Remove dependency on the overrides package (#311)

* Removes dependency on overrides * Changelog * Fixes tests * Remove obsolete parameter
allenai · Nov 30, 2021 · 1591777 · 1591777
1 parent 05dd4e6
commit 1591777
Show file tree

Hide file tree

Showing 106 changed files with 107 additions and 413 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -11,6 +11,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - Following a breaking change in the NLTK API, we now depend on the most recent version only.
 
+### Removed
+
+- Removed the dependency on the `overrides` package
+
 
 ## [v2.8.0](https://github.com/allenai/allennlp-models/releases/tag/v2.8.0) - 2021-11-05
 

diff --git a/allennlp_models/classification/dataset_readers/boolq.py b/allennlp_models/classification/dataset_readers/boolq.py
@@ -3,7 +3,7 @@
 from typing import Optional, Iterable, Dict
 
 from allennlp.common.file_utils import cached_path
-from overrides import overrides
+
 from allennlp.data import DatasetReader, Tokenizer, TokenIndexer, Instance, Field
 from allennlp.data.tokenizers import WhitespaceTokenizer
 from allennlp.data.token_indexers import SingleIdTokenIndexer
@@ -38,7 +38,6 @@ def __init__(
         self.tokenizer = tokenizer or WhitespaceTokenizer()
         self.token_indexers = token_indexers or {"tokens": SingleIdTokenIndexer()}
 
-    @overrides
     def _read(self, file_path) -> Iterable[Instance]:
         file_path = cached_path(file_path, extract_archive=True)
         with open(file_path) as f:
@@ -51,7 +50,6 @@ def _read(self, file_path) -> Iterable[Instance]:
                     label=record.get("label"),
                 )
 
-    @overrides
     def text_to_instance(  # type: ignore
         self, passage: str, question: str, label: Optional[bool] = None
     ) -> Instance:

diff --git a/allennlp_models/classification/dataset_readers/stanford_sentiment_tree_bank.py b/allennlp_models/classification/dataset_readers/stanford_sentiment_tree_bank.py
@@ -2,7 +2,7 @@
 import logging
 
 from allennlp.data import Tokenizer
-from overrides import overrides
+
 from nltk.tree import Tree
 
 from allennlp.common.file_utils import cached_path
@@ -72,7 +72,6 @@ def __init__(
             )
         self._granularity = granularity
 
-    @overrides
     def _read(self, file_path):
         with open(cached_path(file_path), "r") as data_file:
             logger.info("Reading instances from lines in file at: %s", file_path)
@@ -91,7 +90,6 @@ def _read(self, file_path):
                     if instance is not None:
                         yield instance
 
-    @overrides
     def text_to_instance(self, tokens: List[str], sentiment: str = None) -> Optional[Instance]:
         """
         We take `pre-tokenized` input here, because we might not have a tokenizer in this class.
@@ -154,6 +152,5 @@ def make_token(t: Union[str, Token]):
             fields["label"] = LabelField(sentiment)
         return Instance(fields)
 
-    @overrides
     def apply_token_indexers(self, instance: Instance) -> None:
         instance.fields["tokens"].token_indexers = self._token_indexers
diff --git a/allennlp_models/classification/models/biattentive_classification_network.py b/allennlp_models/classification/models/biattentive_classification_network.py
@@ -1,7 +1,7 @@
 from typing import Dict, Union
 
 import numpy
-from overrides import overrides
+
 import torch
 from torch import nn
 import torch.nn.functional as F
@@ -201,7 +201,6 @@ def __init__(
         self.loss = torch.nn.CrossEntropyLoss()
         initializer(self)
 
-    @overrides
     def forward(
         self,  # type: ignore
         tokens: TextFieldTensors,
@@ -319,7 +318,6 @@ def forward(
 
         return output_dict
 
-    @overrides
     def make_output_human_readable(
         self, output_dict: Dict[str, torch.Tensor]
     ) -> Dict[str, torch.Tensor]:
@@ -333,7 +331,6 @@ def make_output_human_readable(
         output_dict["label"] = labels
         return output_dict
 
