{"id":13653884,"url":"https://github.com/vlukiyanov/pt-avitm","last_synced_at":"2025-04-23T06:32:09.010Z","repository":{"id":130657960,"uuid":"163538705","full_name":"vlukiyanov/pt-avitm","owner":"vlukiyanov","description":" PyTorch implementation of AVITM (Autoencoding Variational Inference For Topic Models)","archived":false,"fork":false,"pushed_at":"2022-07-15T18:41:14.000Z","size":2806,"stargazers_count":36,"open_issues_count":3,"forks_count":6,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-11-10T04:36:38.351Z","etag":null,"topics":["autoencoder","avitm","pytorch","topic-modeling"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/vlukiyanov.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}},"created_at":"2018-12-29T20:20:28.000Z","updated_at":"2024-09-17T21:39:42.000Z","dependencies_parsed_at":"2024-01-14T14:29:34.395Z","dependency_job_id":"cbc6b03a-4a53-41d4-a48c-4ce0c4e64a6a","html_url":"https://github.com/vlukiyanov/pt-avitm","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vlukiyanov%2Fpt-avitm","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vlukiyanov%2Fpt-avitm/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vlukiyanov%2Fpt-avitm/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vlukiyanov%2Fpt-avitm/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vlukiyanov","download_url":"https://codeload.github.com/vlukiyanov/pt-avitm/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250385336,"owners_count":21421901,"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":["autoencoder","avitm","pytorch","topic-modeling"],"created_at":"2024-08-02T02:01:19.801Z","updated_at":"2025-04-23T06:32:03.987Z","avatar_url":"https://github.com/vlukiyanov.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# pt-avitm\n[![Build Status](https://travis-ci.org/vlukiyanov/pt-avitm.svg?branch=master)](https://travis-ci.org/vlukiyanov/pt-avitm) [![codecov](https://codecov.io/gh/vlukiyanov/pt-avitm/branch/master/graph/badge.svg)](https://codecov.io/gh/vlukiyanov/pt-avitm)\n[![Codacy Badge](https://api.codacy.com/project/badge/Grade/212b5a014c0a4399a9074b0db5b8ecbe)](https://www.codacy.com/app/vlukiyanov/pt-avitm?utm_source=github.com\u0026amp;utm_medium=referral\u0026amp;utm_content=vlukiyanov/pt-avitm\u0026amp;utm_campaign=Badge_Grade)\n\nPyTorch implementation of a version of the Autoencoding Variational Inference For Topic Models (AVITM) algorithm. Compatible with PyTorch 1.0.0 and Python 3.6 or 3.7 with or without CUDA.\n\nThis follows (*or attempts to; note this implementation is unofficial*) the algorithm described in \"Autoencoding Variational Inference For Topic Models\" of Akash Srivastava, Charles Sutton (https://arxiv.org/abs/1703.01488).\n\n## Examples\n\nYou can find a number of examples in the examples directory, see also Usage below.\n\n## Usage\n\nThe simplest way to use the library is using the sklearn-compatible API, as below.\n\n```python\nimport sklearn.datasets\nfrom sklearn.feature_extraction.text import CountVectorizer\nfrom sklearn.pipeline import make_pipeline\n\nfrom ptavitm.sklearn_api import ProdLDATransformer\n\ntexts = sklearn.datasets.fetch_20newsgroups()['data']\n\npipeline = make_pipeline(\n    CountVectorizer(\n        stop_words='english',\n        max_features=2500,\n        max_df=0.9\n    ),\n    ProdLDATransformer()\n)\n\npipeline.fit(texts)\nresult = pipeline.transform(texts)\n```\n\n## Other implementations of AVITM and similar\n\n* Original TensorFlow: https://github.com/akashgit/autoencoding_vi_for_topic_models \n* PyTorch: https://github.com/hyqneuron/pytorch-avitm\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvlukiyanov%2Fpt-avitm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvlukiyanov%2Fpt-avitm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvlukiyanov%2Fpt-avitm/lists"}