SQLContext

Instance Constructors

new SQLContext(sparkContext: JavaSparkContext)
new SQLContext(sc: SparkContext)

Value Members

final def !=(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def ##(): Int

Definition Classes
AnyRef → Any
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def applySchemaToPythonRDD(rdd: RDD[Array[Any]], schema: StructType): DataFrame

Apply a schema defined by the schema to an RDD.
Apply a schema defined by the schema to an RDD. It is only used by PySpark.

Attributes
protected[org.apache.spark.sql]
def applySchemaToPythonRDD(rdd: RDD[Array[Any]], schemaString: String): DataFrame

Apply a schema defined by the schemaString to an RDD.
Apply a schema defined by the schemaString to an RDD. It is only used by PySpark.

Attributes
protected[org.apache.spark.sql]
final def asInstanceOf[T0]: T0

Definition Classes
Any
def baseRelationToDataFrame(baseRelation: BaseRelation): DataFrame

Convert a BaseRelation created for external data sources into a DataFrame.
Convert a BaseRelation created for external data sources into a DataFrame.

Since
1.3.0
def cacheManager: CacheManager

Attributes
protected[org.apache.spark.sql]
def cacheTable(tableName: String): Unit

Caches the specified table in-memory.
Caches the specified table in-memory.

Since
1.3.0
def clearCache(): Unit

Removes all cached tables from the in-memory cache.
Removes all cached tables from the in-memory cache.

Since
1.3.0
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
def conf: SQLConf

Attributes
protected[org.apache.spark.sql]
def createDataFrame(data: List[_], beanClass: Class[_]): DataFrame

Applies a schema to an List of Java Beans.
Applies a schema to an List of Java Beans.
WARNING: Since there is no guaranteed ordering for fields in a Java Bean, SELECT * queries will return the columns in an undefined order.

Since
1.6.0
def createDataFrame(rdd: JavaRDD[_], beanClass: Class[_]): DataFrame

Applies a schema to an RDD of Java Beans.
Applies a schema to an RDD of Java Beans.
WARNING: Since there is no guaranteed ordering for fields in a Java Bean, SELECT * queries will return the columns in an undefined order.

Since
1.3.0
def createDataFrame(rdd: RDD[_], beanClass: Class[_]): DataFrame

Applies a schema to an RDD of Java Beans.
Applies a schema to an RDD of Java Beans.
WARNING: Since there is no guaranteed ordering for fields in a Java Bean, SELECT * queries will return the columns in an undefined order.

Since
1.3.0
def createDataFrame(rows: List[Row], schema: StructType): DataFrame

:: DeveloperApi :: Creates a DataFrame from an java.util.List containing Rows using the given schema.
:: DeveloperApi :: Creates a DataFrame from an java.util.List containing Rows using the given schema. It is important to make sure that the structure of every Row of the provided List matches the provided schema. Otherwise, there will be runtime exception.

Annotations
@DeveloperApi()
Since
1.6.0
def createDataFrame(rowRDD: JavaRDD[Row], schema: StructType): DataFrame

:: DeveloperApi :: Creates a DataFrame from an JavaRDD containing Rows using the given schema.
:: DeveloperApi :: Creates a DataFrame from an JavaRDD containing Rows using the given schema. It is important to make sure that the structure of every Row of the provided RDD matches the provided schema. Otherwise, there will be runtime exception.

Annotations
@DeveloperApi()
Since
1.3.0

def createDataFrame(rowRDD: RDD[Row], schema: StructType): DataFrame

:: DeveloperApi :: Creates a DataFrame from an RDD containing Rows using the given schema.

:: DeveloperApi :: Creates a DataFrame from an RDD containing Rows using the given schema. It is important to make sure that the structure of every Row of the provided RDD matches the provided schema. Otherwise, there will be runtime exception. Example:

import org.apache.spark.sql._
import org.apache.spark.sql.types._
val sqlContext = new org.apache.spark.sql.SQLContext(sc)

val schema =
  StructType(
    StructField("name", StringType, false) ::
    StructField("age", IntegerType, true) :: Nil)

val people =
  sc.textFile("examples/src/main/resources/people.txt").map(
    _.split(",")).map(p => Row(p(0), p(1).trim.toInt))
val dataFrame = sqlContext.createDataFrame(people, schema)
dataFrame.printSchema
// root
// |-- name: string (nullable = false)
// |-- age: integer (nullable = true)

dataFrame.createOrReplaceTempView("people")
sqlContext.sql("select name from people").collect.foreach(println)

Annotations: @DeveloperApi()
Since: 1.3.0

def createDataFrame[A <: Product](data: Seq[A])(implicit arg0: scala.reflect.api.JavaUniverse.TypeTag[A]): DataFrame

:: Experimental :: Creates a DataFrame from a local Seq of Product.
:: Experimental :: Creates a DataFrame from a local Seq of Product.

