关于 XGBoost

XGBoost 是一个优化过的分布式梯度提升库，旨在实现高度高效、灵活和 可移植。它在梯度提升框架下实现了机器学习算法。XGBoost 提供了并行树提升（也称为 GBDT、GBM），可以快速准确地解决许多数据科学问题。相同的代码可以在主要的分布式环境（Hadoop、SGE、MPI）上运行，并能解决数十亿以上的样本问题。

这里有一些快速入门示例，请查阅文档。

Python

import xgboost as xgb
# read in data
dtrain = xgb.DMatrix('demo/data/agaricus.txt.train')
dtest = xgb.DMatrix('demo/data/agaricus.txt.test')
# specify parameters via map
param = {'max_depth':2, 'eta':1, 'objective':'binary:logistic' }
num_round = 2
bst = xgb.train(param, dtrain, num_round)
# make prediction
preds = bst.predict(dtest)

R

library(xgboost)
# load data
data(agaricus.train, package = 'xgboost')
data(agaricus.test, package = 'xgboost')
train <- agaricus.train
test <- agaricus.test
# fit model
bst <- xgboost(data = train$data, label = train$label, max_depth = 2, eta = 1, nrounds = 2,
               nthread = 2, objective = "binary:logistic")
# predict
pred <- predict(bst, test$data)

Julia

using XGBoost
# read data
train_X, train_Y = readlibsvm("demo/data/agaricus.txt.train", (6513, 126))
test_X, test_Y = readlibsvm("demo/data/agaricus.txt.test", (1611, 126))
# fit model
num_round = 2
bst = xgboost(train_X, num_round, label=train_Y, eta=1, max_depth=2)
# predict
pred = predict(bst, test_X)

Scala

import ml.dmlc.xgboost4j.scala.DMatrix
import ml.dmlc.xgboost4j.scala.XGBoost

object XGBoostScalaExample {
  def main(args: Array[String]) {
    // read trainining data, available at xgboost/demo/data
    val trainData =
      new DMatrix("/path/to/agaricus.txt.train")
    // define parameters
    val paramMap = List(
      "eta" -> 0.1,
      "max_depth" -> 2,
      "objective" -> "binary:logistic").toMap
    // number of iterations
    val round = 2
    // train the model
    val model = XGBoost.train(trainData, paramMap, round)
    // run prediction
    val predTrain = model.predict(trainData)
    // save model to the file.
    model.saveModel("/local/path/to/model")
  }
}