Serialize morph rules with tagger

Serialize `morph_rules` with the tagger alongside the `tag_map`.

Use `Morphology.load_tag_map` and `Morphology.load_morph_exceptions` to
load these settings rather than reinitializing the morphology each time
they are changed.

spacy/pipeline/pipes.pyx

@@ -359,9 +359,7 @@ class Tagger(Pipe):
         if new_tag_map:
             if "_SP" in orig_tag_map:
                 new_tag_map["_SP"] = orig_tag_map["_SP"]
-            vocab.morphology = Morphology(vocab.strings, new_tag_map,
-                                          vocab.morphology.lemmatizer,
-                                          exc=vocab.morphology.exc)
+            vocab.morphology.load_tag_map(new_tag_map)
         self.set_output(len(self.labels))
         doc_sample = [Doc(self.vocab, words=["hello", "world"])]
         if pipeline is not None:
@@ -400,10 +398,7 @@ class Tagger(Pipe):
         if values is None:
             values = {POS: "X"}
         tag_map[label] = values
-        self.vocab.morphology = Morphology(
-            self.vocab.strings, tag_map=tag_map,
-            lemmatizer=self.vocab.morphology.lemmatizer,
-            exc=self.vocab.morphology.exc)
+        self.vocab.morphology.load_tag_map(tag_map)
         return 1
 
     def use_params(self, params):
@@ -417,6 +412,8 @@ class Tagger(Pipe):
         serialize["cfg"] = lambda: srsly.json_dumps(self.cfg)
         tag_map = dict(sorted(self.vocab.morphology.tag_map.items()))
         serialize["tag_map"] = lambda: srsly.msgpack_dumps(tag_map)
+        morph_rules = dict(self.vocab.morphology.exc)
+        serialize["morph_rules"] = lambda: srsly.msgpack_dumps(morph_rules)
         return util.to_bytes(serialize, exclude)
 
     def from_bytes(self, bytes_data, exclude=tuple()):
@@ -428,14 +425,18 @@ class Tagger(Pipe):
 
         def load_tag_map(b):
             tag_map = srsly.msgpack_loads(b)
-            self.vocab.morphology = Morphology(
-                self.vocab.strings, tag_map=tag_map,
-                lemmatizer=self.vocab.morphology.lemmatizer,
-                exc=self.vocab.morphology.exc)
+            self.vocab.morphology.load_tag_map(tag_map)
 
+        def load_morph_rules(b):
+            morph_rules = srsly.msgpack_loads(b)
+            self.vocab.morphology.load_morph_exceptions(morph_rules)
+
+        self.vocab.morphology = Morphology(self.vocab.strings, dict(),
+            lemmatizer=self.vocab.morphology.lemmatizer)
         deserialize = {
             "vocab": lambda b: self.vocab.from_bytes(b),
             "tag_map": load_tag_map,
+            "morph_rules": load_morph_rules,
             "cfg": lambda b: self.cfg.update(srsly.json_loads(b)),
             "model": lambda b: load_model(b),
         }
@@ -444,9 +445,11 @@ class Tagger(Pipe):
 
     def to_disk(self, path, exclude=tuple()):
         tag_map = dict(sorted(self.vocab.morphology.tag_map.items()))
+        morph_rules = dict(self.vocab.morphology.exc)
         serialize = {
             "vocab": lambda p: self.vocab.to_disk(p),
             "tag_map": lambda p: srsly.write_msgpack(p, tag_map),
+            "morph_rules": lambda p: srsly.write_msgpack(p, morph_rules),
             "model": lambda p: self.model.to_disk(p),
             "cfg": lambda p: srsly.write_json(p, self.cfg),
         }
@@ -462,15 +465,19 @@ class Tagger(Pipe):
 
         def load_tag_map(p):
             tag_map = srsly.read_msgpack(p)
-            self.vocab.morphology = Morphology(
-                self.vocab.strings, tag_map=tag_map,
-                lemmatizer=self.vocab.morphology.lemmatizer,
-                exc=self.vocab.morphology.exc)
+            self.vocab.morphology.load_tag_map(tag_map)
 
+        def load_morph_rules(p):
+            morph_rules = srsly.read_msgpack(p)
+            self.vocab.morphology.load_morph_exceptions(morph_rules)
+
+        self.vocab.morphology = Morphology(self.vocab.strings, dict(),
+            lemmatizer=self.vocab.morphology.lemmatizer)
         deserialize = {
             "vocab": lambda p: self.vocab.from_disk(p),
             "cfg": lambda p: self.cfg.update(_load_cfg(p)),
             "tag_map": load_tag_map,
+            "morph_rules": load_morph_rules,
             "model": load_model,
         }
         util.from_disk(path, deserialize, exclude)

spacy/tests/pipeline/test_tagger.py

@@ -17,6 +17,8 @@ def test_label_types():
 
 TAG_MAP = {"N": {"pos": "NOUN"}, "V": {"pos": "VERB"}, "J": {"pos": "ADJ"}}
 
+MORPH_RULES = {"V": {"like": {"lemma": "luck"}}}
+
 TRAIN_DATA = [
     ("I like green eggs", {"tags": ["N", "V", "J", "N"]}),
     ("Eat blue ham", {"tags": ["V", "J", "N"]}),
@@ -26,9 +28,9 @@ TRAIN_DATA = [
 def test_overfitting_IO():
     # Simple test to try and quickly overfit the tagger - ensuring the ML models work correctly
     nlp = English()
+    nlp.vocab.morphology.load_tag_map(TAG_MAP)
+    nlp.vocab.morphology.load_morph_exceptions(MORPH_RULES)
     tagger = nlp.create_pipe("tagger")
-    for tag, values in TAG_MAP.items():
-        tagger.add_label(tag, values)
     train_examples = []
     for t in TRAIN_DATA:
         train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1]))
@@ -47,6 +49,7 @@ def test_overfitting_IO():
     assert doc[1].tag_ is "V"
     assert doc[2].tag_ is "J"
     assert doc[3].tag_ is "N"
+    assert doc[1].lemma_ == "luck"
 
     # Also test the results are still the same after IO
     with make_tempdir() as tmp_dir:
@@ -57,3 +60,4 @@ def test_overfitting_IO():
         assert doc2[1].tag_ is "V"
         assert doc2[2].tag_ is "J"
         assert doc2[3].tag_ is "N"
+        assert doc[1].lemma_ == "luck"