refineTable: Expands data.table

In palryalen/ahw: Re-weighting point processes based on additive hazard models

Description

Refines dataFr so that each individual at risk get a row for each of the provided event times

Usage

refineTable(dataFr, atRiskState, eventTimes)

Arguments

dataFr	data.frame or data.table on long format
atRiskState	At risk state(s)
eventTimes	Observed event times

Value

data.table

Author(s)

Pål Christie Ryalen <[e-mail]>

Examples

##---- Should be DIRECTLY executable !! ----
##-- ==>  Define data, use random,
##--	or do  help(data=index)  for the standard data sets.

## The function is currently defined as
function (dataFr, atRiskState, eventTimes) 
{
    sortedEventTimes <- sort(eventTimes)
    baseTable <- as.data.table(dataFr)
    baseTable$rowNumber <- 1:nrow(baseTable)
    baseTable[, `:=`(isAtRisk, 1 * (from.state %in% atRiskState))]
    baseTable[, `:=`(numRep, 0)]
    baseTable[isAtRisk == 1, `:=`(numRep, as.numeric(sum(from <= 
        eventTimes & to > eventTimes))), by = rowNumber]
    baseTable[, `:=`(numRep, numRep + 1)]
    baseTable[, `:=`(to.state, as.character(to.state))]
    Table <- baseTable[rep(1:nrow(baseTable), times = baseTable[, 
        numRep]), ]
    Table[, `:=`(putEventTimes, 0)]
    Table[numRep > 1, `:=`(putEventTimes, c(sortedEventTimes[sortedEventTimes >= 
        from[1] & sortedEventTimes < to[1]], to[1])), by = id]
    Table[numRep == 1, `:=`(putEventTimes, to)]
    Table[, `:=`(to, putEventTimes)]
    Table[, `:=`(from, c(from[1], to[-length(to)])), by = id]
    Table[, `:=`(to.state, c(rep(0, length(to) - 1), baseTable$to.state[rowNumber[1]])), 
        by = rowNumber]
    return(Table)
  }

palryalen/ahw documentation built on Sept. 29, 2021, 6:20 p.m.