{
  "fetched_at": "2026-10-20T07:45:31Z",
  "source_url": "https://www.kaggle.com/competitions/dru-kaggle-intro/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## The data has been divided into 2 groups : \n* Train Set (**train_mobile.csv**) \n* Test Set (**test_mobile.csv**) \n\nThe training set should be used to build your machine learning models. For the training set, you have `price_range` (it is our target or class label) for each mobile sales data point. The test dataset will be used to predict `price_range` on unseen data and compose your submission file. So, the test set does not have the `price_range` (target variable) for each mobile sales data point.\n\nUse the model you trained to predict the price range for each data point in the test set. The training set contains 1500 data points. Each data point has 20 features and one target variable.\n\nThe test set contains 500 data points. Each data point has 20 features.\n\n##The data contains the following fields:\n\n* `battery_power` - total energy stored in the battery (in mAh)\n* `blue` - has bluetooth (yes or no)\n* `clock_speed` - processor speed when executes the instructions\n* `dual_sim` - has dual sim capability (yes or no)\n* `fc` - large resolution of front camera (in MegaPixels)\n* `four_g` - has 4G connectivity (yes or no)\n* `int_memory` - large internal memory (in GB)\n* `m_dep` - mobile thickness (in cm)\n* `mobile_wt` - mobile mass (in gram)\n* `n_cores` - number of cores in the processors (pcs)\n* `pc - large` resolution of rear camera (in MegaPixels)\n* `px_height` - length of the pixel resolution\n* `px_width` - width of the pixel resolution\n* `ram` - capacity of Random Access Memory (in MB)\n* `sc_h` - screen length (cm)\n* `sc_w` - screen width (cm)\n* `talk_time` - the longest call time that can be made from a fully charged mobile until it runs out (in hours)\n* `three_g` - has 3G connectivity (yes or no)\n* `touch_screen` - has touch screen (yes or no)\n* `wifi` - has wifi (yes or no)\n* `price_range` - this is the target variable with value of 0 (low cost), 1 (medium cost), 2 (high cost), 3 (very high cost)\n\n## sample_submission.csv\n\nThe **sample_submission.csv** file is provided as an example of how you should structure your predictions. So, your submission should have:\n\n* a `index` column containing unique id of each mobile from test_mobile.csv.\n* a `price_range` column (that you will create!) with target values 0, 1, 2, 3.\n\nHere is an example of [sample_submission.csv](https://www.kaggle.com/c/dru-kaggle-intro/overview/evaluation) file.\n\n## Files\n\n*   **train_mobile.csv** - the train set\n*   **test_mobile.csv** - the test set\n*   **sample_submission.csv** - a sample submission file in the correct format",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Hey! This is the first introductory Kaggle lab of the 6th module.\nIn this lab, you will classify the price range of mobile phones depending on their characteristics📱→💲\n\nYou will be given [guidance](https://github.com/DataRootUniversity/ds-fundamentals/blob/master/dru-kaggle-intro/dru_kaggle_intro_template.ipynb) on how to do this lab, but you can add your own steps to improve the classification quality.\n\nThis competition uses a modified [Mobile Price](https://www.kaggle.com/iabhishekofficial/mobile-price-classification)  dataset.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<!-- Evaluation -->\n<h1>Evaluation</h1>\n<p>\n  Submissions are evaluated on MeanFScore, which at Kaggle is actually a\n  <a href=\"https://en.wikipedia.org/wiki/F-score\" target=\"_blank\"\n     rel=\"noopener noreferrer\">micro-averaged&nbsp;F1-score</a>.\n</p>\n<p>\n  The F1 metric weights recall and precision equally, and a good retrieval\n  algorithm will simultaneously maximise both.\n</p>\n\n<!-- Submission File -->\n<h1>Submission File</h1>\n<p>\n  For each <code>index</code> in the test set, you must predict a price\n  <code>price_range</code>. The file should contain a header and have the\n  following format:\n</p>\n\n<pre><code>index,price_range\n1812,0\n624,1\n678,3\netc.\n</code></pre>\n\n<blockquote>You can submit results up to 20&nbsp;times a day.</blockquote>\n\n<h2>Happy coding&nbsp;!</h2>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "* Don't cheat!\n* Have fun :)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}