From 05675c4791b1134d838934b957d16844c12a8e9d Mon Sep 17 00:00:00 2001
From: Maja Jablonska <majajjablonska@gmail.com>
Date: Sat, 11 Nov 2023 18:51:57 +1100
Subject: [PATCH] Optimize imports
---
combo/config/from_parameters.py | 6 ++----
combo/config/registry.py | 3 +--
combo/data/api.py | 2 +-
combo/data/batch.py | 8 ++++----
combo/data/dataset_readers/conllu.py | 14 ++++++--------
combo/data/dataset_readers/dataset_reader.py | 4 ++--
.../dataset_readers/dataset_utils/span_utils.py | 1 -
.../universal_dependencies_dataset_reader.py | 4 +---
...trained_transformer_fixed_mismatched_indexer.py | 1 -
.../pretrained_transformer_mismatched_indexer.py | 6 +++---
.../data/token_indexers/single_id_token_indexer.py | 8 ++++----
.../token_const_padding_characters_indexer.py | 4 +---
combo/data/token_indexers/token_indexer.py | 1 -
combo/data/tokenizers/character_tokenizer.py | 2 +-
combo/data/tokenizers/lambo_tokenizer.py | 5 +++--
.../tokenizers/pretrained_transformer_tokenizer.py | 2 +-
combo/data/tokenizers/sentence_splitter.py | 2 +-
combo/data/tokenizers/spacy_tokenizer.py | 3 +--
combo/data/tokenizers/tokenizer.py | 2 +-
combo/data/tokenizers/whitespace_tokenizer.py | 2 +-
combo/data/vocabulary.py | 7 +++----
combo/main.py | 3 +--
.../token_embedders/character_token_embedder.py | 2 --
combo/nn/base.py | 9 +++------
combo/predictors/predictor_model.py | 10 ++++------
combo/training/trainer.py | 13 -------------
26 files changed, 45 insertions(+), 79 deletions(-)
delete mode 100644 combo/training/trainer.py
diff --git a/combo/config/from_parameters.py b/combo/config/from_parameters.py
index 200c52f..e853042 100644
--- a/combo/config/from_parameters.py
+++ b/combo/config/from_parameters.py
@@ -1,9 +1,7 @@
+import functools
import inspect
-from typing import Any, Callable, Dict, List, Optional
import typing
-import functools
-
-import json
+from typing import Any, Callable, Dict, List, Optional
from combo.common.params import Params
from combo.config.exceptions import RegistryException
diff --git a/combo/config/registry.py b/combo/config/registry.py
index d4b1544..8b12813 100644
--- a/combo/config/registry.py
+++ b/combo/config/registry.py
@@ -1,5 +1,4 @@
-from collections import defaultdict
-from typing import Any, Callable, Optional, Type, Union, Dict, List, Tuple
+from typing import Optional, Type, Dict, Tuple
from combo.config.exceptions import RegistryException
diff --git a/combo/data/api.py b/combo/data/api.py
index 649a3a8..6233cc0 100644
--- a/combo/data/api.py
+++ b/combo/data/api.py
@@ -3,7 +3,7 @@ import dataclasses
import json
from dataclasses import dataclass, field
from typing import Optional, List, Dict, Any, Union, Tuple
-from tokenizers import Token
+from combo.data.tokenizers import Token
import conllu
from overrides import overrides
diff --git a/combo/data/batch.py b/combo/data/batch.py
index 8181354..d6d3785 100644
--- a/combo/data/batch.py
+++ b/combo/data/batch.py
@@ -13,9 +13,9 @@ from combo.common.util import ensure_list
from combo.data import Instance, Vocabulary
from combo.utils import ConfigurationError
-
logger = logging.getLogger(__name__)
+
class Batch(Iterable):
"""
A batch of Instances. In addition to containing the instances themselves,
@@ -79,9 +79,9 @@ class Batch(Iterable):
return {**padding_lengths}
def as_tensor_dict(
- self,
- padding_lengths: Dict[str, Dict[str, int]] = None,
- verbose: bool = False,
+ self,
+ padding_lengths: Dict[str, Dict[str, int]] = None,
+ verbose: bool = False,
) -> Dict[str, Union[torch.Tensor, Dict[str, torch.Tensor]]]:
