{
  "fetched_at": "2026-10-20T07:15:40Z",
  "source_url": "https://www.kaggle.com/competitions/eds-232-ocean-chemistry-prediction-for-calcofi/data",
  "pages": [
    {
      "name": "data-description",
      "content": "This dataset was downloaded from the CalCOFI data portal.  Bottle and cast data was downloaded and merged, then relevant variables were selected.  \n\nYou will use the data contained in the train.csv file to train a model that will predict dissolved inorganic carbon (DIC) content in the water samples.  \n  \nFiles\n\n*   **train.csv** - the training set\n*   **test.csv** - the test set\n*   **sample_submission.csv** - a sample submission file in the correct format\n\nColumns\nA database description is available here: [https://calcofi.org/data/oceanographic-data/bottle-database/](url)\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "For this quarter's final lab, you will be using the knowledge of machine learning that you have gained this quarter to training models to predict dissolved inorganic carbon in water samples collected by the [California Cooperative Oceanic Fisheries Investigations](https://calcofi.org/) program (CalCOFI).  \n\n## Your Task\n\nAcquire domain knowledge. (Dr. Satterthwaite's presentation)\nExplore the data.\nPreprocessing.\nChoose a model algorithm.\nTune relevant parameters (Cross validation).\nSubmit your prediction.\n\n##Submitting your lab and predictions\n\nYou will first need to create an online notebook on Kaggle.  You can set it up to be .Rmd form and then paste code from an .Rmd in RStudio into the notebook.  This is where your lab will be graded, to make sure you have proper documentation of your code for each of the steps in the model process.\n\nIf you'd like to work as a team you can.  Each team member will create their own account but you will have a joint submission.\n\nKaggle's [competition documentation](https://www.kaggle.com/docs/competitions)\n\nInstructions on [submitting predictions](https://www.kaggle.com/docs/competitions#making-a-submission).\n\nOnce you have created your online notebook and used it to submit your predictions for the competition, please share (via share button at the top right of the notebook screen) your notebook with both Brian (user name: bhyleee) and I (Mateo Robbins) so we can view and grade your code.  Don't forget to annotate you code and guide the viewer through the ML steps you went through and the decisions you made along the way.\n\nKaggle has the test data that it will use to evaluate your submission's performance.  You will have both a public and private score, based on different subsets of the test data.  The public score will be visible to everyone so we can see who is winning.  The private score will be used to determine the winner.\n`\n## Acknowledgements\n\nWe thank CalCOFI and Dr. Erin Satterthwaite for providing this dataset.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is the RMSE.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "The Rules:\n- Have Fun\n- Collaborate\n- Enjoy Spring Break",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}