GBDT_Simple_Tutorial icon indicating copy to clipboard operation
GBDT_Simple_Tutorial copied to clipboard

verified publisher icon Freemanzxp
→

Metadata

python实现GBDT的回归、二分类以及多分类，将算法流程详情进行展示解读并可视化，庖丁解牛地理解GBDT。Gradient Boosting Decision Trees regression, dichotomy and multi-classification are realized based on py...

Results 5 GBDT_Simple_Tutorial issues
Sort by recently updated
recently updated
newest added

如何保存并读取模型

请问如何保存模型到本地，并读取呢

jiangminmin avatar jiangminmin

多分类数据集中为啥其中两个一样的数据： [4, 30, 60, 1], [5, 30, 60, 2] 被分为不同类别

多分类数据集中为啥其中两个一样的数据： [4, 30, 60, 1], [5, 30, 60, 2] 被分为不同类别

jiangminmin avatar jiangminmin

pydotplus.graphviz.InvocationException: Program terminated with status: 1. stderr follows: Format: "png" not recognized. Use one of:

2 comment

LHH-James avatar LHH-James

数据获取

请问训练数据和测试数据从哪获取呢

scjaiyueliang avatar scjaiyueliang

BinomialDeviance损失函数中损失函数计算错误

2 comment

你好，个人认为，BinomialDeviance损失函数中，计算loss的公式有问题，类似于sklearn包中的损失计算，此处的正确的公式应该是：-2.0（y*f - log（1 + exp(f)）），代码中是-2.0（y*f - （1 + exp(f)））

zhang2010hao avatar zhang2010hao

← Metadata

708
Stars
195
Forks
Watchers

Owner

verified publisher icon Freemanzxp

Metadata

python实现GBDT的回归、二分类以及多分类，将算法流程详情进行展示解读并可视化，庖丁解牛地理解GBDT。Gradient Boosting Decision Trees regression, dichotomy and multi-classification are realized based on py...

Back