def generateRandomData()

in src/main/scala/com/amazon/deequ/analyzers/applicability/Applicability.scala [248:280]

27 lines of code
12 McCabe index (conditional complexity)


  def generateRandomData(schema: StructType, numRows: Int): DataFrame = {

    val rows = (0 to numRows).map { _ =>

      val cells = schema.fields.map { field =>

        val cell: scala.Any = field.dataType match {
          case StringType => randomString(field.nullable)
          case IntegerType => randomInteger(field.nullable)
          case FloatType => randomFloat(field.nullable)
          case DoubleType => randomDouble(field.nullable)
          case ByteType => randomByte(field.nullable)
          case ShortType => randomShort(field.nullable)
          case LongType => randomLong(field.nullable)
          case decimalType: DecimalType =>
            randomDecimal(field.nullable, decimalType.precision, decimalType.scale)
          case TimestampType => randomTimestamp(field.nullable)
          case BooleanType => randomBoolean(field.nullable)
          case _ =>
            throw new IllegalArgumentException(
              "Applicability check can only handle basic datatypes " +
                s"for columns (string, integer, float, double, decimal, boolean) " +
                s"not ${field.dataType}")
        }

        cell
      }

      Row(cells: _*)
    }

    session.createDataFrame(session.sparkContext.parallelize(rows), schema)
  }