Detect substring in column

Detects a substring in a column and filters the dataset at CBS: rows that have a code that does not contain (one of) x are filtered out.

Usage

contains(x, column = NULL, allowed = NULL)

has_substring(x, column = NULL, allowed = NULL)

Arguments

x

substring to be detected in column

column

column name

allowed

character with allowed values. If supplied it will check if x is a code in allowed.

See also

Other odata4 query: eq()

Examples

if (interactive()){

  # filter on Perioden (see meta$PeriodenCodes)
  cbs4_get_data("84287NED"
               , Perioden = "2019MM12" # december 2019
               )

  # filter on multiple Perioden (see meta$PeriodenCodes)
  cbs4_get_data("84287NED"
               , Perioden = c("2019MM12", "2020MM01") # december 2019, january 2020
               )

  # to filter on a dimension just add the filter to the query

  # filter on Perioden (see meta$PeriodenCodes)
  cbs4_get_data("84287NED"
               , Perioden = "2019MM12" # december 2019
               , BedrijfstakkenBranchesSBI2008 = "T001081"
               )


  # filter on Perioden with contains
  cbs4_get_data("84287NED"
                , Perioden = contains("2020")
                , BedrijfstakkenBranchesSBI2008 = "T001081"
  )

  # filter on Perioden with multiple contains
  cbs4_get_data("84287NED"
                , Perioden = contains(c("2019MM1", "2020"))
                , BedrijfstakkenBranchesSBI2008 = "T001081"
  )

  # filter on Perioden with contains or = "2019MM12
  cbs4_get_data("84287NED"
                , Perioden = contains("2020") | "2019MM12"
                , BedrijfstakkenBranchesSBI2008 = "T001081"
  )

  # This all works on observations too
  cbs4_get_observations( id        = "80784ned"     # table id
                       , Perioden  = "2019JJ00"     # Year 2019
                       , Geslacht  = "1100"         # code for total gender
                       , RegioS    = contains("PV") # provinces
                       , Measure   = "M003371_2"    # topic selection
                       )

  # supply your own odata 4 query
  cbs4_get_data("84287NED", query = "$filter=Perioden eq '2019MM12'")

  # an odata 4 query will overrule other filter statements
  cbs4_get_data("84287NED"
               , Perioden = "2018MM12"
               , query = "$filter=Perioden eq '2019MM12'"
               )

  # With query argument an odata4 expression with other (filter) functions can be used
  cbs4_get_observations(
    id     = "80784ned"    # table id
    ,query = paste0(       # odata4 query
       "$skip=4",          # skip the first 4 rows of the filtered result
       "&$top=20",         # then slice the first 20 rows of the filtered result
       "&$select=Measure,Geslacht,Perioden,RegioS,Value", # omit the Id and ValueAttribute fields
       "&$filter=endswith(Measure,'_1')") # filter only Measure ending on '_1'
    )

}