{"id":26154498,"url":"https://github.com/datacanvasio/deeptables","last_synced_at":"2025-05-14T16:13:47.772Z","repository":{"id":41085734,"uuid":"248690852","full_name":"DataCanvasIO/DeepTables","owner":"DataCanvasIO","description":"DeepTables:  Deep-learning Toolkit for Tabular data","archived":false,"fork":false,"pushed_at":"2024-11-21T08:57:21.000Z","size":6029,"stargazers_count":677,"open_issues_count":27,"forks_count":119,"subscribers_count":23,"default_branch":"master","last_synced_at":"2025-03-25T10:00:21.731Z","etag":null,"topics":["afm","autoint","ctr-prediction","dcn-model","deep-learning","deepfm","factorization-machines","fgcnn","fibinet","fm","pnn","structured-data","tabular-data","wide-and-deep","xdeepfm"],"latest_commit_sha":null,"homepage":"https://deeptables.readthedocs.io","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/DataCanvasIO.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-03-20T07:11:41.000Z","updated_at":"2025-02-24T10:37:21.000Z","dependencies_parsed_at":"2024-01-08T09:30:23.491Z","dependency_job_id":"386ce7bc-9d02-4b9a-9b28-a4d0dc9b4dcc","html_url":"https://github.com/DataCanvasIO/DeepTables","commit_stats":null,"previous_names":[],"tags_count":10,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DataCanvasIO%2FDeepTables","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DataCanvasIO%2FDeepTables/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DataCanvasIO%2FDeepTables/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DataCanvasIO%2FDeepTables/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DataCanvasIO","download_url":"https://codeload.github.com/DataCanvasIO/DeepTables/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246531984,"owners_count":20792735,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["afm","autoint","ctr-prediction","dcn-model","deep-learning","deepfm","factorization-machines","fgcnn","fibinet","fm","pnn","structured-data","tabular-data","wide-and-deep","xdeepfm"],"created_at":"2025-03-11T08:29:59.886Z","updated_at":"2025-04-01T11:01:37.135Z","avatar_url":"https://github.com/DataCanvasIO.png","language":"Python","readme":"# DeepTables\n\n\n[![Python Versions](https://img.shields.io/pypi/pyversions/deeptables.svg)](https://pypi.org/project/deeptables)\n[![TensorFlow Versions](https://img.shields.io/badge/TensorFlow-2.0+-blue.svg)](https://pypi.org/project/deeptables)\n[![Downloads](https://pepy.tech/badge/deeptables)](https://pepy.tech/project/deeptables)\n[![PyPI Version](https://img.shields.io/pypi/v/deeptables.svg)](https://pypi.org/project/deeptables)\n\n\n[![Documentation Status](https://readthedocs.org/projects/deeptables/badge/?version=latest)](https://deeptables.readthedocs.io/)\n[![Build Status](https://travis-ci.org/DataCanvasIO/deeptables.svg?branch=master)](https://travis-ci.org/DataCanvasIO/deeptables)\n[![Coverage Status](https://coveralls.io/repos/github/DataCanvasIO/deeptables/badge.svg?branch=master)](https://coveralls.io/github/DataCanvasIO/deeptables?branch=master)\n[![License](https://img.shields.io/github/license/DataCanvasIO/deeptables.svg)](https://github.com/DataCanvasIO/deeptables/blob/master/LICENSE)\n\n## We Are Hiring！\nDear folks, we are opening several precious positions based in Beijing both for professionals and interns avid in AutoML/NAS, please send your resume/cv to yangjian@zetyun.com. (Application deadline: TBD.) \n\n## DeepTables: Deep-learning Toolkit for Tabular data\nDeepTables(DT) is an easy-to-use toolkit that enables deep learning to unleash great power on tabular data.\n\n\n## Overview\n\nMLP (also known as Fully-connected neural networks) have been shown inefficient in learning distribution representation. The \"add\" operations of the perceptron layer have been proven poor performance to exploring multiplicative feature interactions. In most cases, manual feature engineering is necessary and this work requires extensive domain knowledge and very cumbersome. How learning feature interactions efficiently in neural networks becomes the most important problem.