Merge pull request #37 from tqchen/unity

Unity

demo/kaggle-higgs/README.md

@@ -17,3 +17,9 @@ make
 Speed
 =====
 speedtest.py compares xgboost's speed on this dataset with sklearn.GBM
+
+
+Using R module
+=====
+* Alternatively, you can run using R, higgs-train.R and higgs-pred.R
+

demo/kaggle-higgs/higgs-pred.R

@@ -0,0 +1,23 @@
+# include xgboost library, must set chdir=TRURE
+source("../../wrapper/xgboost.R", chdir=TRUE)
+
+modelfile <- "higgs.model"
+outfile <- "higgs.pred.csv"
+dtest <- read.csv("data/test.csv", header=TRUE)
+data <- as.matrix(dtest[2:31])
+idx <- dtest[[1]]
+
+xgmat <- xgb.DMatrix(data, missing = -999.0)
+bst <- xgb.Booster(params=list("nthread"=16), modelfile=modelfile)
+ypred <- xgb.predict(bst, xgmat)
+
+rorder <- rank(ypred, ties.method="first")
+
+threshold <- 0.15
+# to be completed
+ntop <- length(rorder) - as.integer(threshold*length(rorder))
+plabel <- ifelse(rorder > ntop, "s", "b")
+outdata <- list("EventId" = idx,
+                "RankOrder" = rorder,
+                "Class" = plabel)
+write.csv(outdata, file = outfile, quote=FALSE, row.names=FALSE)

demo/kaggle-higgs/higgs-pred.py

@@ -21,8 +21,7 @@ idx = dtest[:,0]
 
 print ('finish loading from csv ')
 xgmat = xgb.DMatrix( data, missing = -999.0 )
-bst = xgb.Booster({'nthread':16})
+bst = xgb.Booster({'nthread':16}, model_file = modelfile)
-bst.load_model( modelfile )
 ypred = bst.predict( xgmat )
 
 res  = [ ( int(idx[i]), ypred[i] ) for i in range(len(ypred)) ] 

demo/kaggle-higgs/higgs-train.R

@@ -0,0 +1,31 @@
+# include xgboost library, must set chdir=TRURE
+source("../../wrapper/xgboost.R", chdir=TRUE)
+testsize <- 550000
+
+dtrain <- read.csv("data/training.csv", header=TRUE)
+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))
+
+xgmat <- xgb.DMatrix(data, info = list(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" = 16)
+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')
+