easy-ml/test/ol_test_xgb.py

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

from entitys import DataSplitEntity
from online_learning import OnlineLearningTrainerXgb

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)

    data = DataSplitEntity(train_data=dat[:609], test_data=dat[609:])

    # 特征处理
    cfg = {
        # 模型，请参考ol_resources_demo目录下文件
        # 模型文件 model.pkl
        "path_resources": "/root/notebook/ol_resources_demo",
        # 项目名称，影响数据存储位置
        "project_name": "OnlineLearningDemo",
        "y_column": "creditability",
        # 学习率
        "lr": 0.01,
        "jupyter_print": True,
        # 压力测试
        "stress_test": False,
        # 压力测试抽样次数
        "stress_sample_times": 10,
        "columns_anns": {
            "age_in_years": "年龄"
        },
        "params_xgb": {
            'objective': 'binary:logistic',
            'eval_metric': 'auc',
            'learning_rate': 0.1,
            'max_depth': 3,
            'subsample': None,
            'colsample_bytree': None,
            'alpha': 0,
            'lambda': 1,
            'num_boost_round': 7,
            'early_stopping_rounds': 20,
            'verbose_eval': 10,
            'random_state': 2025,
            'save_pmml': True,
            'trees_print': False,
            # tree_refresh tree_add
            'oltype': "tree_add",
            'add_columns': ['age_in_years'],
        }
    }

    # 训练并生成报告
    trainer = OnlineLearningTrainerXgb(data=data, **cfg)
    trainer.train()
    trainer.report()

    print(time.time() - time_now)