{
  "fetched_at": "2026-10-24T18:05:28Z",
  "source_url": "https://www.kaggle.com/competitions/forest-cover-type-prs-2018/data",
  "pages": [
    {
      "name": "rules",
      "content": "# One account per participant\nYou cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.\n\n#No private sharing outside teams\nPrivately sharing code or data outside of teams is not permitted. It's okay to share code if made available to all participants on the forums.\n\n#Team Mergers\nTeam mergers are not allowed in this competition.\n\n#Team Limits\nThe maximum size of a team is 1 participant.\n\n# Submission Limits\nYou may submit a maximum of 5 entries per day.\n\nYou may select up to 3 final submissions for judging.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "The study area includes four wilderness areas located in the Roosevelt National Forest of northern Colorado. Each observation is a 30m x 30m patch. You are asked to predict an integer classification for the forest cover type. The seven types are:\n\n1. Spruce/Fir\n2. Lodgepole Pine\n3. Ponderosa Pine\n4. Cottonwood/Willow\n5. Aspen\n6. Douglas-fir\n7. Krummholz\n\nThe training set (11340 observations) contains both features and the Cover_Type. The test set contains only the features. You must predict the Cover_Type for every row in the test set (3780 observations).\n\n# Data Fields\n__Elevation__ - Elevation in meters  \n__Aspect__ - Aspect in degrees azimuth  \n__Slope__ - Slope in degrees  \n__Horizontal_Distance_To_Hydrology__ - Horz Dist to nearest surface water features  \n__Vertical_Distance_To_Hydrology__ - Vert Dist to nearest surface water features  \n__Horizontal_Distance_To_Roadways__ - Horz Dist to nearest roadway  \n__Hillshade_9am__ (0 to 255 index) - Hillshade index at 9am, summer solstice  \n__Hillshade_Noon__ (0 to 255 index) - Hillshade index at noon, summer solstice  \n__Hillshade_3pm__ (0 to 255 index) - Hillshade index at 3pm, summer solstice  \n__Horizontal_Distance_To_Fire_Points__ - Horz Dist to nearest wildfire ignition points  \n__Wilderness_Area__ (4 binary columns, 0 = absence or 1 = presence) - Wilderness area designation  \n__Soil_Type__ (40 binary columns, 0 = absence or 1 = presence) - Soil Type designation  \n__Cover_Type__ (7 types, integers 1 to 7) - Forest Cover Type designation  \n\nThe wilderness areas are:\n\n1. Rawah Wilderness Area\n2. Neota Wilderness Area\n3. Comanche Peak Wilderness Area\n4. Cache la Poudre Wilderness Area\n\nThe soil types are:\n\n1. Cathedral family - Rock outcrop complex, extremely stony.\n2. Vanet - Ratake families complex, very stony.\n3. Haploborolis - Rock outcrop complex, rubbly.\n4. Ratake family - Rock outcrop complex, rubbly.\n5. Vanet family - Rock outcrop complex complex, rubbly.\n6. Vanet - Wetmore families - Rock outcrop complex, stony.\n7. Gothic family.\n8. Supervisor - Limber families complex.\n9. Troutville family, very stony.\n10. Bullwark - Catamount families - Rock outcrop complex, rubbly.\n11. Bullwark - Catamount families - Rock land complex, rubbly.\n12. Legault family - Rock land complex, stony.\n13. Catamount family - Rock land - Bullwark family complex, rubbly.\n14. Pachic Argiborolis - Aquolis complex.\n15. unspecified in the USFS Soil and ELU Survey.\n16. Cryaquolis - Cryoborolis complex.\n17. Gateview family - Cryaquolis complex.\n18. Rogert family, very stony.\n19. Typic Cryaquolis - Borohemists complex.\n20. Typic Cryaquepts - Typic Cryaquolls complex.\n21. Typic Cryaquolls - Leighcan family, till substratum complex.\n22. Leighcan family, till substratum, extremely bouldery.\n23. Leighcan family, till substratum - Typic Cryaquolls complex.\n24. Leighcan family, extremely stony.\n25. Leighcan family, warm, extremely stony.\n26. Granile - Catamount families complex, very stony.\n27. Leighcan family, warm - Rock outcrop complex, extremely stony.\n28. Leighcan family - Rock outcrop complex, extremely stony.\n29. Como - Legault families complex, extremely stony.\n30. Como family - Rock land - Legault family complex, extremely stony.\n31. Leighcan - Catamount families complex, extremely stony.\n32. Catamount family - Rock outcrop - Leighcan family complex, extremely stony.\n33. Leighcan - Catamount families - Rock outcrop complex, extremely stony.\n34. Cryorthents - Rock land complex, extremely stony.\n35. Cryumbrepts - Rock outcrop - Cryaquepts complex.\n36. Bross family - Rock land - Cryumbrepts complex, extremely stony.\n37. Rock outcrop - Cryumbrepts - Cryorthents complex, extremely stony.\n38. Leighcan - Moran families - Cryaquolls complex, extremely stony.\n39. Moran family - Cryorthents - Leighcan family complex, extremely stony.\n40. Moran family - Cryorthents - Rock land complex, extremely stony.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "In this competition you are asked to predict the forest cover type (the predominant kind of tree cover) from strictly cartographic variables (as opposed to remotely sensed data). The actual forest cover type for a given 30 x 30 meter cell was determined from US Forest Service (USFS) Region 2 Resource Information System data. Independent variables were then derived from data obtained from the US Geological Survey and USFS. The data is in raw form (not scaled) and contains binary columns of data for qualitative independent variables such as wilderness areas and soil type.\n\nThis study area includes four wilderness areas located in the Roosevelt National Forest of northern Colorado. These areas represent forests with minimal human-caused disturbances, so that existing forest cover types are more a result of ecological processes rather than forest management practices.\n\n# Acknowledgements\nKaggle is hosting this competition for the machine learning community to use for fun and practice. This dataset was provided by Jock A. Blackard and Colorado State University. We also thank the UCI machine learning repository for hosting the dataset. If you use the problem in publication, please cite:\n\nBache, K. & Lichman, M. (2013). UCI Machine Learning Repository. Irvine, CA: University of California, School of Information and Computer Science",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submissions are evaluated on multi-class classification accuracy.\n\nSubmission File\nYour submission file should have the observation Id and a predicted cover type (an integer between 1 and 7, inclusive). The file should contain a header and have the following format:\n\n    Id,Cover_Type\n    15121,1\n    15122,1\n    15123,1\n    ...",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}