From f0cf4a2dca7cd2685d0842dbe5111d541288d661 Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal+gh@gmail.com>
Date: Wed, 29 Jul 2020 13:47:37 +0200
Subject: [PATCH] Update tests

---
 .../tests/serialize/test_serialize_config.py  |  4 +--
 spacy/tests/test_tok2vec.py                   | 29 ++++++++++---------
 2 files changed, 17 insertions(+), 16 deletions(-)

diff --git a/spacy/tests/serialize/test_serialize_config.py b/spacy/tests/serialize/test_serialize_config.py
index ef5c7f8f4..ce35add42 100644
--- a/spacy/tests/serialize/test_serialize_config.py
+++ b/spacy/tests/serialize/test_serialize_config.py
@@ -41,7 +41,7 @@ factory = "tagger"
 @architectures = "spacy.Tagger.v1"
 
 [components.tagger.model.tok2vec]
-@architectures = "spacy.Tok2VecTensors.v1"
+@architectures = "spacy.Tok2VecListener.v1"
 width = ${components.tok2vec.model:width}
 """
 
@@ -71,7 +71,7 @@ def my_parser():
     tok2vec = build_Tok2Vec_model(
         MultiHashEmbed(
             width=321,
-            embed_size=5432,
+            rows=5432,
             also_embed_subwords=True,
             also_use_static_vectors=False
         ),
diff --git a/spacy/tests/test_tok2vec.py b/spacy/tests/test_tok2vec.py
index 6b7170fe3..76b5e64df 100644
--- a/spacy/tests/test_tok2vec.py
+++ b/spacy/tests/test_tok2vec.py
@@ -1,7 +1,8 @@
 import pytest
 
 from spacy.ml.models.tok2vec import build_Tok2Vec_model
-from spacy.ml.models.tok2vec import MultiHashEmbed, MaxoutWindowEncoder
+from spacy.ml.models.tok2vec import MultiHashEmbed, CharacterEmbed
+from spacy.ml.models.tok2vec import MishWindowEncoder, MaxoutWindowEncoder
 from spacy.vocab import Vocab
 from spacy.tokens import Doc
 
@@ -60,26 +61,26 @@ def test_tok2vec_batch_sizes(batch_size, width, embed_size):
 
 
 # fmt: off
-@pytest.mark.xfail(reason="TODO: Update for new signature")
 @pytest.mark.parametrize(
-    "tok2vec_config",
+    "width,embed_arch,embed_config,encode_arch,encode_config",
     [
-        {"width": 8, "embed_size": 100, "char_embed": False, "nM": 64, "nC": 8, "pretrained_vectors": None, "window_size": 1, "conv_depth": 2, "bilstm_depth": 0, "maxout_pieces": 3, "subword_features": True, "dropout": None},
-        {"width": 8, "embed_size": 100, "char_embed": True, "nM": 64, "nC": 8, "pretrained_vectors": None, "window_size": 1, "conv_depth": 2, "bilstm_depth": 0, "maxout_pieces": 3, "subword_features": True, "dropout": None},
-        {"width": 8, "embed_size": 100, "char_embed": False, "nM": 64, "nC": 8, "pretrained_vectors": None, "window_size": 1, "conv_depth": 6, "bilstm_depth": 0, "maxout_pieces": 3, "subword_features": True, "dropout": None},
-        {"width": 8, "embed_size": 100, "char_embed": False, "nM": 64, "nC": 8, "pretrained_vectors": None, "window_size": 1, "conv_depth": 6, "bilstm_depth": 0, "maxout_pieces": 3, "subword_features": True, "dropout": None},
-        {"width": 8, "embed_size": 100, "char_embed": False, "nM": 64, "nC": 8, "pretrained_vectors": None, "window_size": 1, "conv_depth": 2, "bilstm_depth": 0, "maxout_pieces": 3, "subword_features": False, "dropout": None},
-        {"width": 8, "embed_size": 100, "char_embed": False, "nM": 64, "nC": 8, "pretrained_vectors": None, "window_size": 3, "conv_depth": 2, "bilstm_depth": 0, "maxout_pieces": 3, "subword_features": False, "dropout": None},
-        {"width": 8, "embed_size": 100, "char_embed": True, "nM": 81, "nC": 8, "pretrained_vectors": None, "window_size": 3, "conv_depth": 2, "bilstm_depth": 0, "maxout_pieces": 3, "subword_features": False, "dropout": None},
-        {"width": 8, "embed_size": 100, "char_embed": True, "nM": 81, "nC": 9, "pretrained_vectors": None, "window_size": 3, "conv_depth": 2, "bilstm_depth": 0, "maxout_pieces": 3, "subword_features": False, "dropout": None},
+        (8, MultiHashEmbed, {"rows": 100, "also_embed_subwords": True, "also_use_static_vectors": False}, MaxoutWindowEncoder, {"window_size": 1, "maxout_pieces": 3, "depth": 2}),
+        (8, MultiHashEmbed, {"rows": 100, "also_embed_subwords": True, "also_use_static_vectors": False}, MishWindowEncoder, {"window_size": 1, "depth": 6}),
+        (8, CharacterEmbed, {"rows": 100, "nM": 64, "nC": 8}, MaxoutWindowEncoder, {"window_size": 1, "maxout_pieces": 3, "depth": 3}),
+        (8, CharacterEmbed, {"rows": 100, "nM": 16, "nC": 2}, MishWindowEncoder, {"window_size": 1, "depth": 3}),
     ],
 )
 # fmt: on
-def test_tok2vec_configs(tok2vec_config):
+def test_tok2vec_configs(width, embed_arch, embed_config, encode_arch, encode_config):
+    embed_config["width"] = width
+    encode_config["width"] = width
     docs = get_batch(3)
-    tok2vec = build_Tok2Vec_model_from_old_args(**tok2vec_config)
+    tok2vec = build_Tok2Vec_model(
+        embed_arch(**embed_config),
+        encode_arch(**encode_config)
+    )
     tok2vec.initialize(docs)
     vectors, backprop = tok2vec.begin_update(docs)
     assert len(vectors) == len(docs)
-    assert vectors[0].shape == (len(docs[0]), tok2vec_config["width"])
+    assert vectors[0].shape == (len(docs[0]), width)
     backprop(vectors)