{
  "fetched_at": "2026-10-19T11:38:18Z",
  "source_url": "https://www.kaggle.com/competitions/bt4012-in-class-kaggle-competition-2021-october/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Data Files\n*   **train.csv** - the training set\n*   **test.csv** - the test set\n*   **sample_submission.csv** - a sample submission file in the correct format\n\n## Columns\n\n*   `id` - This field is only available in the **test.csv**. It is a unique identifier of each test image\n*  `rxcy` - This is the pixel intensity value for position (x, y), where r stands for row and c stands for column\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "# BT4012 In-class Kaggle Competition\n\nThis competition is to solve an anomaly detection problem. The data is sampled from [Character Font Images Dataset](https://archive.ics.uci.edu/ml/datasets/Character+Font+Images). In this subset, <characters from a particular font are treated as normal data and characters from some other fonts are randomly sampled as anomalies.>\n \n## What will be the competition like?\n- Due on **8th November 2021 11:59 PM (UTC)**\n- Given a training dataset, make predictions on a test dataset\n- You can make submissions in .csv format up to 3x per day\n- Your top accuracy score will be ranked on a public leaderboard\n- The public leaderboard is based on 30% of your submission\n- At the end of the competition, you will be ranked on a private leaderboard\n- The private leaderboard is based on the other 70% of your submission\n- You may select 2 submissions for the final private leaderboard ranking\n- [Kaggle Tutorials](https://www.dropbox.com/s/dco0ung4aomf8fp/kaggledata_code.zip?dl=0)\n\n## How will you be graded?\n- **20% of final grade**\n- **3 components: report, programming and ranking**\n\n### 1. Kaggle competition private leaderboard ranking (4%)\nYou will be awarded 2% in this component if your submission outperforms the provided simple baseline in the private leaderboard. The other 2% will be awarded based on your relative ranking. \n\n### 2. Programming (6%)\nYou should submit a well documented jupyter notebook as well as a *requirements.txt* by **15th November 2021 23:59** Singapore time.  Your code should be written in python 3. All external dependencies should be clearly specified.\n- **1%** clear instructions on how to run the code\n- **1%** error free code\n- **4%** documentation\n\n### 3. Report (10%)\nYou need to submit a short report by **15th November 2021 23:59** Singapore time. Name your report with your NUS Student Number, i.e. A0123456Z.pdf\n\nYour report must include the following 3 sections:\n\n- Data preprocessing, feature engineering, and how you came out with these approaches.\n- Model building and validation.\n- The models you explored, why they were chosen, and how you arrived at the final model for your top 2 submissions.\n\nThere is a 4 page limit on substantive content comprising the above sections including tables and graphs, and any such content exceeding this limit will be ignored. You should use the normal layout of Microsoft word, Calibri with size 11 and single spacing. For section heads and title,, you should use the same font and size with **bold**. \n\nFinally, submit a Jupyter notebook (.ipynb) for the final model for your top submission, together with your report. Name this file with your NUS Student Number, i.e. **A0123456Z.ipynb**. The file should include your code for data preprocessing, feature engineering, prediction validation, and generating your .csv submission. Please also submit the requirements file with name: **A0123456Z-requirements.txt**\n\nThe submission folder is **LumiNUS &gt; Kaggle**\n\n\n## Important\nUpon signing up for Kaggle and joining the competition, kindly change the Display Name in your Kaggle profile to your NUS student number, e.g. \"A0123456Z\". \n\nDo not sign up using more than one Kaggle account.\n\nThis is a competition between individual participants. You should work on this problem on your own.\n\nPlease read the Overview, Data, and Rules pages carefully.\n\nPlease note with respect to the End Time of this competition (see Timeline) that it is specified in UTC.rom ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submissions are evaluated on [area under the ROC curve](http://en.wikipedia.org/wiki/Receiver_operating_characteristic) between the predicted probability and the observed target.\n\n## Submission Format\nFor every Comment in the dataset, submission files should contain two columns: id and target. target should have a value between 0 and 1.\n\nThe file should contain a header and have the following format:\n```\nId,Predicted\n0,0.9\n1,0.1\n2,0.5\netc.\n```",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "# One account per participant\nYou may not sign up for this Kaggle competition using multiple accounts and therefore may not make submissions from multiple accounts.\n\n# No sharing of code or data\nYou may not privately share code or data with another or other participant(s).\n\n# No plagiarism\nThere is a zero tolerance  policy regarding plagiarism.\n\n# No Auto ML tools\ne.g. You may only use open source non-auto ml tools. For example, you should not try to use auto keras. In addition,  h20, datarobot, Google auto ML or any other Auto ML tools are to be used. Anyway, you need to provide the code that is able to generate the predictions. \n\n# No usage of external data\nYou may not use any data other than the training and test data provided. Your submission must be reproducible only with the code in your Jupyter notebook / python script to be submitted and the training and test data. Any attempt to hack this competition will have the consequence of a score penalty.\n\n# Submission limit\nYou may make a maximum of 3 submissions each day.\nYou may select up to 2 final submissions for assessment.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}