#!/usr/bin/env python3 """Verify data on Hugging Face""" import os import logging import pandas as pd from huggingface_hub import hf_hub_download logging.basicConfig(level=logging.INFO) logger = logging.getLogger(__name__) HF_TOKEN = os.getenv("HF_TOKEN") HF_USERNAME = os.getenv("HF_USERNAME", "SharleyK") DATASET_NAME = os.getenv("DATASET_NAME", "PredictiveMaintenance") repo_id = f"{HF_USERNAME}/{DATASET_NAME}" logger.info(f"Verifying dataset: {repo_id}") downloaded_file = hf_hub_download( repo_id=repo_id, repo_type="dataset", filename="engine_data.csv", token=HF_TOKEN) df = pd.read_csv(downloaded_file) logger.info(f"✓ Dataset shape: {df.shape}") logger.info(f"✓ Columns: {list(df.columns)}") logger.info("✓ Data verification completed!")