Annotations
@Experimental()
Since
1.3.0
def createDataFrame[A <: Product](rdd: RDD[A])(implicit arg0: scala.reflect.api.JavaUniverse.TypeTag[A]): DataFrame

:: Experimental :: Creates a DataFrame from an RDD of Product (e.g.
:: Experimental :: Creates a DataFrame from an RDD of Product (e.g. case classes, tuples).

Annotations
@Experimental()
Since
1.3.0
def createDataset[T](data: List[T])(implicit arg0: Encoder[T]): Dataset[T]
def createDataset[T](data: RDD[T])(implicit arg0: Encoder[T]): Dataset[T]
def createDataset[T](data: Seq[T])(implicit arg0: Encoder[T]): Dataset[T]
def createExternalTable(tableName: String, source: String, schema: StructType, options: Map[String, String]): DataFrame

:: Experimental :: (Scala-specific) Create an external table from the given path based on a data source, a schema and a set of options.
:: Experimental :: (Scala-specific) Create an external table from the given path based on a data source, a schema and a set of options. Then, returns the corresponding DataFrame.

Annotations
@Experimental()
Since
1.3.0
def createExternalTable(tableName: String, source: String, schema: StructType, options: Map[String, String]): DataFrame

:: Experimental :: Create an external table from the given path based on a data source, a schema and a set of options.
:: Experimental :: Create an external table from the given path based on a data source, a schema and a set of options. Then, returns the corresponding DataFrame.

Annotations
@Experimental()
Since
1.3.0
def createExternalTable(tableName: String, source: String, options: Map[String, String]): DataFrame

:: Experimental :: (Scala-specific) Creates an external table from the given path based on a data source and a set of options.
:: Experimental :: (Scala-specific) Creates an external table from the given path based on a data source and a set of options. Then, returns the corresponding DataFrame.

Annotations
@Experimental()
Since
1.3.0
def createExternalTable(tableName: String, source: String, options: Map[String, String]): DataFrame

:: Experimental :: Creates an external table from the given path based on a data source and a set of options.
:: Experimental :: Creates an external table from the given path based on a data source and a set of options. Then, returns the corresponding DataFrame.

Annotations
@Experimental()
Since
1.3.0
def createExternalTable(tableName: String, path: String, source: String): DataFrame

:: Experimental :: Creates an external table from the given path based on a data source and returns the corresponding DataFrame.
:: Experimental :: Creates an external table from the given path based on a data source and returns the corresponding DataFrame.

Annotations
@Experimental()
Since
1.3.0
def createExternalTable(tableName: String, path: String): DataFrame

:: Experimental :: Creates an external table from the given path and returns the corresponding DataFrame.
:: Experimental :: Creates an external table from the given path and returns the corresponding DataFrame. It will use the default data source configured by spark.sql.sources.default.

Annotations
@Experimental()
Since
1.3.0
def dropTempTable(tableName: String): Unit

Drops the temporary table with the given table name in the catalog.
Drops the temporary table with the given table name in the catalog. If the table has been cached/persisted before, it's also unpersisted.
tableName
the name of the table to be unregistered.

Since
1.3.0
def emptyDataFrame: DataFrame

:: Experimental :: Returns a DataFrame with no rows or columns.
:: Experimental :: Returns a DataFrame with no rows or columns.

Annotations
@Experimental()
Since
1.3.0
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def executePlan(plan: LogicalPlan): QueryExecution

Attributes
protected[org.apache.spark.sql]
def executeSql(sql: String): QueryExecution

Attributes
protected[org.apache.spark.sql]
def experimental: ExperimentalMethods

:: Experimental :: A collection of methods that are considered experimental, but can be used to hook into the query planner for advanced functionality.
:: Experimental :: A collection of methods that are considered experimental, but can be used to hook into the query planner for advanced functionality.

