{
    "info": {
        "author": "Andrew Moore, Henry Moss",
        "author_email": "andrew.p.moore94@gmail.com",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 3 - Alpha",
            "Programming Language :: Python :: 3.6"
        ],
        "description": "# FIESTA (Fast IdEntification of State-of-The-Art models using adaptive bandit algorithms)\n[![licence](https://img.shields.io/hexpm/l/plug.svg)](https://opensource.org/licenses/Apache-2.0) [![Build Status](https://travis-ci.org/apmoore1/fiesta.svg?branch=master)](https://travis-ci.org/apmoore1/fiesta) [![codecov](https://codecov.io/gh/apmoore1/fiesta/branch/master/graph/badge.svg)](https://codecov.io/gh/apmoore1/fiesta)\n\n## Quick links:\n1. [Documentation](https://apmoore1.github.io/fiesta/) - You can find the motivation of the project code base there as well.\n2. [Tutorials](https://apmoore1.github.io/fiesta/#tutorials)\n\n## Installing\nRequires Python 3.6.1 or greater.\n\n`pip install fiesta-nlp`\n\n## Experiments in the paper\n### NER experiments\nThe code used to create the NER results can be founder [here](https://github.com/apmoore1/NER) with all of the instructions on:\n1. How the data was split.\n2. How to re-run the models.\n3. How the images in the paper were created.\n4. Links to all of the original F1 results and data splits.\n\n### Target Dependent Sentiment Analysis experiments\nThe 500 Macro F1 results from the 12 different TDSA models can be found within [`test_f1.json` file](./results/TDSA/test_f1.json). For replication purposes we have created a [Google Colab notebook](https://github.com/apmoore1/fiesta/blob/master/notebooks/Advantages_of_Model_Selection.ipynb) which can be found here that shows how the results from the paper can be replicated. Further more this notebook is a good example of how to use the `fiesta` library when you already have results and do not need to evaluate any modles.\n\n## Citing (This will be updated when the ACL version of the paper is published)\nIf you use FIESTA in your research, please cite [FIESTA: Fast IdEntification of State-of-The-Art models using adaptive bandit algorithms](https://arxiv.org/pdf/1906.12230.pdf)\n```\n@article{moss2019fiesta,\n  title={FIESTA: Fast IdEntification of State-of-The-Art models using adaptive bandit algorithms},\n  author={Moss, Henry B and Moore, Andrew and Leslie, David S and Rayson, Paul},\n  journal={arXiv preprint arXiv:1906.12230},\n  year={2019}\n}\n```\n\n## General Acknowledgments\nThis code base and it's related FIESTA paper could not have been done without:\n1. [Henry Moss's](https://www.lancaster.ac.uk/maths/people/henry-moss) time funded through EPSRC Doctoral Training Grant and the STOR-i Centre for Doctoral Training.\n2. [Andrew Moore's](https://apmoore1.github.io/) time funded through EPSRC Doctoral Training Grant.\n3. [Paul Rayson's](https://www.lancaster.ac.uk/staff/rayson/) and [David Leslie's](https://www.lancaster.ac.uk/people-profiles/david-leslie) time.\n4. Resources -- The loan of a NVIDIA GP100-equipped workstation from [Dr Chris Jewell](https://chicas.lancaster-university.uk/people/jewell.html) at the [Centre for Health Informatics, Computing, and Statistics, Lancaster University](https://chicas.lancaster-university.uk/).\n5. We lastly thank the comments and advise of the reviewers from ACL 2019 which has greatly improved the paper.\n\n## Issue template Acknowledgment\nWe copied/adapted the issues templates from the [allennlp](https://github.com/allenai/allennlp) project.\n\n\n",
        "description_content_type": "text/markdown",
        "docs_url": null,
        "download_url": "",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/apmoore1/fiesta",
        "keywords": "",
        "license": "Apache License 2.0",
        "maintainer": "",
        "maintainer_email": "",
        "name": "fiesta-nlp",
        "package_url": "https://pypi.org/project/fiesta-nlp/",
        "platform": "",
        "project_url": "https://pypi.org/project/fiesta-nlp/",
        "project_urls": {
            "Homepage": "https://github.com/apmoore1/fiesta"
        },
        "release_url": "https://pypi.org/project/fiesta-nlp/0.0.1/",
        "requires_dist": [
            "numpy",
            "scipy"
        ],
        "requires_python": ">=3.6.1",
        "summary": "Fast IdEntification of State-of-The-Art models using adaptive bandit algorithms",
        "version": "0.0.1"
    },
    "last_serial": 5532321,
    "releases": {
        "0.0.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "8c586543e79d313eb958623ad6936ff7",
                    "sha256": "9746aa0116570083006bc5debf2517618044c9e5cf35a0ecd5575cc4946c3aea"
                },
                "downloads": -1,
                "filename": "fiesta_nlp-0.0.1-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "8c586543e79d313eb958623ad6936ff7",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": ">=3.6.1",
                "size": 12694,
                "upload_time": "2019-07-14T22:26:14",
                "url": "https://files.pythonhosted.org/packages/e0/55/b886c9ed55ff9ddbc40e2f36abde62218015f4abdf73358e96637c47a748/fiesta_nlp-0.0.1-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "99c50d18d5e1d2387d3f1a5eb75da6f2",
                    "sha256": "87ef50b3d6cf993848fb48289a224ec3112c7edacab3e03b77f36fd23ea960e2"
                },
                "downloads": -1,
                "filename": "fiesta_nlp-0.0.1.tar.gz",
                "has_sig": false,
                "md5_digest": "99c50d18d5e1d2387d3f1a5eb75da6f2",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": ">=3.6.1",
                "size": 8832,
                "upload_time": "2019-07-14T22:26:16",
                "url": "https://files.pythonhosted.org/packages/ea/33/c2cbce5b8d504879fe4db1ccf11724c2f3e9c2a02f97a1dad1c2e2e8d588/fiesta_nlp-0.0.1.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "8c586543e79d313eb958623ad6936ff7",
                "sha256": "9746aa0116570083006bc5debf2517618044c9e5cf35a0ecd5575cc4946c3aea"
            },
            "downloads": -1,
            "filename": "fiesta_nlp-0.0.1-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "8c586543e79d313eb958623ad6936ff7",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.6.1",
            "size": 12694,
            "upload_time": "2019-07-14T22:26:14",
            "url": "https://files.pythonhosted.org/packages/e0/55/b886c9ed55ff9ddbc40e2f36abde62218015f4abdf73358e96637c47a748/fiesta_nlp-0.0.1-py3-none-any.whl"
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "99c50d18d5e1d2387d3f1a5eb75da6f2",
                "sha256": "87ef50b3d6cf993848fb48289a224ec3112c7edacab3e03b77f36fd23ea960e2"
            },
            "downloads": -1,
            "filename": "fiesta_nlp-0.0.1.tar.gz",
            "has_sig": false,
            "md5_digest": "99c50d18d5e1d2387d3f1a5eb75da6f2",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.6.1",
            "size": 8832,
            "upload_time": "2019-07-14T22:26:16",
            "url": "https://files.pythonhosted.org/packages/ea/33/c2cbce5b8d504879fe4db1ccf11724c2f3e9c2a02f97a1dad1c2e2e8d588/fiesta_nlp-0.0.1.tar.gz"
        }
    ]
}