{
  "fetched_at": "2026-10-24T12:35:44Z",
  "source_url": "https://www.kaggle.com/competitions/bdcoe-datahack/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<h1><strong>File descriptions</strong></h1>\r\n<p><strong>train_dataset.csv</strong> - the training data. The training dataset comprises 300 data-points with <g class=\"gr_ gr_78 gr-alert gr_spell gr_run_anim ContextualSpelling multiReplace\" id=\"78\" data-gr-id=\"78\">16 dimensional</g> inputs and <g class=\"gr_ gr_40 gr-alert gr_spell gr_run_anim ContextualSpelling multiReplace\" id=\"40\" data-gr-id=\"40\">one dimensional</g> real-valued outputs.</p>\r\n<p><br /><strong>test_dataset.csv</strong> - the test set inputs. The test dataset comprises 200 data-points with <g class=\"gr_ gr_77 gr-alert gr_spell gr_run_anim ContextualSpelling multiReplace\" id=\"77\" data-gr-id=\"77\">16 dimensional</g> input features. The outputs are missing and the goal is to predict them. In addition, at some of the test <g class=\"gr_ gr_45 gr-alert gr_gramm gr_run_anim Punctuation only-ins replaceWithoutSep\" id=\"45\" data-gr-id=\"45\">points</g> a subset of the inputs is also missing. The test inputs are also available as a CSV file in the same format as the training data. Missing inputs and indicated by the value NA.</p>\r\n<p><br /><strong>sample_submission.</strong><g class=\"gr_ gr_41 gr-alert gr_spell gr_run_anim ContextualSpelling ins-del multiReplace\" id=\"41\" data-gr-id=\"41\">csv</g> - a sample submission file in the correct format. For each test <g class=\"gr_ gr_48 gr-alert gr_gramm gr_run_anim Punctuation only-ins replaceWithoutSep\" id=\"48\" data-gr-id=\"48\"><g class=\"gr_ gr_42 gr-alert gr_spell gr_run_anim ContextualSpelling\" id=\"42\" data-gr-id=\"42\">datapoint</g></g> you must predict the missing real-valued output. These predictions should be submitted in the same format as the training outputs. The first row must contain column names (ID, Total.Interactions). Below this row, the first column must contain the data-point index (that runs from 1 through to 200) and the second column must contain the predictions (integer numbers).</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<h1><strong>Regression competition</strong></h1>\r\n<p>Here are the key details for the regression competition:</p>\r\n<p><strong>Description of training data</strong></p>\r\n<p>The training dataset comprises 300 data-points with <g class=\"gr_ gr_136 gr-alert gr_spell gr_run_anim ContextualSpelling multiReplace\" id=\"136\" data-gr-id=\"136\">16 dimensional</g> inputs and <g class=\"gr_ gr_52 gr-alert gr_spell gr_disable_anim_appear ContextualSpelling multiReplace\" id=\"52\" data-gr-id=\"52\">one dimensional</g> real-valued outputs. The training dataset is available as a CSV file. The first row of each CSV file contains the column names and the first column contains the data-point index (running from 1 to 300). There are standard functions to read these files in many programming languages, e.g. read.csv in R and csv.reader or <g class=\"gr_ gr_37 gr-alert gr_spell gr_disable_anim_appear ContextualSpelling ins-del multiReplace\" id=\"37\" data-gr-id=\"37\">numpy</g>.loadtxt in Python.</p>\r\n<p><strong>Description of test data</strong></p>\r\n<p>The test dataset comprises 200 data-points with <g class=\"gr_ gr_135 gr-alert gr_spell gr_run_anim ContextualSpelling multiReplace\" id=\"135\" data-gr-id=\"135\">16 dimensional</g> input features. The outputs are missing and the goal is to predict them. In addition, at some of the test <g class=\"gr_ gr_45 gr-alert gr_gramm gr_disable_anim_appear Punctuation only-ins replaceWithoutSep\" id=\"45\" data-gr-id=\"45\">points</g> a subset of the inputs is also missing. The test inputs are also available as a CSV file in the same format as the training data. Missing inputs are indicated by the value NA.