Merge pull request #5 from dmlc/master

Update to latest version

CHANGES.md

@@ -41,6 +41,9 @@ on going at master
   - Fixed possible problem of poisson regression for R.
 * Python module now throw exception instead of crash terminal when a parameter error happens.
 * Python module now has importance plot and tree plot functions.
+* Python module now accepts different learning rates for each boosting round.
+* Python now allows model training continuation from previously saved model.
+* Additional parameters added for sklearn wrapper
 * Java api is ready for use
 * Added more test cases and continuous integration to make each build more robust
 * Improvements in sklearn compatible module

CONTRIBUTORS.md

@@ -13,6 +13,8 @@ Committers are people who have made substantial contribution to the project and
   - Bing is the original creator of xgboost python package and currently the maintainer of [XGBoost.jl](https://github.com/antinucleon/XGBoost.jl).
 * [Michael Benesty](https://github.com/pommedeterresautee)
   - Micheal is a lawyer, data scientist in France, he is the creator of xgboost interactive analysis module in R.
+* [Yuan Tang](https://github.com/terrytangyuan)
+  - Yuan is a data scientist in Chicago, US. He contributed mostly in R and Python packages. 
 
 Become a Comitter
 -----------------
@@ -34,7 +36,6 @@ List of Contributors
 * [Zygmunt Zając](https://github.com/zygmuntz)
   - Zygmunt is the master behind the early stopping feature frequently used by kagglers.
 * [Ajinkya Kale](https://github.com/ajkl)
-* [Yuan Tang](https://github.com/terrytangyuan)
 * [Boliang Chen](https://github.com/cblsjtu)
 * [Vadim Khotilovich](https://github.com/khotilov)
 * [Yangqing Men](https://github.com/yanqingmen)
@@ -49,5 +50,9 @@ List of Contributors
   - Masaaki is the initial creator of xgboost python plotting module.
 * [Hongliang Liu](https://github.com/phunterlau)
   - Hongliang is the maintainer of xgboost python PyPI package for pip installation.
+* [daiyl0320](https://github.com/daiyl0320)
+  - daiyl0320 contributed patch to xgboost distributed version more robust, and scales stably on TB scale datasets.
 * [Huayi Zhang](https://github.com/irachex)
 * [Johan Manders](https://github.com/johanmanders)
+* [yoori](https://github.com/yoori)
+* [Mathias Müller](https://github.com/far0n)

Makefile

@@ -189,7 +189,6 @@ pythonpack:
 	cp -r multi-node xgboost-deploy/xgboost
 	cp -r windows xgboost-deploy/xgboost
 	cp -r src xgboost-deploy/xgboost
-
 	#make python
 
 pythonbuild:

R-package/R/getinfo.xgb.DMatrix.R

@@ -35,15 +35,15 @@ getinfo <- function(object, ...){
 #' @param ... other parameters
 #' @rdname getinfo
 #' @method getinfo xgb.DMatrix
-setMethod("getinfo", signature = "xgb.DMatrix", 
+setMethod("getinfo", signature = "xgb.DMatrix",
           definition = function(object, name) {
               if (typeof(name) != "character") {
                   stop("xgb.getinfo: name must be character")
               }
               if (class(object) != "xgb.DMatrix") {
                   stop("xgb.setinfo: first argument dtrain must be xgb.DMatrix")
               }
-              if (name != "label" && name != "weight" && 
+              if (name != "label" && name != "weight" &&
                       name != "base_margin" && name != "nrow") {
                   stop(paste("xgb.getinfo: unknown info name", name))
               }
@@ -54,4 +54,3 @@ setMethod("getinfo", signature = "xgb.DMatrix",
               }
               return(ret)
           })
-

R-package/R/predict.xgb.Booster.R

@@ -30,8 +30,8 @@ setClass("xgb.Booster",
 #' pred <- predict(bst, test$data)
 #' @export
 #' 
-setMethod("predict", signature = "xgb.Booster", 
-          definition = function(object, newdata, missing = NA, 
+setMethod("predict", signature = "xgb.Booster",
+          definition = function(object, newdata, missing = NA,
                                 outputmargin = FALSE, ntreelimit = NULL, predleaf = FALSE) {
   if (class(object) != "xgb.Booster"){
     stop("predict: model in prediction must be of class xgb.Booster")
@@ -48,14 +48,14 @@ setMethod("predict", signature = "xgb.Booster",
       stop("predict: ntreelimit must be equal to or greater than 1")
     }
   }
-  option = 0
+  option <- 0
   if (outputmargin) {
     option <- option + 1
   }
   if (predleaf) {
     option <- option + 2
   }
-  ret <- .Call("XGBoosterPredict_R", object$handle, newdata, as.integer(option), 
+  ret <- .Call("XGBoosterPredict_R", object$handle, newdata, as.integer(option),
                as.integer(ntreelimit), PACKAGE = "xgboost")
   if (predleaf){
       len <- getinfo(newdata, "nrow")
@@ -68,4 +68,3 @@ setMethod("predict", signature = "xgb.Booster",
   }
   return(ret)
 })
-

