change name

demo/kaggle-otto/README.MD

@@ -0,0 +1,25 @@
+Benckmark for Otto Group Competition
+=========
+
+This is a folder containing the benchmark for the [Otto Group Competition on Kaggle](http://www.kaggle.com/c/otto-group-product-classification-challenge).
+
+## Getting started
+
+1. Put `train.csv` and `test.csv` under the `data` folder
+2. Run the script
+3. Submit the `submission.csv`
+
+The parameter `nthread` controls the number of cores to run on, please set it to suit your machine.
+
+## R-package
+
+To install the R-package of xgboost, please run
+
+```r
+devtools::install_github('tqchen/xgboost',subdir='R-package')
+```
+
+Windows users may need to install [RTools](http://cran.r-project.org/bin/windows/Rtools/) first.
+
+
+

demo/kaggle-otto/otto_train_pred.R

@@ -0,0 +1,43 @@
+require(xgboost)
+require(methods)
+
+train = read.csv('data/train.csv',header=TRUE,stringsAsFactors = F)
+test = read.csv('data/test.csv',header=TRUE,stringsAsFactors = F)
+train = train[,-1]
+test = test[,-1]
+
+y = train[,ncol(train)]
+y = gsub('Class_','',y)
+y = as.integer(y)-1 #xgboost take features in [0,numOfClass)
+
+x = rbind(train[,-ncol(train)],test)
+x = as.matrix(x)
+x = matrix(as.numeric(x),nrow(x),ncol(x))
+trind = 1:length(y)
+teind = (nrow(train)+1):nrow(x)
+
+# Set necessary parameter
+param <- list("objective" = "multi:softprob",
+              "eval_metric" = "mlogloss",
+              "num_class" = 9,
+              "nthread" = 8)
+
+# Run Cross Valication
+cv.nround = 50
+bst.cv = xgb.cv(param=param, data = x[trind,], label = y, 
+                nfold = 3, nrounds=cv.nround)
+
+# Train the model
+nround = 50
+bst = xgboost(param=param, data = x[trind,], label = y, nrounds=nround)
+
+# Make prediction
+pred = predict(bst,x[teind,])
+pred = matrix(pred,9,length(pred)/9)
+pred = t(pred)
+
+# Output submission
+pred = format(pred, digits=2,scientific=F) # shrink the size of submission
+pred = data.frame(1:nrow(pred),pred)
+names(pred) = c('id', paste0('Class_',1:9))
+write.csv(pred,file='submission.csv', quote=FALSE,row.names=FALSE)