1.sparkSQL
import org.apache.spark.sql.catalyst.encoders.ExpressionEncoder
import org.apache.spark.sql.Encoder
import org.apache.spark.sql.Row
import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.types._
object SparkSQLExample {
// 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)
def main(args: Array[String]):Unit = {
val spark = SparkSession
.builder()
.master("local")
.appName("Spark SQL basic example")
.config("spark.some.config.option", "some-value")
.getOrCreate()
// For implicit conversions like converting RDDs to DataFrames
import spark.implicits._
// $example off:init_session$
runBasicDataFrameExample(spark)
runDatasetCreationExample(spark)
runInferSchemaExample(spark)
runProgrammaticSchemaExample(spark)
spark.stop()
}
private def runBasicDataFrameExample(spark: SparkSession): Unit = {
// $example on:create_df$
val df = spark.read.json("people.json")
// Displays the content of the DataFrame to stdout
df.show()
// +----+-------+
// | age| name|
// +----+-------+
// |null|Michael|
// | 30| Andy|
// | 19| Justin|
// +----+-------+
// $example off:create_df$
// $example on:untyped_ops$
// 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|
// +----+-----+
// $example off:untyped_ops$
// $example on:run_sql$
// 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|
// +----+-------+
// $example off:run_sql$
}
private def runDatasetCreationExample(spark: SparkSession): Unit = {
import spark.implicits._
// $example on:create_ds$
// 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 = "people.json"
val peopleDS = spark.read.json(path).as[Person]
peopleDS.show()
// +----+-------+
// | age| name|
// +----+-------+
// |null|Michael|
// | 30| Andy|
// | 19| Justin|
// +----+-------+
// $example off:create_ds$
}
private def runInferSchemaExample(spark: SparkSession): Unit = {
// $example on:schema_inferring$
// 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("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))
// $example off:schema_inferring$
}
private def runProgrammaticSchemaExample(spark: SparkSession): Unit = {
import spark.implicits._
// $example on:programmatic_schema$
// Create an RDD
val peopleRDD = spark.sparkContext.textFile("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|
// +-------------+
// $example off:programmatic_schema$
}
}
2.SQL查询
import org.apache.spark.sql.SparkSession
object SQLDataSourceExample {
case class Person(name: String, age: Long)
def main(args: Array[String]) {
val spark = SparkSession
.builder()
.master("local")
.appName("Spark SQL data sources example")
.config("spark.some.config.option", "some-value")
.getOrCreate()
runBasicDataSourceExample(spark)
runBasicParquetExample(spark)
runParquetSchemaMergingExample(spark)
runJsonDatasetExample(spark)
//runJdbcDatasetExample(spark)
spark.stop()
}
private def runBasicDataSourceExample(spark: SparkSession): Unit = {
// $example on:generic_load_save_functions$
val usersDF = spark.read.load("users.parquet")
usersDF.select("name", "favorite_color").write.save("namesAndFavColors.parquet")
// $example off:generic_load_save_functions$
// $example on:manual_load_options$
val peopleDF = spark.read.format("json").load("people.json")
peopleDF.select("name", "age").write.format("parquet").save("namesAndAges.parquet")
// $example off:manual_load_options$
// $example on:direct_sql$
val sqlDF = spark.sql("SELECT * FROM parquet.`users.parquet`")
// $example off:direct_sql$
}
private def runBasicParquetExample(spark: SparkSession): Unit = {
// $example on:basic_parquet_example$
// Encoders for most common types are automatically provided by importing spark.implicits._
import spark.implicits._
val peopleDF = spark.read.json("people.json")
// DataFrames can be saved as Parquet files, maintaining the schema information
peopleDF.write.parquet("people.parquet")
// Read in the parquet file created above
// Parquet files are self-describing so the schema is preserved
// The result of loading a Parquet file is also a DataFrame
val parquetFileDF = spark.read.parquet("people.parquet")
// Parquet files can also be used to create a temporary view and then used in SQL statements
parquetFileDF.createOrReplaceTempView("parquetFile")
val namesDF = spark.sql("SELECT name FROM parquetFile WHERE age BETWEEN 13 AND 19")
namesDF.map(attributes => "Name: " + attributes(0)).show()
// +------------+
// | value|
// +------------+
// |Name: Justin|
// +------------+
// $example off:basic_parquet_example$
}
private def runParquetSchemaMergingExample(spark: SparkSession): Unit = {
// $example on:schema_merging$
// This is used to implicitly convert an RDD to a DataFrame.
import spark.implicits._
// Create a simple DataFrame, store into a partition directory
val squaresDF = spark.sparkContext.makeRDD(1 to 5).map(i => (i, i * i)).toDF("value", "square")
squaresDF.write.parquet("data/test_table/key=1")
// Create another DataFrame in a new partition directory,
// adding a new column and dropping an existing column
val cubesDF = spark.sparkContext.makeRDD(6 to 10).map(i => (i, i * i * i)).toDF("value", "cube")
cubesDF.write.parquet("data/test_table/key=2")
// Read the partitioned table
val mergedDF = spark.read.option("mergeSchema", "true").parquet("data/test_table")
mergedDF.printSchema()
// The final schema consists of all 3 columns in the Parquet files together
// with the partitioning column appeared in the partition directory paths
// root
// |-- value: int (nullable = true)
// |-- square: int (nullable = true)
// |-- cube: int (nullable = true)
// |-- key: int (nullable = true)
// $example off:schema_merging$
}
private def runJsonDatasetExample(spark: SparkSession): Unit = {
// $example on:json_dataset$
// A JSON dataset is pointed to by path.
// The path can be either a single text file or a directory storing text files
val path = "people.json"
val peopleDF = spark.read.json(path)
// The inferred schema can be visualized using the printSchema() method
peopleDF.printSchema()
// root
// |-- age: long (nullable = true)
// |-- name: string (nullable = true)
// Creates a temporary view using the DataFrame
peopleDF.createOrReplaceTempView("people")
// SQL statements can be run by using the sql methods provided by spark
val teenagerNamesDF = spark.sql("SELECT name FROM people WHERE age BETWEEN 13 AND 19")
teenagerNamesDF.show()
// +------+
// | name|
// +------+
// |Justin|
// +------+
// Alternatively, a DataFrame can be created for a JSON dataset represented by
// an RDD[String] storing one JSON object per string
val otherPeopleRDD = spark.sparkContext.makeRDD(
"""{"name":"Yin","address":{"city":"Columbus","state":"Ohio"}}""" :: Nil)
val otherPeople = spark.read.json(otherPeopleRDD)
otherPeople.show()
// +---------------+----+
// | address|name|
// +---------------+----+
// |[Columbus,Ohio]| Yin|
// +---------------+----+
// $example off:json_dataset$
}
private def runJdbcDatasetExample(spark: SparkSession): Unit = {
// $example on:jdbc_dataset$
val jdbcDF = spark.read
.format("jdbc")
.option("url", "jdbc:postgresql:dbserver")
.option("dbtable", "schema.tablename")
.option("user", "username")
.option("password", "password")
.load()
// $example off:jdbc_dataset$
}
}