Conditional Random Fields

@@ -39,7 +39,7 @@ from nltk.corpus import stopwords
 # 1) Best model
 
 # Examples
-# python3.4 training-validation-v1.py
+# python training-validation-v1.py
 # --inputPath /export/space1/users/compu2/bionlp/conditional-random-fields/data-sets
 # --trainingFile training-data-set-35.txt
 # --testFile test-data-set-30.txt
@@ -58,29 +58,29 @@ def word2features(sent, i):
     postag = listElem[2]
 
     features = {
-        'word': word,
-        #'lemma': lemma,
+        #'word': word,
+        'lemma': lemma,
         #'postag': postag,
     }
     if i > 0:
         listElem = sent[i - 1].split('|')
-        word1 = listElem[0]
+        #word1 = listElem[0]
         lemma1 = listElem[1]
         postag1 = listElem[2]
         features.update({
-            '-1:word': word1,
-            #'-1:lemma': lemma1,
+            #'-1:word': word1,
+            '-1:lemma': lemma1,
             #'-1:postag': postag1,
         })
 
     if i < len(sent) - 1:
         listElem = sent[i + 1].split('|')
-        word1 = listElem[0]
+        #word1 = listElem[0]
         lemma1 = listElem[1]
         postag1 = listElem[2]
         features.update({
-            '+1:word': word1,
-            #'+1:lemma': lemma1,
+            #'+1:word': word1,
+            '+1:lemma': lemma1,
             #'+1:postag': postag1,
         })
     return features
@@ -234,7 +234,7 @@ if __name__ == "__main__":
     # crf = rs.best_estimator_
     nameReport = options.trainingFile.replace('.txt', '.fStopWords_' + str(options.excludeStopWords) + '.fSymbols_' + str(
         options.excludeSymbols) + '.txt')
-    with open(os.path.join(options.outputPath, "reports", "report_" + nameReport), mode="w") as oFile:
+    with open(os.path.join(options.outputPath, "reports-l", "report_" + nameReport), mode="w") as oFile:
         oFile.write("********** TRAINING **********\n")
         oFile.write("Training file: " + options.trainingFile + '\n')
         oFile.write('\n')