style: Black

src/hatespeech/clean_data.py

@@ -180,7 +180,6 @@ def clean_text(text: str) -> Union[str, None]:
     # Replace 8 digits with " [CVR] " if "cvr" is in the text, else replace with
     # " [PHONE] " Check if an 8 digit number is present in text
     if re.search(r"(?<!\d)(\d\d ?){4}(?!\d)", text):
-
         # Check if 'cvr' in text
         if "cvr" in text.lower():
             text = re.sub(r"(?<!\d)(\d\d ?){4}(?!\d)", " [CVR] ", text)

src/hatespeech/labelling_functions.py

@@ -39,7 +39,6 @@ def initialise_models():
 
     # Initialise progress bar
     with tqdm(desc="Loading models", total=6, leave=False) as pbar:
-
         # Download word tokenizer if not already downloaded
         try:
             nltk.download("punkt", quiet=True)

src/hatespeech/prepare_data_for_annotation.py

@@ -36,7 +36,6 @@ def prepare_data_for_annotation(config: DictConfig) -> List[str]:
     # resulting dataframe in the annotated directory, and split up the dataframe into a
     # validation and test split, and store those too
     if config.testing:
-
         # Create test annotated data
         labels = [np.random.choice(["Offensive", "Not Offensive"]) for _ in texts]
         df_test = pd.DataFrame({"text": texts, "label": labels})