defect-analysis/analyze_key_factors.py

"""查找不良关键因子。"""

import argparse

import pandas as pd

from defect_analysis.ml.key_factors import find_key_factors
from defect_analysis.schemas import normalize_defect_schema


def analyze_csv_key_factors(csv_path, *, target_defect_type=None, target_severity=None, top_n=20):
    df = pd.read_csv(csv_path, parse_dates=["timestamp"], encoding="utf-8-sig")
    df = normalize_defect_schema(df)
    return find_key_factors(
        df,
        target_defect_type=target_defect_type,
        target_severity=target_severity,
        top_n=top_n,
    )


def main():
    parser = argparse.ArgumentParser(description="查找不良关键因子")
    parser.add_argument("--csv", default="defect_data.csv", help="缺陷 CSV 文件路径")
    parser.add_argument("--target-defect-type", help="目标缺陷类型，例如 气泡/划痕/漏光")
    parser.add_argument("--target-severity", help="目标严重等级，例如 严重")
    parser.add_argument("--top-n", type=int, default=20)
    args = parser.parse_args()

    result = analyze_csv_key_factors(
        args.csv,
        target_defect_type=args.target_defect_type,
        target_severity=args.target_severity,
        top_n=args.top_n,
    )
    if result.empty:
        print("未找到显著关键因子，请检查目标条件或增加样本量。")
    else:
        print(result.to_string(index=False))


if __name__ == "__main__":
    main()