schema draft 2

schema_draft.json

{
   "type":"object",
   "properties":{
      "dataset":{
         "type":"object",
         "properties":{
            "description":{
               "type":"string"
            },
            "unitOfAnalysis":{
               "type":"string"
            },
            "structure":{
               "type":"string",
               "enum":[
                  "wide",
                  "long",
                  "unknown"
               ]
            },
            "rowCount":{
               "type":"integer",
               "description":"Number of rows or observations in the dataset"
            },
            "variableCount":{
               "type":"integer",
               "description":"Number of variables or features or columns in the dataset"
            },
            "dataSource":{
               "description":"Object containing descriptions of original source of dataset",
               "type":[
                  "object",
                  "null"
               ],
               "oneOf":[
                  {
                     "properties":{
                        "name":{
                           "description":"Name such as a file name or database table name",
                           "type":"string"
                        },
                        "type":{
                           "description":"Type of data source",
                           "type":"string",
                           "enum":[
                              "File",
                              "SQL database"
                           ]
                        },
                        "format":{
                           "description":"Pertains to the type.  For example, a file that is \"text/csv\" or a SQL database that is \"Postgres version 9.1\"",
                           "type":"string"
                        },
                        "filesize":{
                           "description":"Filesize in bytes. (optional)",
                           "type":"integer"
                        }
                     },
                     "required":[
                        "name",
                        "type"
                     ]
                  },
                  {
                     "type":"null"
                  }
               ]
            },
            "citation":{
               "description":"Object containing a schema.org Dataset description",
               "type":"object",
               "properties":{
                  "name":{
                     "description":"Name of the dataset",
                     "type":"string"
                  }
               }
            }
         },
         "required":[
            "description",
            "unitOfAnalysis",
            "structure",
            "rowCount",
            "variableCount"
         ]
      },
      "variables":{
         "type":"object",
         "patternProperties":{
            "^[_a-zA-Z0-9]+$":{
               "type":"object",
               "properties":{
                  "variableName":{
                     "type":"string"
                  },
                  "description":{
                     "type":"string",
                     "description":"Brief explanation of the variable "
                  },
                  "numchar":{
                     "type":"string",
                     "description":"Describes the variable as numeric or character valued",
                     "enum":[
                        "character",
                        "numeric"
                     ]
                  },
                  "nature":{
                     "type":"string",
                     "description":"Describes the classification of data into Nominal, Ordinal, Ratio, Interval, Percentage.",
                     "enum":[
                        "interval",
                        "nominal",
                        "ordinal",
                        "percent",
                        "ratio",
                        "other"
                     ]
                  },
                  "binary":{
                     "type":"boolean",
                     "description":"Signifies that the data can only take two values"
                  },
                  "interval":{
                     "type":"string",
                     "description":"Describes numeric variables as either continuously valued, or discrete valued",
                     "enum":[
                        "continuous",
                        "discrete"
                     ]
                  },
                  "time":{
                     "description":"Signifies that the variable describes points in time",
                     "oneOf":[
                        {
                           "type":"boolean"
                        },
                        {
                           "type":"string",
                           "enum":[
                              "unknown"
                           ]
                        }
                     ]
                  },
                  "invalidCount":{
                     "type":"integer",
                     "description":"Counts the number of invalid observations, including missing values, nulls, NA's and any observation with a value enumerated in invalidSpecialCodes"
                  },
                  "invalidSpecialCodes":{
                     "type":"array",
                     "items":{
                        "type":"number"
                     },
                     "description":"Any numbers that represent invalid observations"
                  },
                  "validCount":{
                     "type":"integer",
                     "description":"Counts the number of valid observations"
                  },
                  "uniqueCount":{
                     "type":"integer",
                     "description":"Count of unique values, including invalid signifiers"
                  },
                  "median":{
                     "type":[
                        "number",
                        "string"
                     ],
                     "description":"A central value in the distribution such that there are as many values equal or above, as there are equal or below this value.",
                     "oneOf":[
                        {
                           "type":"number"
                        },
                        {
                           "type":"string",
                           "enum":[
                              "NA"
                           ]
                        }
                     ]
                  },
                  "mean":{
                     "type":[
                        "number",
                        "string"
                     ],
                     "description":"Average of all numeric values, which are not contained in invalidSpecialCodes",
                     "oneOf":[
                        {
                           "type":"number"
                        },
                        {
