tods/axolotl/tests/data/datasets/boston_dataset_1/datasetDoc.json

{
  "about": {
    "datasetID": "boston_dataset_1",
    "datasetName": "Boston Dataset",
    "description": "The Boston house-price data of Harrison, D. and Rubinfeld, D.L. 'Hedonic prices and the demand for clean air', J. Environ. Economics & Management, vol.5, 81-102, 1978.  Used in Belsley, Kuh & Welsch, 'Regression diagnostics ...', Wiley, 1980.  N.B. Various transformations are used in the table on pages 244-261 of the latter.",
    "datasetVersion": "4.0.0",
    "datasetSchemaVersion": "4.0.0",
    "sourceURI": "http://lib.stat.cmu.edu/datasets/boston",
    "license": "unknown",
    "digest": "7797ade70da006a47c32db5dd24be51a6956dbf8d600c4720e53576d32e451e6"
  },
  "dataResources": [
    {
      "resID": "learningData",
      "resPath": "tables/learningData.csv",
      "resType": "table",
      "resFormat": {
        "text/csv": [
          "csv"
        ]
      },
      "isCollection": false,
      "columnsCount": 15,
      "columns": [
        {
          "colIndex": 0,
          "colName": "d3mIndex",
          "colType": "integer",
          "role": [
            "index"
          ]
        },
        {
          "colIndex": 1,
          "colName": "CRIM",
          "colDescription": "per capita crime rate by town",
          "colType": "real",
          "role": [
            "attribute"
          ]
        },
        {
          "colIndex": 2,
          "colName": "ZN",
          "colDescription": "proportion of residential land zoned for lots over 25,000 sq.ft.",
          "colType": "real",
          "role": [
            "attribute"
          ]
        },
        {
          "colIndex": 3,
          "colName": "INDUS",
          "colDescription": "proportion of non-retail business acres per town",
          "colType": "real",
          "role": [
            "attribute"
          ]
        },
        {
          "colIndex": 4,
          "colName": "CHAS",
          "colDescription": "Charles River dummy variable (= 1 if tract bounds river; 0 otherwise)",
          "colType": "boolean",
          "role": [
            "attribute"
          ]
        },
        {
          "colIndex": 5,
          "colName": "NOX",
          "colDescription": "nitric oxides concentration (parts per 10 million)",
          "colType": "real",
          "role": [
            "attribute",
            "suggestedTarget"
          ]
        },
        {
          "colIndex": 6,
          "colName": "RM",
          "colDescription": "average number of rooms per dwelling",
          "colType": "real",
          "role": [
            "attribute"
          ]
        },
        {
          "colIndex": 7,
          "colName": "AGE",
          "colDescription": "proportion of owner-occupied units built prior to 1940",
          "colType": "real",
          "role": [
            "attribute"
          ]
        },
        {
          "colIndex": 8,
          "colName": "DIS",
          "colDescription": "weighted distances to five Boston employment centres",
          "colType": "real",
          "role": [
            "attribute"
          ]
        },
        {
          "colIndex": 9,
          "colName": "RAD",
          "colDescription": "index of accessibility to radial highways",
          "colType": "categorical",
          "role": [
            "attribute"
          ]
        },
        {
          "colIndex": 10,
          "colName": "TAX",
          "colDescription": "full-value property-tax rate per $10,000",
          "colType": "integer",
          "role": [
            "attribute"
          ]
        },
        {
          "colIndex": 11,
          "colName": "PTRATIO",
          "colDescription": "pupil-teacher ratio by town",
          "colType": "real",
          "role": [
            "attribute"
          ]
        },
        {
          "colIndex": 12,
          "colName": "B",
          "colDescription": "1000(Bk - 0.63)^2 where Bk is the proportion of blacks by town",
          "colType": "real",
          "role": [
            "attribute"
          ]
        },
        {
          "colIndex": 13,
          "colName": "LSTAT",
          "colDescription": "% lower status of the population",
          "colType": "real",
          "role": [
            "attribute"
          ]
        },
        {
          "colIndex": 14,
          "colName": "MEDV",
          "colDescription": "Median value of owner-occupied homes in $1000's\n",
          "colType": "real",
          "role": [
            "attribute",
            "suggestedTarget"
          ]
        }
      ]
    }
  ]
}