diff --git a/R-package/R/getinfo.xgb.DMatrix.R b/R-package/R/getinfo.xgb.DMatrix.R
index 3a79fd2fb..2a7ae8e5e 100644
--- a/R-package/R/getinfo.xgb.DMatrix.R
+++ b/R-package/R/getinfo.xgb.DMatrix.R
@@ -6,7 +6,7 @@ setClass('xgb.DMatrix')
 #' 
 #' @examples
 #' data(iris)
-#' iris[,5] <- as.numeric(iris[,5])
+#' iris[,5] <- as.numeric(iris[,5]=='setosa')
 #' dtrain <- xgb.DMatrix(as.matrix(iris[,1:4]), label=iris[,5])
 #' labels <- getinfo(dtrain, "label")
 #' @rdname getinfo
diff --git a/R-package/R/predict.xgb.Booster.R b/R-package/R/predict.xgb.Booster.R
index 390ac689e..a41b26873 100644
--- a/R-package/R/predict.xgb.Booster.R
+++ b/R-package/R/predict.xgb.Booster.R
@@ -11,11 +11,12 @@ setClass("xgb.Booster")
 #'   value of sum of functions, when outputmargin=TRUE, the prediction is 
 #'   untransformed margin value. In logistic regression, outputmargin=T will
 #'   output value before logistic transformation.
-#' @param ntreelimit limit number of trees used in prediction, this parameter is only valid for gbtree, but not for gblinear.
-#'   set it to be value bigger than 0. It will use all trees by default.
+#' @param ntreelimit limit number of trees used in prediction, this parameter is
+#'  only valid for gbtree, but not for gblinear. set it to be value bigger 
+#'  than 0. It will use all trees by default.
 #' @examples
 #' data(iris)
-#' bst <- xgboost(as.matrix(iris[,1:4]),as.numeric(iris[,5]), nrounds = 2)
+#' bst <- xgboost(as.matrix(iris[,1:4]),as.numeric(iris[,5]=='setosa'), nrounds = 2)
 #' pred <- predict(bst, as.matrix(iris[,1:4]))
 #' @export
 #' 
diff --git a/R-package/R/slice.xgb.DMatrix.R b/R-package/R/slice.xgb.DMatrix.R
index 8a93efc4d..72f94893a 100644
--- a/R-package/R/slice.xgb.DMatrix.R
+++ b/R-package/R/slice.xgb.DMatrix.R
@@ -8,7 +8,7 @@ setClass('xgb.DMatrix')
 #' 
 #' @examples
 #' data(iris)
-#' iris[,5] <- as.numeric(iris[,5])
+#' iris[,5] <- as.numeric(iris[,5]=='setosa')
 #' dtrain <- xgb.DMatrix(as.matrix(iris[,1:4]), label=iris[,5])
 #' dsub <- slice(dtrain, 1:3)
 #' @rdname slice
diff --git a/R-package/R/xgb.DMatrix.R b/R-package/R/xgb.DMatrix.R
index d52847ef2..3b320d73f 100644
--- a/R-package/R/xgb.DMatrix.R
+++ b/R-package/R/xgb.DMatrix.R
@@ -12,7 +12,7 @@
 #' 
 #' @examples
 #' data(iris)
-#' iris[,5] <- as.numeric(iris[,5])
+#' iris[,5] <- as.numeric(iris[,5]=='setosa')
 #' dtrain <- xgb.DMatrix(as.matrix(iris[,1:4]), label=iris[,5])
 #' xgb.DMatrix.save(dtrain, 'iris.xgb.DMatrix')
 #' dtrain <- xgb.DMatrix('iris.xgb.DMatrix')
diff --git a/R-package/R/xgb.DMatrix.save.R b/R-package/R/xgb.DMatrix.save.R
index 4fcb71301..4f4f49399 100644
--- a/R-package/R/xgb.DMatrix.save.R
+++ b/R-package/R/xgb.DMatrix.save.R
@@ -7,7 +7,7 @@
 #' 
 #' @examples
 #' data(iris)
-#' iris[,5] <- as.numeric(iris[,5])
+#' iris[,5] <- as.numeric(iris[,5]=='setosa')
