fix

app.py

@@ -1,5 +1,3 @@
-from __future__ import annotations
-
 import gradio
 import pandas as pd
 from matplotlib import pyplot as plt
@@ -44,7 +42,7 @@ def main():
     interface = gradio.Interface(
         title="Making graphs accessible",
         description="Generate textual representation of a graph\n"
-                    "https://www.kaggle.com/competitions/benetech-making-graphs-accessible",
+        "https://www.kaggle.com/competitions/benetech-making-graphs-accessible",
         fn=lambda image: predict_string(image, model),
         inputs="image",
         outputs="text",

data.py

@@ -1,5 +1,3 @@
-from __future__ import annotations
-
 import dataclasses
 import enum
 import functools
@@ -231,23 +229,23 @@ class AnnotatedImage:
 
 def generate_annotated_images():
     for image_id in tqdm.autonotebook.tqdm(
-            load_train_image_ids(), "Iterating over annotated images"
+        load_train_image_ids(), "Iterating over annotated images"
     ):
         yield AnnotatedImage.from_image_id(image_id)
 
 
-@functools.lru_cache
+@functools.cache
 def load_train_image_ids() -> list[str]:
     train_image_ids = [i.replace(".jpg", "") for i in os.listdir("data/train/images")]
     return train_image_ids[: 1000 if CONFIG.debug else None]
 
 
-@functools.lru_cache
+@functools.cache
 def load_test_image_ids() -> list[str]:
     return [i.replace(".jpg", "") for i in os.listdir("data/test/images")]
 
 
-@functools.lru_cache
+@functools.cache
 def load_image_annotation(image_id: str) -> dict:
     return json.load(open(f"data/train/annotations/{image_id}.json"))
 
@@ -309,7 +307,7 @@ def to_token_str(value: str or enum.Enum):
         return f"<{string}>"
 
 
-@functools.lru_cache
+@functools.cache
 def get_extra_tokens() -> types.SimpleNamespace:
     token_ns = types.SimpleNamespace()
 
@@ -333,7 +331,7 @@ def convert_number_to_scientific_string(value: int or float) -> str:
 
 
 def convert_axis_data_to_string(
-        axis_data: list[str or float], values_type: ValuesType
+    axis_data: list[str or float], values_type: ValuesType
 ) -> str:
     formatted_axis_data = []
     for value in axis_data:

metrics.py

@@ -1,5 +1,3 @@
-from __future__ import annotations
-
 import numpy as np
 import rapidfuzz
 import sklearn

model.py

@@ -1,5 +1,3 @@
-from __future__ import annotations
-
 import collections
 import dataclasses
 import types
@@ -30,7 +28,7 @@ class Model:
 
 
 def add_unknown_tokens_to_tokenizer(
-        tokenizer, encoder_decoder, unknown_tokens: list[str]
+    tokenizer, encoder_decoder, unknown_tokens: list[str]
 ):
     tokenizer.add_tokens(unknown_tokens)
     encoder_decoder.decoder.resize_token_embeddings(len(tokenizer))
@@ -53,7 +51,7 @@ def find_unknown_tokens_for_tokenizer(tokenizer) -> collections.Counter:
 
 
 def replace_pad_token_id_with_negative_hundred_for_hf_transformers_automatic_batch_transformation(
-        tokenizer, token_ids
+    tokenizer, token_ids
 ):
     token_ids[token_ids == tokenizer.pad_token_id] = -100
     return token_ids
@@ -144,7 +142,7 @@ def build_model(config: types.SimpleNamespace or object) -> Model:
 
 
 def generate_token_strings(
-        model: Model, images: torch.Tensor, skip_special_tokens=True
+    model: Model, images: torch.Tensor, skip_special_tokens=True
 ) -> list[str]:
     decoder_output = model.encoder_decoder.generate(
         images,

train.py

@@ -1,5 +1,3 @@
-from __future__ import annotations
-
 import os
 
 import pandas as pd
@@ -22,12 +20,12 @@ from utils import set_tokenizers_parallelism, set_torch_device_order_pci_bus
 
 class MetricsCallback(pl.callbacks.Callback):
     def on_validation_batch_start(
-            self, trainer, pl_module, batch: Batch, batch_idx, dataloader_idx=0
+        self, trainer, pl_module, batch: Batch, batch_idx, dataloader_idx=0
     ):
         predicted_strings = generate_token_strings(pl_module.model, images=batch.images)
 
         for expected_data_index, predicted_string in zip(
-                batch.data_indices, predicted_strings, strict=True
+            batch.data_indices, predicted_strings, strict=True
         ):
             benetech_score = benetech_score_string_prediction(
                 expected_data_index=expected_data_index,
@@ -52,7 +50,7 @@ class MetricsCallback(pl.callbacks.Callback):
 
 class TransformersPreTrainedModelsCheckpointIO(pl.plugins.CheckpointIO):
     def __init__(
-            self, pretrained_models: list[transformers.modeling_utils.PreTrainedModel]
+        self, pretrained_models: list[transformers.modeling_utils.PreTrainedModel]
     ):
         super().__init__()
         self.pretrained_models = pretrained_models

utils.py

@@ -1,5 +1,3 @@
-from __future__ import annotations
-
 import os
 import pickle
 from typing import Callable, TypeVar
@@ -16,7 +14,7 @@ def set_torch_device_order_pci_bus():
 
 
 def load_pickle_or_build_object_and_save(
-        pickle_path: str, build_object: Callable[[], T], overwrite=False
+    pickle_path: str, build_object: Callable[[], T], overwrite=False
 ) -> T:
     if overwrite or not os.path.exists(pickle_path):
         pickle.dump(build_object(), open(pickle_path, "wb"))