HyperGBM

HyperGBM copied to clipboard

oaksharks

共线性检测

1

请问共线性检测是计算方差膨胀系数吗？输出结果是保留某个特征，对应的删除某个特征，这个依据是什么？

apooth

In the feature selection stage, no feature is selected, and an error was returned: `07-11 13:49:59 I hypernets.e.compete.py 882 - feature_selection drop 10 columns, 0 kept` ` raise ValueError("No data...

zhangxjohn

怎么提高max_no_improvement_trials

1

在搜索中中很容易因为达到了max_no_improvement_trials就终止搜索，怎么禁用掉这一项，或者把它设高点？

flyleeee

LIUZhaohan0

运行hypergbm/examples/01.quick-start.ipynb时，trial会报错cannot pickle '_hashlib.HASH' object

3

**System information** - OS Platform and Distribution : centos 7.6 - Python version: 3.8.18 - HyperGBM version: 0.3.0 **Describe the current behavior** 运行到下面这行代码时， experiment = make_experiment(train_data.copy(), target='target', reward_metric='precision', pos_label=1,random_state=1234, max_trials=20)...

calculatechen

bug

1

程序运行报错. **System information** - OS Platform and Distribution (e.g., CentOS 7.6):linux - Python version:3.7 - HyperGBM version:0.3.0 - Other Python packages(run `pip list`): - Package Version ------------------ ------------ backcall 0.2.0...

wangjianqiao111

TypeError: fit() got an unexpected keyword argument 'verbose'

2

Please make sure that this is a bug. **System information** - OS Platform and Distribution (e.g., CentOS 7.6):linux - Python version:3.7 - HyperGBM version:0.3.0 - Other Python packages(run `pip list`):...

wangjianqiao111

如何写自定义评价函数，需要保证训练集和验证集的AUC差的最小，且验证AUC最好的。

5

示例中的reward_metric的函数，好像只传了训练集的预测值和实际值？

cfkstat

Jupyter不显示可视化

2

HyperGBM[notebook]在Jypter不显示可视化

cfkstat