X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=R%2FR6_Model.R;h=171966676cd17cb942706176c089963c4197da77;hb=HEAD;hp=05cb7d8dd4bd52cb261a4110b56103799a83c1f8;hpb=17ea2f13e0c32c107db20677750bd7a98bb7e0f8;p=agghoo.git

diff --git a/R/R6_Model.R b/R/R6_Model.R
index 05cb7d8..d48825e 100644
--- 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")
@@ -71,7 +68,7 @@ Model <- R6::R6Class("Model",
     getGmodel = function(family, task) {
       if (family == "tree") {
         function(dataHO, targetHO, param) {
-          require(rpart)
+          base::require(rpart)
           method <- ifelse(task == "classification", "class", "anova")
           if (is.null(colnames(dataHO)))
             colnames(dataHO) <- paste0("V", 1:ncol(dataHO))
@@ -92,15 +89,6 @@ Model <- R6::R6Class("Model",
           }
         }
       }
-      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)
-        }
-      }
       else if (family == "ppr") {
         function(dataHO, targetHO, param) {
           model <- stats::ppr(dataHO, targetHO, nterms=param)
@@ -110,13 +98,13 @@ Model <- R6::R6Class("Model",
       else if (family == "knn") {
         if (task == "classification") {
           function(dataHO, targetHO, param) {
-            require(class)
+            base::require(class)
             function(X) class::knn(dataHO, X, cl=targetHO, k=param)
           }
         }
         else {
           function(dataHO, targetHO, param) {
-            require(FNN)
+            base::require(FNN)
             function(X) FNN::knn.reg(dataHO, X, y=targetHO, k=param)$pred
           }
         }
@@ -126,7 +114,7 @@ Model <- R6::R6Class("Model",
     getParams = function(family, data, target, task) {
       if (family == "tree") {
         # Run rpart once to obtain a CV grid for parameter cp
-        require(rpart)
+        base::require(rpart)
         df <- data.frame(cbind(data, target=target))
         ctrl <- list(
           cp = 0,
@@ -143,13 +131,6 @@ Model <- R6::R6Class("Model",
         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 == "classification"),
-                       len = min(10, p-1))
-      }
       else if (family == "ppr")
         # This is nterms in ppr() function
         1:10