Mercurial > repos > davidvanzessen > shm_csr
comparison baseline/script_xlsx.py @ 83:729738462297 draft
"planemo upload commit c0ffc68aec5836d5b20b543106493056a87edf57"
| author | rhpvorderman |
|---|---|
| date | Wed, 15 Sep 2021 12:24:06 +0000 |
| parents | c33d93683a09 |
| children |
comparison
equal
deleted
inserted
replaced
| 82:a103134ee6e0 | 83:729738462297 |
|---|---|
| 32 currentId = "" | 32 currentId = "" |
| 33 with xlrd.open_workbook(args.input, 'r') as wb: | 33 with xlrd.open_workbook(args.input, 'r') as wb: |
| 34 with open(args.output, 'a') as o: | 34 with open(args.output, 'a') as o: |
| 35 for sheet in wb.sheets(): | 35 for sheet in wb.sheets(): |
| 36 if sheet.cell(1,gene_column).value.find("IGHV") < 0: | 36 if sheet.cell(1,gene_column).value.find("IGHV") < 0: |
| 37 print "Genes not in column " + LETTERS[gene_column] + ", skipping sheet " + sheet.name | 37 print("Genes not in column " + LETTERS[gene_column] + ", skipping sheet " + sheet.name) |
| 38 continue | 38 continue |
| 39 o.write(">>>" + sheet.name + "\n") | 39 o.write(">>>" + sheet.name + "\n") |
| 40 outputdic = dict() | 40 outputdic = dict() |
| 41 for rowindex in range(1, sheet.nrows): | 41 for rowindex in range(1, sheet.nrows): |
| 42 ref = sheet.cell(rowindex, gene_column).value.replace(">", "") | 42 ref = sheet.cell(rowindex, gene_column).value.replace(">", "") |
| 44 outputdic[ref] += [(sheet.cell(rowindex, id_column).value.replace(">", ""), sheet.cell(rowindex, seq_column).value)] | 44 outputdic[ref] += [(sheet.cell(rowindex, id_column).value.replace(">", ""), sheet.cell(rowindex, seq_column).value)] |
| 45 else: | 45 else: |
| 46 outputdic[ref] = [(sheet.cell(rowindex, id_column).value.replace(">", ""), sheet.cell(rowindex, seq_column).value)] | 46 outputdic[ref] = [(sheet.cell(rowindex, id_column).value.replace(">", ""), sheet.cell(rowindex, seq_column).value)] |
| 47 #print outputdic | 47 #print outputdic |
| 48 | 48 |
| 49 for k in outputdic.keys(): | 49 for k in list(outputdic.keys()): |
| 50 if k in refdic: | 50 if k in refdic: |
| 51 o.write(">>" + k + "\n") | 51 o.write(">>" + k + "\n") |
| 52 o.write(refdic[k] + "\n") | 52 o.write(refdic[k] + "\n") |
| 53 for seq in outputdic[k]: | 53 for seq in outputdic[k]: |
| 54 #print seq | 54 #print seq |
| 55 o.write(">" + seq[0] + "\n") | 55 o.write(">" + seq[0] + "\n") |
| 56 o.write(seq[1] + "\n") | 56 o.write(seq[1] + "\n") |
| 57 else: | 57 else: |
| 58 print k + " not in reference, skipping " + k | 58 print(k + " not in reference, skipping " + k) |