# This complex return type is actually predefined elsewhere as a DataArray,
# but we can't use it because mypy doesn't like it.
diff --git a/combo/data/dataset_readers/conllu.py b/combo/data/dataset_readers/conllu.py
index 21e85b7..ca9cbbf 100644
--- a/combo/data/dataset_readers/conllu.py
+++ b/combo/data/dataset_readers/conllu.py
@@ -7,17 +7,15 @@ import itertools
import logging
from typing import Dict, List, Optional, Sequence, Iterable
-from overrides import overrides
-
-from combo.data.token_indexers.single_id_token_indexer import SingleIdTokenIndexer
-from combo.data.token_indexers.token_indexer import TokenIndexer, Token
-from combo.utils import ConfigurationError
+from combo.config import Registry
+from combo.config.from_parameters import FromParameters, register_arguments
+from combo.data import Instance
from combo.data.dataset_readers.dataset_reader import DatasetReader, DatasetReaderInput
from combo.data.dataset_readers.dataset_utils.span_utils import to_bioul
-from combo.data import Instance
from combo.data.fields import MetadataField, TextField, Field, SequenceLabelField
-from combo.config import Registry
-from combo.config.from_parameters import FromParameters, register_arguments
+from combo.data.token_indexers.single_id_token_indexer import SingleIdTokenIndexer
+from combo.data.token_indexers.token_indexer import TokenIndexer, Token
+from combo.utils import ConfigurationError
logger = logging.getLogger(__name__)
diff --git a/combo/data/dataset_readers/dataset_reader.py b/combo/data/dataset_readers/dataset_reader.py
index 9834cd2..b7bc935 100644
--- a/combo/data/dataset_readers/dataset_reader.py
+++ b/combo/data/dataset_readers/dataset_reader.py
@@ -4,7 +4,7 @@ https://github.com/allenai/allennlp/blob/main/allennlp/data/dataset_readers/data
"""
import logging
from os import PathLike
-from typing import Iterable, Iterator, Optional, Union, TypeVar, Dict, List
+from typing import Iterable, Iterator, Optional, Union, Dict, List
from overrides import overrides
from torch.utils.data import IterableDataset
@@ -13,8 +13,8 @@ from combo.config import FromParameters, Registry
from combo.config.from_parameters import register_arguments
from combo.data import SpacyTokenizer, SingleIdTokenIndexer
from combo.data.instance import Instance
-from combo.data.tokenizers import Tokenizer
from combo.data.token_indexers import TokenIndexer
+from combo.data.tokenizers import Tokenizer
logger = logging.getLogger(__name__)
diff --git a/combo/data/dataset_readers/dataset_utils/span_utils.py b/combo/data/dataset_readers/dataset_utils/span_utils.py
index 4d25add..cb39714 100644
--- a/combo/data/dataset_readers/dataset_utils/span_utils.py
+++ b/combo/data/dataset_readers/dataset_utils/span_utils.py
@@ -4,7 +4,6 @@ https://github.com/allenai/allennlp/blob/80fb6061e568cb9d6ab5d45b661e86eb61b92c8
"""
from typing import Callable, List, Set, Tuple, TypeVar, Optional
-import warnings
from combo.data.tokenizers.tokenizer import Token
from combo.utils import ConfigurationError, InvalidTagSequence
diff --git a/combo/data/dataset_readers/universal_dependencies_dataset_reader.py b/combo/data/dataset_readers/universal_dependencies_dataset_reader.py
index 8117c45..eb336ae 100644
--- a/combo/data/dataset_readers/universal_dependencies_dataset_reader.py
+++ b/combo/data/dataset_readers/universal_dependencies_dataset_reader.py
@@ -9,9 +9,9 @@ from typing import List, Any, Dict, Iterable, Tuple
import conllu
import torch
+from conllu import parser
from overrides import overrides
-from combo import data
from combo.config import Registry
from combo.config.from_parameters import register_arguments
from combo.data import Vocabulary, fields, Instance, Token
@@ -22,8 +22,6 @@ from combo.data.fields.metadata_field import MetadataField
from combo.data.fields.sequence_label_field import SequenceLabelField
from combo.data.fields.text_field import TextField
from combo.data.token_indexers import TokenIndexer
-from conllu import parser
