fixing corner cases of reduced memory prediction for hpdRF_paralleltree

vertica · Oct 14, 2015 · a673f7a · a673f7a
1 parent b4d5c33
commit a673f7a
Show file tree

Hide file tree

Showing 3 changed files with 12 additions and 14 deletions.
diff --git a/algorithms/HPdclassifier/R/hpdRF_parallelTree.R b/algorithms/HPdclassifier/R/hpdRF_parallelTree.R
@@ -365,18 +365,13 @@ hpdrandomForest <- hpdRF_parallelTree <- function(formula, data,
 	oob_predictions = NULL
 	if(completeModel)
 	{
-		tryCatch({
 		if(do.trace)
 			.master_output("\tComputing oob statistics")
 			timing_info <- Sys.time()
 		oob_predictions = .predictOOB(forest, observations, 
 			responses, oob_indices, cutoff, classes, 
-			reduceModel = reduceModel,do.trace)
+			ntree = ntree, reduceModel = reduceModel, do.trace)
 			forest = oob_predictions$dforest
-			},error = function(e)
-			{
-				stop(paste("aborting oob computations. received error:", e))
-			})
 		if(do.trace)
 		.master_output("\tcurrent distributed forest size: ",
 			format(round(d.object.size(forest)/1024/1024,2),nsmall = 2), 

diff --git a/algorithms/HPdclassifier/R/hpdRFdistributed.R b/algorithms/HPdclassifier/R/hpdRFdistributed.R
@@ -555,7 +555,7 @@
 
 
 .predictOOB <- function(forest, observations, responses, oob_indices, 
-	    cutoff, classes, reduceModel = FALSE, trace = FALSE)
+	    cutoff, classes, ntree, reduceModel = FALSE, trace = FALSE)
 {
 
 	timing_info <- Sys.time()
@@ -571,8 +571,12 @@
 
 
 	dforest = forest
+	if(ntree < npartitions(forest))
+	dforest = .redistributeForest(forest,as.list(1:ntree))
+	rm(forest)
 	suppressWarnings({
-	votes = darray(npartitions =c(npartitions(dforest),npartitions(observations)))
+	votes = darray(npartitions =c(npartitions(dforest),
+	      	npartitions(observations)))
 	})
 	foreach(i,0:(npartitions(votes)-1), 
 		function(predictions=splits(votes,i+1),
@@ -585,6 +589,7 @@
 	{
 		tree_ids = which(!sapply(forest,is.null))
 		tree_ids = tree_ids[-1]
+
 		forest = .Call("unserializeForest",forest, 
 		       	    PACKAGE = "HPdclassifier")  
 		forestparam = .Call("getForestParameters", forest,  
@@ -612,16 +617,18 @@
 		predictions = matrix(as.double(NA), 
 			      	ncol = nrow(observations),
 				length(tree_ids))
-				
+
 		tree_ids = tree_ids - 1
 		oob_indices = lapply(oob_indices, as.integer)
+
 		.Call("forestPredictOOB", forest, predictions, observations,
 					  oob_indices, as.integer(tree_ids))
 
 		.Call("garbageCollectForest",forest)
 		update(predictions)
 	},progress = FALSE)
 
+
 	timing_info <- Sys.time() - timing_info
 	if(trace)
 	.master_output(format(round(timing_info, 2),nsmall = 2))

diff --git a/algorithms/HPdclassifier/src/hpdRFpredict.cpp b/algorithms/HPdclassifier/src/hpdRFpredict.cpp
@@ -499,11 +499,7 @@ extern "C"
     for(int tree_index = 0; tree_index < length(R_tree_ids); tree_index++)
       {
 	int tree_id = INTEGER(R_tree_ids)[tree_index]-1;
-	SEXP indices;
-	if(length(R_indices) > 1)
-	  indices = VECTOR_ELT(R_indices,tree_id);
-	else
-	  indices = R_indices;
+	SEXP indices = VECTOR_ELT(R_indices,tree_id);
 	for(int i = 0; i < length(indices); i++)
 	  {
 	    int obs_index = INTEGER(indices)[i]-1;