 #' dtrain <- xgb.DMatrix(as.matrix(iris[,1:4]), label=iris[,5])
 #' xgb.DMatrix.save(dtrain, 'iris.xgb.DMatrix')
 #' dtrain <- xgb.DMatrix('iris.xgb.DMatrix')
diff --git a/R-package/R/xgb.dump.R b/R-package/R/xgb.dump.R
index 09406dc99..78fcf4d0b 100644
--- a/R-package/R/xgb.dump.R
+++ b/R-package/R/xgb.dump.R
@@ -13,7 +13,7 @@
 #'
 #' @examples
 #' data(iris)
-#' bst <- xgboost(as.matrix(iris[,1:4]),as.numeric(iris[,5]), nrounds = 2)
+#' bst <- xgboost(as.matrix(iris[,1:4]),as.numeric(iris[,5]=='setosa'), nrounds = 2)
 #' xgb.dump(bst, 'iris.xgb.model.dump')
 #' @export
 #' 
diff --git a/R-package/R/xgb.load.R b/R-package/R/xgb.load.R
index 626c08d0d..54afe65dd 100644
--- a/R-package/R/xgb.load.R
+++ b/R-package/R/xgb.load.R
@@ -6,7 +6,7 @@
 #' 
 #' @examples
 #' data(iris)
-#' bst <- xgboost(as.matrix(iris[,1:4]),as.numeric(iris[,5]), nrounds = 2)
+#' bst <- xgboost(as.matrix(iris[,1:4]),as.numeric(iris[,5]=='setosa'), nrounds = 2)
 #' xgb.save(bst, 'iris.xgb.model')
 #' bst <- xgb.load('iris.xgb.model')
 #' pred <- predict(bst, as.matrix(iris[,1:4]))
diff --git a/R-package/R/xgb.save.R b/R-package/R/xgb.save.R
index 64add0ca9..c211429ad 100644
--- a/R-package/R/xgb.save.R
+++ b/R-package/R/xgb.save.R
@@ -7,7 +7,7 @@
 #' 
 #' @examples
 #' data(iris)
-#' bst <- xgboost(as.matrix(iris[,1:4]),as.numeric(iris[,5]), nrounds = 2)
+#' bst <- xgboost(as.matrix(iris[,1:4]),as.numeric(iris[,5]=='setosa'), nrounds = 2)
 #' xgb.save(bst, 'iris.xgb.model')
 #' bst <- xgb.load('iris.xgb.model')
 #' pred <- predict(bst, as.matrix(iris[,1:4]))
diff --git a/R-package/R/xgb.train.R b/R-package/R/xgb.train.R
index d29bad569..5a7b03090 100644
--- a/R-package/R/xgb.train.R
+++ b/R-package/R/xgb.train.R
@@ -44,7 +44,7 @@
 #' 
 #' @examples
 #' data(iris)
-#' iris[,5] <- as.numeric(iris[,5])
+#' iris[,5] <- as.numeric(iris[,5]=='setosa')
 #' dtrain <- xgb.DMatrix(as.matrix(iris[,1:4]), label=iris[,5])
 #' dtest <- dtrain
 #' watchlist <- list(eval = dtest, train = dtrain)
diff --git a/R-package/R/xgboost.R b/R-package/R/xgboost.R
index f3b5c66ec..e8888afcd 100644
--- a/R-package/R/xgboost.R
+++ b/R-package/R/xgboost.R
@@ -34,7 +34,7 @@
 #' 
 #' @examples
 #' data(iris)
-#' bst <- xgboost(as.matrix(iris[,1:4]),as.numeric(iris[,5]), nrounds = 2)
+#' bst <- xgboost(as.matrix(iris[,1:4]),as.numeric(iris[,5]=='setosa'), nrounds = 2)
 #' pred <- predict(bst, as.matrix(iris[,1:4]))
 #' @export
 #' 
diff --git a/R-package/man/getinfo.Rd b/R-package/man/getinfo.Rd
index 05a25c152..7206d6b17 100644
--- a/R-package/man/getinfo.Rd
+++ b/R-package/man/getinfo.Rd
@@ -21,7 +21,7 @@ Get information of an xgb.DMatrix object
 }
 \examples{
 data(iris)
-iris[,5] <- as.numeric(iris[,5])
+iris[,5] <- as.numeric(iris[,5]=='setosa')
 dtrain <- xgb.DMatrix(as.matrix(iris[,1:4]), label=iris[,5])
 labels <- getinfo(dtrain, "label")
