From 6c09f53c6bff8a57720b39cd806b38380a75c2fa Mon Sep 17 00:00:00 2001
From: yunfan <yunfan.shao@outlook.com>
Date: Sat, 20 Oct 2018 11:17:08 +0800
Subject: [PATCH] update

---
 fastNLP/core/dataset.py          | 14 ++++++++++++++
 fastNLP/loader/dataset_loader.py |  7 +++++++
 2 files changed, 21 insertions(+)

diff --git a/fastNLP/core/dataset.py b/fastNLP/core/dataset.py
index a10a24d2..f1f3f2a8 100644
--- a/fastNLP/core/dataset.py
+++ b/fastNLP/core/dataset.py
@@ -99,12 +99,26 @@ class DataSet(list):
         return self
 
     def update_vocab(self, **name_vocab):
+        """using certain field data to update vocabulary.
+
+        e.g. ::
+
+            # update word vocab and label vocab seperately
+            dataset.update_vocab(word_seq=word_vocab, label_seq=label_vocab)
+        """
         for field_name, vocab in name_vocab.items():
             for ins in self:
                 vocab.update(ins[field_name].contents())
         return self
 
     def set_origin_len(self, origin_field, origin_len_name=None):
+        """make dataset tensor output contain origin_len field.
+
+        e.g. ::
+
+            # output "word_seq_origin_len", lengths based on "word_seq" field
+            dataset.set_origin_len("word_seq")
+        """
         if origin_field is None:
             self.origin_len = None
         else:
diff --git a/fastNLP/loader/dataset_loader.py b/fastNLP/loader/dataset_loader.py
index c9e76622..5feb62a6 100644
--- a/fastNLP/loader/dataset_loader.py
+++ b/fastNLP/loader/dataset_loader.py
@@ -75,6 +75,13 @@ class DataSetLoader(BaseLoader):
         super(DataSetLoader, self).__init__()
 
     def load(self, path):
+        """ load data in `path` into a dataset
+        """
+        raise NotImplementedError
+
+    def convert(self, data):
+        """convert list of data into dataset
+        """
         raise NotImplementedError
 
 class RawDataSetLoader(DataSetLoader):