{
  "fetched_at": "2026-10-19T21:27:06Z",
  "source_url": "https://www.kaggle.com/competitions/dataquest2020/data",
  "pages": [
    {
      "name": "rules",
      "content": "The winners will have to submit their final notebooks for confirmation.\nALL THE BEST!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<h2>File Desprictions : </h2>\n<ul>\n<li><strong>energy_train.csv</strong>- the training set</li>\n<li><strong>energy_test.csv</strong>- the test set</li>\n<li><strong>sample_submission.csv</strong>- a sample submission file in the correct format</li>\n</ul>\n\n<h2>Label Descriptions : </h2>\n<ul>\n<li><strong>date</strong> - the date when the values were calculated</li>\n<li><strong>WattHour</strong> - energy consumed by all the appliances</li>\n<li><strong>luminosity</strong> - rate of emission of light</li>\n<li><strong>degree_C1</strong> - temperature in manager's office</li>\n<li><strong>moisture_1</strong> - moisture in manager's office</li>\n<li><strong>degree_C2</strong> - temperature in factory floor</li>\n<li><strong>moisture_2</strong> - moisture in factory floor</li>\n<li><strong>degree_C3</strong> - temperature in packaging dept.</li>\n<li><strong>moisture_3</strong> - moisture in packaging dept.</li>\n<li><strong>degree_C4</strong> - temperature in canteen</li>\n<li><strong>moisture_4</strong> - moisture in canteen</li>\n<li><strong>degree_C5</strong> - temperature in locker room</li>\n<li><strong>moisture_5</strong> - moisture in locker room</li>\n<li><strong>degree_C6</strong> - temperature in production room</li>\n<li><strong>moisture_6</strong> - moisture in production room</li>\n<li><strong>degree_C7</strong> - temperature in quality-control room</li>\n<li><strong>moisture_7</strong> - moisture in quality-control room</li>\n<li><strong>degree_C8</strong> - temperature in main office</li>\n<li><strong>moisture_8</strong> - moisture in main office</li>\n<li><strong>degree_C9</strong> - temperature in shipping dept.</li>\n<li><strong>moisture_9</strong> - moisture in shipping dept.</li>\n<li><strong>degree_Cout</strong> - outside temperature</li>\n<li><strong>Pressure</strong> - pressure in mmHg</li>\n<li><strong>moisture_out</strong> - moisture in surroundings</li>\n<li><strong>Wind</strong> - windspeed in m/s</li>\n<li><strong>Clarity</strong> - clarity in vision due to climate</li>\n<li><strong>dew_index</strong> - dew density in the atmosphere</li>\n<li><strong>random_variable_1</strong> - nondimensional</li>\n<li><strong>random_variable_2</strong> - nondimensional</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<h2>DataQuest 2020 - Organised by PASC</h2><br>\n<strong>Gear up guys, you have a new problem statement to solve! :) </strong><br>\n<p>The temperature and the moisture conditions in a factory outlet were calculated using a wireless sensor. The data that was observed was averaged over 10 minute time slots. The various temperatures calculated for the different rooms inside the factory are given. Two random variables were added in the data-set for testing the regression models and to filter out non-predictive parameters. Predict the energy consumed.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation metric for this competition is <a href=\"https://en.wikipedia.org/wiki/Root-mean-square_deviation\"> Root Mean Square Error. </a>RMSE is the most widely used metric for regression tasks and is the square root of the averaged squared difference between the target value and the value predicted by the model. It is preferred more in some cases because the errors are first squared before averaging which poses a high penalty on large errors. This implies that RMSE is useful when large errors are undesired.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}