R-package/R/predict.xgb.Booster.handle.R

@@ -5,15 +5,14 @@
 #' @param object Object of class "xgb.Boost.handle"
 #' @param ... Parameters pass to \code{predict.xgb.Booster}
 #' 
-setMethod("predict", signature = "xgb.Booster.handle", 
+setMethod("predict", signature = "xgb.Booster.handle",
           definition = function(object, ...) {
   if (class(object) != "xgb.Booster.handle"){
     stop("predict: model in prediction must be of class xgb.Booster.handle")
   }
-  
+
   bst <- xgb.handleToBooster(object)
-  
-  ret = predict(bst, ...)
+
+  ret <- predict(bst, ...)
   return(ret)
 })
-

R-package/R/setinfo.xgb.DMatrix.R

@@ -32,7 +32,7 @@ setinfo <- function(object, ...){
 #' @param ... other parameters
 #' @rdname setinfo
 #' @method setinfo xgb.DMatrix
-setMethod("setinfo", signature = "xgb.DMatrix", 
+setMethod("setinfo", signature = "xgb.DMatrix",
           definition = function(object, name, info) {
             xgb.setinfo(object, name, info)
           })

R-package/R/slice.xgb.DMatrix.R

@@ -23,19 +23,19 @@ slice <- function(object, ...){
 #' @param ... other parameters
 #' @rdname slice
 #' @method slice xgb.DMatrix
-setMethod("slice", signature = "xgb.DMatrix", 
+setMethod("slice", signature = "xgb.DMatrix",
           definition = function(object, idxset, ...) {
               if (class(object) != "xgb.DMatrix") {
                   stop("slice: first argument dtrain must be xgb.DMatrix")
               }
-              ret <- .Call("XGDMatrixSliceDMatrix_R", object, idxset, 
+              ret <- .Call("XGDMatrixSliceDMatrix_R", object, idxset,
                            PACKAGE = "xgboost")
-              
+
               attr_list <- attributes(object)
               nr <- xgb.numrow(object)
               len <- sapply(attr_list,length)
-              ind <- which(len==nr)
-              if (length(ind)>0) {
+              ind <- which(len == nr)
+              if (length(ind) > 0) {
                   nms <- names(attr_list)[ind]
                   for (i in 1:length(ind)) {
                     attr(ret,nms[i]) <- attr(object,nms[i])[idxset]

R-package/R/utils.R

@@ -1,4 +1,4 @@
-#' @importClassesFrom Matrix dgCMatrix dgeMatrix
+  #' @importClassesFrom Matrix dgCMatrix dgeMatrix
 #' @import methods
 
