{
  "fetched_at": "2026-10-20T07:31:07Z",
  "source_url": "https://www.kaggle.com/competitions/decision-trees-from-scratch-2024/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<h1>Data</h1>\n_________________________\n<strong>The features you will receive are:</strong>\n\nage (in number of days)\n\ngender (1 for women, 2 for men)\n\nheight (in cm)\n\nweight (in kg)\n\naphi (systolic blood pressure)\n\naplo (diastolic blood pressure)\n\ncholesterol (1 for normal, 2 for above normal, 3 for well above normal)\n\ngluc (glucose levels, 1 for normal, 2 for above normal, 3 for well above normal)\n\nsmoke (whether or not the individual smokes)\n\nalco (whether or not the person consumes alcohol, 0 or 1)\n\nactive (whether person engages in some form of physical activity)\n\n_________________________________\n\n<strong>The target (what you will be trying to predict):</strong>\n\ncardio (whether or not the individual has a cardiovascular disease)\n\n_____________________________\n<h2>File descriptions</h2>\n<ul>\n<li><strong>train.csv</strong> - the training set</li>\n<li><strong>test.csv</strong> - the test set</li>\n<li><strong>sample.csv</strong> - a sample submission file in the correct format</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "In this competition, you will predict whether or not someone has a cardiovascular disease given info about their health. You can use either a decision tree or a random forest.\n\nDon't use any libraries like scikit learn. You should code the decision tree algorithm yourself. You can use numpy and pandas for simple computation and data IO if you wish. However, it is entirely possible to do this competition without any libraries.\n\nYou can find shell code in slideshow for the random forests lecture at https://tjmachinelearning.com/schedule/2324\n\nFor some more decision trees resources, check out a learning resources guide we compiled for the 2020 National Machine Learning Open competition we hosted (https://docs.google.com/document/d/1VoxJVC6Vv13XN2XuJFd5ZMcaCBCCJnjYHvQaxpjfuRE/edit?usp=sharing)\n\nAs always, if you are still confused on how to get started there are lots of great decision tree tutorials out there (for example https://machinelearningmastery.com/implement-decision-tree-algorithm-scratch-python/), and you can always reach out to any of the officers or email tjmachinelearning@gmail.com for help",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "We will be using categorization accuracy to score submissions (percentage of correct classifications)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Don't use any libraries like scikit learn. You should code the decision tree/random forest algorithm yourself. You can use numpy and pandas for simple computation and data IO if you wish. However, it is entirely possible to do this competition without any libraries.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}