{"id":19208080,"url":"https://github.com/pr38/dask_backward_feature_selection","last_synced_at":"2026-04-16T14:01:19.978Z","repository":{"id":163693325,"uuid":"249547760","full_name":"pr38/dask_backward_feature_selection","owner":"pr38","description":"Backward step-wise feature selection using Dask, scikit-learn compatible","archived":false,"fork":false,"pushed_at":"2020-12-21T20:03:02.000Z","size":46,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-02-23T06:46:42.134Z","etag":null,"topics":["dask","feature-selection","machine-learning","python","scikit-learn"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/pr38.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-03-23T21:26:48.000Z","updated_at":"2023-05-16T18:02:45.000Z","dependencies_parsed_at":null,"dependency_job_id":"f8d8da7a-db90-4262-9794-1e876767fc93","html_url":"https://github.com/pr38/dask_backward_feature_selection","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/pr38/dask_backward_feature_selection","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pr38%2Fdask_backward_feature_selection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pr38%2Fdask_backward_feature_selection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pr38%2Fdask_backward_feature_selection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pr38%2Fdask_backward_feature_selection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pr38","download_url":"https://codeload.github.com/pr38/dask_backward_feature_selection/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pr38%2Fdask_backward_feature_selection/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31888935,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-16T11:36:10.202Z","status":"ssl_error","status_checked_at":"2026-04-16T11:36:09.652Z","response_time":69,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["dask","feature-selection","machine-learning","python","scikit-learn"],"created_at":"2024-11-09T13:24:06.644Z","updated_at":"2026-04-16T14:01:19.917Z","avatar_url":"https://github.com/pr38.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Dask Backward Feature Selection\nBackward step-wise feature selection using Dask, scikit-learn compatible.\n\nScale out feature seletion using distributed computing/Dask!\n\nI created this due to the fact that mlxtend's SequentialFeatureSelector did not use joblib in a Dask compatable way.\n\nInstall\n-------\n\n\u003e pip install git+https://github.com/pr38/dask_backward_feature_selection\n\nExample Usage\n-------\n```python \nimport numpy as np\nimport pandas as pd\n\nfrom sklearn.tree import DecisionTreeRegressor\nfrom sklearn.datasets import load_boston\n\nfrom dask.distributed import Client, LocalCluster\n\nfrom dask_backward_feature_selection import DaskBackwardFeatureSelector\n\n#You should be useing Dask's yarn or kubernates cluster deployments\n#if you are going to be running this localy you are better off useing mlxtend's SequentialFeatureSelector \ncluster = LocalCluster(3)\nclient = Client(cluster)\n\nboston = load_boston()\nX = boston['data']\ny = boston['target']\n\ndfs = DaskBackwardFeatureSelector(DecisionTreeRegressor(),client)\n#kwargs for DaskBackwardFeatureSelector are:\n#k_features: the smallest combination of features DaskBackwardFeatureSelector will examine.\n#cv: if \"cv\" is an int, it will refer to the number of  cross validation folds for each feature combination tested. \n#cv can also be a scikitlearn CV class.\n#scoring: can be string (https://scikit-learn.org/stable/modules/generated/sklearn.metrics.get_scorer.html#sklearn.metrics.get_scorer)\n#, or a scikitlearn scoring class.\n#if scatter is true, each thread in the cluster will keep a copy of the training data and estimator.\n\ndfs.fit(X,y)\n\n#positions of top performing combination of features in X matrix.\ndfs.k_feature_idx_\n\n#we can treat DaskBackwardFeatureSelector as an estimator after training.\ndfs.predict(X)\n\n\n#also DaskBackwardFeatureSelector can act as transformer.\ndfs.transform(X,y)\n\n#finally we can examine the best performing feature combinations for each step, for other use cases (ie:one-standard-error rule).\npd.DataFrame(dfs.metric_dict_ )\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpr38%2Fdask_backward_feature_selection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpr38%2Fdask_backward_feature_selection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpr38%2Fdask_backward_feature_selection/lists"}