 # depends on matrix
@@ -15,30 +15,30 @@ xgb.setinfo <- function(dmat, name, info) {
     stop("xgb.setinfo: first argument dtrain must be xgb.DMatrix")
   }
   if (name == "label") {
-    if (length(info)!=xgb.numrow(dmat))
+    if (length(info) != xgb.numrow(dmat))
       stop("The length of labels must equal to the number of rows in the input data")
-    .Call("XGDMatrixSetInfo_R", dmat, name, as.numeric(info), 
+    .Call("XGDMatrixSetInfo_R", dmat, name, as.numeric(info),
           PACKAGE = "xgboost")
     return(TRUE)
   }
   if (name == "weight") {
-    if (length(info)!=xgb.numrow(dmat))
+    if (length(info) != xgb.numrow(dmat))
       stop("The length of weights must equal to the number of rows in the input data")
-    .Call("XGDMatrixSetInfo_R", dmat, name, as.numeric(info), 
+    .Call("XGDMatrixSetInfo_R", dmat, name, as.numeric(info),
           PACKAGE = "xgboost")
     return(TRUE)
   }
   if (name == "base_margin") {
     # if (length(info)!=xgb.numrow(dmat))
     #   stop("The length of base margin must equal to the number of rows in the input data")
-    .Call("XGDMatrixSetInfo_R", dmat, name, as.numeric(info), 
+    .Call("XGDMatrixSetInfo_R", dmat, name, as.numeric(info),
           PACKAGE = "xgboost")
     return(TRUE)
   }
   if (name == "group") {
-    if (sum(info)!=xgb.numrow(dmat))
+    if (sum(info) != xgb.numrow(dmat))
       stop("The sum of groups must equal to the number of rows in the input data")
-    .Call("XGDMatrixSetInfo_R", dmat, name, as.integer(info), 
+    .Call("XGDMatrixSetInfo_R", dmat, name, as.integer(info),
           PACKAGE = "xgboost")
     return(TRUE)
   }
@@ -68,7 +68,7 @@ xgb.Booster <- function(params = list(), cachelist = list(), modelfile = NULL) {
     if (typeof(modelfile) == "character") {
       .Call("XGBoosterLoadModel_R", handle, modelfile, PACKAGE = "xgboost")
     } else if (typeof(modelfile) == "raw") {
-      .Call("XGBoosterLoadModelFromRaw_R", handle, modelfile, PACKAGE = "xgboost")      
+      .Call("XGBoosterLoadModelFromRaw_R", handle, modelfile, PACKAGE = "xgboost")
     } else {
       stop("xgb.Booster: modelfile must be character or raw vector")
     }
@@ -122,7 +122,7 @@ xgb.get.DMatrix <- function(data, label = NULL, missing = NA, weight = NULL) {
     } else if (inClass == "xgb.DMatrix") {
       dtrain <- data
     } else if (inClass == "data.frame") {
-      stop("xgboost only support numerical matrix input, 
+      stop("xgboost only support numerical matrix input,
            use 'data.frame' to transform the data.")
     } else {
       stop("xgboost: Invalid input of data")
@@ -142,8 +142,7 @@ xgb.iter.boost <- function(booster, dtrain, gpair) {
   if (class(dtrain) != "xgb.DMatrix") {
     stop("xgb.iter.update: second argument must be type xgb.DMatrix")
   }
-  .Call("XGBoosterBoostOneIter_R", booster, dtrain, gpair$grad, gpair$hess, 
-        PACKAGE = "xgboost")
+  .Call("XGBoosterBoostOneIter_R", booster, dtrain, gpair$grad, gpair$hess, PACKAGE = "xgboost")
   return(TRUE)
 }
 
@@ -157,9 +156,9 @@ xgb.iter.update <- function(booster, dtrain, iter, obj = NULL) {
   }
 
