{
  "fetched_at": "2026-10-20T11:09:16Z",
  "source_url": "https://www.kaggle.com/competitions/forest-fire-prediction/data",
  "pages": [
    {
      "name": "data-description",
      "content": "The data divides for training and testing are named train.csv and test.csv, respectively. There are **200** instances in the training split and **50** examples in the testing split. The complete descriptions for these splits are given below.\n\n## train.csv (200 examples)\nThe training set consists of the following feature columns:\n\n1. Day (Data type - INT)\n2. Month (Data type - INT)\n3. Year (Data type - INT)\n4. Temperature (Data type - INT)\n5. RH (Data type - INT)\n6. Ws (Data type - INT)\n7.  Rain (Data type - FLOAT)\n8. FFMC (Data type - FLOAT)\n9. DMC (Data type - FLOAT)\n10. DC (Data type - FLOAT)\n11. ISI (Data type - FLOAT)\n12. BUI (Data type - FLOAT)\n13. FWI (Data type - FLOAT)\n\n\nThe column - \"**Classes (Data type - string)**\" is the label column. \n\n## test.csv (50 examples)\nThe test split includes all of the training dataset's feature columns. Your task is to forecast the labels (**Classes** column) for each of these cases corresponding to their respective ID and submit the data in the same style as **sample_submission.csv**.\n\n**Important** - Please keep in mind that the numbers in sample_submission.csv are only placeholders; you must build your own submission file for the whole test set.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "# Forest Fire Prediction Challenge\nWith rising global temperatures, forest fires are becoming more common and larger and present an increasing threat to the environment. If we can predict them in advance we will be able to prevent them and thus save lives and the environment.\n## Problem Statement:\nYou will be given various parameters such as relative humidity, temperature, wind speed, etc. and your task will be to develop a program to predict whether or not there will be a forest fire.\n\n## Dataset:\nYou are provided two splits of data - train, and test. Navigate to the Data Section for more details regarding these.\n\n## Duration:\nThe coding challenge will be open to submissions from the 7th to the 19th of February (EOD).\n\n## Submission:\nYou will have to submit the solution in the form of a .csv file, with the predicted values for each test case (using the ID column to denote the case). A sample submission file (sample_submission.csv) has been provided along with the dataset, you may simply fill the predictions column in the same before uploading it as the solution. But you are not done yet!\n\nYou also need to submit the link to your Colab Notebook (https://colab.research.google.com/) containing the code you used for generating the submission file. Kindly set view access to 'Everyone' while generating the shareable link.\n\nThese details must be furnished at: https://forms.gle/E6uHUaU8Q86XWVaR7\nKindly note that submitting the solution description and Colab Notebook on the aforementioned Google Form is mandatory, and the code submitted must be able to replicate your final submission file.\n\n**Important:** In case you are using Kaggle notebooks, then strictly keep your notebook private. Sharing your Kaggle notebook publicly will make you liable for disqualification. Also, even if you are using Kaggle notebooks for writing your code, you need to first import it to Google Colaboratory and then share the link of the same, as mentioned above.\n\nIn case you are new to Kaggle, here is a handy link to Kaggle's [competition documentation](https://www.kaggle.com/docs/competitions), which includes, among other things, instructions on [submitting predictions](https://www.kaggle.com/docs/competitions#making-a-submission).\n\n## Acknowledgements:\nThis challenge was created with the help of Yash Vashistha and Rupal Shah.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "**The evaluation procedure for this challenge is as follows:**\n\n1.  Submit your prediction file in the format as described in the Data section. \n2. Submit your solution approach and Colab notebook [here](https://forms.gle/E8jkusGWFKcvMpAM7) as mentioned in the Description section. \n3. Hang on tight until the results come out.\n\nWe will evaluate participants' performances based on the [Root Mean Squared Error or RMSE](https://en.wikipedia.org/wiki/Root-mean-square_deviation) on the Test Set, as well as the solution description and Colab notebooks submitted.\n\nAn RMSE value of 0 denotes 100% correct predictions.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "The following rules apply to this challenge:\n\n- Plagiarism will not be tolerated.\n- You can make only 20 submissions per day.\n- Keep your submission file in the exact same format as given in sample_submission.csv.\n- The deadline for this contest is 31st January, 2022 - 11:59pm.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}