 }
diff --git a/R-package/man/predict-xgb.Booster-method.Rd b/R-package/man/predict-xgb.Booster-method.Rd
index d192997d2..9c19b8f33 100644
--- a/R-package/man/predict-xgb.Booster-method.Rd
+++ b/R-package/man/predict-xgb.Booster-method.Rd
@@ -18,15 +18,16 @@ value of sum of functions, when outputmargin=TRUE, the prediction is
 untransformed margin value. In logistic regression, outputmargin=T will
 output value before logistic transformation.}
 
-\item{ntreelimit}{limit number of trees used in prediction, this parameter is only valid for gbtree, but not for gblinear.
-set it to be value bigger than 0. It will use all trees by default.}
+\item{ntreelimit}{limit number of trees used in prediction, this parameter is
+only valid for gbtree, but not for gblinear. set it to be value bigger
+than 0. It will use all trees by default.}
 }
 \description{
 Predicted values based on xgboost model object.
 }
 \examples{
 data(iris)
-bst <- xgboost(as.matrix(iris[,1:4]),as.numeric(iris[,5]), nrounds = 2)
+bst <- xgboost(as.matrix(iris[,1:4]),as.numeric(iris[,5]=='setosa'), nrounds = 2)
 pred <- predict(bst, as.matrix(iris[,1:4]))
 }
 
diff --git a/R-package/man/slice.Rd b/R-package/man/slice.Rd
index 7acb14a32..a4d0a4568 100644
--- a/R-package/man/slice.Rd
+++ b/R-package/man/slice.Rd
@@ -23,7 +23,7 @@ orginal xgb.DMatrix object
 }
 \examples{
 data(iris)
-iris[,5] <- as.numeric(iris[,5])
+iris[,5] <- as.numeric(iris[,5]=='setosa')
 dtrain <- xgb.DMatrix(as.matrix(iris[,1:4]), label=iris[,5])
 dsub <- slice(dtrain, 1:3)
 }
diff --git a/R-package/man/xgb.DMatrix.Rd b/R-package/man/xgb.DMatrix.Rd
index 166d69f68..ea7ff8ce6 100644
--- a/R-package/man/xgb.DMatrix.Rd
+++ b/R-package/man/xgb.DMatrix.Rd
@@ -20,7 +20,7 @@ Contruct xgb.DMatrix object from dense matrix, sparse matrix or local file.
 }
 \examples{
 data(iris)
-iris[,5] <- as.numeric(iris[,5])
+iris[,5] <- as.numeric(iris[,5]=='setosa')
 dtrain <- xgb.DMatrix(as.matrix(iris[,1:4]), label=iris[,5])
 xgb.DMatrix.save(dtrain, 'iris.xgb.DMatrix')
 dtrain <- xgb.DMatrix('iris.xgb.DMatrix')
diff --git a/R-package/man/xgb.DMatrix.save.Rd b/R-package/man/xgb.DMatrix.save.Rd
index e5e70501d..2692069dc 100644
--- a/R-package/man/xgb.DMatrix.save.Rd
+++ b/R-package/man/xgb.DMatrix.save.Rd
@@ -15,7 +15,7 @@ Save xgb.DMatrix object to binary file
 }
 \examples{
 data(iris)
-iris[,5] <- as.numeric(iris[,5])
+iris[,5] <- as.numeric(iris[,5]=='setosa')
 dtrain <- xgb.DMatrix(as.matrix(iris[,1:4]), label=iris[,5])
 xgb.DMatrix.save(dtrain, 'iris.xgb.DMatrix')
 dtrain <- xgb.DMatrix('iris.xgb.DMatrix')
diff --git a/R-package/man/xgb.dump.Rd b/R-package/man/xgb.dump.Rd
index 4d6933811..a4ac12cd4 100644
--- a/R-package/man/xgb.dump.Rd
+++ b/R-package/man/xgb.dump.Rd
@@ -21,7 +21,7 @@ Save a xgboost model to text file. Could be parsed later.
