New Feature: display more detail when Error E067 (#2639)

* Fix off-by-one error

* Add verbose option

* Update verbose option

* Update documents for verbose option

spacy/cli/train.py

@@ -36,12 +36,13 @@ from ..compat import json_dumps
     gold_preproc=("Use gold preprocessing", "flag", "G", bool),
     version=("Model version", "option", "V", str),
     meta_path=("Optional path to meta.json. All relevant properties will be "
-               "overwritten.", "option", "m", Path))
+               "overwritten.", "option", "m", Path),
+    verbose=("Display more information for debug", "option", None, bool))
 def train(lang, output_dir, train_data, dev_data, n_iter=30, n_sents=0,
          parser_multitasks='', entity_multitasks='',
           use_gpu=-1, vectors=None, no_tagger=False,
           no_parser=False, no_entities=False, gold_preproc=False,
-          version="0.0.0", meta_path=None):
+          version="0.0.0", meta_path=None, verbose=False):
     """
     Train a model. Expects data in spaCy's JSON format.
     """
@@ -143,7 +144,7 @@ def train(lang, output_dir, train_data, dev_data, n_iter=30, n_sents=0,
                                 gold_preproc=gold_preproc))
                 nwords = sum(len(doc_gold[0]) for doc_gold in dev_docs)
                 start_time = timer()
-                scorer = nlp_loaded.evaluate(dev_docs)
+                scorer = nlp_loaded.evaluate(dev_docs, verbose)
                 end_time = timer()
                 if use_gpu < 0:
                     gpu_wps = None

spacy/gold.pyx

@@ -30,7 +30,7 @@ def tags_to_entities(tags):
             continue
         elif tag.startswith('I'):
             if start is None:
-                raise ValueError(Errors.E067.format(tags=tags[:i]))
+                raise ValueError(Errors.E067.format(tags=tags[:i+1]))
             continue
         if tag.startswith('U'):
             entities.append((tag[2:], i, i))

website/api/cli.jade

@@ -260,7 +260,7 @@ p
 +code(false, "bash", "$", false, false, true).
     python -m spacy train [lang] [output_dir] [train_data] [dev_data] [--n-iter]
     [--n-sents] [--use-gpu] [--meta-path] [--vectors] [--no-tagger] [--no-parser]
-    [--no-entities] [--gold-preproc]
+    [--no-entities] [--gold-preproc] [--verbose]
 
 +table(["Argument", "Type", "Description"])
     +row
@@ -344,6 +344,11 @@ p
         +cell flag
         +cell Show help message and available arguments.
 
+    +row
+        +cell #[code --verbose]
+        +cell flag
+        +cell Show more detail message during training.
+
     +row("foot")
         +cell creates
         +cell model, pickle