{
  "fetched_at": "2026-10-19T21:28:30Z",
  "source_url": "https://www.kaggle.com/competitions/csci-5622-problem-set-4-2020-spring/data",
  "pages": [
    {
      "name": "rules",
      "content": "There are very few restrictions on this activity. \n\nUnlike our other assignments, you may use whatever languages and ML packages you would like. We recommend you continue to use Python / Jupyter / SKLearn as that is what we will be supporting in this class / on Piazza.\n\nDo not collaborate with other students! \n\nMore strict than usual:\n\nDo not post implementation questions publicly on Piazza\n\n(if someone does, please ignore it)\n\nReach out to David / Bhalchandra (You can post a private question on Piazza) \n\nDo not seek out / use additional datasets\n\nSubmissions cap of 2 per day is implemented in Kaggle.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "train-features.csv contains the features of the examples / cases, separated by commas, that you will use to train your classifiers. You must associate the features found in each row / line with the output found in the corresponding row / line in train-output.csv to create a full case.\n\ntest-features.csv contains the features of the examples / cases that you will need to predict using your trained model.\n\nSee train.names for header descriptions of the train and test features. This will be helpful in understanding how you may need to normalize, bin, or otherwise update your data to better suit your classifiers.\n\nYou can use test-submission.demo to see what an example submission file should look like. This file is a baseline case - you can even upload it to make sure your Kaggle account is working correctly!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<h2>About this Activity</h2>\nFor Problem Set 4, we're stripping away a lot of the structure behind the problem and instead asking you to simply predict income from a series of demographic and employment features.\n<h2>About the Dataset</h2>\nYou have been given two training documents - train.data and train.names - which contain the *features* (in the .data file) and the *outcomes* (in the .names file) in the Data tab above, with rows corresponding to cases. You have also been given test.data with the test case features. Your objective is to provide a test.names file that predicts the outcomes for each case. See the Data page for full details.\n<h2>About Submissions</h2>\nTo submit a set of predictions, upload your properly formatted document in the Submit Predictions section. Use the sample in the Data section for guidance on formatting your submission. Check the Leaderboard section to see how you're doing!\n\n(EDITED TO ADD 3/18 - You have to be logged in to Kaggle to submit, and Kaggle has some tricky rules in place to ensure each human only has one account. If your account is associated with your given name in the course roster or your campus username, I can easily link your activity to your grade. If your Kaggle account is a personal account, under a pseudonym, etc. that's fine - you'll just have to make that link in your brief description. Thanks!)\n\n<h2>Rules</h2>\nFull details of how submissions work, etc. can be found in the Rules tab above as well as on Canvas. There are some important details to note here on the main page.\n- You may only submit up to two predictions to Kaggle per day. Use internal validation processes (K-fold cross validation, etc) to optimize!\n-  You are working on this homework alone. This is not a group assignment!\n\nOtherwise, this homework follows the same rules as other homework assignments - you should be working independently, using Piazza as a resource but not as a coding crutch. There are many approaches to solve this problem, and not everyone has to use the same one!\n<h2>Acknowledgements</h2>\nWe thank the UCI Machine Learning Repository for access to this dataset.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}