[Predator] Switch from scorer-based classifier to loglinear classifier.

appengine/findit/crash/occurrence.py

 # Copyright 2016 The Chromium Authors. All rights reserved.
 # Use of this source code is governed by a BSD-style license that can be
 # found in the LICENSE file.
 
 class Occurrence(list):
   """A list of indices where something occurs in a list.
 
   The list of indices can be accessed directly, since this class is a
   subclass of ``list``. In addition to this list, we also have a ``name`
   property which specifies what thing is occurring in those positions. For
@@ skipping 22 matching lines @@
       they're actually allowed to be anything which can serve as a key
       in a dict.
 
   Returns:
     A dict mapping each "name" in ``names`` to an Occurrence object,
     each of which contains a list of the indices where that name occurs
     in ``names``.
   """
   occurrences = {}
   for index, name in enumerate(names or []):
+    if not name:
+      continue
+
     if name not in occurrences:
       occurrences[name] = Occurrence(name, [index])
     else:
       occurrences[name].append(index)
 
   return occurrences
 
 
 def DefaultOccurrenceRanking(occurrence):
   """Default function for ranking an occurrence.
@@ skipping 40 matching lines @@
     rank_function (callable): what rank value to give an occurrence. If
       you don't supply this argument, or if you provide a falsy value,
       then we will fall back to using the ``DefaultOccurrenceRanking``.
 
   Returns:
     A length-``top_n`` list of "names" ordered by the ``rank_function``.
   """
   if not rank_function:  # pragma: no cover.
     rank_function = DefaultOccurrenceRanking
 
-  # TODO(wrengr): can't we do this sorting/filtering/truncation in one pass?
+  # TODO(wrengr): generalize the filter function into another parameter.
   occurrences = sorted(GetOccurrences(names).values(), key=rank_function)
 
-  # Filter out unnamed classes. Alas, we can't sort these out before
-  # constructing the concordance, because then our indices would be off.
-  # TODO(wrengr): generalize the filter function into another parameter.
-  classes = [occurrence.name for occurrence in occurrences if occurrence.name]
-
-  return classes[:top_n]
+  return [occurrence.name for occurrence in occurrences[:top_n]]