| Name | multiego JSON |
| Version |
0.0.15
JSON |
| download |
| home_page | |
| Summary | This is ego method.Some of code are non-originality, just copy for use. All the referenced code are marked,details can be shown in their sources |
| upload_time | 2022-12-10 13:57:12 |
| maintainer | wangchangxin |
| docs_url | None |
| author | wangchangxin |
| requires_python | >=3.6 |
| license | |
| keywords |
ego
multiplyego
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# Multiply EGO
EGO (Efficient global optimization) and multiply target EGO method.
References:
Jones, D. R., Schonlau, M. & Welch, W. J. Efficient global optimization of expensive black-box functions. J. Global
Optim. 13, 455–492 (1998)
[](https://pypi.org/project/multiego/)
[](https://github.com/MGEdata/multiego/releases/latest)
# Install
```bash
pip install multiego
```
# Usage
```bash
if __name__ == "__main__":
from sklearn.datasets import fetch_california_housing
import numpy as np
from multiego.ego import search_space, Ego
from sklearn.model_selection import GridSearchCV
from sklearn.svm import SVR
#####model1#####
model = SVR() #pre-trained good model with optimized prarmeters for special features
###
X, y = fetch_california_housing(return_X_y=True)
X = X[:, :5]
searchspace_list = [
np.arange(0.01, 1, 0.1),
np.array([0, 20, 30, 50, 70, 90]),
np.arange(1, 10, 1),
np.array([0, 1]),
np.arange(0.4, 0.6, 0.02),
]
searchspace = search_space(*searchspace_list)
#
me = Ego(searchspace, X, y, 500, model, n_jobs=6)
re = me.egosearch()
```
Introduction
-------------
[**multiego.ego.Ego**](https://github.com/MGEdata/multiego/blob/master/multiego/ego.py)
For `sklean-type` single model.
[**multiego.base_ego.BaseEgo**](https://github.com/MGEdata/multiego/blob/master/multiego/base_ego.py)
1. For any user-defined single model, just need offer mean and std of search space.
2. For big search space out of memory , just need offer mean and std of search space.
[**multiego.multiplyego.MultiEgo**](https://github.com/MGEdata/multiego/blob/master/multiego/multiplyego.py)
For `sklean-type` models.
[**multiego.base_multiplyego.BaseMultiEgo**](https://github.com/MGEdata/multiego/blob/master/multiego/base_multiplyego.py)
1. For any user-defined models, just need offer predict_y of search space.
2. For big search space out of memory, just need offer predict_y of search space.
link
-----------
More examples can be found in [test](https://github.com/MGEdata/multiego/tree/master/test).
More powerful can be found [mipego](https://github.com/wangronin/MIP-EGO)
Raw data
{
"_id": null,
"home_page": "",
"name": "multiego",
"maintainer": "wangchangxin",
"docs_url": null,
"requires_python": ">=3.6",
"maintainer_email": "",
"keywords": "ego,multiplyego",
"author": "wangchangxin",
"author_email": "986798607@qq.com",
"download_url": "https://files.pythonhosted.org/packages/93/1a/4958391a3b271b9de5cb1def946cf2823110e868dcf165091a37adc72265/multiego-0.0.15.tar.gz",
"platform": "Windows",
"description": "# Multiply EGO\r\n\r\nEGO (Efficient global optimization) and multiply target EGO method.\r\n\r\nReferences:\r\nJones, D. R., Schonlau, M. & Welch, W. J. Efficient global optimization of expensive black-box functions. J. Global\r\nOptim. 13, 455\u2013492 (1998)\r\n\r\n[](https://pypi.org/project/multiego/)\r\n[](https://github.com/MGEdata/multiego/releases/latest)\r\n\r\n\r\n# Install\r\n\r\n```bash\r\npip install multiego\r\n```\r\n\r\n# Usage\r\n\r\n```bash\r\nif __name__ == \"__main__\":\r\n from sklearn.datasets import fetch_california_housing\r\n import numpy as np\r\n from multiego.ego import search_space, Ego\r\n from sklearn.model_selection import GridSearchCV\r\n from sklearn.svm import SVR\r\n\r\n #####model1#####\r\n model = SVR() #pre-trained good model with optimized prarmeters for special features\r\n ###\r\n\r\n X, y = fetch_california_housing(return_X_y=True)\r\n X = X[:, :5] \r\n searchspace_list = [\r\n np.arange(0.01, 1, 0.1),\r\n np.array([0, 20, 30, 50, 70, 90]),\r\n np.arange(1, 10, 1),\r\n np.array([0, 1]),\r\n np.arange(0.4, 0.6, 0.02),\r\n ]\r\n searchspace = search_space(*searchspace_list)\r\n #\r\n me = Ego(searchspace, X, y, 500, model, n_jobs=6)\r\n\r\n re = me.egosearch()\r\n```\r\n\r\nIntroduction\r\n-------------\r\n[**multiego.ego.Ego**](https://github.com/MGEdata/multiego/blob/master/multiego/ego.py) \r\n\r\nFor `sklean-type` single model.\r\n\r\n[**multiego.base_ego.BaseEgo**](https://github.com/MGEdata/multiego/blob/master/multiego/base_ego.py)\r\n\r\n1. For any user-defined single model, just need offer mean and std of search space.\r\n2. For big search space out of memory , just need offer mean and std of search space.\r\n\r\n[**multiego.multiplyego.MultiEgo**](https://github.com/MGEdata/multiego/blob/master/multiego/multiplyego.py)\r\n\r\nFor `sklean-type` models.\r\n\r\n[**multiego.base_multiplyego.BaseMultiEgo**](https://github.com/MGEdata/multiego/blob/master/multiego/base_multiplyego.py) \r\n\r\n1. For any user-defined models, just need offer predict_y of search space.\r\n2. For big search space out of memory, just need offer predict_y of search space.\r\n\r\nlink\r\n-----------\r\nMore examples can be found in [test](https://github.com/MGEdata/multiego/tree/master/test).\r\n\r\nMore powerful can be found [mipego](https://github.com/wangronin/MIP-EGO)\r\n\r\n",
"bugtrack_url": null,
"license": "",
"summary": "This is ego method.Some of code are non-originality, just copy for use. All the referenced code are marked,details can be shown in their sources",
"version": "0.0.15",
"split_keywords": [
"ego",
"multiplyego"
],
"urls": [
{
"comment_text": "",
"digests": {
"md5": "82904f09280d404f5a9da3dbfef13366",
"sha256": "32dca1af119f75934a9cab4de204ed172d94ffce1d90175e233e859faa861461"
},
"downloads": -1,
"filename": "multiego-0.0.15.tar.gz",
"has_sig": false,
"md5_digest": "82904f09280d404f5a9da3dbfef13366",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.6",
"size": 14504,
"upload_time": "2022-12-10T13:57:12",
"upload_time_iso_8601": "2022-12-10T13:57:12.526289Z",
"url": "https://files.pythonhosted.org/packages/93/1a/4958391a3b271b9de5cb1def946cf2823110e868dcf165091a37adc72265/multiego-0.0.15.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2022-12-10 13:57:12",
"github": false,
"gitlab": false,
"bitbucket": false,
"lcname": "multiego"
}
