comparison Intchecks/Script_intensity_check.R @ 2:cab3e0dfb566 draft default tip

Uploaded

1:d1133a7c26f9

  
  # Table match check with Rchecklibrary
  table.check <- match3(DM, SM, VM)
  check.err(table.check)

  
  rownames(DM) <- DM[,1]
  var_names <- DM[,1]
  DM <- DM[,-1]
  DM <- data.frame(t(DM))

  stat.list <- strsplit(chosen.stat,",")[[1]]
  
  
  # check class.col, class1 and the number of classes ---------------------------------------------------------
  

    c_class <- as.factor(c_class)
    nb_class <- nlevels(c_class)
    classnames <- levels(c_class)
  
    if((nb_class < 2)&&(test.fold=="Yes")){
      err.1class <- c("\n The column",class.col, "contains only one class, fold calculation could not be executed \n")
      cat(err.1class)  
    }
  
    if((nb_class > (nrow(SM))/3)&&(method == "each_class")){
      class.err <- c("\n There are too many classes, think about reducing the number of classes and excluding those
                    with few samples \n")
      cat(class.err)
    }

  
    if(method == "one_class"){  

  }
    
    
  # Statistics ------------------------------------------------------------------------------------------------
  
  
  ### Initialization
  
  DM <- cbind(c_class,DM)
  

2:cab3e0dfb566

  
  # Table match check with Rchecklibrary
  table.check <- match3(DM, SM, VM)
  check.err(table.check)

  # Transposing the dataMatrix
  rownames(DM) <- DM[,1]
  var_names <- DM[,1]
  DM <- DM[,-1]
  DM <- data.frame(t(DM))
  
  # Re-ordering the dataMatrix to match the sampleMetadata file order
  DM <- merge(x=cbind(1:nrow(SM),SM), y=DM, by.x=2, by.y=0)
  DM <- DM[order(DM[,2]),]
  rownames(DM) <- DM[,1]
  DM <- DM[,-c(1:(ncol(SM)+1))]
  
  
  stat.list <- strsplit(chosen.stat,",")[[1]]
  
  
  # check class.col, class1 and the number of classes ---------------------------------------------------------
  

    c_class <- as.factor(c_class)
    nb_class <- nlevels(c_class)
    classnames <- levels(c_class)
  
    if((nb_class < 2)&&(test.fold=="Yes")){
      err.1class <- c("\n The column",class.col, "contains only one class, fold calculation could not be executed. \n")
      cat(err.1class)  
    }
  
    if((nb_class > (nrow(SM))/3)&&(method == "each_class")){
      class.err <- c("\n There are too many classes, think about reducing the number of classes and excluding those
                    with few samples. \n")
      cat(class.err)
    }

  
    if(method == "one_class"){  

  }
    
    
  # Statistics ------------------------------------------------------------------------------------------------
  
  # Check whether the dataMatrix contains non-numeric values
  if(!(is.numeric(as.matrix(DM)))){
    # findchar definition
    findchar <- function(myval){
      if(is.na(myval)){
        return("ok")
      }else{
        mytest <- as.character(myval)
        if(is.na(as.numeric(mytest[1]))){
          return("char")
        }else{
          return("ok")
        }
      }
    }
    # findchar application
    chardiag <- suppressWarnings(apply(DM,2,vapply,findchar,"character"))
    charlist <- which(chardiag == "char")
    err.stock <- paste("\n- - - - - - - - -\nYour dataMatrix contains",
                       length(charlist),
                       "non-numeric value(s). To help you check your data, please find below a short overview:\n")
    charover <- 1
    while((length(err.stock)<10)&(length(err.stock)<(length(charlist)+1))){
      charex <- paste("variable",colnames(DM)[ceiling(charlist[charover]/nrow(DM))],
                      "- sample",rownames(DM)[charlist[charover]-floor(charlist[charover]/nrow(DM))*nrow(DM)],
                      "~> value:",as.matrix(DM)[charlist[charover]],"\n")
      err.stock <- c(err.stock,charex)
      charover <- charover + 1
    }
    stop(c(err.stock,"The dataMatrix file is supposed to contain only numeric values.\n- - - - - - - - -\n"))
  }
  
  ### Initialization
  
  DM <- cbind(c_class,DM)