DD: S3 class with the data dictionary (variable specifications)

In david-salgado/StQ: Tools to manage metadata-incorporated key-value pair datasets

Description

Definition of an S3 class named DD with the specification of each variable.

The class DD comprises a list whose first component is an object of class VarNameCorresp and name VNC and the rest of components are objects of class data.table of names ID, MicroData, ParaData, Aggregates, AggWeights, Other.

Usage

DD(
  VNC = BuildVNC(),
  ID = data.table(Variable = character(0), Sort = character(0), Class = character(0),
    Length = character(0), Qual1 = character(0), ValueRegExp = character(0)),
  MicroData = data.table(Variable = character(0), Sort = character(0), Class =
    character(0), Length = character(0), Qual1 = character(0), ValueRegExp =
    character(0)),
  ParaData = data.table(Variable = character(0), Sort = character(0), Class =
    character(0), Length = character(0), Qual1 = character(0), ValueRegExp =
    character(0)),
  Aggregates = data.table(Variable = character(0), Sort = character(0), Class =
    character(0), Length = character(0), Qual1 = character(0), ValueRegExp =
    character(0)),
  AggWeights = data.table(Variable = character(0), Sort = character(0), Class =
    character(0), Length = character(0), Qual1 = character(0), ValueRegExp =
    character(0)),
  Other = data.table(Variable = character(0), Sort = character(0), Class =
    character(0), Length = character(0), Qual1 = character(0), ValueRegExp =
    character(0))
)

Arguments

VNC	Object of class VNC.
ID	Object of class data.table.
MicroData	Object of class data.table.
ParaData	Object of class data.table.
Aggregates	Object of class data.table.
AggWeights	Object of class data.table.
Other	Object of class data.table.

Examples

library(data.table)
### We build the VNC object
VarList <- list(ID = data.table(IDQual = c('NumIdEst', rep('', 4)),
                                NonIDQual = c('','','','',''),
                                IDDD = c('', 'Name', 'Surname', 'PostalAddr', 'PhoneNo'),
                                NumIdEst = c('', rep('.', 4)),
                                UnitName = c('numidest', 'nombre', 'apellidos', 'direccion', 'telefono'),
                                InFiles = rep('FI', 5)),
MicroData = data.table(IDQual = c('NumIdEst', rep('', 2)),
                       NonIDQual = c('', 'Market', ''),
                       IDDD = c(rep('', 2), 'NewOrders'),
                       NumIdEst = c(rep('', 2), '.'),
                       Market = c(rep('', 2), '1'),
                       UnitName = c('numidest', '', 'cp09'),
                       InFiles = rep('FF, FD, FG', 3)),
ParaData = data.table(IDQual = c('NumIdEst', rep('', 2)),
                      NonIDQual = c('', 'Action', ''),
                      IDDD = c(rep('', 2), 'Date'),
                      NumIdEst = c(rep('', 2), '.'),
                      Action = c(rep('', 2), 'Imputation'),
                      UnitName = c('numidest', '', 'FechaImput'),
                      InFiles = rep('FP', 3)))

VNC <- BuildVNC(VarList)

IDdt <- data.table(Variable = c('NumIdEst', 'Name', 'Surname', 'PostalAddr', 'PhoneNo'),
                   Sort = c('IDQual', rep('IDDD', 4)),
                   Class = rep('character', 5),
                   Length = c('11', '15', '15', '20','9'),
                   Qual1 = c('', rep('NumIdEst', 4)),
                   ValueRegExp = c('[0-9]{9}PP', '.+', '.+', '.+', '(6|9)[0-9]{8}'))
Microdt <- data.table(Variable = c('NumIdEst', 'Market', 'NewOrders'),
                      Sort = c('IDQual', 'NonIDQual', 'IDDD'),
                      Class = c(rep('character', 2), 'numeric'),
                      Length = c('11', '2', '7'),
                      Qual1 = c(rep('', 2), 'NumIdEst'),
                      ValueRegExp = c('[0-9]{9}PP', '.+', '([0-9]{1, 10}| )'))
Paradt <- data.table(Variable = c('NumIdEst', 'Action', 'Date'),
                     Sort = c('IDQual', 'NonIDQual', 'IDDD'),
                     Class = rep('character', 3),
                     Length = c('11', '10', '10'),
                     Qual1 = c(rep('', 2), 'NumIdEst'),
                     Qual2 = c(rep('', 2), 'Action'),
                     ValueRegExp = c('[0-9]{9}PP', 'Collection|Editing|Imputation',
                                     '(([0-9]{2}-(0[1-9]|1(0-2))-[0-9]{4})| )'))

DD <- DD(VNC = VNC, ID = IDdt, MicroData = Microdt, ParaData = Paradt)
DD

david-salgado/StQ documentation built on Aug. 12, 2021, 3:23 p.m.