eclipse配置spark1.6.0教程
https://kevin12.iteye.com/blog/2274179
这里注意修改,根据自己的修改
com.Johnson
Spark_2.3.1
1.0-SNAPSHOT
4.0.0
<groupId>com.Johnson</groupId>
<artifactId>Spark_2.3.1</artifactId>
<version>1.0-SNAPSHOT</version>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<scala.version>2.11.8</scala.version>
<spark.version>2.3.1</spark.version>
<hadoop.version>2.6.0</hadoop.version>
<hbase.version>1.2.0</hbase.version>
<phoenix.version>4.14.0</phoenix.version>
</properties>
<repositories>
<repository>
<id>scala-tools.org</id>
<name>Scala-Tools Maven2 Repository</name>
<url>http://scala-tools.org/repo-releases</url>
</repository>
<repository>
<id>cloudera</id>
<url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
</repository>
</repositories>
<pluginRepositories>
<pluginRepository>
<id>scala-tools.org</id>
<name>Scala-Tools Maven2 Repository</name>
<url>http://scala-tools.org/repo-releases</url>
</pluginRepository>
</pluginRepositories>
<dependencies>
<dependency>
<groupId>org.scala-lang</groupId>
<artifactId>scala-library</artifactId>
<version>${scala.version}</version>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.4</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.specs</groupId>
<artifactId>specs</artifactId>
<version>1.2.5</version>
<scope>test</scope>
</dependency>
<!--<dependency>-->
<!--<groupId>com.alibaba</groupId>-->
<!--<artifactId>fastjson</artifactId>-->
<!--<version>1.2.7</version>-->
<!--</dependency>-->
<dependency>
<groupId>javax.servlet</groupId>
<artifactId>javax.servlet-api</artifactId>
<version>3.0.1</version>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-databind</artifactId>
<version>2.4.4</version>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-core</artifactId>
<version>2.6.7</version>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-databind</artifactId>
<version>2.6.7</version>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.module</groupId>
<artifactId>jackson-module-scala_2.11</artifactId>
<version>2.6.7.1</version>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.module</groupId>
<artifactId>jackson-module-paranamer</artifactId>
<version>2.7.9</version>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-annotations</artifactId>
<version>2.6.7</version>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-core</artifactId>
<version>2.8.2</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-client</artifactId>
<version>${hbase.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-common</artifactId>
<version>${hbase.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<version>${hadoop.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>${hadoop.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-server</artifactId>
<version>${hbase.version}</version>
</dependency>
<dependency>
<groupId>org.apache.zookeeper</groupId>
<artifactId>zookeeper</artifactId>
<version>3.4.5</version>
</dependency>
<dependency>
<groupId>com.101tec</groupId>
<artifactId>zkclient</artifactId>
<version>0.10</version>
</dependency>
<dependency>
<groupId>com.yammer.metrics</groupId>
<artifactId>metrics-core</artifactId>
<version>2.2.0</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-protocol</artifactId>
<version>${hbase.version}</version>
</dependency>
<dependency>
<groupId>org.apache.htrace</groupId>
<artifactId>htrace-core</artifactId>
<version>3.2.0-incubating</version>
</dependency>
<dependency>
<groupId>io.netty</groupId>
<artifactId>netty-all</artifactId>
<version>4.1.24.Final</version>
</dependency>
<dependency>
<groupId>org.threeten</groupId>
<artifactId>threeten-extra</artifactId>
<version>1.2</version>
</dependency>
<dependency>
<groupId>com.cloudera.sparkts</groupId>
<artifactId>sparkts</artifactId>
<version>0.4.1</version>
</dependency>
<dependency>
<groupId>mysql</groupId>
<artifactId>mysql-connector-java</artifactId>
<version>5.1.38</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming_2.11</artifactId>
<version>${spark.version}</version>
<!--<exclusions>-->
<!--<exclusion>-->
<!--<artifactId>lz4</artifactId>-->
<!--<groupId>net.jpountz.lz4</groupId>-->
<!--</exclusion>-->
<!--</exclusions>-->
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-mllib_2.11</artifactId>
<version>${spark.version}</version>
<!--<exclusions>-->
<!--<exclusion>-->
<!--<artifactId>lz4</artifactId>-->
<!--<groupId>net.jpountz.lz4</groupId>-->
<!--</exclusion>-->
