FIX In case of duplicates, use the max value (#44)

wikilinks · Jun 19, 2018 · eee26ec · eee26ec
1 parent 264f6d4
commit eee26ec
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 2 deletions.
diff --git a/doc/approximate.rst b/doc/approximate.rst
@@ -82,7 +82,8 @@ columns:
 * weight
 
 For types not in this weight file, exact matches between gold type and system
-type score 1, and otherwise score is 0.
+type score 1, and otherwise score is 0. If multiple gold/system entries exist,
+the maximum weight is used.
 
 The following example scores 0.123 where the gold type is ``type1`` and the
 system type is ``type2``.

diff --git a/neleval/configs.py b/neleval/configs.py
@@ -280,7 +280,9 @@ def __init__(self, path):
             for l in f:
                 gold, sys, weight = l.split('\t')
                 weight = float(weight)
-                self.values[gold, sys] = weight
+                self.values[gold, sys] = max(weight,
+                                             self.values.get((gold, sys),
+                                                             weight))
 
     def __call__(self, gold_type, sys_type):
         return self.values.get((gold_type, sys_type),