{
  "fetched_at": "2026-10-19T15:17:35Z",
  "source_url": "https://www.kaggle.com/competitions/cosc6389contest2/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Format of submission\n\nYour submission file should be in the csv format with two columns: id and y. Example:\n\nid,y \n\n1,1\n\n2,1\n\n3,3\n\n... 480,2",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "The training data file consists of 720 rows and 3074 columns. 720 rows represent for 720 images. The first column is the id and the second column is the class of image (integer between 1 and 3). The other columns are the predictors. There are 32*32 = 1024 pixels for each image, and every pixel can be quantified by an additive RGB model (https://en.wikipedia.org/wiki/RGB_color_model) with three color measurements: r for red, g for green, and b for blue. Hence, the total number of predictors is 1024*3 = 3072. The predictor name contains three pieces of information for the pixel: rgb, column, and row For example, “r0102” means red for the pixel in column 1 (x=1) and row 2 (y=33-2=31), “g1005” means green for the pixel in column 10 (x=10) and row 5 (y=33-5=28), and “b3120” means blue for the pixel in column 31 (x=31) and row 20 (y=33-20=13).",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}