comparison mergeXenaMutation.py @ 20:914bc8ee6222

Debugged the merge mutation data tool

19:371579dd9bc6

    if i not in requiredColsPos:
      columnDic [data[i]]=i

  return columnDic

def summarizeColumns(infiles, fileColumn, allCols, ferror):
  for infile in inFiles:
    columnDic = header (infile, ferror)
    fileColumn [infile] = columnDic
    for col in columnDic:
      if col not in allCols:

  if len(sys.argv[:]) <6:
    print "python mergeMultipleXenaMutation.py outputXenaMutation outputPhenotypeMatrix errorLog inputfile(s)"
    print "this is merging data A+B=C for mutation by position type of data\n"
    sys.exit(1)

    #
    # The input files to this script are two or more matrices, in which
    # columns represent samples and rows represent genes or measurements.
    # There are two output files: outMergedData contains the input data merged
    # into a single matrix, and outSourceMatrix is a two-column matrix
    # indicating which file each sample (or column label) came from.  This
    # assumes that each sample came from at most one file.
    #
    parser = argparse.ArgumentParser()
    parser.add_argument("inFileA", type=str, help="First input file")
    parser.add_argument("inFileB", type=str, help="Second input file")
    parser.add_argument("outMergedData", type=str,
                        help="Filename for the merged dataset")
    parser.add_argument("outSourceMatrix", type=str,
                        help="""Filename for a Nx2 matrix that indicates
                                the source file of each column""")
    parser.add_argument("errorLog", type=str,
                        help="""Error log""")
    parser.add_argument("--aLabel", type=str, default=None,
                        help="User-friendly label for the first input file")
    parser.add_argument("--bLabel", type=str, default=None,
                        help="User-friendly label for the second input file")
    args = parser.parse_args()

                                    
    #inFiles = sys.argv[4:]
    print inFiles
    errofile = args.errorLog
    outfile = args.outMergedData
    print outfile
    outPhenotypeFile = args.outSourceMatrix
    print outPhenotypeFile
    
    ferror = open(errofile,'w')
    
    #get all the columns, build fileColumn dictionary
    fileColumn={}
    allCols =[]
    summarizeColumns(inFiles, fileColumn, allCols, ferror)
    ferror.close()

    #output header line
    fout = open(outfile,'w')
    outputHeader (requiredCOLs,allCols,fout)

    #process and output combined mutationXena file
    fout = open(outfile,'a')

    columnDic = fileColumn[args.inFileA]
    processAndOutput(args.inFileA,requiredCOLs,allCols,columnDic,fout)
    columnDic = fileColumn[args.inFileB]
    processAndOutput(args.inFileB,requiredCOLs,allCols,columnDic,fout)
    fout.close()

    #collect sample from source information
    sampleDic ={}
    if args.aLabel is None:
      collectSource(args.inFileA, args.inFileA, sampleDic)
    else:
      collectSource(args.inFileA, args.aLabel, sampleDic
    if args.bLabel is None:
      collectSource(args.inFileB, args.inFileB, sampleDic)
    else:
      collectSource(args.inFileB, args.bLabel, sampleDic


    #output sample source information as phenotype matrix
    outputSampleDic (sampleDic, outPhenotypeFile)

20:914bc8ee6222

    if i not in requiredColsPos:
      columnDic [data[i]]=i

  return columnDic

def summarizeColumns(inFiles, fileColumn, allCols, ferror):
  for infile in inFiles:
    columnDic = header (infile, ferror)
    fileColumn [infile] = columnDic
    for col in columnDic:
      if col not in allCols:

  if len(sys.argv[:]) <6:
    print "python mergeMultipleXenaMutation.py outputXenaMutation outputPhenotypeMatrix errorLog inputfile(s)"
    print "this is merging data A+B=C for mutation by position type of data\n"
    sys.exit(1)

  #
  # The input files to this script are two or more matrices, in which
  # columns represent samples and rows represent genes or measurements.
  # There are two output files: outMergedData contains the input data merged
  # into a single matrix, and outSourceMatrix is a two-column matrix
  # indicating which file each sample (or column label) came from.  This
  # assumes that each sample came from at most one file.
  #
  parser = argparse.ArgumentParser()
  parser.add_argument("outMergedData", type=str,
                      help="Filename for the merged dataset")
  parser.add_argument("outSourceMatrix", type=str,
                      help="""Filename for a Nx2 matrix that indicates
                                the source file of each column""")
  parser.add_argument("errorLog", type=str,
                      help="""Error log""")
  parser.add_argument("inFileA", type=str, help="First input file")
  parser.add_argument("inFileB", type=str, help="Second input file")
  parser.add_argument("--aLabel", type=str, default=None,
                      help="User-friendly label for the first input file")
  parser.add_argument("--bLabel", type=str, default=None,
                      help="User-friendly label for the second input file")
  args = parser.parse_args()

                                    
  #inFiles = sys.argv[4:]
  inFiles = list()
  inFiles.append(args.inFileA)
  inFiles.append(args.inFileB)
  errofile = args.errorLog
  outfile = args.outMergedData
  #print outfile
  outPhenotypeFile = args.outSourceMatrix
  #print outPhenotypeFile
    
  ferror = open(errofile,'w')
    
  #get all the columns, build fileColumn dictionary
  fileColumn={}
  allCols =[]
  summarizeColumns(inFiles, fileColumn, allCols, ferror)
  ferror.close()

  #output header line
  fout = open(outfile,'w')
  outputHeader (requiredCOLs,allCols,fout)
  
  #process and output combined mutationXena file
  fout = open(outfile,'a')

  columnDic = fileColumn[args.inFileA]
  processAndOutput(args.inFileA,requiredCOLs,allCols,columnDic,fout)
  columnDic = fileColumn[args.inFileB]
  processAndOutput(args.inFileB,requiredCOLs,allCols,columnDic,fout)
  fout.close()
  
  #collect sample from source information
  sampleDic ={}
  if args.aLabel is None:
    collectSource(args.inFileA, args.inFileA, sampleDic)
  else:
    collectSource(args.inFileA, args.aLabel, sampleDic)
  if args.bLabel is None:
    collectSource(args.inFileB, args.inFileB, sampleDic)
  else:
    collectSource(args.inFileB, args.bLabel, sampleDic)


  #output sample source information as phenotype matrix
  outputSampleDic (sampleDic, outPhenotypeFile)