kg-agent/scripts/analyze_production_data.py

"""Generate field profiles, quality assessments, and QA context for production data."""

from __future__ import annotations

import argparse
import sys
from pathlib import Path

from step1_data_aggregation.data_analysis import analyze_production_data_from_env


ROOT = Path(__file__).resolve().parents[1]


def main() -> None:
    if hasattr(sys.stdout, "reconfigure"):
        sys.stdout.reconfigure(encoding="utf-8")
    parser = argparse.ArgumentParser(description="为 production Excel 生成字段分析、质量评估和 QA 上下文")
    parser.add_argument("--templates", type=Path, help="metadata directory (overrides METADATA_TEMPLATE_DIR)")
    parser.add_argument("--production", type=Path, default=ROOT / "data" / "production")
    parser.add_argument("--output", type=Path, default=ROOT / "data" / "production" / "analysis")
    args = parser.parse_args()
    results = analyze_production_data_from_env(
        dotenv_path=ROOT / ".env",
        template_dir=args.templates,
        production_dir=args.production,
        analysis_dir=args.output,
    )
    print("已生成生产数据字段分析与质量评估：")
    for result in results:
        print(
            f"- {result.template}: {result.row_count} 行, {result.field_count} 字段, "
            f"质量分 {result.quality_score:g} -> {result.report_file}"
        )


if __name__ == "__main__":
    main()