Phandango fix

ariba/summary.py

@@ -233,17 +233,22 @@ def _write_phandango_csv(cls, rows, outfile):
         # columns the same, and then all variant columns the same
         header_line = ['name']
         var_regex = re.compile('^.*;var\.[np.]\.\S+$')
+        var_columns = []
 
-        for heading in rows[0][1:]:
-            if var_regex.search(heading) is None:
-                header_line.append(heading + ':z1')
-            else:
-                header_line.append(heading + ':z2')
+        for i in range(1, len(rows[0]), 1):
+            heading = rows[0][i]
+            if var_regex.search(heading) is not None:
+                var_columns.append(i)
+
+            header_line.append(heading + ':o1')
 
         f = pyfastaq.utils.open_file_write(outfile)
         print(*header_line, sep=',', file=f)
         for row in rows[1:]:
-            print(*row, sep=',', file=f)
+            to_print = list(row)
+            for i in var_columns:
+                to_print[i] *= 3
+            print(*to_print, sep=',', file=f)
         pyfastaq.utils.close(f)
 
 

ariba/tasks/summary.py

@@ -7,7 +7,7 @@ def run():
         usage = 'ariba summary [options] <outfile> [report1.tsv report2.tsv ...]',
         epilog = 'Files must be listed after the output file and/or the option --fofn must be used. If both used, all files in the filename specified by --fofn AND the files listed after the output file will be used as input. The input report files must be in tsv format, not xls.')
     parser.add_argument('-f', '--fofn', help='File of filenames of ariba reports in tsv format (not xls) to be summarised. Must be used if no input files listed after the outfile.', metavar='FILENAME')
-    parser.add_argument('--phandango', help='Write files that can be used as input to phandango, named with the given prefix. Writes a tree and csv file, which can be drag and dropped straight into JS Candy', metavar='files_prefix')
+    parser.add_argument('--phandango', help='Write files that can be used as input to phandango, named with the given prefix. Writes a tree and csv file, which can be drag and dropped straight into phandango', metavar='files_prefix')
     parser.add_argument('--min_id', type=float, help='Minimum percent identity cutoff to count as assembled [%(default)s]', default=90, metavar='FLOAT')
     parser.add_argument('--no_filter', action='store_true', help='Do not filter rows or columns of output that are all 0 (by default, they are removed from the output)')
     parser.add_argument('outfile', help='Name of output file. If file ends with ".xls", then an excel spreadsheet is written. Otherwise a tsv file is written')

ariba/tests/data/summary_test_write_phandango_csv.csv

@@ -1,5 +1,5 @@
-name,seq1:z1,seq1;var.p.I14L:z2,seq1;var.p.P42Q:z2,seq2:z1,seq2;var.n.A14T:z2
-file1,3,0,1,3,1
-file2,3,1,0,3,0
+name,seq1:o1,seq1;var.p.I14L:o1,seq1;var.p.P42Q:o1,seq2:o1,seq2;var.n.A14T:o1
+file1,3,0,3,3,3
+file2,3,3,0,3,0
 file3,1,0,0,3,0
-file4,2,1,0,0,0
+file4,2,3,0,0,0

ariba/tests/data/summary_test_write_phandango_files.csv

@@ -1,5 +1,5 @@
-name,seq1:z1,seq1;var.p.I14L:z2,seq1;var.p.P42Q:z2,seq2:z1,seq2;var.n.A14T:z2
-file1,3,0,1,3,1
-file2,3,1,0,3,0
+name,seq1:o1,seq1;var.p.I14L:o1,seq1;var.p.P42Q:o1,seq2:o1,seq2;var.n.A14T:o1
+file1,3,0,3,3,3
+file2,3,3,0,3,0
 file3,1,0,0,3,0
-file4,2,1,0,0,0
+file4,2,3,0,0,0