NO | 步骤1 |
1 | 搭建环境前写个demo代码 |
2 | 安装配置jdk1.8 |
3 | 安装配置scala2.11.18 |
4 | 导入pom.xml中依赖jar |
5 | 下载Hadoop的bin包,设定环境变量HADOOP_HOME,值为解压后的目录 |
6 | 下载winutils.exe将其放到$HADOOP_HOME/bin/目录下 |
7 | 配置程序启动参数local |
8 | 启动 |
<properties>
<scala.version>2.11</scala.version>
<spark.version>2.0.1</spark.version>
</properties>
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_${scala.version}</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming_${scala.version}</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_${scala.version}</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-mllib_${scala.version}</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-hive_${scala.version}</artifactId>
<version>${spark.version}</version>
</dependency>