Update spaCy pipeline

README.md

@@ -59,7 +59,7 @@ model-index:
 | Feature | Description |
 | --- | --- |
 | **Name** | `en_engagement_spl_RoBERTa_acad_max1_do02` |
-| **Version** | `0.2.5.1130` |
+| **Version** | `0.2.6.1130` |
 | **spaCy** | `>=3.3.0,<3.4.0` |
 | **Default Pipeline** | `transformer`, `tagger`, `parser`, `ner`, `trainable_transformer`, `span_finder`, `spancat` |
 | **Components** | `transformer`, `tagger`, `parser`, `ner`, `trainable_transformer`, `span_finder`, `spancat` |

custom_functions.py

@@ -10,4 +10,181 @@ from spacy.tokens import DocBin, Doc
 
 # make the config work
 # from scripts.rel_model import create_relation_model, create_classification_layer, create_instances, create_tensors
-from scripts.custom_comps.SpanCat_extention import build_mean_max_reducer1, build_mean_max_reducer2, build_mean_max_reducer3, build_mean_max_reducer4
+# from scripts.custom_comps.SpanCat_extention import build_mean_max_reducer1, build_mean_max_reducer2, build_mean_max_reducer3, build_mean_max_reducer4
+
+from typing import List, Tuple, cast
+from thinc.api import Model, with_getitem, chain, list2ragged, Logistic
+from thinc.api import Maxout, Linear, concatenate, glorot_uniform_init, PyTorchLSTM
+from thinc.api import reduce_mean, reduce_max, reduce_first, reduce_last
+from thinc.types import Ragged, Floats2d
+
+from spacy.util import registry
+from spacy.tokens import Doc
+from spacy.ml.extract_spans import extract_spans
+
+# @registry.layers("spacy.LinearLogistic.v1")
+# def build_linear_logistic(nO=None, nI=None) -> Model[Floats2d, Floats2d]:
+#     """An output layer for multi-label classification. It uses a linear layer
+#     followed by a logistic activation.
+#     """
+#     return chain(Linear(nO=nO, nI=nI, init_W=glorot_uniform_init), Logistic())
+
+
+@registry.layers("mean_max_reducer.v1.5")
+def build_mean_max_reducer1(hidden_size: int,
+                            dropout: float = 0.0) -> Model[Ragged, Floats2d]:
+    """Reduce sequences by concatenating their mean and max pooled vectors,
+    and then combine the concatenated vectors with a hidden layer.
+    """
+    return chain(
+        concatenate(
+            cast(Model[Ragged, Floats2d], reduce_last()),
+            cast(Model[Ragged, Floats2d], reduce_first()),
+            reduce_mean(),
+            reduce_max(),
+        ),
+        Maxout(nO=hidden_size, normalize=True, dropout=dropout),
+    )
+
+
+@registry.layers("mean_max_reducer.v2")
+def build_mean_max_reducer2(hidden_size: int,
+                            dropout: float = 0.0) -> Model[Ragged, Floats2d]:
+    """Reduce sequences by concatenating their mean and max pooled vectors,
+    and then combine the concatenated vectors with a hidden layer.
+    """
+    return chain(
+        concatenate(
+            cast(Model[Ragged, Floats2d], reduce_last()),
+            cast(Model[Ragged, Floats2d], reduce_first()),
+            reduce_mean(),
+            reduce_max(),
+        ), Maxout(nO=hidden_size, normalize=True, dropout=dropout),
+        Maxout(nO=hidden_size, normalize=True, dropout=dropout))
+
+
+# @registry.layers("mean_max_reducer.v2")
+# def build_mean_max_reducer2(hidden_size: int,
+#                             depth: int) -> Model[Ragged, Floats2d]:
+#     """Reduce sequences by concatenating their mean and max pooled vectors,
+#     and then combine the concatenated vectors with a hidden layer.
+#     """
+#     return chain(
+#         concatenate(
+#             cast(Model[Ragged, Floats2d], reduce_last()),
+#             cast(Model[Ragged, Floats2d], reduce_first()),
+#             reduce_mean(),
+#             reduce_max(),
+#         ), Maxout(nO=hidden_size, normalize=True, dropout=0.0),
+#         PyTorchLSTM(nO=64, nI=hidden_size, bi=True, depth=depth, dropout=0.2))
+
+
+@registry.layers("mean_max_reducer.v3")
+def build_mean_max_reducer3(hidden_size: int,
+                            maxout_pieces: int = 3,
+                            dropout: float = 0.0) -> Model[Ragged, Floats2d]:
+    """Reduce sequences by concatenating their mean and max pooled vectors,
+    and then combine the concatenated vectors with a hidden layer.
+    """
+    hidden_size2 = int(hidden_size / 2)
+    hidden_size3 = int(hidden_size / 2)
+    return chain(
+        concatenate(
+            cast(Model[Ragged, Floats2d], reduce_last()),
+            cast(Model[Ragged, Floats2d], reduce_first()),
