candidate-API-1.R

#predicate, group, select and aggregate are user defined functions
#it is assumed a vectorized version is used when needed

#pass through
mapreduce(input,
          map = function(k,v) keyval(k,v))
#vec version
#vectorized.map says how many records to process in one map, default 1
mapreduce(input,
          map = function(k,v) keyval(k,v, vectorized = TRUE), 
          vectorized = list(map = TRUE))

#filter
mapreduce(input,
          map = function(k,v) if(predicate(k,v)) keyval(k,v))
#vec version
mapreduce(input, 
          map = function(k,v) {filter = predicate(k,v); 
                               keyval(k[filter], v[filter], vectorized = TRUE)},
          vectorized = list(map = TRUE))
#vec version, structured case
#structured says to convert list to data frame. Fails if not possible. If TRUE,
#it means both map and reduce, or it is a named vector or list(map = TRUE, reduce = FALSE)
#default both FALSE
mapreduce(input, 
          map = function(k,v) {filter = predicate(k,v); 
                               keyval(k[filter,], v[filter,], vectorized = TRUE)},
          vectorized = list(map = TRUE),
          structured = list(map = TRUE))

#select
mapreduce(input,
          map = function(k,v) keyval(k, select(v)))
#vec version
mapreduce(input,
          map = function(k,v) keyval(k, select(v), vectorized = TRUE),
          vectorized = list(map = TRUE))
#vec version, structured case
mapreduce(input,
          map = function(k,v) keyval(k, v[,fields], vectorized = TRUE),
          vectorized = list(map = TRUE),
          structured = list(map = TRUE))


#bigsum
mapreduce(input, 
          map  = function(k,v) keyval(group(k,v),v), 
          reduce = function(k, vv) keyval(k, sum(unlist(vv))))
#vec version
mapreduce(input, 
          map  = function(k,v) keyval(group(k,v),v, vectorized = TRUE), 
          reduce = function(k, vv) keyval(k, sum(unlist(vv))), 
          vectorized = list(map = TRUE))
#vec version, structured case
mapreduce(input, 
          map  = function(k,v) keyval(group(k,v),v, vectorized = TRUE), 
          reduce = function(k, vv) keyval(k, sum(vv)) , 
          vectorized = list(map = TRUE),
          structured = list(map = TRUE))
#or structured = c(T,T) or list(map = TRUE, reduce = TRUE)

#embarrassingly parallel
mapreduce(input, 
          map = function(k,v) keyval(group(k,v), v),
          reduce = function(k, vv) keyval(k, aggregate(vv)))
#vec version
mapreduce(input, 
          map = function(k,v) keyval(group(k,v), v, vectorized = TRUE),
          reduce = function(k, vv) keyval(k, aggregate(vv)),
          vectorized = list(map = TRUE))
#vec version, structured case
mapreduce(input, 
          map = function(k,v) keyval(group(k,v), v),
          reduce = function(k, vv) keyval(k, some.function(vv))
          vectorized.map = TRUE,
          structured = list(map = TRUE))