{
  "fetched_at": "2026-10-20T04:31:23Z",
  "source_url": "https://www.kaggle.com/competitions/c001hw1/data",
  "pages": [
    {
      "name": "data-description",
      "content": "### Dataset attributes & their meaning\n\nThe dataset has 22 attributes, each explained below, including the numerical mapping made to the categorical variables\n\n- **age** (Age of suitor)\n- **gender**('female':0,'male':1 )\n- **height**( Height in inches)\n- **kgs** (Weight in kgs)\n- **bmi** (BMI calculated based on height and weight)\n- **eating** ('Doesn't Matter':0, 'Jain': 1, 'Vegetarian': 2, 'Vegetarian With Eggs': 3, 'Non Vegetarian':4)\n- **family_type** ('Doesn't Matter': 0, 'Others':3, 'Nuclear': 1, 'Joint family both parents': 2, 'Joint family only mother':2, 'Joint family father mother and brothers sisters':2, 'Joint family single parent brothers and or sisters':2, 'Joint family only father': 2)\n- **status** ('Doesn't Matter': 0, 'Middle Class': 1, 'Upper Middle Class': 2, 'High Class': 3, 'Rich / Affluent':4)\n- **marital status** ('Doesn't Matter': 0, 'Never Married': 1, 'Divorced': 2, 'Annulled': 3, 'Widowed': 4, 'Married': 5)\n- **manglik** ('No': 0, 'Yes': 1, 'Do Not Know': 2)\n- **Horoscope** Believe in horoscope matching ('No': 0, 'Yes': 1)\n- **drinking** ('Doesn't Matter':0, 'No': 1, 'Occasionally': 2, 'Yes': 3)\n- **smoking** ('Doesn't Matter': 0, 'No': 1, 'Moderate': 2, 'Yes': 3)\n- **values** ('Orthodox': 1, 'Traditional': 2, 'Moderate': 3, 'Liberal': 4, 'Modern': 5, 'International':6, 'Others': 7)\n- **caste_imp** ('No': 0, 'Yes': 1)\n- **complexion** ('Very Fair ': 1, 'Very Fair': 1, 'Fair ': 2, 'Fair': 2, 'Whetish Medium ': 4, 'Whetish Medium': 4, 'Wheatish': 3, 'Wheatish ':3, 'Dark ':5, 'Dark':5)\n- **body** ('Slim': 1, 'Average': 2, 'Heavy': 3, 'Athletic': 4)\n- **education** ('High School':0, 'Some college':1,'Undergrad':2, 'Grad':3, 'Doctorate':4) \n- **employed** ('Not Working':0, 'Public Sector': 1, 'State Government': 2, 'Central Government': 3, 'Private Sector':4, 'MNC':5, 'Others':6, \"Doesn't Matter\": 7)\n- **living** Living with parents ('No': 0, 'Yes': 1)\n-** city**('International': 1, 'Mumbai': 2, 'Delhi':3, 'Kolkata':4,'Bengaluru':5, 'Chennai':6, 'Hyderabad':7, 'Pune':8, 'Ahmedabad':9,'Surat':10, 'Vishakapatnam':11, 'Others':12)\n- **income** (Annual income in dollars)\n\nThe response variable is '**income**', the other 21 attributes can be used as both categorical or continuous for model fitting.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Problem Statement",
      "content": "![](https://github.com/hargun3045/blog-dump/blob/master/modi.png?raw=true)\n## Homework 1 \n\n>This Kaggle contest is a part of homework 1 of Univ.Ai course AI-1 run by Professor Pavlos Protopapas.\n\nOwing to a large number of people underreporting their income to evade taxes, the Income Tax Department of India wants you to build a machine learning model that can predict the income of a given tax-payer based on commonly available information.\n\nThe goal of the contest is to build the best model to predict the income based on the attributes provided in the dataset.\n\nThe measuring metric is R2 score. The winning model will be the one with the highest R2 score and the winning team will win a prize.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}