{"id":13473478,"url":"https://github.com/ari-dasci/S-TSFE-DL","last_synced_at":"2025-03-26T19:34:10.984Z","repository":{"id":42328329,"uuid":"350819371","full_name":"ari-dasci/S-TSFE-DL","owner":"ari-dasci","description":"Time Series Feature Extraction using Deep Learning","archived":false,"fork":false,"pushed_at":"2024-03-05T11:35:03.000Z","size":946,"stargazers_count":58,"open_issues_count":0,"forks_count":9,"subscribers_count":5,"default_branch":"main","last_synced_at":"2025-03-22T02:41:19.507Z","etag":null,"topics":["cnn","convolutional","deep-learning","feature-extraction","keras","lstm","neural-networks","python3","pytorch","pytorch-lightning","recurrent","rnn","tensorflow","time-series"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ari-dasci.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGES.rst","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":"2021-03-23T18:38:14.000Z","updated_at":"2025-03-20T06:31:09.000Z","dependencies_parsed_at":"2023-01-22T00:01:35.685Z","dependency_job_id":"74488d7c-ea13-4894-b6fb-786c2e2e001f","html_url":"https://github.com/ari-dasci/S-TSFE-DL","commit_stats":{"total_commits":126,"total_committers":4,"mean_commits":31.5,"dds":"0.19841269841269837","last_synced_commit":"4d3e4e613857a14f30880199ba130c0ce5043ded"},"previous_names":[],"tags_count":12,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ari-dasci%2FS-TSFE-DL","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ari-dasci%2FS-TSFE-DL/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ari-dasci%2FS-TSFE-DL/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ari-dasci%2FS-TSFE-DL/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ari-dasci","download_url":"https://codeload.github.com/ari-dasci/S-TSFE-DL/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245722832,"owners_count":20661831,"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":["cnn","convolutional","deep-learning","feature-extraction","keras","lstm","neural-networks","python3","pytorch","pytorch-lightning","recurrent","rnn","tensorflow","time-series"],"created_at":"2024-07-31T16:01:04.007Z","updated_at":"2025-03-26T19:34:10.506Z","avatar_url":"https://github.com/ari-dasci.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# TSFEDL: A Python Library for Time Series Spatio-Temporal Feature Extraction and Prediction using Deep Learning.\n\n## Description\n\nTime series feature extraction is a classical problem in time series analysis. Classical addition and multiplication models have been used for this purpose until the appearance of Artificial Neural Networks and Deep Learning. This problem has gained attention since multiple real-life problems imply the usage of time series.\n\nIn this repository, we introduce a new Python module which compiles 20 backbones for time series feature extraction using Deep Learning. This module has been created to cover the necessity of a versatile and expandable piece of software for practitioners to use in their problems.\n\n## How to run\n\n### Conda environment for GPU clusters\n\nTo easily use the library inside a conda environment the following commands are recommended to install the module. First of all install pip inside anaconda, which will install python inside the environment as well to encapsulate the whole installation.\n\n```bash\nconda install -c anaconda pip\n```\n\nAfter this, if a GPU is going to be used, we should install cuDNN 8.2.1 for the current tensorflow-gpu version (2.6.0). The NVIDIA CUDA toolkit will be also installed as a cuDNN dependency.\n\n```bash\nconda install -c anaconda cudnn==8.2.1\n```\n\nFinally, we can install the TSFEDL library using pip3 (which will be inside the conda environment, you can check this by running \"which pip3\"). This will install as dependencies pytorch-lightning, pytorch, tensorflow-gpu and all the needed packages. Use the --use-feature=2020-resolver flag if the installation runs into an error.\n\n```bash\npip3 install --use-feature=2020-resolver tsfedl\n```\n\nOtherwise use\n\n```bash\npip3 install tsfedl\n```\n\nAfter this everything is set up.\n\n### PyPi\n\nThe module is uploaded to PyPi for an easy installation:\n```bash\npip install tsfedl\n```\nor\n```bash\npip3 install tsfedl\n```\n\n### Documentation\n\nThe documentation of the model can be found in https://s-tsfe-dl.readthedocs.io/en/latest/\n\n### Using the repository\n\nFirst, install dependencies\n\n```bash\n# clone project\ngit clone https://github.com/ari-dasci/S-TSFE-DL.git\n\n# install project\ncd S-TSFE-DL\npip install -e .\n```   \n\n### Examples\n\nTo run an example, navigate to any file and run it.\n\n```bash\ncd project/examples\n\n# run example\npython arrythmia_experiment.py\n```\n\n## Imports\nThis project is set up as a package which means you can now easily import any file into any other file like so:\n\n```python\nimport tensorflow as tf\nimport TSFEDL.models_keras as TSFEDL\n\n# get the OhShuLih model\nmodel = TSFEDL.OhShuLih(input_tensor=input, include_top=True)\n\n# compile and fit as usual\nmodel.compile(optimizer='Adam')\nmodel.fit(X, y, epochs=20)\n```\n\n## Citation\n\nPlease cite this work as:\n\nTime Series Feature Extraction using Deep Learning library (https://github.com/ari-dasci/S-TSFE-DL/)\n\n```\n@article{AGUILERAMARTOS2023223,\ntitle = {{TSFEDL}: A python library for time series spatio-temporal feature extraction and prediction using deep learning},\njournal = {Neurocomputing},\nvolume = {517},\npages = {223-228},\nyear = {2023},\ndoi = {https://doi.org/10.1016/j.neucom.2022.10.062},\nauthor = {Ignacio Aguilera-Martos and Ángel M. García-Vico and Julián Luengo and Sergio Damas and Francisco J. Melero and José Javier Valle-Alonso and Francisco Herrera}\n}\n```\n\nArXiV reference with extended material: https://arxiv.org/abs/2206.03179\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fari-dasci%2FS-TSFE-DL","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fari-dasci%2FS-TSFE-DL","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fari-dasci%2FS-TSFE-DL/lists"}