采用jar提交集群模式流程为：
本地完成代码开发 –> 本地编译打包 -> 提交集群执行
创建三层包
需要先创建三层package（eg:cn.nokia.bigdata），然后在package下创建object，如下图
Paste_Image.png
稍微修改了下官方例子
package cn.nokia.bigdata
import org.apache.spark.{SparkConf, SparkContext}
// $example on$
import org.apache.spark.mllib.classification.{LogisticRegressionModel, LogisticRegressionWithLBFGS}
import org.apache.spark.mllib.evaluation.MulticlassMetrics
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.mllib.util.MLUtils
// $example off$
object Test {
def main(args: Array[String]): Unit = {
// val conf = new SparkConf().setAppName("LogisticRegressionWithLBFGSExample")
val conf = new SparkConf().setAppName("LogisticRegressionWithLBFGSExample").setMaster("local[*]")
val sc = new SparkContext(conf)
// $example on$
// Load training data in LIBSVM format.
//val data = MLUtils.loadLibSVMFile(sc, "file:///usr/local/spark-2.1.0/data/mllib/sample_libsvm_data.txt")
val data = MLUtils.loadLibSVMFile(sc, "D:\\spark\\data\\mllib\\sample_libsvm_data.txt")
// Split data into training (60%) and test (40%).
val splits = data.randomSplit(Array(0.6, 0.4), seed = 11L)
val training = splits(0).cache()
val test = splits(1)
// Run training algorithm to build the model
val model = new LogisticRegressionWithLBFGS()
.setNumClasses(10)
.run(training)
// Compute raw scores on the test set.
val predictionAndLabels = test.map { case LabeledPoint(label, features) =>
val prediction = model.predict(features)
(prediction, label)
}
// Get evaluation metrics.
val metrics = new MulticlassMetrics(predictionAndLabels)
val accuracy = metrics.accuracy
println(s"Accuracy = $accuracy")
// Save and load model
model.save(sc, "target/tmp/scalaLogisticRegressionWithLBFGSModl")
val sameModel = LogisticRegressionModel.load(sc,
"target/tmp/scalaLogisticRegressionWithLBFGSModel")
// $example off$
sc.stop()
}
}
// scalastyle:on println
当前项目结构
Paste_Image.png
打开项目结构
File -> Project Structure：
Paste_Image.png
快捷按钮
Paste_Image.png
artifact => + => jar
Paste_Image.png
选择主类：
Paste_Image.png
输出设置
Paste_Image.png
编译
Paste_Image.png
Paste_Image.png
build（首次打包） rebuild（重新打包）clean（清理当前内容）
打包完后，可以在如下目录中找到对应jar包：
Paste_Image.png
本地提交
D:\spark\bin>spark-submit --class cn.nokia.bigdata.Test spark.jar local
Paste_Image.png
Paste_Image.png
