| Name | ICPy JSON |
| Version |
0.0.6
JSON |
| download |
| home_page | None |
| Summary | Invariant Causal Prediction for python |
| upload_time | 2024-03-22 15:21:20 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | !=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,>=2.7 |
| license | None |
| keywords |
statistics
casual-inference
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
## ICPy
[](https://github.com/jan-glx/ICPy/actions/workflows/ci.yml) [](https://htmlpreview.github.io/?https://github.com/jan-glx/ICPy/blob/python-coverage-comment-action-data/htmlcov/index.html)
[](https://pypi.org/project/ICPy/)
This packages provides a simple python implementation of Invariant Causal Prediction (ICP) [1].<br>
The source code for the actual algorithm resides in [./src/icp/ICP.py](./src/icpy/ICP.py). <br>
See also the original implementation in the R package [InvariantCausalPrediction](https://cran.r-project.org/web/packages/InvariantCausalPrediction/index.html).
### Installation
``` bash
pip install ICPy
```
### Usage
``` python
import icpy as icpy
import numpy as np
np.random.seed(seed=1)
n = 100
noise = 0.1
E = np.repeat([0, 1, 2], np.ceil(n / 3.0))[0:n] # "Environment"
A = np.random.normal(scale=noise, size=[n]) + np.equal(E, 1) # Node A
B = A + np.random.normal(scale=noise, size=[n]) / 3 + np.equal(E, 2) # Node B
C = B + np.random.normal(scale=noise, size=[n]) # Node C
# /--->---\
# E -> A -> B -> C
icpy.invariant_causal_prediction(X=np.column_stack((A, B)), y=C, z=E) # test if A or B are parents of C
```
Output
``` python
ICP(S_hat=array([1], dtype=int64), # Column 1 = Node B was (correctly) identified as parent of C
p_values=array([ 1.51508232e-01, 4.59577055e-37]), # error levels at which A and B would/are indentied as parent of C
p_value=0.16416488336322549) # p-value for testing against violation of the model assumptions (e.g. a direct effect of E on C)
```
### News
v0.0.003 (2020-05-15)
* fix failing import (thanks to [@lgmoneda](https://github.com/lgmoneda), [#1](https://github.com/jan-glx/ICPy/pull/1))
* fix issues when environments are not subsequent whole numbers starting at 0 (thanks to [@lgmoneda](https://github.com/lgmoneda), [#1](https://github.com/jan-glx/ICPy/pull/1))
### References
[1] J. Peters, P. Bühlmann, N. Meinshausen, Causal inference by using invariant prediction: identification and confidence intervals, J. R. Stat. Soc. Ser. B Stat. Methodol. 78 (2016) 947-1012. doi:10.1111/rssb.12167.
Raw data
{
"_id": null,
"home_page": null,
"name": "ICPy",
"maintainer": null,
"docs_url": null,
"requires_python": "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,>=2.7",
"maintainer_email": "Jan Gleixner <jan.gleixner+icpy@gmail.com>",
"keywords": "statistics, casual-inference",
"author": null,
"author_email": "Jan Gleixner <jan.gleixner+icpy@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/c2/25/bf3d0b8f852f71d2808c180dbb126c16e2abd00bd5bf8a9cb0fc505e046a/ICPy-0.0.6.tar.gz",
"platform": null,
