Merge pull request #6229 from svlandeg/bugfix/disabled

spacy/errors.py

@@ -456,6 +456,8 @@ class Errors:
             "issue tracker: http://github.com/explosion/spaCy/issues")
 
     # TODO: fix numbering after merging develop into master
+    E900 = ("Could not run the full 'nlp' pipeline for evaluation. If you specified "
+            "frozen components, make sure they were already initialized and trained. ")
     E901 = ("Failed to remove existing output directory: {path}. If your "
             "config and the components you train change between runs, a "
             "non-empty output directory can lead to stale pipeline data. To "

spacy/language.py

@@ -1034,6 +1034,9 @@ class Language:
                     )
                 )
             disable = to_disable
+        # DisabledPipes will restore the pipes in 'disable' when it's done, so we need to exclude
+        # those pipes that were already disabled.
+        disable = [d for d in disable if d not in self._disabled]
         return DisabledPipes(self, disable)
 
     def make_doc(self, text: str) -> Doc:

spacy/tests/pipeline/test_pipe_methods.py

@@ -129,6 +129,7 @@ def test_enable_pipes_method(nlp, name):
 
 @pytest.mark.parametrize("name", ["my_component"])
 def test_disable_pipes_context(nlp, name):
+    """Test that an enabled component stays enabled after running the context manager."""
     nlp.add_pipe("new_pipe", name=name)
     assert nlp.has_pipe(name)
     with nlp.select_pipes(disable=name):
@@ -136,6 +137,18 @@ def test_disable_pipes_context(nlp, name):
     assert nlp.has_pipe(name)
 
 
+@pytest.mark.parametrize("name", ["my_component"])
+def test_disable_pipes_context_restore(nlp, name):
+    """Test that a disabled component stays disabled after running the context manager."""
+    nlp.add_pipe("new_pipe", name=name)
+    assert nlp.has_pipe(name)
+    nlp.disable_pipes(name)
+    assert not nlp.has_pipe(name)
+    with nlp.select_pipes(disable=name):
+        assert not nlp.has_pipe(name)
+    assert not nlp.has_pipe(name)
+
+
 def test_select_pipes_list_arg(nlp):
     for name in ["c1", "c2", "c3"]:
         nlp.add_pipe("new_pipe", name=name)

spacy/training/loop.py

@@ -249,7 +249,10 @@ def create_evaluation_callback(
 
     def evaluate() -> Tuple[float, Dict[str, float]]:
         dev_examples = list(dev_corpus(nlp))
+        try:
             scores = nlp.evaluate(dev_examples)
+        except KeyError as e:
+            raise KeyError(Errors.E900) from e
         # Calculate a weighted sum based on score_weights for the main score.
         # We can only consider scores that are ints/floats, not dicts like
         # entity scores per type etc.