XGB-25:Callback函数

本文档提供了XGBoost Python包中使用的回调API的基本概述。在XGBoost 1.3中,为Python包设计了一个新的回调接口,它为设计各种扩展提供了灵活性,用于训练。此外,XGBoost还预定义了许多回调函数,用于支持提前停止early stopping、检查点checkpoints等。

使用内置回调函数

默认情况下,XGBoost 中的训练方法具有参数,如 early_stopping_roundsverbose/verbose_eval,当指定这些参数时,训练过程将在内部定义相应的回调函数。例如,当指定了 early_stopping_rounds 时,EarlyStopping 回调将在迭代循环内调用。也可以直接将此回调函数传递给 XGBoost:

python 复制代码
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split

import xgboost as xgb
import numpy as np

X, y = load_breast_cancer(return_X_y=True)
X_train, X_valid, y_train, y_valid = train_test_split(X, y, stratify=y, random_state=94)

D_train = xgb.DMatrix(X_train, y_train)
D_valid = xgb.DMatrix(X_valid, y_valid)

# Define a custom evaluation metric used for early stopping.
def eval_error_metric(predt, dtrain: xgb.DMatrix):
    label = dtrain.get_label()
    r = np.zeros(predt.shape)
    gt = predt > 0.5
    r[gt] = 1 - label[gt]
    le = predt <= 0.5
    r[le] = label[le]
    return 'CustomErr', np.sum(r)

# Specify which dataset and which metric should be used for early stopping.
early_stop = xgb.callback.EarlyStopping(rounds=early_stopping_rounds,
                                        metric_name='CustomErr',
                                        data_name='Train')

booster = xgb.train(
    {'objective': 'binary:logistic',
     'eval_metric': ['error', 'rmse'],
     'tree_method': 'hist'}, D_train,
    evals=[(D_train, 'Train'), (D_valid, 'Valid')],
    feval=eval_error_metric,
    num_boost_round=1000,
    callbacks=[early_stop],
    verbose_eval=False)

dump = booster.get_dump(dump_format='json')
assert len(early_stop.stopping_history['Train']['CustomErr']) == len(dump)

定义自己的回调函数

XGBoost提供了一个回调接口类:TrainingCallback,用户定义的回调应该继承这个类并覆盖相应的方法。在示例中有使用和定义回调函数的工作示例。

python 复制代码
import argparse
import os
import tempfile
from typing import Dict

import numpy as np
from matplotlib import pyplot as plt
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split

import xgboost as xgb


class Plotting(xgb.callback.TrainingCallback):
    """Plot evaluation result during training.  Only for demonstration purpose as it's
    quite slow to draw using matplotlib.

    """

    def __init__(self, rounds: int) -> None:
        self.fig = plt.figure()
        self.ax = self.fig.add_subplot(111)
        self.rounds = rounds
        self.lines: Dict[str, plt.Line2D] = {}
        self.fig.show()
        self.x = np.linspace(0, self.rounds, self.rounds)
        plt.ion()

    def _get_key(self, data: str, metric: str) -> str:
        return f"{data}-{metric}"

    def after_iteration(
        self, model: xgb.Booster, epoch: int, evals_log: Dict[str, dict]
    ) -> bool:
        """Update the plot."""
        if not self.lines:
            for data, metric in evals_log.items():
                for metric_name, log in metric.items():
                    key = self._get_key(data, metric_name)
                    expanded = log + [0] * (self.rounds - len(log))
                    (self.lines[key],) = self.ax.plot(self.x, expanded, label=key)
                    self.ax.legend()
        else:
            # https://pythonspot.com/matplotlib-update-plot/
            for data, metric in evals_log.items():
                for metric_name, log in metric.items():
                    key = self._get_key(data, metric_name)
                    expanded = log + [0] * (self.rounds - len(log))
                    self.lines[key].set_ydata(expanded)
            self.fig.canvas.draw()
        # False to indicate training should not stop.
        return False


def custom_callback() -> None:
    """Demo for defining a custom callback function that plots evaluation result during
    training."""
    X, y = load_breast_cancer(return_X_y=True)
    X_train, X_valid, y_train, y_valid = train_test_split(X, y, random_state=0)

