easy-ml/train_test_xgb.py

# -*- coding: utf-8 -*-
"""
@author: yq
@time: 2024/11/27
@desc: 
"""
import time

from entitys import DataSplitEntity, MlConfigEntity
from pipeline import Pipeline

if __name__ == "__main__":
    time_now = time.time()
    import scorecardpy as sc

    # 加载数据
    dat = sc.germancredit()
    dat_columns = dat.columns.tolist()
    dat_columns = [c.replace(".","_") for c in dat_columns]
    dat.columns = dat_columns

    dat["creditability"] = dat["creditability"].apply(lambda x: 1 if x == "bad" else 0)

    # dat["credit_amount_corr1"] = dat["credit_amount"] * 2
    # dat["credit_amount_corr2"] = dat["credit_amount"] * 3

    data = DataSplitEntity(train_data=dat[:709], test_data=dat[709:])

    # 训练并生成报告
    # train_pipeline = Pipeline(MlConfigEntity.from_config('config/demo/ml_config_template.json'), data)
    # 特征处理
    cfg = {
        # 项目名称，影响数据存储位置
        "project_name": "demo",
        # jupyter下输出内容
        "jupyter_print": True,
        # 是否开启粗分箱
        "format_bin": True,
        "max_feature_num": 20,
        # 压力测试
        "stress_test": True,
        # 压力测试抽样次数
        "stress_sample_times": 10,
        # y
        "y_column": "creditability",
        # 参与建模的候选变量
        # "x_columns": [
        # "duration_in_month",
        # "credit_amount",
        # "age_in_years",
        # "purpose",
        # "credit_history",
        # "random",

        # "credit_amount_corr1",
        # "credit_amount_corr2",
        #   ],
        # 变量释义
        "columns_anns": {
            "age_in_years": "年龄",
            "credit_history": "借贷历史"
        },
        # 被排除的变量
        "columns_exclude": [],
        # 强制使用的变量
        # "columns_include": ["credit_amount"],
        "model_type": "xgb",
        "feature_strategy": "norm",
    }

    train_pipeline = Pipeline(data=data, **cfg)
    train_pipeline.train()
    train_pipeline.report()

    print(time.time() - time_now)