{
  "fetched_at": "2026-10-19T21:53:12Z",
  "source_url": "https://www.kaggle.com/competitions/ce263n-hw4/data",
  "pages": [
    {
      "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 - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<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>submission.csv</strong> - a file you need to fill in your predictions</li>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Given training data (train.csv) on Uber/Lyft trip OD locations, starting time and durations, we would like to estimate travel times between two specified locations at a given departure time using machine learning models (SVR, random forest, neural networks, …). \n\nThe training dataset (train.csv) contains a csv file with ride start and end locations (specified as WGS84 coordinates), trip start time (local time), and trip duration in seconds. Each line is a trip and has the following format:\n\n```row_id, start_lng, start_lat, end_lng, end_lat, datetime, duration```\n\nThe test dataset (test.csv) contains a csv file with ride start and end locations (specified as WGS84 coordinates), and trip start time (local time). You need to build model based on the training set and estimate the travel times for all trips in the test set. \nEach line in the test set has the following format:\n\n```row_id, start_lng, start_lat, end_lng, end_lat, datetime```\n\nYour output file, titled submission.csv, should have two columns: row id (row_id) and estimated duration (duration) in seconds for each line in the test file, where the row_id column refers to the corresponding row in the test file for which you are making the prediction. It should also have the following header specified as the first line of the file:\n\n```row_id, duration```\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Quality of your classifier(s) will be assessed using root mean squared error (RMSE) of your predicted versus the actual durations on the test set (test.csv). The evaluation function is based on the following code.\n\n```from sklearn.metrics import mean_squared_error```\n```np.sqrt(mean_squared_error(prediction, ground_truth))```",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}