-
from combo.data.vocabulary import get_slices_if_not_provided
from combo.utils import checks, pad_sequence_to_length
diff --git a/combo/data/token_indexers/pretrained_transformer_fixed_mismatched_indexer.py b/combo/data/token_indexers/pretrained_transformer_fixed_mismatched_indexer.py
index 89dc2c8..6fb6a20 100644
--- a/combo/data/token_indexers/pretrained_transformer_fixed_mismatched_indexer.py
+++ b/combo/data/token_indexers/pretrained_transformer_fixed_mismatched_indexer.py
@@ -10,7 +10,6 @@ from overrides import overrides
from combo.config import Registry
from combo.config.from_parameters import register_arguments
from combo.data import Vocabulary
-from combo.data.token_indexers.token_indexer import TokenIndexer
from combo.data.token_indexers import IndexedTokenList
from combo.data.token_indexers.pretrained_transformer_indexer import PretrainedTransformerIndexer
from combo.data.token_indexers.pretrained_transformer_mismatched_indexer import PretrainedTransformerMismatchedIndexer
diff --git a/combo/data/token_indexers/pretrained_transformer_mismatched_indexer.py b/combo/data/token_indexers/pretrained_transformer_mismatched_indexer.py
index 5f5ddc8..161c71d 100644
--- a/combo/data/token_indexers/pretrained_transformer_mismatched_indexer.py
+++ b/combo/data/token_indexers/pretrained_transformer_mismatched_indexer.py
@@ -3,18 +3,18 @@ Adapted from AllenNLP
https://github.com/allenai/allennlp/blob/main/allennlp/data/token_indexers/pretrained_transformer_mismatched_indexer.py
"""
-from typing import Dict, List, Any, Optional
import logging
+from typing import Dict, List, Any, Optional
import torch
from overrides import overrides
-from combo.config import Registry, FromParameters
+from combo.config import Registry
from combo.config.from_parameters import register_arguments
from combo.data import Vocabulary
-from combo.data.tokenizers import Token
from combo.data.token_indexers import TokenIndexer, IndexedTokenList
from combo.data.token_indexers.pretrained_transformer_indexer import PretrainedTransformerIndexer
+from combo.data.tokenizers import Token
from combo.utils import pad_sequence_to_length
logger = logging.getLogger(__name__)
diff --git a/combo/data/token_indexers/single_id_token_indexer.py b/combo/data/token_indexers/single_id_token_indexer.py
index 20489e2..81b99b1 100644
--- a/combo/data/token_indexers/single_id_token_indexer.py
+++ b/combo/data/token_indexers/single_id_token_indexer.py
@@ -3,16 +3,16 @@ Adapted from AllenNLP
https://github.com/allenai/allennlp/blob/80fb6061e568cb9d6ab5d45b661e86eb61b92c82/allennlp/data/token_indexers/single_id_token_indexer.py
"""
-from typing import Dict, List, Optional, Any
import itertools
+from typing import Dict, List, Optional
from overrides import overrides
-from combo.config import FromParameters, Registry
+from combo.config import Registry
from combo.config.from_parameters import register_arguments
-from combo.data.vocabulary import Vocabulary
-from combo.data.tokenizers import Token
from combo.data.token_indexers import TokenIndexer, IndexedTokenList
+from combo.data.tokenizers import Token
+from combo.data.vocabulary import Vocabulary
_DEFAULT_VALUE = "THIS IS A REALLY UNLIKELY VALUE THAT HAS TO BE A STRING"
diff --git a/combo/data/token_indexers/token_const_padding_characters_indexer.py b/combo/data/token_indexers/token_const_padding_characters_indexer.py
index 10f54c8..ea1d89e 100644
--- a/combo/data/token_indexers/token_const_padding_characters_indexer.py
+++ b/combo/data/token_indexers/token_const_padding_characters_indexer.py
@@ -7,13 +7,11 @@ import itertools
from typing import List, Dict
import torch
+from overrides import overrides
from combo.config import Registry
from combo.config.from_parameters import register_arguments
from combo.data.token_indexers import IndexedTokenList
-from combo.data.token_indexers.token_indexer import TokenIndexer
-from overrides import overrides
-
from combo.data.token_indexers.token_characters_indexer import TokenCharactersIndexer
