Skip to content

Commit

Permalink
xgboost 调参数
Browse files Browse the repository at this point in the history
  • Loading branch information
shataowei committed Nov 20, 2019
1 parent 8a4d15f commit 7de3286
Show file tree
Hide file tree
Showing 3 changed files with 21 additions and 57 deletions.
69 changes: 13 additions & 56 deletions .idea/workspace.xml

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

1 change: 1 addition & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -242,6 +242,7 @@
- [xgboost特征重要性是如何得到的](机器学习/集成学习/Xgboost.md#L164)
- [XGBoost中如何对树进行剪枝](机器学习/集成学习/Xgboost.md#L164)
- [XGBoost模型如果过拟合了怎么解决](机器学习/集成学习/Xgboost.md#L164)
- [xgboost如何调参数](机器学习/集成学习/Xgboost.md#L164)
- FM/FFM
- SVM
- [简单介绍SVM](机器学习/支持向量机/支持向量机.md#L164)
Expand Down
8 changes: 7 additions & 1 deletion 机器学习/集成学习/Xgboost.md
Original file line number Diff line number Diff line change
Expand Up @@ -76,4 +76,10 @@ MAPE:![](https://tva1.sinaimg.cn/large/006y8mN6gy1g94mx7uyuej303f0170sj.jpg)
- 增大叶子结点的权重
- 增大惩罚系数
- subsample的力度变大,降低异常点的影响
- 减小learning rate,提高estimator
- 减小learning rate,提高estimator

# xgboost如何调参数?
- 先确定learningrate和estimator
- 再确定每棵树的基本信息,max_depth和 min_child_weight
- 再确定全局信息:比如最小分裂增益,子采样参数,正则参数
- 重新降低learningrate,得到最优解

0 comments on commit 7de3286

Please sign in to comment.