\n\nVarious models have been proposed to CTR prediction and continue to outperform existing state-of-the-art approaches to the late years. Well-known examples include FM, DeepFM, Wide\u0026Deep, DCN, PNN, etc. These models can also provide good performance on tabular data under reasonable utilization.\n\nDT aims to utilize the latest research findings to provide users with an end-to-end toolkit on tabular data.\n\nDT has been designed with these key goals in mind:\n\n* Easy to use, non-experts can also use.\n* Provide good performance out of the box.\n* Flexible architecture and easy expansion by user.\n\n## Tutorials\nPlease refer to the official docs at [https://deeptables.readthedocs.io/en/latest/](https://deeptables.readthedocs.io/en/latest/).\n* [Quick Start](https://deeptables.readthedocs.io/en/latest/quick_start.html)\n* [Examples](https://deeptables.readthedocs.io/en/latest/examples.html)\n* [ModelConfig](https://deeptables.readthedocs.io/en/latest/model_config.html)\n* [Models](https://deeptables.readthedocs.io/en/latest/models.html)\n* [Layers](https://deeptables.readthedocs.io/en/latest/layers.html)\n* [AutoML](https://deeptables.readthedocs.io/en/latest/automl.html)\n\n## Installation\n\n`pip` is recommended to install DeepTables:\n\n```bash\npip install tensorflow deeptables\n```\n\nNote:\n* Tensorflow is required by DeepTables, install it before running DeepTables. \n\n**GPU** Setup (Optional)\n\nTo use DeepTables with GPU devices, install `tensorflow-gpu` instead of `tensorflow`.\n\n```bash\npip install tensorflow-gpu deeptables\n```\n\n\n***Verify the installation***:\n\n```bash\npython -c \"from deeptables.utils.quicktest import test; test()\"\n```\n\n## Optional dependencies\nFollowing libraries are not hard dependencies and are not automatically installed when you install DeepTables. To use all functionalities of DT, these optional dependencies must be installed.\n\n```bash\npip install shap\n```\n\n## Example：\n\n### A simple binary classification example\n```python\nimport numpy as np\nfrom deeptables.models import deeptable, deepnets\nfrom deeptables.datasets import dsutils\nfrom sklearn.model_selection import train_test_split\n\n#loading data\ndf = dsutils.load_bank()\ndf_train, df_test = train_test_split(df, test_size=0.2, random_state=42)\n\ny = df_train.pop('y')\ny_test = df_test.pop('y')\n\n#training\nconfig = deeptable.ModelConfig(nets=deepnets.DeepFM)\ndt = deeptable.DeepTable(config=config)\nmodel, history = dt.fit(df_train, y, epochs=10)\n\n#evaluation\nresult = dt.evaluate(df_test,y_test, batch_size=512, verbose=0)\nprint(result)\n\n#scoring\npreds = dt.predict(df_test)\n```\n\n### A solution using DeepTables to win the 1st place in Kaggle Categorical Feature Encoding Challenge II\n\n[Click here](https://github.com/DataCanvasIO/DeepTables/blob/master/deeptables/examples/Kaggle%20-%20Categorical%20Feature%20Encoding%20Challenge%20II.ipynb)\n\n## Citation\n\nIf you use DeepTables in your research, please cite us as follows:\n\n   Jian Yang, Xuefeng Li, Haifeng Wu. **DeepTables: A Deep Learning Python Package for Tabular Data.** https://github.com/DataCanvasIO/DeepTables, 2022. Version 0.2.x.\n\nBibTex:\n\n```\n@misc{deeptables,\n  author={Jian Yang, Xuefeng Li, Haifeng Wu},\n  title={{DeepTables}: { A Deep Learning Python Package for Tabular Data}},\n  howpublished={https://github.com/DataCanvasIO/DeepTables},\n  note={Version 0.2.x},\n  year={2022}\n}\n```\n\n## DataCanvas\n\n![](https://raw.githubusercontent.com/DataCanvasIO/DeepTables/master/docs/source/images/dc_logo_1.png)\n\nDeepTables is an open source project created by [DataCanvas](https://www.datacanvas.com/). \n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdatacanvasio%2Fdeeptables","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdatacanvasio%2Fdeeptables","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdatacanvasio%2Fdeeptables/lists"}