</p>\r\n<p><strong>Submission of predictions</strong></p>\r\n<p>For each test <g class=\"gr_ gr_36 gr-alert gr_spell gr_disable_anim_appear ContextualSpelling\" id=\"36\" data-gr-id=\"36\"><g class=\"gr_ gr_49 gr-alert gr_gramm gr_disable_anim_appear Punctuation only-ins replaceWithoutSep\" id=\"49\" data-gr-id=\"49\">datapoint</g></g> you must predict the missing real-valued output. These predictions should be submitted in the same format as the training outputs. The first row must contain column names (ID, Total.Interactions). Below this row, the first column must contain the data-point index (that runs from 1 through to 200) and the second column must contain the predictions (integer numbers).</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<h1><strong>Evaluation</strong></h1>\r\n<p><strong>Evaluation metric</strong></p>\r\n<p>The Root Mean Squared Error (RMSE) will be used for evaluation. The RMSE is defined as the root of the average squared error between the prediction and <g class=\"gr_ gr_61 gr-alert gr_spell gr_run_anim ContextualSpelling ins-del multiReplace\" id=\"61\" data-gr-id=\"61\">groundtruth</g>.</p>\r\n<p><img src=\"https://s4.postimg.org/q8bacm371/rmse.png\" alt=\"rmse\" width=\"500\" height=\"184\" style=\"display: block; margin-left: auto; margin-right: auto;\" /></p>\r\n<p>Outputs associated with missing inputs contribute equally to those without.</p>\r\n<p><strong>Leaderboard and final evaluation</strong></p>\r\n<p>The predictions <g class=\"gr_ gr_54 gr-alert gr_gramm gr_run_anim Grammar multiReplace\" id=\"54\" data-gr-id=\"54\">on</g> 50% of the test data points are used to score the submission according to the RMSE and maintain a public leaderboard. The predictions <g class=\"gr_ gr_56 gr-alert gr_gramm gr_run_anim Grammar multiReplace\" id=\"56\" data-gr-id=\"56\">on</g> the remaining 50% of the test data points will be used, after the competition closes, for the final evaluation. This prevents overfitting on the public test data.</p>\r\n<p><strong>Submission rules</strong></p>\r\n<p>Each team may only submit 10 sets of predictions each day. When the competition closes, each team will select 1 set of predictions to put forward for the final evaluation.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "<h1><strong>Competition Rules</strong></h1>\r\n<p><strong>One account per participant</strong></p>\r\n<p>You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.</p>\r\n<p><strong>No private sharing outside teams</strong></p>\r\n<p>Privately 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.</p>\r\n<p><strong>Team Mergers</strong></p>\r\n<p>Team mergers are not allowed in this competition.</p>\r\n<p><strong>Team Limits</strong></p>\r\n<p>There is no maximum team size.</p>\r\n<p><strong>Submission Limits</strong></p>\r\n<p>You may submit a maximum of 10 entries per day.</p>\r\n<p>You may select only 1 final submissions for judging.</p>\r\n<p><strong>Competition Timeline</strong></p>\r\n<p>Start Date: 6/3/2017 12:00 AM IST</p>\r\n<p>Merger Deadline: None</p>\r\n<p>Entry Deadline: None</p>\r\n<p>End Date: 8/3/2014 11:59 PM IST</p>\r\n<p>The rules page is a bit special: it will auto-update the text based on the parameters of the competition. The rules you need to add here are any additional rules relating to dataset usage. You may also put grading information here.</p>\r\n<p><strong>Rules Acceptance</strong></p>\r\n<p>You accepted these rules at 5:36 pm, Sunday 5 March 2017 UTC.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}