-    @overrides
     def get_metrics(self, reset: bool = False) -> Dict[str, float]:
         return {
             metric_name: metric.get_metric(reset) for metric_name, metric in self.metrics.items()

diff --git a/allennlp_models/coref/dataset_readers/conll.py b/allennlp_models/coref/dataset_readers/conll.py
@@ -2,7 +2,6 @@
 import collections
 from typing import Dict, List, Optional, Tuple, DefaultDict
 
-from overrides import overrides
 
 from allennlp.common.file_utils import cached_path
 from allennlp.data.dataset_readers.dataset_reader import DatasetReader
@@ -69,7 +68,6 @@ def __init__(
         self._max_sentences = max_sentences
         self._remove_singleton_clusters = remove_singleton_clusters
 
-    @overrides
     def _read(self, file_path: str):
         # if `file_path` is a URL, redirect to the cache
         file_path = cached_path(file_path)
@@ -90,7 +88,6 @@ def _read(self, file_path: str):
 
             yield self.text_to_instance([s.words for s in sentences], list(clusters.values()))
 
-    @overrides
     def text_to_instance(
         self,  # type: ignore
         sentences: List[List[str]],

diff --git a/allennlp_models/coref/dataset_readers/preco.py b/allennlp_models/coref/dataset_readers/preco.py
@@ -2,7 +2,6 @@
 import logging
 from typing import Dict, List, Optional, Tuple
 
-from overrides import overrides
 
 from allennlp.common.file_utils import cached_path
 from allennlp.data.dataset_readers.dataset_reader import DatasetReader
@@ -65,7 +64,6 @@ def __init__(
         self._max_sentences = max_sentences
         self._remove_singleton_clusters = remove_singleton_clusters
 
-    @overrides
     def _read(self, file_path: str):
         # if `file_path` is a URL, redirect to the cache
         file_path = cached_path(file_path)
@@ -75,7 +73,6 @@ def _read(self, file_path: str):
                 example = json.loads(line)
                 yield self.text_to_instance(example["sentences"], example["mention_clusters"])
 
-    @overrides
     def text_to_instance(
         self,  # type: ignore
         sentences: List[List[str]],

diff --git a/allennlp_models/coref/dataset_readers/winobias.py b/allennlp_models/coref/dataset_readers/winobias.py
@@ -2,7 +2,6 @@
 import collections
 from typing import Any, Dict, List, Optional, Tuple, DefaultDict
 
-from overrides import overrides
 
 from allennlp.common.file_utils import cached_path
 from allennlp.data.dataset_readers.dataset_reader import DatasetReader
@@ -67,7 +66,6 @@ def __init__(
         self._max_span_width = max_span_width
         self._token_indexers = token_indexers or {"tokens": SingleIdTokenIndexer()}
 
-    @overrides
     def _read(self, file_path: str):
 
         for sentence in open(cached_path(file_path), "r"):
@@ -104,7 +102,6 @@ def _read(self, file_path: str):
 
             yield self.text_to_instance([Token(x) for x in words], [x for x in clusters.values()])
 
-    @overrides
     def text_to_instance(
         self,  # type: ignore
         sentence: List[Token],

diff --git a/allennlp_models/coref/metrics/conll_coref_scores.py b/allennlp_models/coref/metrics/conll_coref_scores.py
@@ -1,7 +1,7 @@
 from typing import Any, Dict, List, Tuple
 from collections import Counter
 
-from overrides import overrides
+
 from scipy.optimize import linear_sum_assignment
 import numpy as np
 import torch
@@ -20,7 +20,6 @@ def __init__(self, allow_singletons=False) -> None:
         self.scorers = [Scorer(m) for m in (Scorer.muc, Scorer.b_cubed, Scorer.ceafe)]
         self.allow_singletons = allow_singletons
 
