{"id":42963143,"url":"https://github.com/powderl/local-variable-importance-from-a-global-model","last_synced_at":"2026-01-30T23:29:36.387Z","repository":{"id":130720465,"uuid":"239397935","full_name":"PowderL/Local-variable-importance-from-a-global-model","owner":"PowderL","description":"Python module to calculate local variable importance with the global model","archived":false,"fork":false,"pushed_at":"2020-09-17T07:00:38.000Z","size":55,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2024-01-28T21:39:51.622Z","etag":null,"topics":["forest","heterogenity","importance","random","spatiotemporal","variable"],"latest_commit_sha":null,"homepage":"","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/PowderL.png","metadata":{"files":{"readme":"README.rst","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}},"created_at":"2020-02-10T00:38:35.000Z","updated_at":"2020-09-17T07:00:41.000Z","dependencies_parsed_at":null,"dependency_job_id":"f1326a28-b971-4584-bb2b-0143d0881443","html_url":"https://github.com/PowderL/Local-variable-importance-from-a-global-model","commit_stats":{"total_commits":59,"total_committers":2,"mean_commits":29.5,"dds":"0.11864406779661019","last_synced_commit":"dc070dea74384ba1df8684bacef066f4c83356b7"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/PowderL/Local-variable-importance-from-a-global-model","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PowderL%2FLocal-variable-importance-from-a-global-model","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PowderL%2FLocal-variable-importance-from-a-global-model/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PowderL%2FLocal-variable-importance-from-a-global-model/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PowderL%2FLocal-variable-importance-from-a-global-model/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/PowderL","download_url":"https://codeload.github.com/PowderL/Local-variable-importance-from-a-global-model/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PowderL%2FLocal-variable-importance-from-a-global-model/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28923089,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-30T22:32:35.345Z","status":"ssl_error","status_checked_at":"2026-01-30T22:32:31.927Z","response_time":66,"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":["forest","heterogenity","importance","random","spatiotemporal","variable"],"created_at":"2026-01-30T23:29:35.463Z","updated_at":"2026-01-30T23:29:36.382Z","avatar_url":"https://github.com/PowderL.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"glvi\n============\n\n**glvi** is a Python module for machine learning built on top of **scikit-learn** and is distributed under the MIT license.\n\n**glvi** was developed by Mr. Li for evaluating sptiotemporal heterogeneity of variable imporance through a global model \n\nbuilt on a large time-space scope.\n\n**glvi** inherits from the RandomForestRegressor in **scikit-learn**. If you want to use **glvi** to estimate local variable importance, \n\nmodel fitting is necessary. But at present, using a fitted random forest model from RandomForestRegressor is not supported. To \n\naccelerate the process, parallel is provided which is same with the parallel in **scikit-learn**. The parallel process can be \n\nimplemented by the parameter of ``n_jobs`` which just is consistent with the **scikit-learn**.\n\n**glvi 0.1.5 and later was not supporting Python 2.7 and Python 3.4.**\nglvi 0.1.5 and later require Python 3.5 or newer.\n\nglvi requires:\n\n- Python (\u003e= 3.5)\n- NumPy (\u003e= 1.11.0)\n- SciPy (\u003e= 0.17.0)\n- Pandas (\u003e= 0.24.0)\n- Joblib (\u003e= 0.11.0)\n- Scikit-learn (\u003e= 0.20.0)\nUser installation\n~~~~~~~~~~~~~~~~~\n\nInstall from github is available but is not recommended. If you already have a working installation of numpy, scipy, pandas and scikit-learn, the easiest way to install glvi is using ``pip``   ::\n\t\n\tpip install -U glvi\n\nOr build from source for Windows ::\n\n\tpython setup.py install\n\nFor Linux ::\n\t\n\tpip install --verbose\n\nUser guide\n~~~~~~~~~~~~~~~~~\n\nCompute local variable importance based on decrease in node impurity ::\n\n\tfrom glvi import todi\n\tr_t = todi.lovim(500, max_features=0.3, n_jobs=-1)\n\tr_t.fit(train_x, train_y)\n\tlocal_variable_importance = r_t.compute_feature_importance(X,Y,partition_feature = partition_feature, norm=True,n_jobs=-1)\n\t\nor compute local variable importance based on decrease in accuracy ::\n\n\tfrom glvi import meda\n\tr_m = meda.lovim(500, max_features=0.3, n_jobs=-1)\n\tr_m.fit(train_x, train_y)\n\tlocal_variable_importance = r_m.compute_feature_importance(X,Y,partition_feature = partition_feature, norm=True,n_jobs=-1)\n\t\nDevelopment\n~~~~~~~~~~~~~~~~~\n\nTo acquire lower computation cost, we also developed a another package called **forest-gis** using **Cython** to accelerate the process.\nPlease refer to : https://github.com/PowderL/Tree-based-machine-learning-for-gis.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpowderl%2Flocal-variable-importance-from-a-global-model","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpowderl%2Flocal-variable-importance-from-a-global-model","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpowderl%2Flocal-variable-importance-from-a-global-model/lists"}