{"id":19809905,"url":"https://github.com/lewagon/taxi-fare-deep","last_synced_at":"2025-08-27T01:53:35.555Z","repository":{"id":49980626,"uuid":"327269331","full_name":"lewagon/taxi-fare-deep","owner":"lewagon","description":"Packaged neural network-based predictor for the Kaggle's NY Taxi Fare challenge","archived":false,"fork":false,"pushed_at":"2021-02-12T10:38:57.000Z","size":203,"stargazers_count":3,"open_issues_count":0,"forks_count":21,"subscribers_count":10,"default_branch":"master","last_synced_at":"2025-05-01T08:34:07.240Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","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/lewagon.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":"2021-01-06T09:56:51.000Z","updated_at":"2025-01-05T02:54:02.000Z","dependencies_parsed_at":"2022-08-01T01:38:57.272Z","dependency_job_id":null,"html_url":"https://github.com/lewagon/taxi-fare-deep","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/lewagon/taxi-fare-deep","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lewagon%2Ftaxi-fare-deep","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lewagon%2Ftaxi-fare-deep/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lewagon%2Ftaxi-fare-deep/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lewagon%2Ftaxi-fare-deep/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lewagon","download_url":"https://codeload.github.com/lewagon/taxi-fare-deep/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lewagon%2Ftaxi-fare-deep/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":272278143,"owners_count":24905633,"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","status":"online","status_checked_at":"2025-08-26T02:00:07.904Z","response_time":60,"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":[],"created_at":"2024-11-12T09:18:37.649Z","updated_at":"2025-08-27T01:53:35.500Z","avatar_url":"https://github.com/lewagon.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Taxifare Deep\n\nThis repository is a python-package that allows to fit a deep learning model predicting the price of a taxi course using the [TaxiFare](https://www.kaggle.com/c/new-york-city-taxi-fare-prediction) dataset.\n\n## How to test it directly from Google Collab ?\n\n1. Open [colab.research.google.com](https://colab.research.google.com/)\n2. Create a new collab notebook, and change the runtime to GPU\n3. Pip-install this repo (which is a package) directly from within your collab notebook, by running this cell below\n\n```python\n! pip install --quiet git+https://github.com/lewagon/taxi-fare-deep\n```\n\n## Basic workflow\n\nYou can now try to fit and predict using the following basic workflow\n\n```python\n# Import Trainer class\nfrom taxifare_deep.trainer import Trainer\n\n# Download a sub-sample of rows to train on\ntrainer = Trainer(nrows=10000)\n\n# Clean data\ntrainer.clean()\n\n# Preprocess data and create train/test/split\ntrainer.preproc(test_size=0.3)\n\n# Fit neural network and show training performance\ntrainer.fit(plot_history=True, verbose=1)\n\n# evaluate on test set (by default the holdout from train/test/split)\ntrainer.evaluate(X_test=None, y_test=None)\n```\n\n## Investigate code base\n\n- Feel free to fork this repo to your own github account, and clone it to your local hard drive\n- Try to understand how the code works, following basic workflow above (you can run it on a local notebook after doing `pip install -e .` from the root folder)\n- Feel free to improve it as you see fit\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flewagon%2Ftaxi-fare-deep","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flewagon%2Ftaxi-fare-deep","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flewagon%2Ftaxi-fare-deep/lists"}