                           "type":"string",
                           "enum":[
                              "NA"
                           ]
                        }
                     ]
                  },
                  "max":{
                     "type":[
                        "number",
                        "string"
                     ],
                     "description":"Largest numeric value observed in dataset, that is not contained in invalidSpecialCodes",
                     "oneOf":[
                        {
                           "type":"number"
                        },
                        {
                           "type":"string",
                           "enum":[
                              "NA"
                           ]
                        }
                     ]
                  },
                  "min":{
                     "type":[
                        "number",
                        "string"
                     ],
                     "description":"Least numeric value observed in dataset, that is not contained in invalidSpecialCodes",
                     "oneOf":[
                        {
                           "type":"number"
                        },
                        {
                           "type":"string",
                           "enum":[
                              "NA"
                           ]
                        }
                     ]
                  },
                  "mode":{
                     "type":[
                        "array",
                        "string"
                     ],
                     "description":"Value that occurs most frequently.  Multiple values in the case of ties.",
                     "oneOf":[
                        {
                           "type":"array",
                           "items":{
                              "type":"number"
                           }
                        },
                        {
                           "type":"array",
                           "items":{
                              "type":"string"
                           }
                        },
                        {
                           "type":"string",
                           "enum":[
                              "NA"
                           ]
                        }
                     ]
                  },
                  "modeFreq":{
                     "type":[
                        "integer",
                        "string"
                     ],
                     "description":"Number of times value of mode is observed in variable",
                     "oneOf":[
                        {
                           "type":"integer"
                        },
                        {
                           "type":"string",
                           "enum":[
                              "NA"
                           ]
                        }
                     ]
                  },
                  "fewestValues":{
                     "type":[
                        "array",
                        "string"
                     ],
                     "description":"Value that occurs least frequently.  Multiple values in the case of ties.",
                     "oneOf":[
                        {
                           "type":"array",
                           "items":{
                              "type":"number"
                           }
                        },
                        {
                           "type":"array",
                           "items":{
                              "type":"string"
                           }
                        },
                        {
                           "type":"string",
                           "enum":[
                              "NA"
                           ]
                        }
                     ]
                  },
                  "fewestFreq":{
                     "type":[
                        "integer",
                        "string"
                     ],
                     "description":"Number of times value of fewestValues is observed in variable",
                     "oneOf":[
                        {
                           "type":"integer"
                        },
                        {
                           "type":"string",
                           "enum":[
                              "NA"
                           ]
                        }
                     ]
                  },
                  "midpoint":{
                     "type":[
                        "number",
                        "string"
                     ],
                     "description":"The value equidistant from the reported min and max values",
                     "oneOf":[
                        {
                           "type":"number"
                        },
                        {
                           "type":"string",
                           "xenum":[
                              "NA"
                           ]
                        }
                     ]
                  },
                  "midpointFreq":{
                     "type":[
                        "integer",
                        "string"
                     ],
                     "description":"Number of observations with value equal to minpoint",
                     "oneOf":[
                        {
                           "type":"integer"
                        },
                        {
                           "type":"string",
                           "enum":[
                              "NA"
                           ]
                        }
                     ]
                  },
                  "stdDev":{
                     "type":[
                        "number",
                        "string"
                     ],
                     "description":"Standard deviation of the values, measuring the spread between values, specifically using population formula",
                     "oneOf":[
                        {
                           "type":"number"
                        },
                        {
                           "type":"string",
                           "enum":[
                              "NA"
                           ]
                        }
                     ]
                  },
                  "herfindahlIndex":{
                     "type":[
                        "number",
                        "string"
                     ],
                     "description":"Measure of heterogeneity of a categorical variable which gives the probability that any two randomly sampled observations have the same value",
                     "oneOf":[
                        {
                           "type":"number"
                        },
                        {
                           "type":"string",
                           "enum":[
