{
  "fetched_at": "2026-10-20T10:10:16Z",
  "source_url": "https://www.kaggle.com/competitions/fuel-efficiency-forecasting/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Please download the following data files, including the training set (auto-mpg-train.data) and the test set (auto-mpg-test.data), use the training set to train the model, the test set is used to make fuel efficiency predictions, and upload the test results.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "- Download Auto-mpg data\n   Please download the training and test data from the Data section of this competition web page to ensure that the data is the same for everyone.\n- Install a jupyter notebook in the conda environment on your computer or server\n- Data operation can be designed by yourself, including data cleaning, splitting training set test set, normalization, etc. Data Please use the two files in the Data column on this contest web page, the training set is used to train the model, and the test set is used to make predictions and upload the results.\n- Establish a neural network model based on Pytorch on your own computer or server for training, select MSE as Loss function, and predict fuel efficiency (mpg, miles per gallon).\n- Upload the test result to kaggle and pay attention to the submission limit. After submitting the result, you can choose whether to add the submitted result to the leaderboard. If it is added to the leaderboard, the ranking will be updated in real time.\n- Submit ipynb files to webclass (including code, comments, running results, pictures, etc.)\n- 2 weeks to complete",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Download the auto-mpg-test.data in the data, use the model to forecast the fuel efficiency, do not change the data order, and export the fuel efficiency to a CSV file. The first column in the CSV file is the serial number ID, which is the order in auto-mpg-test.data, and the second column is the predicted result of your model output, which is the fuel efficiency.\n\nExample:\nID   RESULT\n1     30.5\n2     46\n3     40\n...",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "基于Pytorch建⽴神经⽹络模型，选择mse为Loss函数，进⾏燃油效率预报（mpg, miles per gallon），Train和Test数据请在竞赛网页上下载。注意不要将测试数据也进行训练防止数据泄露。",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "Fuel efficiency forecasting—THU—Geoscience High performance computing and big Data course assignment",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}