galileo-forecast

Name	galileo-forecast JSON
Version	0.1.4 JSON
	download
home_page	None
Summary	Thompson Sampling using bootstrap sampling
upload_time	2024-10-20 13:55:41
maintainer	None
docs_url	None
author	Niels Ota
requires_python	<4.0,>=3.10
license	None
keywords
VCS
bugtrack_url
requirements	No requirements were recorded.
Travis-CI	No Travis.
coveralls test coverage	No coveralls.

            # Galileo Forecast

Galileo Forecast is a Python package that implements Thompson Sampling. It provides a flexible wrapper that can be used with various base model classes.

## Installation

You can install Galileo Forecast using pip:

```bash
pip install galileo-forecast
```

## Usage

To use Galileo Forecast, you need to create a wrapper for your base model class. Here's an example with LightGBM:

```python
from galileo_forecast import ThompsonSamplingWrapper
from lightgbm import LGBMClassifier

# make classification data, us sklearn make_classification
from sklearn.datasets import make_classification

# sample data with low hit rate
X, y = make_classification(n_samples=1000, n_features=10, n_informative=1, n_redundant=1, n_clusters_per_class=1, class_sep=0.1)

# create a wrapper for the LightGBM model  
wrapper = ThompsonSamplingWrapper(base_model_class=LGBMClassifier, num_models=10)

# fit the wrapper
wrapper.fit(X, y)

# get the predicted probabilities for the positive class
selected_model_indices, sampled_probabilities = wrapper.predict_proba(X)

# get the fancy output dataframe - contains sampled probabilities, the sampled model and the greedy model, etc.
print(wrapper.get_fancy_output_df().head())

```

## Demo

The demo folder contains Jupyter notebooks that shows how to use the package.




            

Raw data

            {
    "_id": null,
    "home_page": null,
    "name": "galileo-forecast",
    "maintainer": null,
    "docs_url": null,
    "requires_python": "<4.0,>=3.10",
    "maintainer_email": null,
    "keywords": null,
    "author": "Niels Ota",
    "author_email": "ota.niels@bcg.com",
    "download_url": "https://files.pythonhosted.org/packages/7d/ce/8c3b2e16bdb3f84ca0002c57b597631d3ee290149576b3217bb373a6164d/galileo_forecast-0.1.4.tar.gz",
    "platform": null,
    "description": "# Galileo Forecast\n\nGalileo Forecast is a Python package that implements Thompson Sampling. It provides a flexible wrapper that can be used with various base model classes.\n\n## Installation\n\nYou can install Galileo Forecast using pip:\n\n```bash\npip install galileo-forecast\n```\n\n## Usage\n\nTo use Galileo Forecast, you need to create a wrapper for your base model class. Here's an example with LightGBM:\n\n```python\nfrom galileo_forecast import ThompsonSamplingWrapper\nfrom lightgbm import LGBMClassifier\n\n# make classification data, us sklearn make_classification\nfrom sklearn.datasets import make_classification\n\n# sample data with low hit rate\nX, y = make_classification(n_samples=1000, n_features=10, n_informative=1, n_redundant=1, n_clusters_per_class=1, class_sep=0.1)\n\n# create a wrapper for the LightGBM model  \nwrapper = ThompsonSamplingWrapper(base_model_class=LGBMClassifier, num_models=10)\n\n# fit the wrapper\nwrapper.fit(X, y)\n\n# get the predicted probabilities for the positive class\nselected_model_indices, sampled_probabilities = wrapper.predict_proba(X)\n\n# get the fancy output dataframe - contains sampled probabilities, the sampled model and the greedy model, etc.\nprint(wrapper.get_fancy_output_df().head())\n\n```\n\n## Demo\n\nThe demo folder contains Jupyter notebooks that shows how to use the package.\n\n\n\n",
    "bugtrack_url": null,
    "license": null,
    "summary": "Thompson Sampling using bootstrap sampling",
    "version": "0.1.4",
    "project_urls": null,
    "split_keywords": [],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "0fe19190bf0321a7ccb7051daf2603612ab5d287a298f01ab5ead805d4d03d34",
                "md5": "1feae174adb00dd968eca9b06f6e9bd3",
                "sha256": "709092140b5da79b0afc710a8b9f6c66942ce6abdbdb33258b6d0ef945c98610"
            },
            "downloads": -1,
            "filename": "galileo_forecast-0.1.4-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "1feae174adb00dd968eca9b06f6e9bd3",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": "<4.0,>=3.10",
            "size": 22817,
            "upload_time": "2024-10-20T13:55:39",
            "upload_time_iso_8601": "2024-10-20T13:55:39.706860Z",
            "url": "https://files.pythonhosted.org/packages/0f/e1/9190bf0321a7ccb7051daf2603612ab5d287a298f01ab5ead805d4d03d34/galileo_forecast-0.1.4-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "7dce8c3b2e16bdb3f84ca0002c57b597631d3ee290149576b3217bb373a6164d",
                "md5": "cad3f875431d9e4927190bf561eb51ce",
                "sha256": "6b6679e3f81512eef9355d1772877762768805c669da17b3ce5323694a8bc2e8"
            },
            "downloads": -1,
            "filename": "galileo_forecast-0.1.4.tar.gz",
            "has_sig": false,
            "md5_digest": "cad3f875431d9e4927190bf561eb51ce",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": "<4.0,>=3.10",
            "size": 17281,
            "upload_time": "2024-10-20T13:55:41",
            "upload_time_iso_8601": "2024-10-20T13:55:41.255751Z",
            "url": "https://files.pythonhosted.org/packages/7d/ce/8c3b2e16bdb3f84ca0002c57b597631d3ee290149576b3217bb373a6164d/galileo_forecast-0.1.4.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2024-10-20 13:55:41",
    "github": false,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "lcname": "galileo-forecast"
}