开始使用 XGBoost

这是一个快速入门教程，展示了让你快速在二分类任务的演示数据集上尝试XGBoost的代码片段。

链接到其他有用的资源

• 请参阅 安装指南 了解如何安装 XGBoost。

• 参见 文本输入格式 以了解如何使用文本格式指定训练/测试数据。

• 查看 教程 获取提示和教程。

• 更多代码示例请参见 通过示例学习使用XGBoost。

Python

from xgboost import XGBClassifier
# read data
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
data = load_iris()
X_train, X_test, y_train, y_test = train_test_split(data['data'], data['target'], test_size=.2)
# create model instance
bst = XGBClassifier(n_estimators=2, max_depth=2, learning_rate=1, objective='binary:logistic')
# fit model
bst.fit(X_train, y_train)
# make predictions
preds = bst.predict(X_test)

R

# 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")
  }
}