"""
Generate synthetic manual-labeled data for ML model training/demo.
Run this script after metadata has been scanned so there are columns to label.
"""
import random
import sys
import os

sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))

from app.core.database import SessionLocal
from app.models.metadata import DataColumn
from app.models.classification import Category
from app.models.project import ClassificationResult


def main():
    db = SessionLocal()
    try:
        columns = db.query(DataColumn).limit(300).all()
        if not columns:
            print("No columns found in database. Please scan a data source first.")
            return

        categories = db.query(Category).filter(Category.level == 2).all()
        if not categories:
            print("No sub-categories found.")
            return

        # Clear old manual labels to avoid duplicates
        db.query(ClassificationResult).filter(ClassificationResult.source == "manual").delete()
        db.commit()

        count = 0
        for col in columns:
            # Deterministic pseudo-random based on column name for reproducibility
            rng = random.Random(col.name)
            cat = rng.choice(categories)
            # Create a fake manual result (project_id=1 assumed to exist or None)
            result = ClassificationResult(
                project_id=None,
                column_id=col.id,
                category_id=cat.id,
                level_id=cat.parent.level if cat.parent else 3,  # fallback
                source="manual",
                confidence=1.0,
                status="manual",
            )
            db.add(result)
            count += 1

        db.commit()
        print(f"Generated {count} manual labels across {len(categories)} categories.")
    finally:
        db.close()


if __name__ == "__main__":
    main()