"description": "## ICPy\n[](https://github.com/jan-glx/ICPy/actions/workflows/ci.yml) [](https://htmlpreview.github.io/?https://github.com/jan-glx/ICPy/blob/python-coverage-comment-action-data/htmlcov/index.html)\n[](https://pypi.org/project/ICPy/)\n\nThis packages provides a simple python implementation of Invariant Causal Prediction (ICP) [1].<br>\nThe source code for the actual algorithm resides in [./src/icp/ICP.py](./src/icpy/ICP.py). <br>\nSee also the original implementation in the R package [InvariantCausalPrediction](https://cran.r-project.org/web/packages/InvariantCausalPrediction/index.html).\n### Installation\n``` bash\npip install ICPy\n```\n### Usage\n``` python\nimport icpy as icpy\nimport numpy as np\n\nnp.random.seed(seed=1)\nn = 100\nnoise = 0.1\nE = np.repeat([0, 1, 2], np.ceil(n / 3.0))[0:n] # \"Environment\"\nA = np.random.normal(scale=noise, size=[n]) + np.equal(E, 1) # Node A\nB = A + np.random.normal(scale=noise, size=[n]) / 3 + np.equal(E, 2) # Node B\nC = B + np.random.normal(scale=noise, size=[n]) # Node C\n\n# /--->---\\\n# E -> A -> B -> C\n\nicpy.invariant_causal_prediction(X=np.column_stack((A, B)), y=C, z=E) # test if A or B are parents of C\n```\nOutput\n\n``` python\nICP(S_hat=array([1], dtype=int64), # Column 1 = Node B was (correctly) identified as parent of C\n p_values=array([ 1.51508232e-01, 4.59577055e-37]), # error levels at which A and B would/are indentied as parent of C\n p_value=0.16416488336322549) # p-value for testing against violation of the model assumptions (e.g. a direct effect of E on C)\n```\n\n### News\nv0.0.003 (2020-05-15)\n* fix failing import (thanks to [@lgmoneda](https://github.com/lgmoneda), [#1](https://github.com/jan-glx/ICPy/pull/1))\n* fix issues when environments are not subsequent whole numbers starting at 0 (thanks to [@lgmoneda](https://github.com/lgmoneda), [#1](https://github.com/jan-glx/ICPy/pull/1))\n\n### References\n[1] J. Peters, P. B\u00fchlmann, N. Meinshausen, Causal inference by using invariant prediction: identification and confidence intervals, J. R. Stat. Soc. Ser. B Stat. Methodol. 78 (2016) 947-1012. doi:10.1111/rssb.12167.\n",
"bugtrack_url": null,
"license": null,
"summary": "Invariant Causal Prediction for python",
"version": "0.0.6",
"project_urls": {
"source": "https://github.com/jan-glx/ICPy"
},
"split_keywords": [
"statistics",
" casual-inference"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "f95de7ca0300393659771690a65437e8ad2321cc6c2da42fa5c87130d164529d",
"md5": "79fe46ab0db066bda89782ba9d6ebed2",
"sha256": "e92a09337721b06543af3c3d95ce119c3276aa004c156e19c1cf037bc7c5f83c"
},
"downloads": -1,
"filename": "ICPy-0.0.6-py3-none-any.whl",
"has_sig": false,
"md5_digest": "79fe46ab0db066bda89782ba9d6ebed2",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,>=2.7",
"size": 4621,
"upload_time": "2024-03-22T15:21:18",
"upload_time_iso_8601": "2024-03-22T15:21:18.441077Z",
"url": "https://files.pythonhosted.org/packages/f9/5d/e7ca0300393659771690a65437e8ad2321cc6c2da42fa5c87130d164529d/ICPy-0.0.6-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "c225bf3d0b8f852f71d2808c180dbb126c16e2abd00bd5bf8a9cb0fc505e046a",
"md5": "09cff7133f00d06cfb39eb27bba88b12",
"sha256": "2f65df7f9d9be6f6bd52a77ffc8f0858aaa2c6dd4fc7958a278fb3f15cc2b538"
},
"downloads": -1,
"filename": "ICPy-0.0.6.tar.gz",
"has_sig": false,
"md5_digest": "09cff7133f00d06cfb39eb27bba88b12",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,>=2.7",
"size": 5644,
"upload_time": "2024-03-22T15:21:20",
"upload_time_iso_8601": "2024-03-22T15:21:20.916718Z",
"url": "https://files.pythonhosted.org/packages/c2/25/bf3d0b8f852f71d2808c180dbb126c16e2abd00bd5bf8a9cb0fc505e046a/ICPy-0.0.6.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-03-22 15:21:20",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "jan-glx",
"github_project": "ICPy",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "icpy"
}
