clarin_datasets/cst_wikinews_dataset.py

import pandas as pd
from datasets import load_dataset
import streamlit as st

from clarin_datasets.dataset_to_show import DatasetToShow


class CSTWikinewsDataset(DatasetToShow):
    def __init__(self):
        DatasetToShow.__init__(self)
        self.dataset_name = "clarin-pl/cst-wikinews"
        self.description = """

        """

    def load_data(self):
        raw_dataset = load_dataset(self.dataset_name)
        self.data_dict = {
            subset: raw_dataset[subset].to_pandas() for subset in self.subsets
        }

    def show_dataset(self):
        pass