-    @overrides
     def __call__(
         self,  # type: ignore
         top_spans: torch.Tensor,
@@ -64,7 +63,6 @@ def __call__(
                     predicted_clusters, gold_clusters, mention_to_predicted, mention_to_gold
                 )
 
-    @overrides
     def get_metric(self, reset: bool = False) -> Tuple[float, float, float]:
         metrics = (lambda e: e.get_precision(), lambda e: e.get_recall(), lambda e: e.get_f1())
         precision, recall, f1_score = tuple(
@@ -74,7 +72,6 @@ def get_metric(self, reset: bool = False) -> Tuple[float, float, float]:
             self.reset()
         return precision, recall, f1_score
 
-    @overrides
     def reset(self):
         self.scorers = [Scorer(metric) for metric in (Scorer.muc, Scorer.b_cubed, Scorer.ceafe)]
 

diff --git a/allennlp_models/coref/metrics/mention_recall.py b/allennlp_models/coref/metrics/mention_recall.py
@@ -1,5 +1,5 @@
 from typing import Any, Dict, List, Set, Tuple
-from overrides import overrides
+
 
 import torch
 from allennlp.nn.util import dist_reduce_sum
@@ -13,7 +13,6 @@ def __init__(self) -> None:
         self._num_gold_mentions = 0
         self._num_recalled_mentions = 0
 
-    @overrides
     def __call__(
         self,  # type: ignore
         batched_top_spans: torch.Tensor,
@@ -34,7 +33,6 @@ def __call__(
         self._num_gold_mentions += dist_reduce_sum(num_gold_mentions)
         self._num_recalled_mentions += dist_reduce_sum(num_recalled_mentions)
 
-    @overrides
     def get_metric(self, reset: bool = False) -> float:
         if self._num_gold_mentions == 0:
             recall = 0.0
@@ -44,7 +42,6 @@ def get_metric(self, reset: bool = False) -> float:
             self.reset()
         return recall
 
-    @overrides
     def reset(self):
         self._num_gold_mentions = 0
         self._num_recalled_mentions = 0
diff --git a/allennlp_models/coref/models/coref.py b/allennlp_models/coref/models/coref.py
@@ -4,7 +4,7 @@
 
 import torch
 import torch.nn.functional as F
-from overrides import overrides
+
 
 from allennlp.data import TextFieldTensors, Vocabulary
 from allennlp.models.model import Model
@@ -133,7 +133,6 @@ def __init__(
             self._lexical_dropout = lambda x: x
         initializer(self)
 
-    @overrides
     def forward(
         self,  # type: ignore
         text: TextFieldTensors,
@@ -382,7 +381,6 @@ def forward(
             output_dict["document"] = [x["original_text"] for x in metadata]
         return output_dict
 
-    @overrides
     def make_output_human_readable(self, output_dict: Dict[str, torch.Tensor]):
         """
         Converts the list of spans and predicted antecedent indices into clusters
@@ -465,7 +463,6 @@ def make_output_human_readable(self, output_dict: Dict[str, torch.Tensor]):
         output_dict["clusters"] = batch_clusters
         return output_dict
 
-    @overrides
     def get_metrics(self, reset: bool = False) -> Dict[str, float]:
         mention_recall = self._mention_recall.get_metric(reset)
         coref_precision, coref_recall, coref_f1 = self._conll_coref_scores.get_metric(reset)

diff --git a/allennlp_models/coref/predictors/coref.py b/allennlp_models/coref/predictors/coref.py
@@ -1,6 +1,6 @@
 from typing import List, Dict
 
-from overrides import overrides
+
 from spacy.tokens import Doc
 import numpy
 
@@ -79,7 +79,6 @@ def predict_tokenized(self, tokenized_document: List[str]) -> JsonDict:
         instance = self._words_list_to_instance(tokenized_document)
         return self.predict_instance(instance)
 
-    @overrides
     def predictions_to_labeled_instances(
         self, instance: Instance, outputs: Dict[str, numpy.ndarray]
     ) -> List[Instance]:
@@ -193,7 +192,6 @@ def _words_list_to_instance(self, words: List[str]) -> Instance:
         instance = self._dataset_reader.text_to_instance(sentences)
         return instance
 