    D_train = xgb.DMatrix(X_train, y_train)
    D_valid = xgb.DMatrix(X_valid, y_valid)

    num_boost_round = 100
    plotting = Plotting(num_boost_round)

    # Pass it to the `callbacks` parameter as a list.
    xgb.train(
        {
            "objective": "binary:logistic",
            "eval_metric": ["error", "rmse"],
            "tree_method": "hist",
            "device": "cuda",
        },
        D_train,
        evals=[(D_train, "Train"), (D_valid, "Valid")],
        num_boost_round=num_boost_round,
        callbacks=[plotting],
    )


def check_point_callback() -> None:
    """Demo for using the checkpoint callback. Custom logic for handling output is
    usually required and users are encouraged to define their own callback for
    checkpointing operations. The builtin one can be used as a starting point.

    """
    # Only for demo, set a larger value (like 100) in practice as checkpointing is quite
    # slow.
    rounds = 2

    def check(as_pickle: bool) -> None:
        for i in range(0, 10, rounds):
            if i == 0:
                continue
            if as_pickle:
                path = os.path.join(tmpdir, "model_" + str(i) + ".pkl")
            else:
                path = os.path.join(
                    tmpdir,
                    f"model_{i}.{xgb.callback.TrainingCheckPoint.default_format}",
                )
            assert os.path.exists(path)

    X, y = load_breast_cancer(return_X_y=True)
    m = xgb.DMatrix(X, y)
    # Check point to a temporary directory for demo
    with tempfile.TemporaryDirectory() as tmpdir:
        # Use callback class from xgboost.callback
        # Feel free to subclass/customize it to suit your need.
        check_point = xgb.callback.TrainingCheckPoint(
            directory=tmpdir, interval=rounds, name="model"
        )
        xgb.train(
            {"objective": "binary:logistic"},
            m,
            num_boost_round=10,
            verbose_eval=False,
            callbacks=[check_point],
        )
        check(False)

        # This version of checkpoint saves everything including parameters and
        # model.  See: doc/tutorials/saving_model.rst
        check_point = xgb.callback.TrainingCheckPoint(
            directory=tmpdir, interval=rounds, as_pickle=True, name="model"
        )
        xgb.train(
            {"objective": "binary:logistic"},
            m,
            num_boost_round=10,
            verbose_eval=False,
            callbacks=[check_point],
        )
        check(True)


if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("--plot", default=1, type=int)
    args = parser.parse_args()

    check_point_callback()

    if args.plot:
        custom_callback()

参考

相关推荐
蹦蹦跳跳真可爱5892 小时前
Python----计算机视觉处理(Opencv:道路检测之提取车道线)
python·opencv·计算机视觉
Tanecious.4 小时前
机器视觉--python基础语法
开发语言·python
ALe要立志成为web糕手4 小时前
SESSION_UPLOAD_PROGRESS 的利用
python·web安全·网络安全·ctf
Tttian6225 小时前
Python办公自动化(3)对Excel的操作
开发语言·python·excel
蹦蹦跳跳真可爱5896 小时前
Python----机器学习(KNN:使用数学方法实现KNN)
人工智能·python·机器学习
独好紫罗兰6 小时前
洛谷题单2-P5713 【深基3.例5】洛谷团队系统-python-流程图重构
开发语言·python·算法
DREAM.ZL8 小时前
基于python的电影数据分析及可视化系统
开发语言·python·数据分析
Uncertainty!!8 小时前
python函数装饰器
开发语言·python·装饰器
吾日三省吾码9 小时前
Python 脚本:自动化你的日常任务
数据库·python·自动化
snowfoootball9 小时前
基于 Ollama DeepSeek、Dify RAG 和 Fay 框架的高考咨询 AI 交互系统项目方案
前端·人工智能·后端·python·深度学习·高考