from datasets import load_dataset
import streamlit as st
import pandas as pd
from huggingface_hub import HfApi, list_models
import os
import datasets
from datasets import Dataset, DatasetDict
from huggingface_hub import HfFileSystem
fs = HfFileSystem()

# from datasets import Dataset
# Dataset.cleanup_cache_files

DATASET_REPO_URL = "https://huggingface.co/datasets/Seetha/visual_cs"
DATA_FILENAME = "final_data.csv"
DATA_FILE = os.path.join("data", DATA_FILENAME)


st.write('dataset')
dataset = load_dataset("Seetha/visual_cs")
df = pd.DataFrame.from_dict(dataset["train"])

st.write('dataset-retrieved')
st.write(df)

HF_TOKEN = os.environ.get("HF_TOKEN")
st.write("is none?", HF_TOKEN is None)
HfApi().delete_file(path_in_repo = DATA_FILENAME ,repo_id = 'Seetha/visual_cs',token= HF_TOKEN,repo_type='dataset')
st.write('file-deleted')

st.write('Read the CSV file')
data_stakeholdercount = pd.read_csv('final_data.csv')
st.write(data_stakeholdercount)

tds = Dataset.from_pandas(data_stakeholdercount)
ds = DatasetDict()

ds['train'] = tds

st.write(ds)
ds.push_to_hub('Seetha/visual_cs',token= HF_TOKEN)
df.to_csv("hf://datasets/Seetha/visual_cs/test.csv")