Comments (3)
No "group" is defined in HyperGBM now, but it accepts the cross_validator
option to override default settings in cross validation(KFold for regression task and StratifiedKFold for classification task). So you can fake a grouped KFold as cross_validator
to run HyperGBM.
We'll document the cross_validator
option in next release, thank you for your issue.
from hypergbm.
From @talhaanwarch
can you provide a simple snippet ?
You can fake and use a grouped KFold like:
import numpy as np
from sklearn.model_selection import GroupKFold
class MyFakedGroupKFold(GroupKFold):
def get_my_groups(self, X, y):
# setup your groups here
groups = np.random.random_integers(0, self.n_splits, size=(len(y),))
return groups
def split(self, X, y=None, groups=None):
my_groups = self.get_my_groups(X, y)
yield from super().split(X, y, groups=my_groups)
experiment = make_experiment(...
cv=True,
num_fold=3,
cross_validator=MyFakedGroupKFold(n_splits=3),
)
from hypergbm.
@talhaanwarch
I'm so sorry that I deleted your comment by mistake.
from hypergbm.
Related Issues (20)
- How can I build my own dataset? HOT 1
- 我遇到个依赖问题 HOT 2
- bug HOT 1
- TypeError: fit() got an unexpected keyword argument 'verbose' HOT 2
- 运行hypergbm/examples/01.quick-start.ipynb时,trial会报错cannot pickle '_hashlib.HASH' object HOT 3
- May I use a new dataset as the test or validation set instead of splitting it from the training set? HOT 1
- 如何获取ensemble后的最好模型参数 HOT 3
- 运行简单示例程序报错 HOT 8
- 使用Shap对生成的融合模型进行解释 HOT 1
- 怎么提高max_no_improvement_trials HOT 1
- Multiclass and F1 estimator error HOT 2
- In the feature selection stage, no feature is selected.
- 共线性检测 HOT 1
- HyperGBM run on K8s when set the limits of cpu and memory HOT 2
- collinearity_detection has a error when training if using dask distrubuted HOT 2
- Dependencies are broken. Release 0.2.5.4 (the stable) HOT 2
- Feature generation error HOT 2
- Jupyter不显示可视化 HOT 2
- 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。 HOT 5
- hypergbm fiting bug HOT 11
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from hypergbm.