   if (is.null(obj)) {
-    .Call("XGBoosterUpdateOneIter_R", booster, as.integer(iter), dtrain, 
+    .Call("XGBoosterUpdateOneIter_R", booster, as.integer(iter), dtrain,
           PACKAGE = "xgboost")
-  } else {
+    } else {
     pred <- predict(booster, dtrain)
     gpair <- obj(pred, dtrain)
     succ <- xgb.iter.boost(booster, dtrain, gpair)
@@ -190,7 +189,7 @@ xgb.iter.eval <- function(booster, watchlist, iter, feval = NULL, prediction = F
         }
         evnames <- append(evnames, names(w))
       }
-      msg <- .Call("XGBoosterEvalOneIter_R", booster, as.integer(iter), watchlist, 
+      msg <- .Call("XGBoosterEvalOneIter_R", booster, as.integer(iter), watchlist,
                    evnames, PACKAGE = "xgboost")
     } else {
       msg <- paste("[", iter, "]", sep="")
@@ -248,29 +247,29 @@ xgb.cv.mknfold <- function(dall, nfold, param, stratified, folds) {
         if (length(unique(y)) <= 5) y <- factor(y)
       }
       folds <- xgb.createFolds(y, nfold)
-    } else { 
+    } else {
       # make simple non-stratified folds
       kstep <- length(randidx) %/% nfold
       folds <- list()
-      for (i in 1:(nfold-1)) {
-        folds[[i]] = randidx[1:kstep]
-        randidx = setdiff(randidx, folds[[i]])
+      for (i in 1:(nfold - 1)) {
+        folds[[i]] <- randidx[1:kstep]
+        randidx <- setdiff(randidx, folds[[i]])
       }
-      folds[[nfold]] = randidx
+      folds[[nfold]] <- randidx
     }
   }
   ret <- list()
   for (k in 1:nfold) {
     dtest <- slice(dall, folds[[k]])
-    didx = c()
+    didx <- c()
     for (i in 1:nfold) {
       if (i != k) {
         didx <- append(didx, folds[[i]])
       }
     }
     dtrain <- slice(dall, didx)
     bst <- xgb.Booster(param, list(dtrain, dtest))
-    watchlist = list(train=dtrain, test=dtest)
+    watchlist <- list(train=dtrain, test=dtest)
     ret[[k]] <- list(dtrain=dtrain, booster=bst, watchlist=watchlist, index=folds[[k]])
   }
   return (ret)
@@ -283,7 +282,7 @@ xgb.cv.aggcv <- function(res, showsd = TRUE) {
     kv <- strsplit(header[i], ":")[[1]]
     ret <- paste(ret, "\t", kv[1], ":", sep="")
     stats <- c()
-    stats[1] <- as.numeric(kv[2])    
+    stats[1] <- as.numeric(kv[2])
     for (j in 2:length(res)) {
       tkv <- strsplit(res[[j]][i], ":")[[1]]
       stats[j] <- as.numeric(tkv[2])
@@ -311,9 +310,9 @@ xgb.createFolds <- function(y, k = 10)
     ## At most, we will use quantiles. If the sample
     ## is too small, we just do regular unstratified
     ## CV
-    cuts <- floor(length(y)/k)
-    if(cuts < 2) cuts <- 2
-    if(cuts > 5) cuts <- 5
+    cuts <- floor(length(y) / k)
+    if (cuts < 2) cuts <- 2
+    if (cuts > 5) cuts <- 5
     y <- cut(y,
              unique(stats::quantile(y, probs = seq(0, 1, length = cuts))),
              include.lowest = TRUE)
@@ -325,7 +324,7 @@ xgb.createFolds <- function(y, k = 10)
     y <- factor(as.character(y))
     numInClass <- table(y)
     foldVector <- vector(mode = "integer", length(y))
-    
+
     ## For each class, balance the fold allocation as far
     ## as possible, then resample the remainder.
     ## The final assignment of folds is also randomized.

R-package/R/xgb.DMatrix.R

@@ -20,26 +20,26 @@
 #' 
 xgb.DMatrix <- function(data, info = list(), missing = NA, ...) {
   if (typeof(data) == "character") {
-    handle <- .Call("XGDMatrixCreateFromFile_R", data, as.integer(FALSE), 
+    handle <- .Call("XGDMatrixCreateFromFile_R", data, as.integer(FALSE),
                     PACKAGE = "xgboost")
   } else if (is.matrix(data)) {
-    handle <- .Call("XGDMatrixCreateFromMat_R", data, missing, 
+    handle <- .Call("XGDMatrixCreateFromMat_R", data, missing,
                     PACKAGE = "xgboost")
   } else if (class(data) == "dgCMatrix") {
-    handle <- .Call("XGDMatrixCreateFromCSC_R", data@p, data@i, data@x, 
+    handle <- .Call("XGDMatrixCreateFromCSC_R", data@p, data@i, data@x,
                     PACKAGE = "xgboost")
   } else {
-    stop(paste("xgb.DMatrix: does not support to construct from ", 
+    stop(paste("xgb.DMatrix: does not support to construct from ",
                typeof(data)))
   }
   dmat <- structure(handle, class = "xgb.DMatrix")
-  
+
   info <- append(info, list(...))
-  if (length(info) == 0) 
+  if (length(info) == 0)
     return(dmat)
   for (i in 1:length(info)) {
     p <- info[i]
     xgb.setinfo(dmat, names(p), p[[1]])
   }
   return(dmat)
-} 
+}

R-package/R/xgb.DMatrix.save.R

@@ -18,10 +18,10 @@ xgb.DMatrix.save <- function(DMatrix, fname) {
     stop("xgb.save: fname must be character")
   }
   if (class(DMatrix) == "xgb.DMatrix") {
-    .Call("XGDMatrixSaveBinary_R", DMatrix, fname, as.integer(FALSE), 
+    .Call("XGDMatrixSaveBinary_R", DMatrix, fname, as.integer(FALSE),
           PACKAGE = "xgboost")
     return(TRUE)
   }
   stop("xgb.DMatrix.save: the input must be xgb.DMatrix")
   return(FALSE)
-} 
+}