簡介
Spark SQL提供了兩種方式用於將RDD轉換爲Dataset。
- 使用反射機制推斷RDD的數據結構
當spark應用可以推斷RDD數據結構時，可使用這種方式。這種基於反射的方法可以使代碼更簡潔有效。
- 通過編程接口構造一個數據結構，然後映射到RDD上
當spark應用無法推斷RDD數據結構時，可使用這種方式。
反射方式
- scala
// 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 = 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))- java
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|
// +------------+- python
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編程方式
- scala
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|
// +-------------+- java
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|
// +-------------+- python
# Import data types
from pyspark.sql.types import *
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|
# +-------+忠於技術，熱愛分享。歡迎關注公衆號：java大數據編程，瞭解更多技術內容。