+            reduce_mean(),
+            reduce_max(),
+        ),
+        Maxout(nO=hidden_size,
+               nP=maxout_pieces,
+               normalize=True,
+               dropout=dropout),
+        Maxout(nO=hidden_size2,
+               nP=maxout_pieces,
+               normalize=True,
+               dropout=dropout),
+        Maxout(nO=hidden_size3,
+               nP=maxout_pieces,
+               normalize=True,
+               dropout=dropout))
+
+
+@registry.layers("mean_max_reducer.v3.3")
+def build_mean_max_reducer4(hidden_size: int,
+                            depth: int) -> Model[Ragged, Floats2d]:
+    """Reduce sequences by concatenating their mean and max pooled vectors,
+    and then combine the concatenated vectors with a hidden layer.
+    """
+    hidden_size2 = int(hidden_size / 2)
+    hidden_size3 = int(hidden_size / 2)
+    return chain(
+        concatenate(
+            cast(Model[Ragged, Floats2d], reduce_last()),
+            cast(Model[Ragged, Floats2d], reduce_first()),
+            reduce_mean(),
+            reduce_max(),
+        ), Maxout(nO=hidden_size, nP=3, normalize=True, dropout=0.0),
+        Maxout(nO=hidden_size2, nP=3, normalize=True, dropout=0.0),
+        Maxout(nO=hidden_size3, nP=3, normalize=True, dropout=0.0))
+
+
+@registry.architectures("CustomSpanCategorizer.v2")
+def build_spancat_model(
+    tok2vec: Model[List[Doc], List[Floats2d]],
+    reducer: Model[Ragged, Floats2d],
+    scorer: Model[Floats2d, Floats2d],
+) -> Model[Tuple[List[Doc], Ragged], Floats2d]:
+    """Build a span categorizer model, given a token-to-vector model, a
+    reducer model to map the sequence of vectors for each span down to a single
+    vector, and a scorer model to map the vectors to probabilities.
+    tok2vec (Model[List[Doc], List[Floats2d]]): The tok2vec model.
+    reducer (Model[Ragged, Floats2d]): The reducer model.
+    scorer (Model[Floats2d, Floats2d]): The scorer model.
+    """
+    model = chain(
+        cast(
+            Model[Tuple[List[Doc], Ragged], Tuple[Ragged, Ragged]],
+            with_getitem(
+                0,
+                chain(tok2vec,
+                      cast(Model[List[Floats2d], Ragged], list2ragged()))),
+        ),
+        extract_spans(),
+        reducer,
+        scorer,
+    )
+    model.set_ref("tok2vec", tok2vec)
+    model.set_ref("reducer", reducer)
+    model.set_ref("scorer", scorer)
+    return model
+
+
+# @registry.architectures("spacy.SpanCategorizer.v1")
+# def build_spancat_model(
+#     tok2vec: Model[List[Doc], List[Floats2d]],
+#     reducer: Model[Ragged, Floats2d],
+#     scorer: Model[Floats2d, Floats2d],
+# ) -> Model[Tuple[List[Doc], Ragged], Floats2d]:
+#     """Build a span categorizer model, given a token-to-vector model, a
+#     reducer model to map the sequence of vectors for each span down to a single
+#     vector, and a scorer model to map the vectors to probabilities.
+#     tok2vec (Model[List[Doc], List[Floats2d]]): The tok2vec model.
+#     reducer (Model[Ragged, Floats2d]): The reducer model.
+#     scorer (Model[Floats2d, Floats2d]): The scorer model.
+#     """
+#     model = chain(
+#         cast(
+#             Model[Tuple[List[Doc], Ragged], Tuple[Ragged, Ragged]],
+#             with_getitem(
+#                 0,
+#                 chain(tok2vec,
+#                       cast(Model[List[Floats2d], Ragged], list2ragged()))),
+#         ),
+#         extract_spans(),
+#         reducer,
+#         scorer,
+#     )
+#     model.set_ref("tok2vec", tok2vec)
+#     model.set_ref("reducer", reducer)
+#     model.set_ref("scorer", scorer)
+#     return model

en_engagement_spl_RoBERTa_acad_max1_do02-any-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7ab8cb8149a5373d98ee5bfca870b439c9113c1a773f8394110fb27df205a57
-size 928613682
+oid sha256:d4970ef292b571df7416f968d47a309e218448a3f35d4cd3eb9852542bd98da5
+size 928614883

meta.json

@@ -1,7 +1,7 @@
 {
   "lang":"en",
   "name":"engagement_spl_RoBERTa_acad_max1_do02",
-  "version":"0.2.5.1130",
+  "version":"0.2.6.1130",
   "description":"",
   "author":"",
   "email":"",
@@ -330,7 +330,7 @@
     "spancat_loss":359.1590412855
   },
   "requirements":[
-    "spacy-experimental>=0.6.1,<0.7.0",
-    "spacy-transformers>=1.1.7,<1.2.0"
+    "spacy-transformers>=1.1.7,<1.2.0",
+    "spacy-experimental>=0.6.1,<0.7.0"
   ]
 }