 }
 \examples{
 data(iris)
-bst <- xgboost(as.matrix(iris[,1:4]),as.numeric(iris[,5]), nrounds = 2)
+bst <- xgboost(as.matrix(iris[,1:4]),as.numeric(iris[,5]=='setosa'), nrounds = 2)
 xgb.dump(bst, 'iris.xgb.model.dump')
 }
 
diff --git a/R-package/man/xgb.load.Rd b/R-package/man/xgb.load.Rd
index 980daf88d..a8969c07d 100644
--- a/R-package/man/xgb.load.Rd
+++ b/R-package/man/xgb.load.Rd
@@ -13,7 +13,7 @@ Load xgboost model from the binary model file
 }
 \examples{
 data(iris)
-bst <- xgboost(as.matrix(iris[,1:4]),as.numeric(iris[,5]), nrounds = 2)
+bst <- xgboost(as.matrix(iris[,1:4]),as.numeric(iris[,5]=='setosa'), nrounds = 2)
 xgb.save(bst, 'iris.xgb.model')
 bst <- xgb.load('iris.xgb.model')
 pred <- predict(bst, as.matrix(iris[,1:4]))
diff --git a/R-package/man/xgb.save.Rd b/R-package/man/xgb.save.Rd
index ba390d1b4..0dca58287 100644
--- a/R-package/man/xgb.save.Rd
+++ b/R-package/man/xgb.save.Rd
@@ -15,7 +15,7 @@ Save xgboost model from xgboost or xgb.train
 }
 \examples{
 data(iris)
-bst <- xgboost(as.matrix(iris[,1:4]),as.numeric(iris[,5]), nrounds = 2)
+bst <- xgboost(as.matrix(iris[,1:4]),as.numeric(iris[,5]=='setosa'), nrounds = 2)
 xgb.save(bst, 'iris.xgb.model')
 bst <- xgb.load('iris.xgb.model')
 pred <- predict(bst, as.matrix(iris[,1:4]))
diff --git a/R-package/man/xgb.train.Rd b/R-package/man/xgb.train.Rd
index 4da3b0013..75c43cd56 100644
--- a/R-package/man/xgb.train.Rd
+++ b/R-package/man/xgb.train.Rd
@@ -56,7 +56,7 @@ therefore it is more flexible than \code{\link{xgboost}}.
 }
 \examples{
 data(iris)
-iris[,5] <- as.numeric(iris[,5])
+iris[,5] <- as.numeric(iris[,5]=='setosa')
 dtrain <- xgb.DMatrix(as.matrix(iris[,1:4]), label=iris[,5])
 dtest <- dtrain
 watchlist <- list(eval = dtest, train = dtrain)
diff --git a/R-package/man/xgboost.Rd b/R-package/man/xgboost.Rd
index 2b6c1a124..435423d28 100644
--- a/R-package/man/xgboost.Rd
+++ b/R-package/man/xgboost.Rd
@@ -46,7 +46,7 @@ Number of threads can also be manually specified via "nthread" parameter
 }
 \examples{
 data(iris)
-bst <- xgboost(as.matrix(iris[,1:4]),as.numeric(iris[,5]), nrounds = 2)
+bst <- xgboost(as.matrix(iris[,1:4]),as.numeric(iris[,5]=='setosa'), nrounds = 2)
 pred <- predict(bst, as.matrix(iris[,1:4]))
 }
 
diff --git a/R-package/vignettes/xgboost.Rnw b/R-package/vignettes/xgboost.Rnw
index 9ecceca17..45ab1a096 100644
--- a/R-package/vignettes/xgboost.Rnw
+++ b/R-package/vignettes/xgboost.Rnw
@@ -80,7 +80,7 @@ In this section, we will illustrate some common usage of \verb@xgboost@.
