Spark DataFrame和Dataset使用例子

文章目录

• • 1、基本操作
  • • 1.1、创建SparkSession
    • 1.2、创建DataFrames
    • 1.3、创建Dataset操作
    • 1.4、运行sql查询
    • 1.5、创建全局临时视图
    • 1.6、创建Datasets
    • 1.7、与rdd进行互操作
    • • 1.7.1、使用反射推断模式
      • 1.7.2、以编程方式指定模式
  • 2、完整的测试例子

1、基本操作

1.1、创建SparkSession

import org.apache.spark.sql.SparkSession;

SparkSession spark = SparkSession
.builder()
.appName("Java Spark SQL basic example")
.config("spark.some.config.option", "some-value")
.getOrCreate();

1.2、创建DataFrames

import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;

Dataset<Row> df = spark.read().json("examples/src/main/resources/people.json");

// Displays the content of the DataFrame to stdout
df.show();
// +----+-------+
// | age|   name|
// +----+-------+
// |null|Michael|
// |  30|   Andy|
// |  19| Justin|
// +----+-------+

1.3、创建Dataset操作

// col("...") is preferable to df.col("...")
import static org.apache.spark.sql.functions.col;

// Print the schema in a tree format
df.printSchema();
// root
// |-- age: long (nullable = true)
// |-- name: string (nullable = true)

// Select only the "name" column
df.select("name").show();
// +-------+
// |   name|
// +-------+
// |Michael|
// |   Andy|
// | Justin|
// +-------+

// Select everybody, but increment the age by 1
df.select(col("name"), col("age").plus(1)).show();
// +-------+---------+
// |   name|(age + 1)|
// +-------+---------+
// |Michael|     null|
// |   Andy|       31|
// | Justin|       20|
// +-------+---------+

// Select people older than 21
df.filter(col("age").gt(21)).show();
// +---+----+
// |age|name|
// +---+----+
// | 30|Andy|
// +---+----+

// Count people by age
df.groupBy("age").count().show();
// +----+-----+
// | age|count|
// +----+-----+
// |  19|    1|
// |null|    1|
// |  30|    1|
// +----+-----+

1.4、运行sql查询

import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;

// Register the DataFrame as a SQL temporary view
df.createOrReplaceTempView("people");

Dataset<Row> sqlDF = spark.sql("SELECT * FROM people");
sqlDF.show();
// +----+-------+
// | age|   name|
// +----+-------+
// |null|Michael|
// |  30|   Andy|
// |  19| Justin|
// +----+-------+

1.5、创建全局临时视图

// Register the DataFrame as a global temporary view
df.createGlobalTempView("people");

// Global temporary view is tied to a system preserved database `global_temp`
spark.sql("SELECT * FROM global_temp.people").show();
// +----+-------+
// | age|   name|
// +----+-------+
// |null|Michael|
// |  30|   Andy|
// |  19| Justin|
// +----+-------+

// Global temporary view is cross-session
spark.newSession().sql("SELECT * FROM global_temp.people").show();
// +----+-------+
// | age|   name|
// +----+-------+
// |null|Michael|
// |  30|   Andy|
// |  19| Justin|
// +----+-------+

1.6、创建Datasets

import java.util.Arrays;
import java.util.Collections;
import java.io.Serializable;

import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.Encoder;
import org.apache.spark.sql.Encoders;

public static class Person implements Serializable {
  private String name;
  private long age;

  public String getName() {
    return name;
  }

  public void setName(String name) {
    this.name = name;
  }

  public long getAge() {
    return age;
  }

  public void setAge(long age) {
    this.age = age;
  }
}

// Create an instance of a Bean class
Person person = new Person();
person.setName("Andy");
person.setAge(32);

// Encoders are created for Java beans
Encoder<Person> personEncoder = Encoders.bean(Person.class);
Dataset<Person> javaBeanDS = spark.createDataset(
  Collections.singletonList(person),
  personEncoder
);
javaBeanDS.show();
// +---+----+
// |age|name|
// +---+----+
// | 32|Andy|
// +---+----+

// Encoders for most common types are provided in class Encoders
Encoder<Long> longEncoder = Encoders.LONG();
Dataset<Long> primitiveDS = spark.createDataset(Arrays.asList(1L, 2L, 3L), longEncoder);
Dataset<Long> transformedDS = primitiveDS.map(
    (MapFunction<Long, Long>) value -> value + 1L,
    longEncoder);
transformedDS.collect(); // Returns [2, 3, 4]

