CU-1yn0v9e: Fix typo in docstring; more consistent naming

CogStack · Oct 31, 2023 · db1f6f5 · db1f6f5
1 parent bf7f756
commit db1f6f5
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 7 deletions.
diff --git a/medcat/cat.py b/medcat/cat.py
@@ -1546,22 +1546,22 @@ def _multiprocessing_batch(self,
 
         return docs
 
-    @deprecated(message="Use `multiprocessing_batch_nr_of_docs` instead")
+    @deprecated(message="Use `multiprocessing_batch_docs_size` instead")
     def multiprocessing_pipe(self, in_data: Union[List[Tuple], Iterable[Tuple]],
                              nproc: Optional[int] = None,
                              batch_size: Optional[int] = None,
                              only_cui: bool = False,
                              addl_info: List[str] = [],
                              return_dict: bool = True,
                              batch_factor: int = 2) -> Union[List[Tuple], Dict]:
-        return self.multiprocessing_batch_nr_of_docs(in_data=in_data, nproc=nproc,
+        return self.multiprocessing_batch_docs_size(in_data=in_data, nproc=nproc,
                                                      batch_size=batch_size,
                                                      only_cui=only_cui,
                                                      addl_info=addl_info,
                                                      return_dict=return_dict,
                                                      batch_factor=batch_factor)
 
-    def multiprocessing_batch_nr_of_docs(self,
+    def multiprocessing_batch_docs_size(self,
                              in_data: Union[List[Tuple], Iterable[Tuple]],
                              nproc: Optional[int] = None,
                              batch_size: Optional[int] = None,
@@ -1571,7 +1571,7 @@ def multiprocessing_batch_nr_of_docs(self,
                              batch_factor: int = 2) -> Union[List[Tuple], Dict]:
         """Run multiprocessing NOT FOR TRAINING.
 
-        Thios method batches the data based on the number of documents as specified by the user.
+        This method batches the data based on the number of documents as specified by the user.
 
         PS:
         This method supports Windows.

diff --git a/tests/test_cat.py b/tests/test_cat.py
@@ -73,7 +73,7 @@ def test_multiprocessing_pipe(self):
             (2, "The dog is sitting outside the house."),
             (3, "The dog is sitting outside the house."),
         ]
-        out = self.undertest.multiprocessing_batch_nr_of_docs(in_data, nproc=2, return_dict=False)
+        out = self.undertest.multiprocessing_batch_docs_size(in_data, nproc=2, return_dict=False)
         self.assertTrue(type(out) == list)
         self.assertEqual(3, len(out))
         self.assertEqual(1, out[0][0])
@@ -89,7 +89,7 @@ def test_multiprocessing_pipe_with_malformed_texts(self):
             (2, ""),
             (3, None),
         ]
-        out = self.undertest.multiprocessing_batch_nr_of_docs(in_data, nproc=1, batch_size=1, return_dict=False)
+        out = self.undertest.multiprocessing_batch_docs_size(in_data, nproc=1, batch_size=1, return_dict=False)
         self.assertTrue(type(out) == list)
         self.assertEqual(3, len(out))
         self.assertEqual(1, out[0][0])
@@ -105,7 +105,7 @@ def test_multiprocessing_pipe_return_dict(self):
             (2, "The dog is sitting outside the house."),
             (3, "The dog is sitting outside the house.")
         ]
-        out = self.undertest.multiprocessing_batch_nr_of_docs(in_data, nproc=2, return_dict=True)
+        out = self.undertest.multiprocessing_batch_docs_size(in_data, nproc=2, return_dict=True)
         self.assertTrue(type(out) == dict)
         self.assertEqual(3, len(out))
         self.assertEqual({'entities': {}, 'tokens': []}, out[1])