Add CV-voting, remove random forests

[agghoo.git] / R / R6_Model.R

diff --git a/R/R6_Model.R b/R/R6_Model.R
index 8fc2324..1719666 100644 (file)
--- a/R/R6_Model.R
+++ b/R/R6_Model.R
@@ -4,14 +4,12 @@
 #' "Model" class, containing a (generic) learning function, which from
 #' data + target [+ params] returns a prediction function X --> y.
 #' Parameters for cross-validation are either provided or estimated.
-#' Model family can be chosen among "rf", "tree", "ppr" and "knn" for now.
+#' Model family can be chosen among "tree", "ppr" and "knn" for now.
 #'
 #' @importFrom FNN knn.reg
 #' @importFrom class knn
 #' @importFrom stats ppr
-#' @importFrom randomForest randomForest
 #' @importFrom rpart rpart
-#' @importFrom caret var_seq
 #'
 #' @export
 Model <- R6::R6Class("Model",
@@ -30,9 +28,8 @@ Model <- R6::R6Class("Model",
         # (Generic) model not provided
         all_numeric <- is.numeric(as.matrix(data))
         if (!all_numeric)
-          # At least one non-numeric column: use random forests or trees
-          # TODO: 4 = arbitrary magic number...
-          gmodel = ifelse(ncol(data) >= 4, "rf", "tree")
+          # At least one non-numeric column: use trees
+          gmodel = "tree"
         else
           # Numerical data
           gmodel = ifelse(task == "regression", "ppr", "knn")
@@ -40,7 +37,7 @@ Model <- R6::R6Class("Model",
       if (is.null(params))
         # Here, gmodel is a string (= its family),
         # because a custom model must be given with its parameters.
-        params <- as.list(private$getParams(gmodel, data, target))
+        params <- as.list(private$getParams(gmodel, data, target, task))
       private$params <- params
       if (is.character(gmodel))
         gmodel <- private$getGmodel(gmodel, task)
@@ -73,18 +70,23 @@ Model <- R6::R6Class("Model",
         function(dataHO, targetHO, param) {
           require(rpart)
           method <- ifelse(task == "classification", "class", "anova")
+          if (is.null(colnames(dataHO)))
+            colnames(dataHO) <- paste0("V", 1:ncol(dataHO))
           df <- data.frame(cbind(dataHO, target=targetHO))
           model <- rpart::rpart(target ~ ., df, method=method, control=list(cp=param))
-          function(X) predict(model, X)
-        }
-      }
-      else if (family == "rf") {
-        function(dataHO, targetHO, param) {
-          require(randomForest)
-          if (task == "classification" && !is.factor(targetHO))
-            targetHO <- as.factor(targetHO)
-          model <- randomForest::randomForest(dataHO, targetHO, mtry=param)
-          function(X) predict(model, X)
+          if (task == "regression")
+            type <- "vector"
+          else {
+            if (is.null(dim(targetHO)))
+              type <- "class"
+            else
+              type <- "prob"
+          }
+          function(X) {
+            if (is.null(colnames(X)))
+              colnames(X) <- paste0("V", 1:ncol(X))
+            predict(model, as.data.frame(X), type=type)
+          }
         }
       }
       else if (family == "ppr") {
@@ -109,34 +111,26 @@ Model <- R6::R6Class("Model",
       }
     },
     # Return a default list of parameters, given a gmodel family
-    getParams = function(family, data, target) {
+    getParams = function(family, data, target, task) {
       if (family == "tree") {
         # Run rpart once to obtain a CV grid for parameter cp
         require(rpart)
         df <- data.frame(cbind(data, target=target))
         ctrl <- list(
+          cp = 0,
           minsplit = 2,
           minbucket = 1,
-          maxcompete = 0,
-          maxsurrogate = 0,
-          usesurrogate = 0,
-          xval = 0,
-          surrogatestyle = 0,
-          maxdepth = 30)
-        r <- rpart(target ~ ., df, method="class", control=ctrl)
+          xval = 0)
+        method <- ifelse(task == "classification", "class", "anova")
+        r <- rpart(target ~ ., df, method=method, control=ctrl)
         cps <- r$cptable[-1,1]
+        if (length(cps) <= 1)
+          stop("No cross-validation possible: select another model")
         if (length(cps) <= 11)
           return (cps)
         step <- (length(cps) - 1) / 10
         cps[unique(round(seq(1, length(cps), step)))]
       }
-      else if (family == "rf") {
-        p <- ncol(data)
-        # Use caret package to obtain the CV grid of mtry values
-        require(caret)
-        caret::var_seq(p, classification = (task == "classificaton"),
-                       len = min(10, p-1))
-      }
       else if (family == "ppr")
         # This is nterms in ppr() function
         1:10