import org.apache.spark.sql.SparkSession
// 构造SparkSession
val spark = SparkSession
.builder()
.appName("Spark SQL basic example")
.config("spark.some.config.option", "some-value")
.getOrCreate()
// 创建DataFrame
val 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|
// +----+-------+
// DataFrame操作
// This import is needed to use the $-notation
import spark.implicits._
// Print the schema in a tree format
df.printSchema()
// root
// |-- age: long (nullable = true)
// |-- name: string (nullable = true)
// Select only the "name" column
df.select("name").show()
// +-------+
// | name|
// +-------+
// |Michael|
// | Andy|
// | Justin|
// +-------+
// Select everybody, but increment the age by 1
df.select($"name", $"age" + 1).show()
// +-------+---------+
// | name|(age + 1)|
// +-------+---------+
// |Michael| null|
// | Andy| 31|
// | Justin| 20|
// +-------+---------+
// Select people older than 21
df.filter($"age" > 21).show()
// +---+----+
// |age|name|
// +---+----+
// | 30|Andy|
// +---+----+
// Count people by age
df.groupBy("age").count().show()
// +----+-----+
// | age|count|
// +----+-----+
// | 19| 1|
// |null| 1|
// | 30| 1|
// +----+-----+
java
import org.apache.spark.sql.SparkSession;
//构造SparkSession
SparkSession spark = SparkSession
.builder()
.appName("Java Spark SQL basic example")
.config("spark.some.config.option", "some-value")
.getOrCreate();
//创建DataFrame
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
Dataset 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|
// +----+-------+
//DataFrame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|
// +----+-----+
python
from pyspark.sql import SparkSession
# 构造SparkSession
spark = SparkSession \
.builder \
.appName("Python Spark SQL basic example") \
.config("spark.some.config.option", "some-value") \
.getOrCreate()
# 创建DataFrame
# spark is an existing SparkSession
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|
# +----+-------+
# DataFrame操作
# spark, df are from the previous example
# 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(df['name'], df['age'] + 1).show()
# +-------+---------+
# | name|(age + 1)|
# +-------+---------+
# |Michael| null|
# | Andy| 31|
# | Justin| 20|
# +-------+---------+
# Select people older than 21
df.filter(df['age'] > 21).show()
# +---+----+
# |age|name|
# +---+----+
# | 30|Andy|
# +---+----+
# Count people by age
df.groupBy("age").count().show()
# +----+-----+
# | age|count|
# +----+-----+
# | 19| 1|
# |null| 1|
# | 30| 1|
# +----+-----+ DataSet创建及操作
Datasets和RDD类似,但使用专门的Encoder编码器来序列化需要经过网络传输的数据对象,而不用RDD使用的Java序列化或Kryo库。Encoder编码器是动态生成的代码,允许直接执行各种算子操作,而不用反序列化。
scala
// Note: Case classes in Scala 2.10 can support only up to 22 fields. To work around this limit,
// you can use custom classes that implement the Product interface
case class Person(name: String, age: Long)
// Encoders are created for case classes
val caseClassDS = Seq(Person("Andy", 32)).toDS()
caseClassDS.show()
// +----+---+
// |name|age|
// +----+---+
// |Andy| 32|
// +----+---+
// Encoders for most common types are automatically provided by importing spark.implicits._
val primitiveDS = Seq(1, 2, 3).toDS()
primitiveDS.map(_ + 1).collect() // Returns: Array(2, 3, 4)
// DataFrames can be converted to a Dataset by providing a class. Mapping will be done by name
val path = "examples/src/main/resources/people.json"
val peopleDS = spark.read.json(path).as[Person]
peopleDS.show()
// +----+-------+
// | age| name|
// +----+-------+
// |null|Michael|
// | 30| Andy|
// | 19| Justin|
// +----+-------+
java
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 int age;
public String getName() {
return name;
}
public void setName(String name) {
this.name = name;
}
public int getAge() {
return age;
}
public void setAge(int 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 personEncoder = Encoders.bean(Person.class);
Dataset javaBeanDS = spark.createDataset(
Collections.singletonList(person),
personEncoder
);
javaBeanDS.show();
// +---+----+
// |age|name|
// +---+----+
// | 32|Andy|
// +---+----+
// Encoders for most common types are provided in class Encoders
Encoder integerEncoder = Encoders.INT();
Dataset primitiveDS = spark.createDataset(Arrays.asList(1, 2, 3), integerEncoder);
Dataset transformedDS = primitiveDS.map(
(MapFunction) value -> value + 1,
integerEncoder);
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 peopleDS = spark.read().json(path).as(personEncoder);
peopleDS.show();
// +----+-------+
// | age| name|
// +----+-------+
// |null|Michael|
// | 30| Andy|
// | 19| Justin|
// +----+-------+ SQL操作
scala
// Register the DataFrame as a SQL temporary view
df.createOrReplaceTempView("people")
//df.createGlobalTempView("people")
val sqlDF = spark.sql("SELECT * FROM people")
sqlDF.show()
// +----+-------+
// | age| name|
// +----+-------+
// |null|Michael|
// | 30| Andy|
// | 19| Justin|
// +----+-------+