Apache Spark is a fast and general-purpose cluster computing system.It provides high-level APIs in Java, Scala, Python and R, and an optimized engine that supports general execution graphs.

It also supports a rich set of higher-level tools including Spark SQL for SQL and structured data processing, MLlib for machine learning, GraphX for graph processing, and Spark Streaming.

package big.data.analyse.wordcount

import org.apache.spark.sql.SparkSession

/**

  * Created by zhen on 2019/3/9.

  */

object WordCount {

  def main(args: Array[String]) {

    val spark = SparkSession.builder().appName("WordCount")

      .master("local[2]")

      .getOrCreate()

    // 加载数据

    val textRDD = spark.sparkContext.textFile("src/big/data/analyse/wordcount/wordcount.txt")

    val result = textRDD.map(row => row.replace(",", ""))//去除文字中的,防止出现歧义

      .flatMap(row => row.split(" "))//把字符串转换为字符集合

      .map(row => (row, ))//把每个字符串转换为map，便于计数

      .reduceByKey(_+_)//计数

    // 打印结果

    result.foreach(println)

  }

}

(Spark,)

(GraphX,)

(graphs.,)

(learning,)

(general-purpose,)

(Python,)

(APIs,)

(provides,)

(that,)

(is,)

(a,)

(R,)

(high-level,)

(general,)

(processing,)

(fast,)

(including,)

(higher-level,)

(optimized,)

(Apache,)

(in,)

(SQL,)

(system.,)

(Java,)

(of,)

(data,)

(tools,)

(cluster,)

(also,)

(graph,)

(structured,)

(execution,)

(It,)

(MLlib,)

(for,)

(Scala,)

(an,)

(computing,)

(machine,)

(supports,)

(and,)

(engine,)

(set,)

(rich,)

(Streaming.,)