ENH: New --description_file option to save column descriptions out to

file. Used in fmrib config

ukbparse/config.py

@@ -133,7 +133,8 @@ CLI_ARGUMENTS              = collections.OrderedDict((
         (('etf',  'time_format'),       {'default' : 'default'}),
         (('nr',   'num_rows'),          {'type'    : int}),
         (('uf',   'unknown_vars_file'), {}),
-        (('imf',  'icd10_map_file'),    {})]),
+        (('imf',  'icd10_map_file'),    {}),
+        (('def',  'description_file'),  {})]),
 
     ('TSV export options', [
         (('ts',  'tsv_sep'),            {'default' : DEFAULT_TSV_SEP}),
@@ -363,6 +364,9 @@ CLI_ARGUMENT_HELP = {
     'icd10_map_file' :
     'Save converted ICD10 code mappings to file',
 
+    'description_file' :
+    'Save descriptions of each column to file',
+
     # TSV export options
     'tsv_sep'    :
     'Column separator string to use in output file (default: "{}")'.format(

ukbparse/configs/fmrib.cfg

@@ -7,6 +7,7 @@ log_file          log.txt
 unknown_vars_file unknowns.tsv
 non_numeric_file  non_numerics.tsv
 icd10_map_file    icd10_codes.tsv
+description_file  descriptions.tsv
 plugin_file       fmrib
 loader            FMRIB_internal_info.txt FMRIBImaging
 date_format       FMRIBImagingDate

ukbparse/main.py

@@ -7,15 +7,15 @@
 """This module contains the ``ukbparse`` entry point. """
 
 
-import multiprocessing as mp
-import                    sys
-import                    shutil
-import                    logging
-import                    fnmatch
-import                    tempfile
-import                    warnings
-import                    datetime
-import                    calendar
+import multiprocessing     as mp
+import                        sys
+import                        shutil
+import                        logging
+import                        fnmatch
+import                        tempfile
+import                        warnings
+import                        datetime
+import                        calendar
 
 import ukbparse
 import ukbparse.util       as util
@@ -115,6 +115,7 @@ def main(argv=None):
                 finaliseColumns(    dtable, args, unknowns, unprocessed)
                 doExport(           dtable, args)
                 doICD10Export(              args)
+                doDescriptionExport(dtable, args)
 
     finally:
         # shutdown the pool gracefully
@@ -410,6 +411,33 @@ def doICD10Export(args):
                         exc_info=True)
 
 
+def doDescriptionExport(dtable, args):
+    """If a ``--description_file`` has been specified, a description for every
+    file is saved out to the file.
+    """
+    if args.description_file is None:
+        return
+
+    with util.timed('Description export', log):
+        cols     = dtable.allColumns[1:]
+        vartable = dtable.vartable
+
+        try:
+            with open(args.description_file, 'wt') as f:
+                for c in cols:
+
+                    desc = vartable.loc[c.vid, 'Description']
+
+                    if desc == c.name:
+                        desc = 'n/a'
+
+                    f.write('{}\t{}\n'.format(c.name, desc))
+
+        except Exception as e:
+            log.warning('Failed to export descriptions: {}'.format(e),
+                        exc_info=True)
+
+
 def configLogging(args):
     """Configures ``ukbparse`` logging.