ENH: New "metaproc" plugin type, for manipulating column metadata. Used to

generate descriptions for binarised ICD10 columns

ukbparse/custom.py

@@ -12,16 +12,18 @@ and for cleaning and processing.
 The following plugin types currently exist:
 
 
-  +-------------------+------------------------------------------------------+
-  | Plugin type       |                                                      |
-  +-------------------+------------------------------------------------------|
-  | ``sniffer``       | Return information about the columns in a file       |
-  | ``loader``        | Load data from a file                                |
-  | ``cleaner``       | Run a cleaning function on a single column           |
-  | ``processor``     | Run a processing fnction on one or more data columns |
-  | ``formatter``     | Format a column for output                           |
-  | ``exporter``      | Export the processed data set                        |
-  +-------------------+------------------------------------------------------+
+  +-------------------+-------------------------------------------------------+
+  | Plugin type       |                                                       |
+  +-------------------+-------------------------------------------------------|
+  | ``sniffer``       | Return information about the columns in a file        |
+  | ``loader``        | Load data from a file                                 |
+  | ``cleaner``       | Run a cleaning function on a single column            |
+  | ``processor``     | Run a processing function on one or more data columns |
+  | ``metaproc``      | Run a function on a :class:`.Column` ``metadata``     |
+  |                   | value                                                 |
+  | ``formatter``     | Format a column for output                            |
+  | ``exporter``      | Export the processed data set                         |
+  +-------------------+-------------------------------------------------------+
 
 
 To ensure that the ``ukbparse`` command line help is nicely formatted, all
@@ -66,6 +68,7 @@ PLUGIN_TYPES = ['loader',
                 'formatter',
                 'cleaner',
                 'processor',
+                'metaproc',
                 'exporter']
 
 

ukbparse/processing.py

@@ -36,8 +36,10 @@ import              collections
 
 import pyparsing as pp
 
-import ukbparse.util   as util
-import ukbparse.custom as custom
+from . import util
+from . import icd10
+from . import custom
+from . import hierarchy
 
 
 log = logging.getLogger(__name__)
@@ -202,10 +204,11 @@ class Process(object):
         # cleaner functions are not
         # defined in processing_functions,
         # so in this case func will be None.
-        self.__ptype  = ptype
-        self.__name   = name
-        self.__args   = args
-        self.__kwargs = kwargs
+        self.__ptype    = ptype
+        self.__name     = name
+        self.__args     = args
+        self.__kwargs   = kwargs
+        self.__metaproc = kwargs.pop('metaproc', None)
 
 
     def __repr__(self):
@@ -242,11 +245,27 @@ class Process(object):
         """Run the process on the data, passing it the given arguments,
         and any arguments that were passed to :meth:`__init__`.
         """
-        return custom.run(self.__ptype,
-                          self.__name,
-                          *args,
-                          *self.__args,
-                          **self.__kwargs)
+        result = custom.run(self.__ptype,
+                            self.__name,
+                            *args,
+                            *self.__args,
+                            **self.__kwargs)
+
+        if self.__metaproc is not None and \
+           isinstance(result, tuple)   and \
+           len(result) == 4:
+
+            meta  = result[3]
+            mproc = self.__metaproc
+
+            try:
+                meta = [custom.runMetaproc(mproc, m) for m in meta]
+            except Exception as e:
+                log.warning('Metadata processing function failed: %s', e)
+
+            result = tuple(list(result[:3]) + [meta])
+
+        return result
 
 
 def parseProcesses(procs, ptype):
@@ -333,3 +352,23 @@ def makeParser():
     function = funcName + pp.Optional(allargs)
 
     return function
+
+
+@custom.metaproc('icd10.numdesc')
+def icd10DescriptionFromNumeric(val):
+    """Generates a description for a numeric ICD10 code. """
+    val  = icd10.numericToCode(val)
+    hier = hierarchy.getHierarchyFilePath(name='icd10')
+    hier = hierarchy.loadHierarchyFile(hier)
+    desc = hier.description(val)
+    return '{} - {}'.format(val, desc)
+
+
+@custom.metaproc('icd10.codedesc')
+def icd10DescriptionFromCode(val):
+    """Generates a description for an ICD10 code. """
+    val  = icd10.codeToNumeric(val)
+    hier = hierarchy.getHierarchyFilePath(name='icd10')
+    hier = hierarchy.loadHierarchyFile(hier)
+    desc = hier.description(val)
+    return '{} - {}'.format(val, desc)