Merge pull request #1 from YuanTingHsieh/add_alternate_vertical_splits

Add alternate vertical splits

.github/workflows/i386.yml

@@ -0,0 +1,39 @@
+name: XGBoost-i386-test
+
+on: [push, pull_request]
+
+permissions:
+  contents: read # to fetch code (actions/checkout)
+
+jobs:
+  build-32bit:
+    name: Build 32-bit
+    runs-on: ubuntu-latest
+    services:
+      registry:
+        image: registry:2
+        ports:
+          - 5000:5000
+    steps:
+    - uses: actions/checkout@v2.5.0
+      with:
+        submodules: 'true'
+    - name: Set up Docker Buildx
+      uses: docker/setup-buildx-action@v3
+      with:
+        driver-opts: network=host
+    - name: Build and push container
+      uses: docker/build-push-action@v5
+      with:
+        context: .
+        file: tests/ci_build/Dockerfile.i386
+        push: true
+        tags: localhost:5000/xgboost/build-32bit:latest
+        cache-from: type=gha
+        cache-to: type=gha,mode=max
+    - name: Build XGBoost
+      run: |
+        docker run --rm -v $PWD:/workspace -w /workspace \
+          -e CXXFLAGS='-Wno-error=overloaded-virtual -Wno-error=maybe-uninitialized -Wno-error=redundant-move' \
+          localhost:5000/xgboost/build-32bit:latest \
+          tests/ci_build/build_via_cmake.sh

CMakeLists.txt

@@ -39,9 +39,6 @@ elseif(CMAKE_CXX_COMPILER_ID STREQUAL "Clang")
     message(FATAL_ERROR "Need Clang 9.0 or newer to build XGBoost")
   endif()
 endif()
-if(CMAKE_SIZE_OF_VOID_P EQUAL 4)
-  message(FATAL_ERROR "XGBoost does not support 32-bit archs. Please use 64-bit arch instead.")
-endif()
 
 include(${xgboost_SOURCE_DIR}/cmake/PrefetchIntrinsics.cmake)
 find_prefetch_intrinsics()

R-package/NAMESPACE

@@ -15,7 +15,6 @@ S3method(print,xgb.DMatrix)
 S3method(print,xgb.cv.synchronous)
 S3method(setinfo,xgb.Booster)
 S3method(setinfo,xgb.DMatrix)
-S3method(slice,xgb.DMatrix)
 S3method(variable.names,xgb.Booster)
 export("xgb.attr<-")
 export("xgb.attributes<-")
@@ -30,13 +29,12 @@ export(cb.reset.parameters)
 export(cb.save.model)
 export(getinfo)
 export(setinfo)
-export(slice)
 export(xgb.DMatrix)
 export(xgb.DMatrix.hasinfo)
 export(xgb.DMatrix.save)
+export(xgb.DataBatch)
 export(xgb.DataIter)
 export(xgb.ExternalDMatrix)
-export(xgb.ProxyDMatrix)
 export(xgb.QuantileDMatrix)
 export(xgb.QuantileDMatrix.from_iterator)
 export(xgb.attr)
@@ -70,6 +68,7 @@ export(xgb.save)
 export(xgb.save.raw)
 export(xgb.set.config)
 export(xgb.slice.Booster)
+export(xgb.slice.DMatrix)
 export(xgb.train)
 export(xgboost)
 import(methods)