from combo.data.tokenizers import CharacterTokenizer
from combo.utils import pad_sequence_to_length
diff --git a/combo/data/token_indexers/token_indexer.py b/combo/data/token_indexers/token_indexer.py
index b2c86d4..b4b2d4c 100644
--- a/combo/data/token_indexers/token_indexer.py
+++ b/combo/data/token_indexers/token_indexer.py
@@ -6,7 +6,6 @@ https://github.com/allenai/allennlp/blob/main/allennlp/data/token_indexers/token
from typing import Any, Dict, List
import torch
-from overrides import overrides
from combo.config import FromParameters
from combo.data.tokenizers.tokenizer import Token
diff --git a/combo/data/tokenizers/character_tokenizer.py b/combo/data/tokenizers/character_tokenizer.py
index 6b66c13..b407e6f 100644
--- a/combo/data/tokenizers/character_tokenizer.py
+++ b/combo/data/tokenizers/character_tokenizer.py
@@ -3,7 +3,7 @@ Adapted from AllenNLP
https://github.com/allenai/allennlp/blob/main/allennlp/data/tokenizers/character_tokenizer.py
"""
-from typing import List, Union, Dict, Any
+from typing import List, Union
from combo.config import Registry
from combo.config.from_parameters import register_arguments
diff --git a/combo/data/tokenizers/lambo_tokenizer.py b/combo/data/tokenizers/lambo_tokenizer.py
index 2105a40..f37b076 100644
--- a/combo/data/tokenizers/lambo_tokenizer.py
+++ b/combo/data/tokenizers/lambo_tokenizer.py
@@ -1,10 +1,11 @@
-from typing import List, Dict, Any
+from typing import List
+
+from lambo.segmenter.lambo import Lambo
from combo.config import Registry
from combo.config.from_parameters import register_arguments
from combo.data.tokenizers.token import Token
from combo.data.tokenizers.tokenizer import Tokenizer
-from lambo.segmenter.lambo import Lambo
@Registry.register('lambo_tokenizer')
diff --git a/combo/data/tokenizers/pretrained_transformer_tokenizer.py b/combo/data/tokenizers/pretrained_transformer_tokenizer.py
index b884a18..cb12d2a 100644
--- a/combo/data/tokenizers/pretrained_transformer_tokenizer.py
+++ b/combo/data/tokenizers/pretrained_transformer_tokenizer.py
@@ -8,7 +8,7 @@ import dataclasses
import logging
from typing import Any, Dict, List, Optional, Tuple, Iterable
-from transformers import PreTrainedTokenizer, AutoTokenizer
+from transformers import PreTrainedTokenizer
from combo.config import Registry
from combo.config.from_parameters import register_arguments
diff --git a/combo/data/tokenizers/sentence_splitter.py b/combo/data/tokenizers/sentence_splitter.py
index c0383c9..250b01e 100644
--- a/combo/data/tokenizers/sentence_splitter.py
+++ b/combo/data/tokenizers/sentence_splitter.py
@@ -2,7 +2,7 @@
Adapted from AllenNLP
https://github.com/allenai/allennlp/blob/80fb6061e568cb9d6ab5d45b661e86eb61b92c82/allennlp/data/tokenizers/sentence_splitter.py
"""
-from typing import List, Dict, Any
+from typing import List
import spacy
diff --git a/combo/data/tokenizers/spacy_tokenizer.py b/combo/data/tokenizers/spacy_tokenizer.py
index d53bc6f..b884aae 100644
--- a/combo/data/tokenizers/spacy_tokenizer.py
+++ b/combo/data/tokenizers/spacy_tokenizer.py
@@ -3,10 +3,9 @@ Adapted from AllenNLP
https://github.com/allenai/allennlp/blob/main/allennlp/data/tokenizers/spacy_tokenizer.py
"""
-from typing import List, Optional, Dict
+from typing import List, Optional
import spacy
-from overrides import overrides
from spacy.tokens import Doc
from combo.config import Registry
diff --git a/combo/data/tokenizers/tokenizer.py b/combo/data/tokenizers/tokenizer.py
index 4a6ea3c..7b9269c 100644
--- a/combo/data/tokenizers/tokenizer.py
+++ b/combo/data/tokenizers/tokenizer.py
@@ -4,7 +4,7 @@ https://github.com/allenai/allennlp/blob/main/allennlp/data/tokenizers/tokenizer
"""
import logging
-from .token import Token
+from combo.data.tokenizers.token import Token
from typing import List, Optional
from combo.config import FromParameters
diff --git a/combo/data/tokenizers/whitespace_tokenizer.py b/combo/data/tokenizers/whitespace_tokenizer.py