// DataFrames can be converted to a Dataset by providing a class. Mapping based on name
String path = "examples/src/main/resources/people.json";
Dataset<Person> peopleDS = spark.read().json(path).as(personEncoder);
peopleDS.show();
// +----+-------+
// | age|   name|
// +----+-------+
// |null|Michael|
// |  30|   Andy|
// |  19| Justin|
// +----+-------+

1.7、与rdd进行互操作

1.7.1、使用反射推断模式

Spark SQL支持将JavaBeans的RDD自动转换为DataFrame。使用反射获得的BeanInfo定义了表的模式。目前，Spark SQL不支持包含Map字段的JavaBeans。但是支持嵌套JavaBeans和List或Array字段。您可以通过创建一个实现Serializable的类来创建JavaBean，并且该类的所有字段都有getter和setter。

import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.Encoder;
import org.apache.spark.sql.Encoders;

// Create an RDD of Person objects from a text file
JavaRDD<Person> peopleRDD = spark.read()
  .textFile("examples/src/main/resources/people.txt")
  .javaRDD()
  .map(line -> {
    String[] parts = line.split(",");
    Person person = new Person();
    person.setName(parts[0]);
    person.setAge(Integer.parseInt(parts[1].trim()));
    return person;
  });

// Apply a schema to an RDD of JavaBeans to get a DataFrame
Dataset<Row> peopleDF = spark.createDataFrame(peopleRDD, Person.class);
// Register the DataFrame as a temporary view
peopleDF.createOrReplaceTempView("people");

// SQL statements can be run by using the sql methods provided by spark
Dataset<Row> teenagersDF = spark.sql("SELECT name FROM people WHERE age BETWEEN 13 AND 19");

// The columns of a row in the result can be accessed by field index
Encoder<String> stringEncoder = Encoders.STRING();
Dataset<String> teenagerNamesByIndexDF = teenagersDF.map(
    (MapFunction<Row, String>) row -> "Name: " + row.getString(0),
    stringEncoder);
teenagerNamesByIndexDF.show();
// +------------+
// |       value|
// +------------+
// |Name: Justin|
// +------------+

// or by field name
Dataset<String> teenagerNamesByFieldDF = teenagersDF.map(
    (MapFunction<Row, String>) row -> "Name: " + row.<String>getAs("name"),
    stringEncoder);
teenagerNamesByFieldDF.show();
// +------------+
// |       value|
// +------------+
// |Name: Justin|
// +------------+

1.7.2、以编程方式指定模式

当JavaBean类不能提前定义时(例如，记录的结构被编码为字符串，或者文本数据集将被解析，字段将以不同的方式投影给不同的用户)，可以通过三个步骤以编程方式创建dataset 。

• 从原始RDD的行创建一个RDD;
• 创建由StructType表示的模式，该模式与步骤1中创建的RDD中的Rows结构相匹配。
• 通过SparkSession提供的createDataFrame方法将模式应用到RDD的行。

import java.util.ArrayList;
import java.util.List;

import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.function.Function;

import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;

import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.StructField;
import org.apache.spark.sql.types.StructType;

// Create an RDD
JavaRDD<String> peopleRDD = spark.sparkContext()
  .textFile("examples/src/main/resources/people.txt", 1)
  .toJavaRDD();

// The schema is encoded in a string
String schemaString = "name age";

// Generate the schema based on the string of schema
List<StructField> fields = new ArrayList<>();
for (String fieldName : schemaString.split(" ")) {
  StructField field = DataTypes.createStructField(fieldName, DataTypes.StringType, true);
  fields.add(field);
}
StructType schema = DataTypes.createStructType(fields);

// Convert records of the RDD (people) to Rows
JavaRDD<Row> rowRDD = peopleRDD.map((Function<String, Row>) record -> {
  String[] attributes = record.split(",");
  return RowFactory.create(attributes[0], attributes[1].trim());
});

// Apply the schema to the RDD
Dataset<Row> peopleDataFrame = spark.createDataFrame(rowRDD, schema);

// Creates a temporary view using the DataFrame
peopleDataFrame.createOrReplaceTempView("people");

// SQL can be run over a temporary view created using DataFrames
Dataset<Row> results = spark.sql("SELECT name FROM people");

// The results of SQL queries are DataFrames and support all the normal RDD operations
// The columns of a row in the result can be accessed by field index or by field name
Dataset<String> namesDS = results.map(
    (MapFunction<Row, String>) row -> "Name: " + row.getString(0),
    Encoders.STRING());
namesDS.show();
// +-------------+
// |        value|
// +-------------+
// |Name: Michael|
// |   Name: Andy|
// | Name: Justin|
// +-------------+

