from datasets import load_dataset as hf_load_dataset
from pandas import DataFrame, read_csv

REPO_ID = "kompiangg/twitter_hate_speech_classification"

def load_dataset(filename) -> DataFrame:
  datasets = hf_load_dataset(
    REPO_ID, 
    data_files=filename, 
    encoding='latin-1',
    cache_dir='./.cache'
  )

  df = DataFrame(data=datasets['train'])

  return df