<!--</exclusions>-->
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>${hadoop.version}</version>
<!--<exclusions>-->
<!--<exclusion>-->
<!--<groupId>javax.servlet</groupId>-->
<!--<artifactId>*</artifactId>-->
<!--</exclusion>-->
<!--</exclusions>-->
</dependency>
<!--<dependency>-->
<!--<groupId>org.apache.spark</groupId>-->
<!--<artifactId>spark-sql-kafka-0-10_2.11</artifactId>-->
<!--<version>${spark.version}</version>-->
<!--</dependency>-->
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming-kafka-0-10_2.11</artifactId>
<version>${spark.version}</version>
<!--<exclusions>-->
<!--<exclusion>-->
<!--<artifactId>lz4</artifactId>-->
<!--<groupId>net.jpountz.lz4</groupId>-->
<!--</exclusion>-->
<!--</exclusions>-->
</dependency>
<dependency>
<groupId>org.apache.kafka</groupId>
<artifactId>kafka-clients</artifactId>
<version>0.10.2.0</version>
<exclusions>
<exclusion>
<groupId>net.jpountz.lz4</groupId>
<artifactId>lz4</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.kafka</groupId>
<artifactId>kafka_2.11</artifactId>
<version>0.10.2.0</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
<version>${spark.version}</version>
<!--<exclusions>-->
<!--<exclusion>-->
<!--<artifactId>lz4</artifactId>-->
<!--<groupId>net.jpountz.lz4</groupId>-->
<!--</exclusion>-->
<!--</exclusions>-->
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.11</artifactId>
<version>${spark.version}</version>
<!--<exclusions>-->
<!--<exclusion>-->
<!--<artifactId>lz4</artifactId>-->
<!--<groupId>net.jpountz.lz4</groupId>-->
<!--</exclusion>-->
<!--</exclusions>-->
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-hive_2.11</artifactId>
<version>${spark.version}</version>
<!--<exclusions>-->
<!--<exclusion>-->
<!--<artifactId>lz4</artifactId>-->
<!--<groupId>net.jpountz.lz4</groupId>-->
<!--</exclusion>-->
<!--</exclusions>-->
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-catalyst_2.11</artifactId>
<version>${spark.version}</version>
<!--<exclusions>-->
<!--<exclusion>-->
<!--<artifactId>lz4</artifactId>-->
<!--<groupId>net.jpountz.lz4</groupId>-->
<!--</exclusion>-->
<!--</exclusions>-->
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-core</artifactId>
<version>${hadoop.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-common</artifactId>
<version>${hadoop.version}</version>
</dependency>
<!--<dependency>-->
<!--<groupId>org.apache.hadoop</groupId>-->
<!--<artifactId>hadoop-mapreduce-client-jobclient</artifactId>-->
<!--<version>>${hadoop.version}</version>-->
<!--</dependency>-->
<dependency>
<groupId>commons-cli</groupId>
<artifactId>commons-cli</artifactId>
<version>1.2</version>
</dependency>
<!--<dependency>-->
<!--<groupId>org.apache.phoenix</groupId>-->
<!--<artifactId>phoenix</artifactId>-->
<!--<version>${phoenix.version}</version>-->
<!--</dependency>-->
<!--<dependency>-->
<!--<groupId>org.apache.phoenix</groupId>-->
<!--<artifactId>phoenix-spark</artifactId>-->
<!--<version>${phoenix.version}</version>-->
<!--</dependency>-->
</dependencies>
<build>
<sourceDirectory>src/main/scala</sourceDirectory>
<testSourceDirectory>src/test/scala</testSourceDirectory>
<plugins>
<plugin>
<groupId>org.scala-tools</groupId>
<artifactId>maven-scala-plugin</artifactId>
<executions>
<execution>
<goals>
<goal>compile</goal>
<goal>testCompile</goal>
</goals>
</execution>
</executions>
<configuration>
<scalaVersion>${scala.version}</scalaVersion>
<args>
<arg>-target:jvm-1.8</arg>
</args>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-eclipse-plugin</artifactId>
<configuration>
<downloadSources>true</downloadSources>
<buildcommands>
<buildcommand>ch.epfl.lamp.sdt.core.scalabuilder</buildcommand>
</buildcommands>
<additionalProjectnatures>
<projectnature>ch.epfl.lamp.sdt.core.scalanature</projectnature>
</additionalProjectnatures>
<classpathContainers>
<classpathContainer>org.eclipse.jdt.launching.JRE_CONTAINER</classpathContainer>
<classpathContainer>ch.epfl.lamp.sdt.launching.SCALA_CONTAINER</classpathContainer>
</classpathContainers>
</configuration>
</plugin>
</plugins>
</build>
<reporting>
<plugins>
<plugin>
<groupId>org.scala-tools</groupId>
<artifactId>maven-scala-plugin</artifactId>
<configuration>
<scalaVersion>${scala.version}</scalaVersion>
</configuration>
</plugin>
</plugins>
</reporting>
Pycharm配置spark
1:注意修改自己的路径
或者将pyspark复制到anaconda的site-packages目录下:
2:
SPARK_HOME ***
PYTHONPATH ***