2、完整的测试例子

本例子代码是在window下测试，需要下载https://github.com/steveloughran/winutils，解压放在hadoop对应目录

package com.penngo.spark;

import org.apache.log4j.Level;
import org.apache.log4j.Logger;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.*;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.StructField;
import org.apache.spark.sql.types.StructType;

import java.io.Serializable;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Collections;
import java.util.List;

import static org.apache.spark.sql.functions.col;

public class SparkDataset {
    private static final String jsonPath = "D:\\hadoop\\spark\\resources\\people.json";
    private static final String txtPath = "D:\\hadoop\\spark\\resources\\people.txt";
    public static class Person implements Serializable {
        private String name;
        private long age;

        public String getName() {
            return name;
        }

        public void setName(String name) {
            this.name = name;
        }

        public long getAge() {
            return age;
        }

        public void setAge(long age) {
            this.age = age;
        }
    }

    public static void createDataFrame(SparkSession spark) throws Exception{
        // 创建DataFrame
        Dataset<Row> df = spark.read().json(jsonPath);
        df.show();

        // 操作
        operations(df);

        // sql查询
        sqlQuery(spark, df);
    }

    public static void operations(Dataset<Row> df){
        df.printSchema();
        // root
        // |-- age: long (nullable = true)
        // |-- name: string (nullable = true)

        // Select only the "name" column
        df.select("name").show();
        // +-------+
        // |   name|
        // +-------+
        // |Michael|
        // |   Andy|
        // | Justin|
        // +-------+

        // Select everybody, but increment the age by 1
        df.select(col("name"), col("age").plus(1)).show();
        // +-------+---------+
        // |   name|(age + 1)|
        // +-------+---------+
        // |Michael|     null|
        // |   Andy|       31|
        // | Justin|       20|
        // +-------+---------+

        // Select people older than 21
        df.filter(col("age").gt(21)).show();
        // +---+----+
        // |age|name|
        // +---+----+
        // | 30|Andy|
        // +---+----+

        // Count people by age
        df.groupBy("age").count().show();
        // +----+-----+
        // | age|count|
        // +----+-----+
        // |  19|    1|
        // |null|    1|
        // |  30|    1|
        // +----+-----+
    }

    /**
     * SQL查询
     */
    public static void sqlQuery(SparkSession spark, Dataset<Row> df) throws Exception{
        // 临时视图，会话消失，视图也会消失
        df.createOrReplaceTempView("people");

        Dataset<Row> sqlDF = spark.sql("SELECT * FROM people");
        sqlDF.show();

        // 全局视图，全局临时视图绑定到系统保留的数据库' global_temp '
        df.createGlobalTempView("people");
        spark.sql("SELECT * FROM global_temp.people").show();
        // +----+-------+
        // | age|   name|
        // +----+-------+
        // |null|Michael|
        // |  30|   Andy|
        // |  19| Justin|
        // +----+-------+

        // 全局临时视图是跨会话的
        spark.newSession().sql("SELECT * FROM global_temp.people").show();
        // +----+-------+
        // | age|   name|
        // +----+-------+
        // |null|Michael|
        // |  30|   Andy|
        // |  19| Justin|
        // +----+-------+
    }

    public static void createDataset(SparkSession spark){
        // 列表转成dataset
        Person person = new Person();
        person.setName("Andy");
        person.setAge(32);
        Encoder<Person> personEncoder = Encoders.bean(Person.class);
        Dataset<Person> javaBeanDS = spark.createDataset(
                Collections.singletonList(person),
                personEncoder
        );
        System.out.println("createDataset show");
        javaBeanDS.show();
        // +---+----+
        // |age|name|
        // +---+----+
        // | 32|Andy|
        // +---+----+

        Encoder<Long> longEncoder = Encoders.LONG();
        Dataset<Long> primitiveDS = spark.createDataset(Arrays.asList(1L, 2L, 3L), longEncoder);
        Dataset<Long> transformedDS = primitiveDS.map(
                (MapFunction<Long, Long>) value -> value + 1L,
                longEncoder);
        transformedDS.collect(); // Returns [2, 3, 4]

        // 读取文件转成dataset
        Dataset<Person> peopleDS = spark.read().json(jsonPath).as(personEncoder);
        peopleDS.show();
        // +----+-------+
        // | age|   name|
        // +----+-------+
        // |null|Michael|
        // |  30|   Andy|
        // |  19| Justin|
        // +----+-------+
    }

