入门指南

from pyspark.sql import SparkSession

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

import org.apache.spark.sql.SparkSession

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

import org.apache.spark.sql.SparkSession;

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

sparkR.session(appName = "R Spark SQL basic example", sparkConfig = list(spark.some.config.option = "some-value"))

# 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|
# +----+-------+

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|
// +----+-------+

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|
// +----+-------+

df <- read.json("examples/src/main/resources/people.json")

# Displays the content of the DataFrame
head(df)
##   age    name
## 1  NA Michael
## 2  30    Andy
## 3  19  Justin

# Another method to print the first few rows and optionally truncate the printing of long values
showDF(df)
## +----+-------+
## | age|   name|
## +----+-------+
## |null|Michael|
## |  30|   Andy|
## |  19| Justin|
## +----+-------+

# 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|
# +----+-----+

// 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|
// +----+-----+

// 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|
// +----+-----+

# Create the DataFrame
df <- read.json("examples/src/main/resources/people.json")

# Show the content of the DataFrame
head(df)
##   age    name
## 1  NA Michael
## 2  30    Andy
## 3  19  Justin


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

# Select only the "name" column
head(select(df, "name"))
##      name
## 1 Michael
## 2    Andy
## 3  Justin

# Select everybody, but increment the age by 1
head(select(df, df$name, df$age + 1))
##      name (age + 1.0)
## 1 Michael          NA
## 2    Andy          31
## 3  Justin          20

# Select people older than 21
head(where(df, df$age > 21))
##   age name
## 1  30 Andy

# Count people by age
head(count(groupBy(df, "age")))
##   age count
## 1  19     1
## 2  NA     1
## 3  30     1

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

sqlDF = spark.sql("SELECT * FROM people")
sqlDF.show()
# +----+-------+
# | age|   name|
# +----+-------+
# |null|Michael|
# |  30|   Andy|
# |  19| Justin|
# +----+-------+

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

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

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|
// +----+-------+

df <- sql("SELECT * FROM table")

# 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|
# +----+-------+

// 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|
// +----+-------+

// 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|
// +----+-------+

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|
// +----+-------+

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|
// +----+-------+

from pyspark.sql import Row

sc = spark.sparkContext

# Load a text file and convert each line to a Row.
lines = sc.textFile("examples/src/main/resources/people.txt")
parts = lines.map(lambda l: l.split(","))
people = parts.map(lambda p: Row(name=p[0], age=int(p[1])))

# Infer the schema, and register the DataFrame as a table.
schemaPeople = spark.createDataFrame(people)
schemaPeople.createOrReplaceTempView("people")

# SQL can be run over DataFrames that have been registered as a table.
teenagers = spark.sql("SELECT name FROM people WHERE age >= 13 AND age <= 19")

# The results of SQL queries are Dataframe objects.
# rdd returns the content as an :class:`pyspark.RDD` of :class:`Row`.
teenNames = teenagers.rdd.map(lambda p: "Name: " + p.name).collect()
for name in teenNames:
    print(name)
# Name: Justin

// For implicit conversions from RDDs to DataFrames
import spark.implicits._

// Create an RDD of Person objects from a text file, convert it to a Dataframe
val peopleDF = spark.sparkContext
  .textFile("examples/src/main/resources/people.txt")
  .map(_.split(","))
  .map(attributes => Person(attributes(0), attributes(1).trim.toInt))
  .toDF()
// Register the DataFrame as a temporary view
peopleDF.createOrReplaceTempView("people")

// SQL statements can be run by using the sql methods provided by Spark
val teenagersDF = spark.sql("SELECT name, age FROM people WHERE age BETWEEN 13 AND 19")

// The columns of a row in the result can be accessed by field index
teenagersDF.map(teenager => "Name: " + teenager(0)).show()
// +------------+
// |       value|
// +------------+
// |Name: Justin|
// +------------+

// or by field name
teenagersDF.map(teenager => "Name: " + teenager.getAs[String]("name")).show()
// +------------+
// |       value|
// +------------+
// |Name: Justin|
// +------------+

// No pre-defined encoders for Dataset[Map[K,V]], define explicitly
implicit val mapEncoder: Encoder[Map[String, Any]] =
  org.apache.spark.sql.Encoders.kryo[Map[String, Any]]
// Primitive types and case classes can be also defined as
// implicit val stringIntMapEncoder: Encoder[Map[String, Any]] = ExpressionEncoder()

// row.getValuesMap[T] retrieves multiple columns at once into a Map[String, T]
teenagersDF.map(teenager => teenager.getValuesMap[Any](List("name", "age"))).collect()
// Array(Map("name" -> "Justin", "age" -> 19))

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|
// +------------+

# Import data types
from pyspark.sql.types import StringType, StructType, StructField

sc = spark.sparkContext

# Load a text file and convert each line to a Row.
lines = sc.textFile("examples/src/main/resources/people.txt")
parts = lines.map(lambda l: l.split(","))
# Each line is converted to a tuple.
people = parts.map(lambda p: (p[0], p[1].strip()))

# The schema is encoded in a string.
schemaString = "name age"

fields = [StructField(field_name, StringType(), True) for field_name in schemaString.split()]
schema = StructType(fields)

# Apply the schema to the RDD.
schemaPeople = spark.createDataFrame(people, schema)

# Creates a temporary view using the DataFrame
schemaPeople.createOrReplaceTempView("people")

# SQL can be run over DataFrames that have been registered as a table.
results = spark.sql("SELECT name FROM people")

results.show()
# +-------+
# |   name|
# +-------+
# |Michael|
# |   Andy|
# | Justin|
# +-------+

import org.apache.spark.sql.{Encoder, Row}

import org.apache.spark.sql.types._

// Create an RDD
val peopleRDD = spark.sparkContext.textFile("examples/src/main/resources/people.txt")

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

// Generate the schema based on the string of schema
val fields = schemaString.split(" ")
  .map(fieldName => StructField(fieldName, StringType, nullable = true))
val schema = StructType(fields)

// Convert records of the RDD (people) to Rows
val rowRDD = peopleRDD
  .map(_.split(","))
  .map(attributes => Row(attributes(0), attributes(1).trim))

// Apply the schema to the RDD
val peopleDF = spark.createDataFrame(rowRDD, schema)

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

// SQL can be run over a temporary view created using DataFrames
val 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
results.map(attributes => "Name: " + attributes(0)).show()
// +-------------+
// |        value|
// +-------------+
// |Name: Michael|
// |   Name: Andy|
// | Name: Justin|
// +-------------+

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|
// +-------------+