changes to *.in files

git-svn-id: https://scm.gforge.inria.fr/authscm/cfourrie/svn/lingwb/metagger/trunk@2686 dc05b511-7f1d-0410-9f1c-d6f32a2df9e4

bin/Makefile.am

@@ -5,17 +5,20 @@ AUTOMAKE_OPTIONS = foreign
 bin_SCRIPTS =	build_word_list.py	\
 		build_tag_dict.py	\
 		learning_curves.py	\
-		pos_tag.py
+		pos_tag.py		\
+		eval.py
 
 CLEANFILES =	build_word_list.py	\
 		build_tag_dict.py	\
 		learning_curves.py	\
-		pos_tag.py
+		pos_tag.py		\
+		eval.py
 
 BUILT_SOURCES =	build_word_list.py	\
 		build_tag_dict.py	\
 		learning_curves.py	\
-		pos_tag.py
+		pos_tag.py		\
+		eval.py
 
 EDIT = perl -pe "s|\@alexinadir\@|$(alexinadir)|g;\
 		s|\@datadir\@|\$(pkgdatadir)|g; 	\

src/metagger/pos_tagger.py.in

@@ -12,7 +12,6 @@ from collections import defaultdict
 from metagger.mytoken import Token
 from metagger.megam_classifier import MegamClassifier
 from metagger.instance import Instance
-from metagger.result_sink import AccuracySink
 
 
 
@@ -40,7 +39,7 @@ class POSTagger:
 
 
 
-    def train_model(self,_file):
+    def train_model(self,_file, model_path="./model.megam"):
         print >> sys.stderr, "Generating training data..."
         train_inst_file = self.generate_training_data(_file)
         print  >> sys.stderr, "Data file: %s" %train_inst_file
@@ -82,7 +81,7 @@ class POSTagger:
     def tag_token_sequence(self, tokens):
         ''' N-best breath search for the best tag sequence for each sentence'''
         # maintain N-best sequences of tagged tokens
-        sequences = [([],0.0)]  # log prob. 
+        sequences = [([],0.0)]  # log prob.
         for i in range(len(tokens)):
             token = tokens[i]
             n_best_sequences = []
@@ -119,20 +118,20 @@ class POSTagger:
         return best_sequence
 
 
-    def apply(self, _file, sink, outfile=''):
+    def apply(self, _file, outfile=''):
+        # open output file
+        out = sys.stdout
+        if outfile:
+            out = codecs.open( outfile, 'w' )
+        # process sentences
         for line in codecs.open(_file, 'r', 'latin-1'):
             line = line.strip()
             tokens = []
             for item in line.split():
-                token = Token()
-                token.set( item )
+                token = Token( string=item )
                 tokens.append( token )
             tagged_tokens = self.tag_token_sequence( tokens )
-            for t in tagged_tokens:
-                sink.update(t.pos,t.label,t.label_pr_distrib)
-            out = sys.stdout
-            if outfile:
-                out = codecs.open( outfile, 'w' )
+            # print tagged sentence to output file
             tagged_sent = " ".join( [tok.__str__() for tok in tagged_tokens] )
             print >> out, tagged_sent
         return