{"id":30657452,"url":"https://github.com/solanovisitor/foreml","last_synced_at":"2026-04-02T03:12:10.103Z","repository":{"id":41809504,"uuid":"485161681","full_name":"solanovisitor/ForeML","owner":"solanovisitor","description":"A Python package for time series forecasting using Tensorflow and Keras","archived":false,"fork":false,"pushed_at":"2022-04-28T17:24:33.000Z","size":127,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-08-31T11:19:25.713Z","etag":null,"topics":["deep-learning","keras","lstm","machine-learning","pandas","poetry","python","scikit-learn","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/solanovisitor.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}},"created_at":"2022-04-24T23:09:38.000Z","updated_at":"2022-06-29T20:39:23.000Z","dependencies_parsed_at":"2022-08-11T18:01:57.157Z","dependency_job_id":null,"html_url":"https://github.com/solanovisitor/ForeML","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/solanovisitor/ForeML","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/solanovisitor%2FForeML","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/solanovisitor%2FForeML/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/solanovisitor%2FForeML/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/solanovisitor%2FForeML/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/solanovisitor","download_url":"https://codeload.github.com/solanovisitor/ForeML/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/solanovisitor%2FForeML/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31294936,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-02T01:43:37.129Z","status":"online","status_checked_at":"2026-04-02T02:00:08.535Z","response_time":89,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["deep-learning","keras","lstm","machine-learning","pandas","poetry","python","scikit-learn","tensorflow"],"created_at":"2025-08-31T11:13:57.635Z","updated_at":"2026-04-02T03:12:10.082Z","avatar_url":"https://github.com/solanovisitor.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ForeML\nA package for training and evaluating time series forecasting using Tensorflow.\n\n## :brain: Set up the environment\n1. Install [Poetry](https://python-poetry.org/docs/#installation)\n2. Set up the environment:\n```bash\nmake activate\nmake setup\n```\n\n## :mechanical_arm: Install Tensorflow using pip\n```bash\npip install tensorflow\n```\n\n\u003e To install new PyPI packages, run:\n```bash\npoetry add \u003cpackage-name\u003e\n```\n\n## :mage: Basic usage\n**:file_folder: You will find the configurations for your runs in the config folder.**\n#### Change the paths in the main.yaml file to your personal directories that contain your data. For example:\n```bash\nraw:\n  path: /home/user/ForeML/data/raw/test_data.csv\n```\n**:clipboard: The main.yaml file points to the parameters regarding the data processing and model training:**\n```bash\ndefaults:\n  - process: lstm\n  - model: lstm\n  - forecast: lstm\n  - _self_\n\nhypertune: False\n```\n\u003e If you change the hypertune parameter to True, it will run a tunable model with predefined parameters.\n\n**:scissors: The process YAML file listed in the main.yaml should look like this:**\n```bash\ndelimiter: ','\ntarget_index: 5\ndate_index: 3\nn_steps_in: 12\nn_steps_out: 8\nn_features: 1\n```\n- First, select the delimiter for your .csv file. After, you specify your target and datetime column indexes.\n- Finally, you can input the number of timesteps your model will be trained on (n_steps_in) and the timesteps it will forecast (n_steps_out).\n- If your model have more than one feature, you can specify it in the last parameter.\n\n**:pushpin: The model YAML file listed in the main.yaml should look like this:**\n```bash\nname: lstm\ntype: lstm\nn_units: 100\nactivation: relu\ndropout: 0.7\nepochs: 10\nbatch_size: 500\nvalidation_split: 0.2\nlearning_rate: 0.001\nlossfunction: msle\n```\n\u003e You can change the parameters in this file as you desire. Please note some of those won't cause any effect if you choose to hypertune.\n\n**:running_man: When you have all ready and set, you can just run the files you desire:**\n```bash\npython3 /src/process.py\npython3 /src/train_model.py\npython3 /src/forecaster.py\n```\n- process.py will return the .csv with processed data in the right format and the X and y ready to serve as input to the model.\n- train_model.py will train the model with your input data and return a trained model as selected (specified architecture and hypertuning option in the config files).\n- forecaster.py will take your test data, generate predictions on the dataset and compare with actual values, returning a plot for each timestep.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsolanovisitor%2Fforeml","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsolanovisitor%2Fforeml","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsolanovisitor%2Fforeml/lists"}