import kagglehub
import os
import json
import logging
import pandas as pd
from typing import List, Dict

# Setup logging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
logger = logging.getLogger(__name__)

# Paths
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
DATASETS_DIR = os.path.join(BASE_DIR, "datasets")
RAW_DIR = os.path.join(DATASETS_DIR, "raw")
PROCESSED_DIR = os.path.join(DATASETS_DIR, "processed")

os.makedirs(RAW_DIR, exist_ok=True)
os.makedirs(PROCESSED_DIR, exist_ok=True)

class MedicalDataFetcher:
    """Fetches professional medical datasets using kagglehub and public sources"""
    
    def __init__(self):
        self.dataset_map = {
            "medquad": "vishweshsalodkar/medquad-medical-q-a-dataset",
            "healthtap": "itachi9604/healthtap-dataset", # Community curated
            "disease_symptoms": "kaushil268/disease-prediction-using-machine-learning"
        }

    def fetch_all(self):
        """Fetch all mapped datasets"""
        results = {}
        for name, kg_id in self.dataset_map.items():
            try:
                logger.info(f"Fetching {name} from Kaggle: {kg_id}...")
                path = kagglehub.dataset_download(kg_id)
                results[name] = path
                logger.info(f"✓ {name} available at {path}")
            except Exception as e:
                logger.error(f"✗ Failed to fetch {name}: {e}")
        return results

    def verify_local_data(self):
        """Check for existing data in standard paths"""
        paths = {
            "medquad_local": os.path.join(DATASETS_DIR, "medquad", "sample_data.json"),
            "symcat_local": os.path.join(DATASETS_DIR, "symcat", "symptoms.json")
        }
        for name, path in paths.items():
            if os.path.exists(path):
                logger.info(f"✓ Found local data: {name} at {path}")
            else:
                logger.warning(f"! Missing local data: {name}")

if __name__ == "__main__":
    fetcher = MedicalDataFetcher()
    fetcher.verify_local_data()
    # In a real environment, we'd run fetch_all() but since we are in a sandbox 
    # we will prioritize processing what's available and providing placeholders 
    # for the user to populate if Kaggle is restricted.
    print("\n--- Summary ---")
    print("Fetch script ready. Run this locally to populate 'datasets/raw' if data is missing.")