{"id":28975066,"url":"https://github.com/octoenergy/timeserio","last_synced_at":"2025-06-24T12:08:17.856Z","repository":{"id":35013642,"uuid":"196452519","full_name":"octoenergy/timeserio","owner":"octoenergy","description":"Better `keras` models for time series and beyond","archived":false,"fork":false,"pushed_at":"2024-01-11T19:43:45.000Z","size":9898,"stargazers_count":61,"open_issues_count":13,"forks_count":16,"subscribers_count":97,"default_branch":"master","last_synced_at":"2025-06-10T15:07:21.328Z","etag":null,"topics":["data","data-science"],"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/octoenergy.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-07-11T19:18:04.000Z","updated_at":"2024-11-22T06:25:51.000Z","dependencies_parsed_at":"2023-02-12T22:46:22.017Z","dependency_job_id":null,"html_url":"https://github.com/octoenergy/timeserio","commit_stats":null,"previous_names":[],"tags_count":4,"template":false,"template_full_name":null,"purl":"pkg:github/octoenergy/timeserio","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/octoenergy%2Ftimeserio","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/octoenergy%2Ftimeserio/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/octoenergy%2Ftimeserio/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/octoenergy%2Ftimeserio/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/octoenergy","download_url":"https://codeload.github.com/octoenergy/timeserio/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/octoenergy%2Ftimeserio/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261669021,"owners_count":23192362,"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":["data","data-science"],"created_at":"2025-06-24T12:08:15.275Z","updated_at":"2025-06-24T12:08:17.833Z","avatar_url":"https://github.com/octoenergy.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"[![CircleCI](https://circleci.com/gh/octoenergy/timeserio/tree/master.svg?style=svg)](https://circleci.com/gh/octoenergy/timeserio/tree/master) \n[![codecov](https://codecov.io/gh/octoenergy/timeserio/branch/master/graph/badge.svg)](https://codecov.io/gh/octoenergy/timeserio)\n[![PyPI version](https://badge.fury.io/py/timeserio.svg)](https://badge.fury.io/py/timeserio)\n\n# timeserio\n\n`timeserio` is the missing link between `pandas`, `scikit-learn` and `keras`. It simplifies building end-to-end deep learning models - from a DataFrame through feature pipelines to multi-stage models with shared layers. While initially developed for tackling time series problems, it has since been used as a versatile tool for rapid ML model development and deployment.\n\nLoosing track of big networks with multiple inputs and outputs? Forgetting to freeze the right layers?\nStruggling to re-generate the input features? `timeserio` can help!\n\n![complex_network](https://raw.githubusercontent.com/octoenergy/timeserio/master/docs/source/_static/multinetwork_complex.svg?sanitize=true)\n\n## Documentation and Tutorials\n\nPlease see the [official documentation](http://tech.octopus.energy/timeserio/) on how to get started.\n\n## Features\n\n* Enable encapsulated, maintainable and reusable deep learning models\n* Feed data from `pandas` through `scikit-learn` feature pipelines to multiple neural network inputs\n* Manage complex architectures, layer sharing, partial freezing and re-training\n* Provide collection of extensible building blocks with emphasis on time series problems\n\n## Installation\n\n`pip install timeserio`, or install from source - `pip install -e .`\n\nSee [Getting Started](http://tech.octopus.energy/timeserio/overview/getting_started.html#installation)\n\n## Development\n\nWe welcome contributions and enhancements to any part of the code base, documentation, or tool chain.\n\nSee [CONTRIBUTING.md](https://github.com/octoenergy/timeserio/blob/master/CONTRIBUTING.md) for details on setting up the development environment, running tests,\netc.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Foctoenergy%2Ftimeserio","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Foctoenergy%2Ftimeserio","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Foctoenergy%2Ftimeserio/lists"}