使用朴素贝叶斯算法进行男女分类
训练模型,并进行保存
原数据:
maven 依赖
<dependencies>
<!-- 导入spark sql的依赖 -->
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.11</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.scala-lang.modules</groupId>
<artifactId>scala-parser-combinators_2.11</artifactId>
<version>1.0.1</version>
</dependency>
<dependency>
<groupId>org.scala-lang</groupId>
<artifactId>scala-compiler</artifactId>
<version>2.11.8</version>
</dependency>
<dependency>
<groupId>org.scala-lang</groupId>
<artifactId>scala-library</artifactId>
<version>2.11.8</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.spark/spark-mllib -->
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-mllib_2.11</artifactId>
<version>2.2.0</version>
</dependency>
<!-- 指定hadoop-client API的版本 -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId