Merge branch 'master' into master

README.rst

@@ -20,21 +20,21 @@ Installation
 --------
 
 
-        > pip install -r requirements.txt
+        $ pip install -r requirements.txt
 
-        > wget http://text-machine.cs.uml.edu/cliner/models/silver.model
+        $ wget http://text-machine.cs.uml.edu/cliner/models/silver.crf
 
-        > mv silver.model models/silver.model
+        $ mv silver.crf models/silver.crf
 
-        > cliner predict --txt examples/ex_doc.txt --out data/predictions --model models/silver.model --format i2b2
+        $ cliner predict --txt examples/ex_doc.txt --out data/predictions --model models/silver.crf --format i2b2
 
 
 Out-of-the-Box Model
 --------
 
 Although i2b2 licensing prevents us from releasing our cliner models trained on i2b2 data, we generated some comparable models from automatically-annotated MIMIC II text.
 
-This silver MIMIC model can be found at http://text-machine.cs.uml.edu/cliner/models/silver.model
+This silver MIMIC model can be found at http://text-machine.cs.uml.edu/cliner/models/silver.crf
 
 
 Example Data

code/DatasetCliner_experimental.py

@@ -204,7 +204,7 @@ def load_dataset(self,avaliable_datasets_sent,avaliable_datasets_labels, dataset
         dataset_filepaths : dictionary with keys 'train', 'valid', 'test', 'deploy'
         '''       
         start_time = time.time()
-        print('Load dataset... ', end='', flush=True)
+        print('Load dataset... \n')
         if parameters['token_pretrained_embedding_filepath'] != '':
             if token_to_vector==None:
                 token_to_vector = hd.load_pretrained_token_embeddings(parameters)

code/feature_extraction/word_features.py

@@ -37,7 +37,10 @@ def feature_length(word):
     return {('length', ''): len(word)}
 
 def feature_stem_porter(word):
-    return {('stem_porter', porter_st.stem(word)): 1}
+    try:
+        return {('stem_porter', porter_st.stem(word)): 1}
+    except Exception, e:
+        return {}
 
 def feature_mitre(word):
     features = {}