style: update

Author: j5g-moon

src/dataset.py

@@ -40,8 +40,12 @@ def __init__(
         self.model_config = OmegaConf.load(model_config_dir / "transformers.yaml")
         self.tokenizer_config = OmegaConf.load(self.tokenizer_config_path)
         self.tokenizer = SentencePieceBPETokenizer(
-            vocab_file=str(tokenizer_dir / (self.tokenizer_config.tokenizer_name + "-vocab.json")),
-            merges_file=str(tokenizer_dir / (self.tokenizer_config.tokenizer_name + "-merges.txt")),
+            vocab_file=str(
+                tokenizer_dir / (self.tokenizer_config.tokenizer_name + "-vocab.json")
+            ),
+            merges_file=str(
+                tokenizer_dir / (self.tokenizer_config.tokenizer_name + "-merges.txt")
+            ),
         )
         self.source_lines = source_lines
         self.target_lines = target_lines
@@ -50,7 +54,9 @@ def __len__(self) -> int:
         return len(self.source_lines)
 
     def __getitem__(self, index: int) -> Tuple[List[int], List[int]]:
-        source_encoded, target_encoded = self.collate(self.source_lines[index], self.target_lines[index])
+        source_encoded, target_encoded = self.collate(
+            self.source_lines[index], self.target_lines[index]
+        )
         return source_encoded, target_encoded
 
     def _encode(

tests/__init__.py

@@ -1,5 +1,4 @@
 import os
 import sys
 
-
 sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), "..")))

tests/test_dataset.py

@@ -1,5 +1,4 @@
 import pytest  # noqa: E902
-
 from tokenizers import SentencePieceBPETokenizer
 
 from dataset import WMT14Dataset

tests/test_load_dataset.py

@@ -6,4 +6,3 @@
 @pytest.mark.parametrize("langpair", ["de-en"])
 def test_setup(langpair):
     dm = WMT14DataModule(langpair)
-

tests/test_utils.py

@@ -2,7 +2,7 @@
 
 from src.utils import read_lines
 
-test_filepath = 'data/example.de'
+test_filepath = "data/example.de"
 
 
 @pytest.mark.parametrize("filepath", test_filepath)