Merge pull request #70 from ArneBinder/import_pie_models

import `pie-models` instead of `pytorch-ie`

dataset_builders/pie/cdcp/cdcp.py

@@ -1,8 +1,9 @@
 import dataclasses
 import logging
-from typing import Any, Callable, Dict, List, Optional
+from typing import Any, Dict, List, Optional
 
 import datasets
+from pie_models.document.processing.text_span_trimmer import trim_text_spans
 from pytorch_ie.annotations import BinaryRelation, LabeledSpan
 from pytorch_ie.core import Annotation, AnnotationList, annotation_field
 from pytorch_ie.documents import (
@@ -11,7 +12,6 @@
 )
 
 from pie_datasets import GeneratorBasedBuilder
-from pie_datasets.document.processing.text_span_trimmer import trim_text_spans
 
 log = logging.getLogger(__name__)
 

dataset_builders/pie/scidtb_argmin/scidtb_argmin.py

@@ -1,18 +1,18 @@
 import dataclasses
 import logging
-from typing import Any, Callable, Dict, List, Optional, Tuple
+from typing import Any, Dict, List, Tuple
 
 import datasets
+from pie_models.document.processing import token_based_document_to_text_based
 from pytorch_ie.annotations import BinaryRelation, LabeledSpan
-from pytorch_ie.core import AnnotationList, Document, annotation_field
+from pytorch_ie.core import AnnotationList, annotation_field
 from pytorch_ie.documents import (
     TextDocumentWithLabeledSpansAndBinaryRelations,
     TokenBasedDocument,
 )
 from pytorch_ie.utils.span import bio_tags_to_spans
 
 from pie_datasets import GeneratorBasedBuilder
-from pie_datasets.document.processing import token_based_document_to_text_based
 
 log = logging.getLogger(__name__)
 

dataset_builders/pie/tacred/tacred.py

@@ -2,6 +2,7 @@
 from typing import Any, Dict, Optional
 
 import datasets
+from pie_models.document.processing import token_based_document_to_text_based
 from pytorch_ie.annotations import BinaryRelation, LabeledSpan
 from pytorch_ie.core import Annotation, AnnotationList, annotation_field
 from pytorch_ie.documents import (
@@ -10,7 +11,6 @@
 )
 
 from pie_datasets import GeneratorBasedBuilder
-from pie_datasets.document.processing import token_based_document_to_text_based
 
 
 @dataclass(eq=True, frozen=True)

pyproject.toml

@@ -24,7 +24,7 @@ classifiers = [
 
 [tool.poetry.dependencies]
 python = "^3.9"
-pytorch-ie = ">=0.29.1,<0.30.0"
+pie-models = "^0.7.6"
 datasets = "^2.14"
 # this was manually added because we get a conflict with pyarrow otherwise
 pyarrow = "^13"

src/pie_datasets/document/processing/__init__.py

@@ -1,9 +1 @@
 from .generic import Caster, Converter, Pipeline
-from .regex_partitioner import RegexPartitioner
-from .relation_argument_sorter import RelationArgumentSorter
-from .text_span_trimmer import TextSpanTrimmer
-from .tokenization import (
-    text_based_document_to_token_based,
-    token_based_document_to_text_based,
-    tokenize_document,
-)