    /**
     * 非Bean的方式转换：rdd->DataFrame->Dataset
     * @param spark
     * @throws Exception
     */
    public static void rddToDataset(SparkSession spark) throws Exception{
        // 读取文件生成一个Person类型的RDD
        JavaRDD<Person> peopleRDD = spark.read()
                .textFile(txtPath)
                .javaRDD()
                .map(line -> {
                    String[] parts = line.split(",");
                    Person person = new Person();
                    person.setName(parts[0]);
                    person.setAge(Integer.parseInt(parts[1].trim()));
                    return person;
                });

        // RDD转成DataFrame
        Dataset<Row> peopleDF = spark.createDataFrame(peopleRDD, Person.class);
        // 把DataFrame注册为临时视图
        peopleDF.createOrReplaceTempView("people");

        // SQL语句可以通过spark提供的SQL方法来运行
        Dataset<Row> teenagersDF = spark.sql("SELECT name FROM people WHERE age BETWEEN 13 AND 19");

        // 结果中一行的列可以通过字段索引访问
        Encoder<String> stringEncoder = Encoders.STRING();
        Dataset<String> teenagerNamesByIndexDF = teenagersDF.map(
                (MapFunction<Row, String>) row -> "Name: " + row.getString(0),
                stringEncoder);
        teenagerNamesByIndexDF.show();
        // +------------+
        // |       value|
        // +------------+
        // |Name: Justin|
        // +------------+

        // 也可以通过字段名访问
        Dataset<String> teenagerNamesByFieldDF = teenagersDF.map(
                (MapFunction<Row, String>) row -> "Name: " + row.<String>getAs("name"),
                stringEncoder);
        teenagerNamesByFieldDF.show();
        // +------------+
        // |       value|
        // +------------+
        // |Name: Justin|
        // +------------+
    }

    /**
     * 非Bean的方式转换：rdd->DataFrame->Dataset
     * @param spark
     * @throws Exception
     */
    public static void rddToDataset2(SparkSession spark) throws Exception{
        // 创建RDD
        JavaRDD<String> peopleRDD = spark.sparkContext()
                .textFile(txtPath, 1)
                .toJavaRDD();
        // 字段字义
        String schemaString = "name age";
        // 根据schema的字符串生成schema
        List<StructField> fields = new ArrayList<>();
        for (String fieldName : schemaString.split(" ")) {
            StructField field = DataTypes.createStructField(fieldName, DataTypes.StringType, true);
            fields.add(field);
        }
        StructType schema = DataTypes.createStructType(fields);

        // 将RDD(people)的记录转换为视图的Row
        JavaRDD<Row> rowRDD = peopleRDD.map((Function<String, Row>) record -> {
            String[] attributes = record.split(",");
            return RowFactory.create(attributes[0], attributes[1].trim());
        });

        // 将schema应用于RDD，转为DataFrame
        Dataset<Row> peopleDataFrame = spark.createDataFrame(rowRDD, schema);

        // 使用DataFrame创建临时视图
        peopleDataFrame.createOrReplaceTempView("people");

        // SQL可以在使用dataframe创建的临时视图上运行
        Dataset<Row> results = spark.sql("SELECT name FROM people");

        // SQL查询的结果是dataframe，支持所有正常的RDD操作
        // 结果行的列可以通过字段索引或字段名称访问
        Dataset<String> namesDS = results.map(
                (MapFunction<Row, String>) row -> "Name: " + row.getString(0),
                Encoders.STRING());
        namesDS.show();
        // +-------------+
        // |        value|
        // +-------------+
        // |Name: Michael|
        // |   Name: Andy|
        // | Name: Justin|
        // +-------------+
    }

    public static void main(String[] args) throws Exception{
        Logger.getLogger("org.apache.spark").setLevel(Level.WARN);
        Logger.getLogger("org.apache.eclipse.jetty.server").setLevel(Level.OFF);

        //windows下调试spark需要使用https://github.com/steveloughran/winutils
        System.setProperty("hadoop.home.dir", "D:\\hadoop\\hadoop-3.3.1");
        System.setProperty("HADOOP_USER_NAME", "root");

        SparkSession spark = SparkSession
                .builder()
                .appName("SparkDataset")
                .master("local[*]")
                .getOrCreate();

        createDataFrame(spark);

        createDataset(spark);

        rddToDataset(spark);

        rddToDataset2(spark);

        spark.stop();
    }
}

参考自官方文档：https://spark.apache.org/docs/3.1.2/sql-getting-started.html

spark支持数据源：https://spark.apache.org/docs/3.1.2/sql-data-sources.html

spark sql语法相关：https://spark.apache.org/docs/3.1.2/sql-ref.html