 <<Training and prediction with iris>>=
 library(xgboost)
 data(iris)
-bst <- xgboost(as.matrix(iris[,1:4]),as.numeric(iris[,5]), 
+bst <- xgboost(as.matrix(iris[,1:4]),as.numeric(iris[,5]=='setosa'), 
                nrounds = 5)
 xgb.save(bst, 'model.save')
 bst = xgb.load('model.save')
@@ -121,7 +121,7 @@ training from initial prediction value, weighted training instance.
 We can use \verb@xgb.DMatrix@ to construct an \verb@xgb.DMatrix@ object:
 <<xgb.DMatrix>>=
 iris.mat <- as.matrix(iris[,1:4])
-iris.label <- as.numeric(iris[,5])
+iris.label <- as.numeric(iris[,5]=='setosa')
 diris <- xgb.DMatrix(iris.mat, label = iris.label)
 class(diris)
 getinfo(diris,'label')
diff --git a/demo/guide-R/basic_walkthrough.R b/demo/guide-R/basic_walkthrough.R
new file mode 100644
index 000000000..959e5f0ed
--- /dev/null
+++ b/demo/guide-R/basic_walkthrough.R
@@ -0,0 +1,53 @@
+require(xgboost)
+
+dtrain <- xgb.DMatrix('../data/agaricus.txt.train')
+dtest <- xgb.DMatrix('../data/agaricus.txt.test')
+param <- list(max_depth=2,eta=1,silent=1,objective='binary:logistic')
+watchlist <- list(eval = dtest, train = dtrain)
+num_round <- 2
+bst <- xgb.train(param, dtrain, num_round, watchlist)
+preds <- predict(bst, dtest)
+labels <- getinfo(dtest,'label')
+cat('error=', mean(as.numeric(preds>0.5)!=labels),'\n')
+xgb.save(bst, 'xgb.model')
+xgb.dump(bst, 'dump.raw.txt')
+xgb.dump(bst, 'dump.nuce.txt','../data/featmap.txt')
+
+bst2 <- xgb.load('xgb.model')
+preds2 <- predict(bst2,dtest)
+stopifnot(sum((preds-preds2)^2)==0)
+
+
+cat('start running example of build DMatrix from scipy.sparse CSR Matrix\n')
+read.libsvm <- function(fname, maxcol) {
+    content <- readLines(fname)
+    nline <- length(content)
+    label <- numeric(nline)
+    mat <- matrix(0, nline, maxcol + 1)
+    for (i in 1:nline) {
+        arr <- as.vector(strsplit(content[i], " ")[[1]])
+        label[i] <- as.numeric(arr[[1]])
+        for (j in 2:length(arr)) {
+            kv <- strsplit(arr[j], ":")[[1]]
+            # to avoid 0 index
+            findex <- as.integer(kv[1]) + 1
+            fvalue <- as.numeric(kv[2])
+            mat[i, findex] <- fvalue
+        }
+    }
+    mat <- as(mat, "sparseMatrix")
+    return(list(label = label, data = mat))
+}
+csc <- read.libsvm("../data/agaricus.txt.train", 126)
+y <- csc$label
+x <- csc$data
+class(x)
+dtrain <- xgb.DMatrix(x, label = y)
+bst <- xgb.train(param, dtrain, num_round, watchlist)
+
+cat('start running example of build DMatrix from numpy array\n')
+x <- as.matrix(x)
+class(x)
+dtrain <- xgb.DMatrix(x, label = y)
+bst <- xgb.train(param, dtrain, num_round, watchlist)
+