| Name | tfp-causalimpact JSON |
| Version |
0.2.0
JSON |
| download |
| home_page | None |
| Summary | Inferring causal effects using Bayesian Structural Time-Series models |
| upload_time | 2023-05-08 20:44:10 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.8 |
| license | None |
| keywords |
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# TFP CausalImpact
This Python package implements an approach to estimating the causal effect of a
designed intervention on a time series. For example, how many additional daily
clicks were generated by an advertising campaign? Answering a question like this
can be difficult when a randomized experiment is not available. The package aims
to address this difficulty using a structural Bayesian time-series model to
estimate how the response metric might have evolved after the intervention if
the intervention had not occurred [1].
As with all approaches to causal inference on non-experimental data, valid
conclusions require strong assumptions. The CausalImpact package, in particular,
assumes that the outcome time series can be explained in terms of a set of
control time series that were themselves not affected by the intervention.
Furthermore, the relation between treated series and control series is assumed
to be stable during the post-intervention period. Understanding and checking
these assumptions for any given application is critical for obtaining valid
conclusions.
TFP CausalImpact is a Python +
[TensorFlow Probability](https://github.com/tensorflow/probability)
implementation of the
[CausalImpact](https://google.github.io/CausalImpact/) R package developed at
Google by Kay Brodersen and Alain Hauser. TFP CausalImpact is based on both
the original R package and on a Python version
https://github.com/dafiti/causalimpact developed at Dafiti by Willian Fuks.
TFP CausalImpact was developed at Google by Colin Carroll, David Moore,
Jacob Burnim, Kyle Loveless, and Susanna Makela.
*This is not an officially supported Google product.*
[1] _Inferring causal impact using Bayesian structural time-series models._
Kay H. Brodersen, Fabian Gallusser, Jim Koehler, Nicolas Remy,
Steven L. Scott. Annals of Applied Statistics, vol. 9 (2015), pp. 247-274.
https://research.google/pubs/pub41854/
## Getting Started
TFP CausalImpact can be installed via `pip`:
```
pip install tfp-causalimpact
```
And imported as:
```
import causalimpact
```
See also the [Quick-Start Guide](https://github.com/google/tfp-causalimpact/blob/main/docs/quickstart.ipynb).
## Development
Clone TFP CausalImpact, install the development dependencies, and run the unit
tests with:
```
git clone https://github.com/google/tfp-causalimpact.git tfp_causalimpact
cd tfp_causalimpact
pip install flit
flit install --only-deps
pytest -vv -n auto
```
Raw data
{
"_id": null,
"home_page": null,
"name": "tfp-causalimpact",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": null,
"author": null,
"author_email": "TFP CausalImpact Authors <no-reply@google.com>",
"download_url": "https://files.pythonhosted.org/packages/25/81/808cedbd2e8846745927841edc8681b48abc4d38f7a68905efe5d7836073/tfp-causalimpact-0.2.0.tar.gz",
"platform": null,
"description": "# TFP CausalImpact\n\nThis Python package implements an approach to estimating the causal effect of a\ndesigned intervention on a time series. For example, how many additional daily\nclicks were generated by an advertising campaign? Answering a question like this\ncan be difficult when a randomized experiment is not available. The package aims\nto address this difficulty using a structural Bayesian time-series model to\nestimate how the response metric might have evolved after the intervention if\nthe intervention had not occurred [1].\n\nAs with all approaches to causal inference on non-experimental data, valid\nconclusions require strong assumptions. The CausalImpact package, in particular,\nassumes that the outcome time series can be explained in terms of a set of\ncontrol time series that were themselves not affected by the intervention.\nFurthermore, the relation between treated series and control series is assumed\nto be stable during the post-intervention period. Understanding and checking\nthese assumptions for any given application is critical for obtaining valid\nconclusions.\n\nTFP CausalImpact is a Python +\n[TensorFlow Probability](https://github.com/tensorflow/probability)\nimplementation of the\n[CausalImpact](https://google.github.io/CausalImpact/) R package developed at\nGoogle by Kay Brodersen and Alain Hauser. TFP CausalImpact is based on both\nthe original R package and on a Python version\nhttps://github.com/dafiti/causalimpact developed at Dafiti by Willian Fuks.\nTFP CausalImpact was developed at Google by Colin Carroll, David Moore,\nJacob Burnim, Kyle Loveless, and Susanna Makela.\n\n*This is not an officially supported Google product.*\n\n[1] _Inferring causal impact using Bayesian structural time-series models._\n Kay H. Brodersen, Fabian Gallusser, Jim Koehler, Nicolas Remy,\n Steven L. Scott. Annals of Applied Statistics, vol. 9 (2015), pp. 247-274.\n https://research.google/pubs/pub41854/\n\n\n## Getting Started\n\nTFP CausalImpact can be installed via `pip`:\n\n```\npip install tfp-causalimpact\n```\n\nAnd imported as:\n\n```\nimport causalimpact\n```\n\nSee also the [Quick-Start Guide](https://github.com/google/tfp-causalimpact/blob/main/docs/quickstart.ipynb).\n\n\n## Development\n\nClone TFP CausalImpact, install the development dependencies, and run the unit\ntests with:\n\n```\ngit clone https://github.com/google/tfp-causalimpact.git tfp_causalimpact\ncd tfp_causalimpact\n\npip install flit\nflit install --only-deps\n\npytest -vv -n auto\n```\n",
"bugtrack_url": null,
"license": null,
"summary": "Inferring causal effects using Bayesian Structural Time-Series models",
"version": "0.2.0",
"project_urls": {
"homepage": "https://github.com/google/tfp-causalimpact",
"repository": "https://github.com/google/tfp-causalimpact"
},
"split_keywords": [],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "ba49a98ebeb9611479b7f4173dddbccf35ac7c067aa3162be354384dee7d651f",
"md5": "c34ca1c7b1051cfdef0d54abce8cfa3f",
"sha256": "42bac2b858396761905560c99174097f8a6c94866891b213091214c48a2cb917"
},
"downloads": -1,
"filename": "tfp_causalimpact-0.2.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "c34ca1c7b1051cfdef0d54abce8cfa3f",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 37171,
"upload_time": "2023-05-08T20:43:48",
"upload_time_iso_8601": "2023-05-08T20:43:48.476728Z",
"url": "https://files.pythonhosted.org/packages/ba/49/a98ebeb9611479b7f4173dddbccf35ac7c067aa3162be354384dee7d651f/tfp_causalimpact-0.2.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "2581808cedbd2e8846745927841edc8681b48abc4d38f7a68905efe5d7836073",
"md5": "a7f1d54522bc7cf1b7d120091bc31cb9",
"sha256": "7745f43ae97faffc04c8a5105ba0bf323da176407d8d8f663fe4b1042a34f347"
},
"downloads": -1,
"filename": "tfp-causalimpact-0.2.0.tar.gz",
"has_sig": false,
"md5_digest": "a7f1d54522bc7cf1b7d120091bc31cb9",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 79993,
"upload_time": "2023-05-08T20:44:10",
"upload_time_iso_8601": "2023-05-08T20:44:10.043839Z",
"url": "https://files.pythonhosted.org/packages/25/81/808cedbd2e8846745927841edc8681b48abc4d38f7a68905efe5d7836073/tfp-causalimpact-0.2.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-05-08 20:44:10",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "google",
"github_project": "tfp-causalimpact",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "tfp-causalimpact"
}
