{
  "fetched_at": "2026-10-19T20:45:24Z",
  "source_url": "https://www.kaggle.com/competitions/diabetes-prediction-competitiontfug-chd-nov-2022/data",
  "pages": [
    {
      "name": "data-description",
      "content": "### Welcome to the TFUG X Kaggle Campaign hosted by TFUG Chandigarh.\n\nThere are 17 feature variables and 1 target variable - \"Diabetes\". This is a binary classification problem where 0 means no diabetes and 1 means diabetes. The task is to predict the probability of the person having diabetes provided the given data.\n\nFor this competition we have added some synthetic dataset to the acknowledged dataset and a part of the same synthetic dataset is used for public and private dataset. The public leaderboard is defined basis on 25% of the test data and private leaderboard on the remaining 75% of the test data.\n\n## Files\n\n*   **train_data.csv** - the training set\n*   **test_data.csv** - the test set\n*   **sample_submission.csv** - a sample submission file in the correct format\n\n## Columns\n\nThis dataset is composed of various parameters namely,\n*  `age`: 3-level age category (_AGEG5YR see codebook) 1 = 18-24, 9 = 60-64, 13 = 80 or older\n*  `sex`: 0 = female, 1 = male\n*  `HighChol`: 0 = no high cholesterol, 1 = high cholesterol\n*  `CholCheck`: 0 = no cholesterol check in 5 years, 1 = yes cholesterol check in 5 years\n*  `BMI`: Body Mass Index\n*  `Smoker`: Have you smoked at least 100 cigarettes in your entire life? [Note: 5 packs = 100 cigarettes] 0 = no, 1 = yes\n*  `HeartDiseaseorAttack`: Coronary heart disease (CHD) or myocardial infarction (MI) 0 = no, 1 = yes\n*  `PhysActivity`: Physical activity in past 30 days - not including job 0 = no, 1 = yes\n*  `Fruits`: Consume Fruit one or more times per day 0 = no, 1 = yes\n*  `Veggies`: Consume Vegetables 1 or more times per day 0 = no, 1 = yes\n*  `HvyAlcoholConsump`: Adult male: more than 14 drinks per week. Adult female: more than 7 drinks per week. 0 = no, 1 = yes\n*  `GenHlth`: Would you say that in general your health is: (scale 1-5) 1 = excellent, 2 = very good, 3 = good, 4 = fair, 5 = poor\n* `MentHlth`: Days of poor mental health scale 1-30 days\n* `PhysHlth`: Physical illness or injury days in past 30 days scale 1-30\n* `DiffWalk`: Do you have serious difficulty walking or climbing stairs? 0 = no, 1 = yes\n* `Hypertension`: 0 = no hypertension, 1 = hypertension\n* `Stroke`: 0 = no, 1 = yes\n* `Diabetes`: 0 = no diabetes, 1 = diabetes (Target variable)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "**What is  TFUG X Kaggle Campaign?**\nAn associated Kaggle Community Competitions hosted by ML GDEs or TFUGs, sponsored by Google Developers.\n\n**Source**\nThis dataset has been synthetically cured from the original data source using CTGAN, as acknowledged in brief.\n\n**Abstract**\nTo look into the dataset and classify whether a person is likely or unlikely to have Diabetes.\n\n**About this dataset**\nThere are 17 feature variables and 1 target variable - \"Diabetes\". This is a binary classification problem where 0 means no diabetes and 1 means diabetes. The task is to predict the probability of the person having diabetes provided the given data.\n\n**Causes and Challenges**\nIn this dataset, we cover 17 variables that may or may not contribute to Diabetes. Per doctors, the most common form of diabetes are:\n\nBeing overweight, obesity, and physical inactivity\n\nInsulin resistance\n\nGenes and family history\n\nInsulin resistance\n\nGenes and family history\n\nGenetic mutations\n\nHormonal diseases\n\n\n**The Role of Machine Learning**\nThe role of ML here is to use the above parameters to classify whether a person is likely to have Diabetes or not.\n\n**Acknowledgement**\nCitations\nThis dataset has been originally driven from data produced by CDC's BRFSS 2015\n\nThe underlying cleaned data comes from the CDC's BRFSS 2015 on the following link: https://www.kaggle.com/datasets/alexteboul/diabetes-health-indicators-dataset\n\n**License**\nPublic Domain\n\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is [Logloss](https://en.wikipedia.org/wiki/Cross_entropy).\n\n![](https://wikimedia.org/api/rest_v1/media/math/render/svg/1f3f3acfb5549feb520216532a40082193c05ccc)\n\n![Logloss](https://wikimedia.org/api/rest_v1/media/math/render/svg/80f87a71d3a616a0939f5360cec24d702d2593a2)\n\n## Submission Format\n\n**For every submission**, submission files should contain two columns: `id` and `Diabetes`. `id` should be as per the sample_submission.csv file. `Diabetes` should have values between 0 and 1.\n\nThe file should contain a header and have the following format:\n```\nid,Diabetes\n0,1.0\n```",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a community competition hosted by TFUG Chandigarh. The rules are pretty simple and straight forward:\n\n## General\n1. This is a file submission competition where the submission csv file is used for results.\n2. For training, the competition data is to be used and any other data is prohibited until and unless the data has been shared and made public in the discussion forum. The dataset can be shared via a link or a Kaggle dataset.\n\n## Anti-Cheating\n1. Any person found cheating will be disqualified from the competition.\n2. Cheating includes but not limited to:\n    1. Using data without making it public in the discussion forum.\n    2. Having more than 3 team members during the span of the competition.\n\n## Winners\nTeams bagging the first and second position in the private leaderboards will be considered the winners.\n\n## Prize\nThe prize for the winners is 100$ Google Cloud Platform credits to each team member.\n ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Prizes",
      "content": "**Google Cloud Platform Credits**\n\nThe top 2 teams will be awarded $100 worth of Google Cloud Platform (GCP) credits for each team member.\n\nYou can use these credits to utilize the diverse solutions and systems provided by google cloud platform.\n\nhttps://cloud.google.com/",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}