                              "NA"
                           ]
                        }
                     ]
                  },
                  "plotValues":{
                     "type":[
                        "object",
                        "string"
                     ],
                     "description":"Plot points of a bar chart for tracing distribution of variable",
                     "oneOf":[
                        {
                           "type":"object"
                        },
                        {
                           "type":"string",
                           "enum":[
                              "NA"
                           ]
                        }
                     ]
                  },
                  "pdfPlotType":{
                     "type":[
                        "string",
                        "null"
                     ],
                     "description":"Describes default type of plot appropriate to represent distribution of variable",
                     "oneOf":[
                        {
                           "type":"string",
                           "enum":[
                              "bar",
                              "continuous",
                              "NA"
                           ]
                        },
                        {
                           "type":"null"
                        }
                     ]
                  },
                  "pdfPlotX":{
                     "type":[
                        "array",
                        "null"
                     ],
                     "description":"Plot points along x dimension for tracing distribution of variable",
                     "oneOf":[
                        {
                           "type":"array",
                           "items":{
                              "type":"number"
                           }
                        },
                        {
                           "type":"null"
                        }
                     ]
                  },
                  "pdfPlotY":{
                     "type":[
                        "array",
                        "null"
                     ],
                     "description":"Plot points along y dimension for tracing distribution of variable",
                     "oneOf":[
                        {
                           "type":"array",
                           "items":{
                              "type":"number"
                           }
                        },
                        {
                           "type":"null"
                        }
                     ]
                  },
                  "cdfPlotType":{
                     "type":[
                        "string",
                        "null"
                     ],
                     "description":"Describes default type of plot appropriate to represent cumulative distribution of variable",
                     "oneOf":[
                        {
                           "type":"string",
                           "enum":[
                              "bar",
                              "continuous",
                              "NA"
                           ]
                        },
                        {
                           "type":"null"
                        }
                     ]
                  },
                  "cdfPlotX":{
                     "type":[
                        "array",
                        "null"
                     ],
                     "description":"Plot points along x dimension for tracing cumulative distribution of variable",
                     "oneOf":[
                        {
                           "type":"array",
                           "items":{
                              "type":"number"
                           }
                        },
                        {
                           "type":"null"
                        }
                     ]
                  },
                  "cdfPlotY":{
                     "type":[
                        "array",
                        "null"
                     ],
                     "description":"Plot points along y dimension for tracing cumulative distribution of variable",
                     "oneOf":[
                        {
                           "type":"array",
                           "items":{
                              "type":"number"
                           }
                        },
                        {
                           "type":"null"
                        }
                     ]
                  },
                  "interpretation":{
                     "type":[
                        "object",
                        "string"
                     ],
                     "description":"Object containing descriptors to interpret variable",
                     "oneOf":[
                        {
                           "type":"object"
                        },
                        {
                           "type":"string",
                           "enum":[
                              "NA"
                           ]
                        }
                     ]
                  },
                  "tworavens":{
                     "type":[
                        "object",
                        "string"
                     ],
                     "description":"Object containing metadata specifically used by TwoRavens platform",
                     "oneOf":[
                        {
                           "type":"object"
                        },
                        {
                           "type":"string",
                           "enum":[
                              "NA"
                           ]
                        }
                     ]
                  }
               },
               "required":[
                  "variableName",
                  "description",
                  "numchar",
                  "nature",
                  "binary",
                  "interval",
                  "time",
                  "invalidCount",
                  "validCount",
                  "uniqueCount",
                  "median",
                  "mean",
                  "max",
                  "min",
                  "mode",
                  "modeFreq",
                  "fewestValues",
                  "fewestFreq",
                  "midpoint",
                  "midpointFreq",
                  "stdDev",
                  "herfindahlIndex",
                  "plotValues",
                  "pdfPlotType",
                  "pdfPlotX",
                  "pdfPlotY",
                  "cdfPlotType",
                  "cdfPlotX",
                  "cdfPlotY"
               ]
            }
         },
         "additionalProperties":false,
         "minProperties":1
      }
   },
   "required":[
      "dataset",
      "variables"
   ]
}