") - ## print(cbind.data.frame(row = as.numeric(sapply(varDatDifVc, function(varC) which(rownames(varDF) == varC))), - ## name = varDatDifVc)) - ## } - - ## if(ncol(datMN) != nrow(varDF)) { - ## cat("\n\nThe dataMatrix has ", nrow(datMN), " rows (ie variables) whereas the variableMetadata has ", nrow(varDF), " rows\n", sep="") - ## } else if(identical(sort(colnames(datMN)), sort(rownames(varDF)))) { - ## cat("\n\nThe dataMatrix row names and the variableMetadata row names are not in the same order:\n", sep="") - ## print(cbind.data.frame(row = 1:ncol(datMN), - ## dataMatrix_rownames=colnames(datMN), - ## variableMetadata_rownames=rownames(varDF))[colnames(datMN) != rownames(varDF), , drop = FALSE]) - ## } else { - ## cat("\n\nThe dataMatrix row names and the variableMetadata row names are not identical:\n", sep="") - ## print(cbind.data.frame(row = 1:ncol(datMN), - ## dataMatrix_rownames=colnames(datMN), - ## variableMetadata_rownames=rownames(varDF))[colnames(datMN) != rownames(varDF), , drop = FALSE]) - ## } - ## } -## checkF <- function(datInpMN, -## samInpDF, -## varInpDF) { - -## mode(datInpMN) == "numeric" && -## identical(rownames(datInpMN), rownames(samInpDF)) && -## identical(colnames(datInpMN), rownames(varInpDF)) - - -## }