-    @overrides
     def _json_to_instance(self, json_dict: JsonDict) -> Instance:
         """
         Expects JSON that looks like `{"document": "string of document text"}`

diff --git a/allennlp_models/generation/dataset_readers/cnn_dm.py b/allennlp_models/generation/dataset_readers/cnn_dm.py
@@ -6,7 +6,6 @@
 import hashlib
 import ftfy
 
-from overrides import overrides
 
 from allennlp.common.checks import ConfigurationError
 from allennlp.common.file_utils import cached_path
@@ -120,7 +119,6 @@ def _read_story(story_path: str):
     def _strip_extension(filename: str) -> str:
         return os.path.splitext(filename)[0]
 
-    @overrides
     def _read(self, file_path: str):
         # Reset exceeded counts
         self._source_max_exceeded = 0
@@ -157,7 +155,6 @@ def _read(self, file_path: str):
 
                 yield self.text_to_instance(article, summary)
 
-    @overrides
     def text_to_instance(
         self, source_sequence: str, target_sequence: str = None
     ) -> Instance:  # type: ignore
@@ -183,7 +180,6 @@ def text_to_instance(
         else:
             return Instance({"source_tokens": source_field})
 
-    @overrides
     def apply_token_indexers(self, instance: Instance) -> None:
         instance.fields["source_tokens"]._token_indexers = self._source_token_indexers  # type: ignore
         if "target_tokens" in instance.fields:

diff --git a/allennlp_models/generation/dataset_readers/copynet_seq2seq.py b/allennlp_models/generation/dataset_readers/copynet_seq2seq.py
@@ -3,7 +3,7 @@
 import warnings
 
 import torch
-from overrides import overrides
+
 
 from allennlp.common.file_utils import cached_path
 from allennlp.common.util import START_SYMBOL, END_SYMBOL
@@ -118,7 +118,6 @@ def __init__(
                 UserWarning,
             )
 
-    @overrides
     def _read(self, file_path):
         with open(cached_path(file_path), "r") as data_file:
             logger.info("Reading instances from lines in file at: %s", file_path)
@@ -144,7 +143,6 @@ def _tokens_to_ids(tokens: List[Token]) -> List[int]:
             out.append(ids.setdefault(token.text, len(ids)))
         return out
 
-    @overrides
     def text_to_instance(
         self,
         source_string: str,
@@ -207,7 +205,6 @@ def text_to_instance(
 
         return Instance(fields_dict)
 
-    @overrides
     def apply_token_indexers(self, instance: Instance) -> None:
         instance.fields["source_tokens"]._token_indexers = self._source_token_indexers  # type: ignore
         if "target_tokens" in instance.fields:

diff --git a/allennlp_models/generation/dataset_readers/seq2seq.py b/allennlp_models/generation/dataset_readers/seq2seq.py
@@ -3,7 +3,6 @@
 import logging
 import copy
 
-from overrides import overrides
 
 from allennlp.common.checks import ConfigurationError
 from allennlp.common.file_utils import cached_path
@@ -119,7 +118,6 @@ def __init__(
         self._target_max_exceeded = 0
         self.quoting = quoting
 
-    @overrides
     def _read(self, file_path: str):
         # Reset exceeded counts
         self._source_max_exceeded = 0
@@ -150,7 +148,6 @@ def _read(self, file_path: str):
                 self._target_max_tokens,
             )
 
-    @overrides
     def text_to_instance(
         self, source_string: str, target_string: str = None
     ) -> Instance:  # type: ignore
@@ -177,7 +174,6 @@ def text_to_instance(
         else:
             return Instance({"source_tokens": source_field})
 
-    @overrides
     def apply_token_indexers(self, instance: Instance) -> None:
         instance.fields["source_tokens"]._token_indexers = self._source_token_indexers  # type: ignore
         if "target_tokens" in instance.fields: