# Rsdiv: Reranking for Multi-objective Optimized Recommender Systems
[](https://www.python.org)
[](https://pypi.org/project/rsdiv/)
[](https://github.com/smartnews/rsdiv)
[](https://rsdiv.readthedocs.io/en/latest/)
**rsdiv** provides the measurements and improvements for the **multi-objective/diversifying** tasks.
Some of its features include:
- various implementations of **diversifying/ensemble** reranking modules.
- various implementations of core **recommender algorithms**.
- evaluations for recommender systems from a **quantitative/visual** view.
- easy-to-use **benchmarks** for comparing and further analysis.
- automated **hyperparameter** optimization.
## Installation
You can simply install the pre-build binaries with:
```bash
pip install rsdiv
```
More installation options can be found [here](https://rsdiv.readthedocs.io/en/latest/installation.html).
## Basic Usage
[Prepare for a benchmark dataset](https://rsdiv.readthedocs.io/en/latest/notebooks/prepare-for-a-benchmark-dataset.html)
[Evaluate the results in various aspects](https://rsdiv.readthedocs.io/en/latest/notebooks/evaluate-the-results-in-various-aspects.html)
[Train and test a recommender](https://rsdiv.readthedocs.io/en/latest/notebooks/train-and-test-a-recommender.html)
[Reranking for diversity improvement](https://rsdiv.readthedocs.io/en/latest/notebooks/reranking-for-diversity.html)
## TODO
### More diversifying algorithms
- implement the Bounded Greedy Selection Strategy, BGS diversify algorithm
- implement the Determinantal Point Process, DPP diversify algorithm
### Hyperparameter optimization
- compatible with [Optuna](https://github.com/optuna/optuna).
### Ensemble ranking
- support the ensemble ranking modules
## For developers
Contributions welcome! Please contact us.
During your development stage, make sure you have `pre-commit` installed in your local environment:
```bash
pip install pre-commit
pre-commit install
```
Raw data
{
"_id": null,
"home_page": "https://github.com/smartnews/rsdiv",
"name": "rsdiv",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": "",
"keywords": "",
"author": "Yin Cheng",
"author_email": "yin.sjtu@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/5e/f0/75d26ef242952576ef46c97d1a884fb55f2d31f6c4cdbab5887c9e7c4f25/rsdiv-0.2.7.1.tar.gz",
"platform": null,
"description": "# Rsdiv: Reranking for Multi-objective Optimized Recommender Systems\n\n[](https://www.python.org)\n[](https://pypi.org/project/rsdiv/)\n[](https://github.com/smartnews/rsdiv)\n[](https://rsdiv.readthedocs.io/en/latest/)\n\n**rsdiv** provides the measurements and improvements for the **multi-objective/diversifying** tasks.\n\nSome of its features include:\n\n- various implementations of **diversifying/ensemble** reranking modules.\n- various implementations of core **recommender algorithms**.\n- evaluations for recommender systems from a **quantitative/visual** view.\n- easy-to-use **benchmarks** for comparing and further analysis.\n- automated **hyperparameter** optimization.\n\n## Installation\n\nYou can simply install the pre-build binaries with:\n\n```bash\npip install rsdiv\n```\n\nMore installation options can be found [here](https://rsdiv.readthedocs.io/en/latest/installation.html).\n\n## Basic Usage\n\n[Prepare for a benchmark dataset](https://rsdiv.readthedocs.io/en/latest/notebooks/prepare-for-a-benchmark-dataset.html)\n\n[Evaluate the results in various aspects](https://rsdiv.readthedocs.io/en/latest/notebooks/evaluate-the-results-in-various-aspects.html)\n\n[Train and test a recommender](https://rsdiv.readthedocs.io/en/latest/notebooks/train-and-test-a-recommender.html)\n\n[Reranking for diversity improvement](https://rsdiv.readthedocs.io/en/latest/notebooks/reranking-for-diversity.html)\n\n## TODO\n\n### More diversifying algorithms\n\n- implement the Bounded Greedy Selection Strategy, BGS diversify algorithm\n\n- implement the Determinantal Point Process, DPP diversify algorithm\n\n### Hyperparameter optimization\n\n- compatible with [Optuna](https://github.com/optuna/optuna).\n\n### Ensemble ranking\n\n- support the ensemble ranking modules\n\n## For developers\n\nContributions welcome! Please contact us.\n\nDuring your development stage, make sure you have `pre-commit` installed in your local environment:\n\n```bash\npip install pre-commit\npre-commit install\n```\n",
"bugtrack_url": null,
"license": "",
"summary": "",
"version": "0.2.7.1",
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "70976a562245d1d085cdf2ed5b4b644e70ca08a756407061df5afccbe3f082e5",
"md5": "3b869e1b6ed99b74f4c674c4bfe314af",
"sha256": "e324d4979bee5800fe861d43164f1549ef5b48f757f612ad9cf4440bee4a4172"
},
"downloads": -1,
"filename": "rsdiv-0.2.7.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "3b869e1b6ed99b74f4c674c4bfe314af",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 956482,
"upload_time": "2023-01-10T09:39:03",
"upload_time_iso_8601": "2023-01-10T09:39:03.432801Z",
"url": "https://files.pythonhosted.org/packages/70/97/6a562245d1d085cdf2ed5b4b644e70ca08a756407061df5afccbe3f082e5/rsdiv-0.2.7.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "5ef075d26ef242952576ef46c97d1a884fb55f2d31f6c4cdbab5887c9e7c4f25",
"md5": "d52eb0ceb520b52f597a94d485bb810d",
"sha256": "a93363cce718f8bdf0a5fd9c24b4a1598c94a85ee1000e392668489a7925bd81"
},
"downloads": -1,
"filename": "rsdiv-0.2.7.1.tar.gz",
"has_sig": false,
"md5_digest": "d52eb0ceb520b52f597a94d485bb810d",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 947889,
"upload_time": "2023-01-10T09:39:05",
"upload_time_iso_8601": "2023-01-10T09:39:05.251900Z",
"url": "https://files.pythonhosted.org/packages/5e/f0/75d26ef242952576ef46c97d1a884fb55f2d31f6c4cdbab5887c9e7c4f25/rsdiv-0.2.7.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-01-10 09:39:05",
"github": true,
"gitlab": false,
"bitbucket": false,
"github_user": "smartnews",
"github_project": "rsdiv",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "rsdiv"
}
JSON
