From 086433da0d704217a93be29e51fbd362174c82d4 Mon Sep 17 00:00:00 2001
From: unknown <hetong007@gmail.com>
Date: Thu, 28 Aug 2014 22:40:44 -0700
Subject: [PATCH] add speedtest.R by -f

---
 demo/kaggle-higgs/speedtest.R | 71 +++++++++++++++++++++++++++++++++++
 1 file changed, 71 insertions(+)
 create mode 100644 demo/kaggle-higgs/speedtest.R

diff --git a/demo/kaggle-higgs/speedtest.R b/demo/kaggle-higgs/speedtest.R
new file mode 100644
index 000000000..9fb0c561a
--- /dev/null
+++ b/demo/kaggle-higgs/speedtest.R
@@ -0,0 +1,71 @@
+# install xgboost package, see R-package in root folder
+require(xgboost)
+require(gbm)
+require(methods)
+
+testsize <- 550000
+
+dtrain <- read.csv("data/training.csv", header=TRUE, nrows=350001)
+
+# gbm.time = system.time({
+#   gbm.model <- gbm(Label ~ ., data = dtrain[, -c(1,32)], n.trees = 120, 
+#                    interaction.depth = 6, shrinkage = 0.1, bag.fraction = 1,
+#                    verbose = TRUE)
+# })
+# print(gbm.time)
+# Test result: 761.48 secs
+
+dtrain[33] <- dtrain[33] == "s"
+label <- as.numeric(dtrain[[33]])
+data <- as.matrix(dtrain[2:31])
+weight <- as.numeric(dtrain[[32]]) * testsize / length(label)
+
+sumwpos <- sum(weight * (label==1.0))
+sumwneg <- sum(weight * (label==0.0))
+print(paste("weight statistics: wpos=", sumwpos, "wneg=", sumwneg, "ratio=", sumwneg / sumwpos))
+
+xgboost.time = list()
+threads = c(1,2,4,8,16)
+for (i in 1:length(threads)){
+  thread = threads[i]
+  xgboost.time[[i]] = system.time({
+    xgmat <- xgb.DMatrix(data, label = label, weight = weight, missing = -999.0)
+    param <- list("objective" = "binary:logitraw",
+                  "scale_pos_weight" = sumwneg / sumwpos,
+                  "bst:eta" = 0.1,
+                  "bst:max_depth" = 6,
+                  "eval_metric" = "auc",
+                  "eval_metric" = "ams@0.15",
+                  "silent" = 1,
+                  "nthread" = thread)
+    watchlist <- list("train" = xgmat)
+    nround = 120
+    print ("loading data end, start to boost trees")
+    bst = xgb.train(param, xgmat, nround, watchlist );
+    # save out model
+    xgb.save(bst, "higgs.model")
+    print ('finish training')
+  })
+}
+
+xgboost.time
+# [[1]]
+# user  system elapsed 
+# 444.98    1.96  450.22 
+# 
+# [[2]]
+# user  system elapsed 
+# 188.15    0.82  102.41 
+# 
+# [[3]]
+# user  system elapsed 
+# 143.29    0.79   44.18 
+# 
+# [[4]]
+# user  system elapsed 
+# 176.60    1.45   34.04 
+# 
+# [[5]]
+# user  system elapsed 
+# 180.15    2.85   35.26 
+