R-package/R/xgb.Booster.R

@@ -111,6 +111,21 @@ xgb.get.handle <- function(object) {
 #'        If passing "all", will use all of the rounds regardless of whether the model had early stopping or not.
 #' @param strict_shape Default is `FALSE`. When set to `TRUE`, the output
 #'        type and shape of predictions are invariant to the model type.
+#' @param validate_features When `TRUE`, validate that the Booster's and newdata's feature_names
+#'        match (only applicable when both `object` and `newdata` have feature names).
+#'
+#'        If the column names differ and `newdata` is not an `xgb.DMatrix`, will try to reorder
+#'        the columns in `newdata` to match with the booster's.
+#'
+#'        If the booster has feature types and `newdata` is either an `xgb.DMatrix` or `data.frame`,
+#'        will additionally verify that categorical columns are of the correct type in `newdata`,
+#'        throwing an error if they do not match.
+#'
+#'        If passing `FALSE`, it is assumed that the feature names and types are the same,
+#'        and come in the same order as in the training data.
+#'
+#'        Note that this check might add some sizable latency to the predictions, so it's
+#'        recommended to disable it for performance-sensitive applications.
 #' @param ... Not used.
 #'
 #' @details
@@ -271,7 +286,11 @@ xgb.get.handle <- function(object) {
 #' @export
 predict.xgb.Booster <- function(object, newdata, missing = NA, outputmargin = FALSE,
                                 predleaf = FALSE, predcontrib = FALSE, approxcontrib = FALSE, predinteraction = FALSE,
-                                reshape = FALSE, training = FALSE, iterationrange = NULL, strict_shape = FALSE, ...) {
+                                reshape = FALSE, training = FALSE, iterationrange = NULL, strict_shape = FALSE,
+                                validate_features = FALSE, ...) {
+  if (validate_features) {
+    newdata <- validate.features(object, newdata)
+  }
   if (!inherits(newdata, "xgb.DMatrix")) {
     nthread <- xgb.nthread(object)
     newdata <- xgb.DMatrix(
@@ -418,6 +437,85 @@ predict.xgb.Booster <- function(object, newdata, missing = NA, outputmargin = FA
   return(arr)
 }
 
+validate.features <- function(bst, newdata) {
+  if (is.character(newdata)) {
+    # this will be encountered when passing file paths
+    return(newdata)
+  }
+  if (inherits(newdata, "sparseVector")) {
+    # in this case, newdata won't have metadata
+    return(newdata)
+  }
+  if (is.vector(newdata)) {
+    newdata <- as.matrix(newdata)
+  }
+
+  booster_names <- getinfo(bst, "feature_name")
+  checked_names <- FALSE
+  if (NROW(booster_names)) {
+
+    try_reorder <- FALSE
+    if (inherits(newdata, "xgb.DMatrix")) {
+      curr_names <- getinfo(newdata, "feature_name")
+    } else {
+      curr_names <- colnames(newdata)
+      try_reorder <- TRUE
+    }
+
+    if (NROW(curr_names)) {
+      checked_names <- TRUE
+
+      if (length(curr_names) != length(booster_names) || any(curr_names != booster_names)) {
+
+        if (!try_reorder) {
+          stop("Feature names in 'newdata' do not match with booster's.")
+        } else {
+          if (inherits(newdata, "data.table")) {
+            newdata <- newdata[, booster_names, with = FALSE]
+          } else {
+            newdata <- newdata[, booster_names, drop = FALSE]
+          }
+        }
+
+      }
+
+    } # if (NROW(curr_names)) {
+
+  } # if (NROW(booster_names)) {
+
+  if (inherits(newdata, c("data.frame", "xgb.DMatrix"))) {
+
+    booster_types <- getinfo(bst, "feature_type")
+    if (!NROW(booster_types)) {
+      # Note: types in the booster are optional. Other interfaces
+      # might not even save it as booster attributes for example,
+      # even if the model uses categorical features.
+      return(newdata)
+    }
+    if (inherits(newdata, "xgb.DMatrix")) {
+      curr_types <- getinfo(newdata, "feature_type")
+      if (length(curr_types) != length(booster_types) || any(curr_types != booster_types)) {
+        stop("Feature types in 'newdata' do not match with booster's.")
+      }
+    }
+    if (inherits(newdata, "data.frame")) {
+      is_factor <- sapply(newdata, is.factor)
+      if (any(is_factor != (booster_types == "c"))) {
+        stop(
+          paste0(
+            "Feature types in 'newdata' do not match with booster's for same columns (by ",
+            ifelse(checked_names, "name", "position"),
+            ")."
+          )
+        )
+      }
+    }
+
+  }
+
+  return(newdata)
+}
+
 
 #' @title Accessors for serializable attributes of a model
 #'