index 84a54ef..eaf74f7 100644
--- a/combo/data/tokenizers/whitespace_tokenizer.py
+++ b/combo/data/tokenizers/whitespace_tokenizer.py
@@ -1,4 +1,4 @@
-from typing import List, Dict, Any
+from typing import List
from combo.config import Registry
from combo.data.tokenizers.token import Token
diff --git a/combo/data/vocabulary.py b/combo/data/vocabulary.py
index 9f711aa..4f3565c 100644
--- a/combo/data/vocabulary.py
+++ b/combo/data/vocabulary.py
@@ -1,12 +1,11 @@
import codecs
+import glob
import json
+import logging
import os
import re
-import glob
from collections import defaultdict
-from typing import Dict, Optional, Iterable, Set, List, Union, Any
-
-import logging
+from typing import Dict, Optional, Iterable, Set, List, Union
from filelock import FileLock
from transformers import PreTrainedTokenizer
diff --git a/combo/main.py b/combo/main.py
index 65119f9..2faaf18 100755
--- a/combo/main.py
+++ b/combo/main.py
@@ -5,8 +5,7 @@ import tempfile
from typing import Dict
import torch
-from absl import app
-from absl import flags
+from absl import app, flags
import pytorch_lightning as pl
from combo.training.trainable_combo import TrainableCombo
diff --git a/combo/modules/token_embedders/character_token_embedder.py b/combo/modules/token_embedders/character_token_embedder.py
index 7dfce11..1967ecf 100644
--- a/combo/modules/token_embedders/character_token_embedder.py
+++ b/combo/modules/token_embedders/character_token_embedder.py
@@ -11,9 +11,7 @@ from combo.data import Vocabulary
from combo.modules.dilated_cnn import DilatedCnnEncoder
from combo.modules.token_embedders import TokenEmbedder
-"""Embeddings."""
from typing import Optional
-
import torch
import torch.nn as nn
from combo import modules
diff --git a/combo/nn/base.py b/combo/nn/base.py
index 90a71e1..9e16607 100644
--- a/combo/nn/base.py
+++ b/combo/nn/base.py
@@ -1,14 +1,11 @@
-from typing import Dict, Optional, List, Union, Tuple
+from typing import Optional, List, Union, Tuple
import torch
import torch.nn as nn
-from combo.config.registry import Registry
-from combo.config.from_parameters import FromParameters, register_arguments
import combo.utils.checks as checks
-from combo.data.vocabulary import Vocabulary
-from combo.nn.utils import masked_cross_entropy
-from combo.predictors.predictor import Predictor
+from combo.config.from_parameters import FromParameters, register_arguments
+from combo.config.registry import Registry
@Registry.register("linear_layer")
diff --git a/combo/predictors/predictor_model.py b/combo/predictors/predictor_model.py
index d9e1b1e..7002509 100644
--- a/combo/predictors/predictor_model.py
+++ b/combo/predictors/predictor_model.py
@@ -3,25 +3,23 @@ Adapted from AllenNLP
https://github.com/allenai/allennlp/blob/main/allennlp/predictors/predictor.py
"""
-from typing import List, Iterator, Dict, Tuple, Any, Union
-import logging
import json
+import logging
import re
from contextlib import contextmanager
+from typing import List, Iterator, Dict, Tuple, Any
import numpy
+import pytorch_lightning as pl
import torch
from overrides import overrides
-from torch.utils.hooks import RemovableHandle
from torch import Tensor
from torch import backends
-
-import pytorch_lightning as pl
+from torch.utils.hooks import RemovableHandle
from combo.common.util import sanitize
from combo.config import FromParameters
from combo.data.batch import Batch
-from combo.data.dataset_loaders.dataset_loader import TensorDict
from combo.data.dataset_readers.dataset_reader import DatasetReader
from combo.data.instance import JsonDict, Instance
from combo.modules.model import Model
diff --git a/combo/training/trainer.py b/combo/training/trainer.py
deleted file mode 100644
index ebb8ff0..0000000
--- a/combo/training/trainer.py
+++ /dev/null
@@ -1,13 +0,0 @@
-from pytorch_lightning import Trainer
-
-
-class Callback:
- pass
-
-
-class TransferPatienceEpochCallback:
- pass
-
-
-class GradientDescentTrainer(Trainer):
- pass
--
GitLab