Execute an ordered sequence of left joins.

Please see vignette('DependencySorting', package = 'replyr') and vignette('joinController', package= 'replyr') for more details.

executeLeftJoinPlan(
  tDesc,
  columnJoinPlan,
  ...,
  checkColumns = FALSE,
  computeFn = function(x, name) {     dplyr::compute(x, name = name) },
  eagerCompute = TRUE,
  checkColClasses = FALSE,
  verbose = FALSE,
  dryRun = FALSE,
  tempNameGenerator = mk_tmp_name_source("executeLeftJoinPlan")
)

Arguments

tDesc	description of tables, either a data.frame from tableDescription, or a list mapping from names to handles/frames. Only used to map table names to data.
columnJoinPlan	columns to join, from buildJoinPlan (and likely altered by user). Note: no column names must intersect with names of the form table_CLEANEDTABNAME_present.
...	force later arguments to bind by name.
checkColumns	logical if TRUE confirm column names before starting joins.
computeFn	function to call to try and materialize intermediate results.
eagerCompute	logical if TRUE materialize intermediate results with computeFn.
checkColClasses	logical if true check for exact class name matches
verbose	logical if TRUE print more.
dryRun	logical if TRUE do not perform joins, only print steps.
tempNameGenerator	temp name generator produced by wrapr::mk_tmp_name_source, used to record dplyr::compute() effects.

Value

joined table

See also

tableDescription, buildJoinPlan, inspectDescrAndJoinPlan, makeJoinDiagramSpec

Examples

# example data
meas1 <- data.frame(id= c(1,2),
                    weight= c(200, 120),
                    height= c(60, 14))
meas2 <- data.frame(pid= c(2,3),
                    weight= c(105, 110),
                    width= 1)
# get the initial description of table defs
tDesc <- rbind(tableDescription('meas1', meas1),
               tableDescription('meas2', meas2))
# declare keys (and give them consitent names)
tDesc$keys[[1]] <- list(PatientID= 'id')
tDesc$keys[[2]] <- list(PatientID= 'pid')
# build the column join plan
columnJoinPlan <- buildJoinPlan(tDesc)
# decide we don't want the width column
columnJoinPlan$want[columnJoinPlan$resultColumn=='width'] <- FALSE
# double check our plan
if(!is.null(inspectDescrAndJoinPlan(tDesc, columnJoinPlan,
            checkColClasses= TRUE))) {
  stop("bad join plan")
}
# execute the left joins
executeLeftJoinPlan(tDesc, columnJoinPlan,
                    checkColClasses= TRUE,
                    verbose= TRUE)
#> [1] "start meas1 Sun Sep  6 14:10:03 2020"
#> [1] " rename/restrict meas1"
#> [1] "   'PatientID' = 'id'"
#> [1] "   'meas1_weight' = 'weight'"
#> [1] "   'height' = 'height'"
#> [1] " res <- meas1"
#> [1] "done meas1 Sun Sep  6 14:10:03 2020"
#> [1] "start meas2 Sun Sep  6 14:10:03 2020"
#> [1] " rename/restrict meas2"
#> [1] "   'table_meas2_present' = 'table_meas2_present'"
#> [1] "   'PatientID' = 'pid'"
#> [1] "   'meas2_weight' = 'weight'"
#> [1] " res <- left_join(res, meas2,"
#> [1] "                  by = c( 'PatientID' ))"
#> [1] "done meas2 Sun Sep  6 14:10:03 2020"
#>   PatientID meas1_weight height table_meas2_present meas2_weight
#> 1         1          200     60                   0           NA
#> 2         2          120     14                   1          105
# also good
executeLeftJoinPlan(list('meas1'=meas1, 'meas2'=meas2),
                    columnJoinPlan,
                    checkColClasses= TRUE,
                    verbose= TRUE)
#> [1] "start meas1 Sun Sep  6 14:10:03 2020"
#> [1] " rename/restrict meas1"
#> [1] "   'PatientID' = 'id'"
#> [1] "   'meas1_weight' = 'weight'"
#> [1] "   'height' = 'height'"
#> [1] " res <- meas1"
#> [1] "done meas1 Sun Sep  6 14:10:03 2020"
#> [1] "start meas2 Sun Sep  6 14:10:03 2020"
#> [1] " rename/restrict meas2"
#> [1] "   'table_meas2_present' = 'table_meas2_present'"
#> [1] "   'PatientID' = 'pid'"
#> [1] "   'meas2_weight' = 'weight'"
#> [1] " res <- left_join(res, meas2,"
#> [1] "                  by = c( 'PatientID' ))"
#> [1] "done meas2 Sun Sep  6 14:10:03 2020"
#>   PatientID meas1_weight height table_meas2_present meas2_weight
#> 1         1          200     60                   0           NA
#> 2         2          120     14                   1          105