{
  "fetched_at": "2026-10-20T12:45:52Z",
  "source_url": "https://www.kaggle.com/competitions/fall2020-cmpe257-lab1/data",
  "pages": [
    {
      "name": "data-description",
      "content": "About data:\nThe data will be found in heart.csv. The first row is the name of the observed variables. There are 10 variables:\n\n●\tsbp: Systolic blood pressure\n●\ttobacco: Cumulative tobacco consumption, in kg\n●\tldl: Low-density lipoprotein cholesterol\n●\tadiposity: Adipose tissue concentration\n●\tfamhist: Family history of heart disease (1=Present, 0=Absent)\n●\ttypea: Score on test designed to measure type-A behavior\n●\tobesity: Obesity\n●\talcohol: Current consumption of alcohol\n●\tage: Age of subject\n●\tchd: Coronary heart disease at baseline; 1=Yes 0=No. \nchd=1 means alive and chd=0 means dead.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "SubmissionSample",
      "content": "ID,chd\n1,0\n2,0\n3,0\n4,1\n5,1\n.....",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "AboutData",
      "content": "About data:\nThe data will be found in heart.csv. The first row is the name of the observed variables. There are 10 variables:\n\n●\tsbp: Systolic blood pressure\n●\ttobacco: Cumulative tobacco consumption, in kg\n●\tldl: Low-density lipoprotein cholesterol\n●\tadiposity: Adipose tissue concentration\n●\tfamhist: Family history of heart disease (1=Present, 0=Absent)\n●\ttypea: Score on test designed to measure type-A behavior\n●\tobesity: Obesity\n●\talcohol: Current consumption of alcohol\n●\tage: Age of subject\n●\tchd: Coronary heart disease at baseline; 1=Yes 0=No. \nchd=1 means alive and chd=0 means dead.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "About data:\nThe data will be found in heart.csv. The first row is the name of the observed variables. There are 10 variables:\n\n●\tsbp: Systolic blood pressure\n●\ttobacco: Cumulative tobacco consumption, in kg\n●\tldl: Low-density lipoprotein cholesterol\n●\tadiposity: Adipose tissue concentration\n●\tfamhist: Family history of heart disease (1=Present, 0=Absent)\n●\ttypea: Score on test designed to measure type-A behavior\n●\tobesity: Obesity\n●\talcohol: Current consumption of alcohol\n●\tage: Age of subject\n●\tchd: Coronary heart disease at baseline; 1=Yes 0=No. \nchd=1 means alive and chd=0 means dead.\n\n\nEach following row contains the information of one patient. There are 462 samples in total.\n\n\n1.\tIdentify the dataset columns into nominal, categorical, continues etc. categories\n2.\tUse dataframe.info and dataframe.describe to get the insights about the data.\n3.\tFind the number of null values for each columns\nExceute this:->: data.isnull().sum(axis=0)\n\n\n4.\tKnow about the patients (Example of analysis for ages)\na.\tFind the oldest person\nb.\tFind the youngest person\nc.\tFind the average age group\nd.\tFind median age\ne.\tFind the relationship between the deaths and ages(the class column is your prediction variable)\n \n\t\t \n\n\nf.\tFind the age groups whose survival rate is the largest\n  \ng.\tFind similar relationships for at least 3-4 columns that you think can play a role in prediction (For example, tobacco, alcohol consumption, etc.)\nh.\tGet more visuals on data distributions\ni.\tUse plotCorrelationMatrix\nii.\tplotScatterMatrix\niii.\tplotPerColumnDistribution\nUse information from the plots to get an intuition for selecting feature variables\ni.\tFind missing values\ni.\tGet the count of missing values\nii.\tPlot a heat map for missing values\nj.\tApplying a different technique to handle missing values (For each technique verify your prediction results)\ni.\tUse dropna\nii.\tUse replace na with zero or max value\niii.\tUse replace na with mean\niv.\tSearch for additional techniques to handle null values, excluding the above three and test. (Include all the techniques that you used in your report.)\nk.\tApplying the feature scaling technique if you think it is required. (Optional) \nl.\tApplying the regression models that you think is most suited for this problem.\nm.\tAt least one of the models used to compute should be your own implementation using NumPy.\nn.\tUpload your test data predictions to Kaggle competition in the correct submission format.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}