{"id":22833008,"url":"https://github.com/bradleykirton/foundery-case-study","last_synced_at":"2026-04-27T21:31:21.164Z","repository":{"id":44866076,"uuid":"138382878","full_name":"BradleyKirton/foundery-case-study","owner":"BradleyKirton","description":"Case study for FOUNDeRY","archived":false,"fork":false,"pushed_at":"2022-12-08T02:14:11.000Z","size":6320,"stargazers_count":0,"open_issues_count":8,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-31T02:20:42.551Z","etag":null,"topics":["data-science","python"],"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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/BradleyKirton.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2018-06-23T08:00:02.000Z","updated_at":"2018-06-24T17:12:58.000Z","dependencies_parsed_at":"2023-01-25T03:15:34.321Z","dependency_job_id":null,"html_url":"https://github.com/BradleyKirton/foundery-case-study","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/BradleyKirton/foundery-case-study","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BradleyKirton%2Ffoundery-case-study","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BradleyKirton%2Ffoundery-case-study/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BradleyKirton%2Ffoundery-case-study/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BradleyKirton%2Ffoundery-case-study/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/BradleyKirton","download_url":"https://codeload.github.com/BradleyKirton/foundery-case-study/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BradleyKirton%2Ffoundery-case-study/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32356596,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-27T20:07:02.737Z","status":"ssl_error","status_checked_at":"2026-04-27T20:07:00.910Z","response_time":128,"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":["data-science","python"],"created_at":"2024-12-12T21:11:24.116Z","updated_at":"2026-04-27T21:31:21.149Z","avatar_url":"https://github.com/BradleyKirton.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# FOUNDeRY Case Study\n\nUsing all or part of the [cover type](https://archive.ics.uci.edu/ml/datasets/Covertype) data set build a multi-class classification model for predicting types of forest cover from the input data available.\n\n# Project Structure\n\nThis project is structured as follows:\n\n- foundery-case-study/\n  - [data](./data/)\n  - [img](./img/)\n  - [case-study.ipynb](./case-study.ipynb)\n  - [Pipfile](./Pipfile)\n  - [Pipfile.lock](./Pipfile.lock)\n  - [README.md](./README.md)\n\nThis project makes use of pipenv to manage dependencies and virtual environments. All data is stored in the data subfolder however the raw data files are excluded from the repository. The data required in this project is downloaded in the [case-study notebook](./case-study.ipynb).\n\nThe accompanying presentation can be found [here](https://slides.com/bradleystuartkirton/deck-1#/).\n\n# Getting Started\n\nTo get started just clone the repository and install the project dependencies with pipenv. If you don't already have pipenv installed check out the [official docs](https://docs.pipenv.org/) for details on installation.\n\n```bash\n$ git clone https://github.com/BradleyKirton/foundery-case-study\n$ cd foundery-case-study\n$ pipenv install\n$ pipenv shell\n$ jupyter lab\n```\n\n## Project Dependencies\n\nOutside of the Python standard library this project requires the following libraries:\n\n- [jupyterlab](https://jupyter.org/)\n- [requests](http://docs.python-requests.org/en/master/)\n- [pandas](https://pandas.pydata.org/)\n- [scikit-learn](http://scikit-learn.org/stable/index.html)\n- [scipy](https://www.scipy.org/)\n- [altair](https://altair-viz.github.io/)\n- [matplotlib](https://matplotlib.org/)\n- [tqdm](https://tqdm.github.io/)\n\nFor a detailed dependency graph run the following command.\n\n```bash\npipenv graph\n```\n\n# Case Study Overview\n\n### Data Set Information\n\n\u003e\tPredicting forest cover type from cartographic variables only\n\t(no remotely sensed data).  The actual forest cover type for\n\ta given observation (30 x 30 meter cell) was determined from\n\tUS Forest Service (USFS) Region 2 Resource Information System \n\t(RIS) data.  Independent variables were derived from data\n\toriginally obtained from US Geological Survey (USGS) and\n\tUSFS data.  Data is in raw form (not scaled) and contains\n\tbinary (0 or 1) columns of data for qualitative independent\n\tvariables (wilderness areas and soil types).\n\u003e\n\u003e\tThis study area includes four wilderness areas located in the\n\tRoosevelt National Forest of northern Colorado.  These areas\n\trepresent forests with minimal human-caused disturbances,\n\tso that existing forest cover types are more a result of \n\tecological processes rather than forest management practices.\n\u003e\n\u003e\tSome background information for these four wilderness areas:  \n\tNeota (area 2) probably has the highest mean elevational value of \n\tthe 4 wilderness areas. Rawah (area 1) and Comanche Peak (area 3) \n\twould have a lower mean elevational value, while Cache la Poudre \n\t(area 4) would have the lowest mean elevational value. \n\u003e\n\u003e\tAs for primary major tree species in these areas, Neota would have \n\tspruce/fir (type 1), while Rawah and Comanche Peak would probably\n\thave lodgepole pine (type 2) as their primary species, followed by \n\tspruce/fir and aspen (type 5). Cache la Poudre would tend to have \n\tPonderosa pine (type 3), Douglas-fir (type 6), and \n\tcottonwood/willow (type 4).  \n\u003e\n\u003e\tThe Rawah and Comanche Peak areas would tend to be more typical of \n\tthe overall dataset than either the Neota or Cache la Poudre, due \n\tto their assortment of tree species and range of predictive \n\tvariable values (elevation, etc.)  Cache la Poudre would probably \n\tbe more unique than the others, due to its relatively low \n\televation range and species composition. \n\nThe data set contains the following features.\n\n| Name                               |  Data Type    | Measurement                    |    Description                                 |\n|------------------------------------|---------------|--------------------------------|------------------------------------------------|\n| Elevation                          | quantitative  |    meters                      |  Elevation in meters                           |\n| Aspect                             | quantitative  |    azimuth                     |  Aspect in degrees azimuth                     |\n| Slope                              | quantitative  |    degrees                     |  Slope in degrees                              |\n| Horizontal_Distance_To_Hydrology   | quantitative  |    meters                      |  Horz Dist to nearest surface water features   |\n| Vertical_Distance_To_Hydrology     | quantitative  |    meters                      |  Vert Dist to nearest surface water features   |\n| Horizontal_Distance_To_Roadways    | quantitative  |    meters                      |  Horz Dist to nearest roadway                  |\n| Hillshade_9am                      | quantitative  |    0 to 255 index              |  Hillshade index at 9am, summer solstice       |\n| Hillshade_Noon                     | quantitative  |    0 to 255 index              |  Hillshade index at noon, summer soltice       |\n| Hillshade_3pm                      | quantitative  |    0 to 255 index              |  Hillshade index at 3pm, summer solstice       |\n| Horizontal_Distance_To_Fire_Points | quantitative  |    meters                      |  Horz Dist to nearest wildfire ignition points |\n| Wilderness_Area (4 binary columns) | qualitative   |    0 (absence) or 1 (presence) |  Wilderness area designation                   |\n| Soil_Type (40 binary columns)      | qualitative   |    0 (absence) or 1 (presence) |  Soil Type designation                         |\n| Cover_Type (7 types)               | integer       |    1 to 7                      |  Forest Cover Type designation                 |","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbradleykirton%2Ffoundery-case-study","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbradleykirton%2Ffoundery-case-study","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbradleykirton%2Ffoundery-case-study/lists"}