机器学习之基础算法（提升）

第一部分 提升

提升的概念

梯度提升方法 GBDT

梯度提升算法推导

总结

XGBoost

决策树的描述

正则项的定义

XGBoost算法的推导

总结

Adaboost

举例

e2是误分点的权重之和

总结

第二部分 代码示例

# /usr/bin/python
# -*- encoding:utf-8 -*-

import xgboost as xgb
import numpy as np

# 1、xgBoost的基本使用
# 2、自定义损失函数的梯度和二阶导
# 3、binary:logistic/logitraw


# 定义f: theta * x
def log_reg(y_hat, y):
    p = 1.0 / (1.0 + np.exp(-y_hat))
    g = p - y.get_label()
    h = p * (1.0-p)
    return g, h


def error_rate(y_hat, y):
    return 'error', float(sum(y.get_label() != (y_hat > 0.5))) / len(y_hat)


if __name__ == "__main__":
    # 读取数据
    data_train = xgb.DMatrix('agaricus_train.txt')
    data_test = xgb.DMatrix('agaricus_test.txt')
    print data_train
    print type(data_train)

    # 设置参数
    param = {
   'max_depth': 3, 'eta': 1, 'silent': 1, 'objective': 'binary:logistic'} # logitraw
    # param = {'max_depth': 3, 'eta': 0.3, 'silent': 1, 'objective': 'reg:logistic'}
    watchlist = [(data_test, 'eval'), (data_train, 'train')]
    n_round = 7
    # bst = xgb.train(param, data_train, num_boost_round=n_round, evals=watchlist)
    bst = xgb.train(param, data_train, num_boost_round=n_round, evals=watchlist, obj=log_reg, feval=error_rate)

    # 计算错误率
    y_hat = bst.predict(data_test)
    y = data_test.get_label()
    print y_hat
    print y
    error = sum(y != (y_hat > 0.5))
    error_rate = float(error) / len(y_hat)
    print '样本总数