Annotations
@Experimental() @transient()
Since
1.3.0
def externalCatalog: ExternalCatalog

Attributes
protected[org.apache.spark.sql]
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
def getAllConfs: Map[String, String]

Return all the configuration properties that have been set (i.e.
Return all the configuration properties that have been set (i.e. not the default). This creates a new copy of the config properties in the form of a Map.

Since
1.0.0
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
def getConf(key: String, defaultValue: String): String

Return the value of Spark SQL configuration property for the given key.
Return the value of Spark SQL configuration property for the given key. If the key is not set yet, return defaultValue.

Since
1.0.0
def getConf(key: String): String

Return the value of Spark SQL configuration property for the given key.
Return the value of Spark SQL configuration property for the given key.

Since
1.0.0
def hashCode(): Int

Definition Classes
AnyRef → Any
object implicits extends SQLImplicits with Serializable

:: Experimental :: (Scala-specific) Implicit methods available in Scala for converting common Scala objects into DataFrames.
:: Experimental :: (Scala-specific) Implicit methods available in Scala for converting common Scala objects into DataFrames.
```
val sqlContext = new SQLContext(sc)
import sqlContext.implicits._
```
Annotations
@Experimental()
Since
1.3.0
def initializeLogIfNecessary(isInterpreter: Boolean): Unit

Attributes
protected
Definition Classes
Logging
def isCached(tableName: String): Boolean

Returns true if the table is currently cached in-memory.
Returns true if the table is currently cached in-memory.

Since
1.3.0
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
val isRootContext: Boolean
def isTraceEnabled(): Boolean

Attributes
protected
Definition Classes
Logging
def listener: SQLListener

Attributes
protected[org.apache.spark.sql]
def listenerManager: ExecutionListenerManager

An interface to register custom org.apache.spark.sql.util.QueryExecutionListeners that listen for execution metrics.
An interface to register custom org.apache.spark.sql.util.QueryExecutionListeners that listen for execution metrics.

Annotations
@Experimental()
def log: Logger

Attributes
protected
Definition Classes
Logging
def logDebug(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logDebug(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logError(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logError(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logInfo(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logInfo(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logName: String

Attributes
protected
Definition Classes
Logging
def logTrace(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logTrace(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logWarning(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logWarning(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def newSession(): SQLContext

Returns a SQLContext as new session, with separated SQL configurations, temporary tables, registered functions, but sharing the same SparkContext, cached data and other things.
Returns a SQLContext as new session, with separated SQL configurations, temporary tables, registered functions, but sharing the same SparkContext, cached data and other things.

Since
1.6.0
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
def parseDataType(dataTypeString: String): DataType

Parses the data type in our internal string representation.
Parses the data type in our internal string representation. The data type string should have the same format as the one generated by toString in scala. It is only used by PySpark.

Attributes
protected[org.apache.spark.sql]
def parseSql(sql: String): LogicalPlan

Attributes
protected[org.apache.spark.sql]
def range(start: Long, end: Long, step: Long, numPartitions: Int): Dataset[Long]

:: Experimental :: Creates a Dataset with a single LongType column named id, containing elements in an range from start to end (exclusive) with an step value, with partition number specified.
:: Experimental :: Creates a Dataset with a single LongType column named id, containing elements in an range from start to end (exclusive) with an step value, with partition number specified.

Annotations
@Experimental()
Since
2.0.0
def range(start: Long, end: Long, step: Long): Dataset[Long]

:: Experimental :: Creates a Dataset with a single LongType column named id, containing elements in an range from start to end (exclusive) with an step value.
:: Experimental :: Creates a Dataset with a single LongType column named id, containing elements in an range from start to end (exclusive) with an step value.

Annotations
@Experimental()
Since
2.0.0
def range(start: Long, end: Long): Dataset[Long]

:: Experimental :: Creates a Dataset with a single LongType column named id, containing elements in an range from start to end (exclusive) with step value 1.
:: Experimental :: Creates a Dataset with a single LongType column named id, containing elements in an range from start to end (exclusive) with step value 1.

Annotations
@Experimental()
Since
2.0.0
def range(end: Long): Dataset[Long]

:: Experimental :: Creates a Dataset with a single LongType column named id, containing elements in an range from 0 to end (exclusive) with step value 1.
:: Experimental :: Creates a Dataset with a single LongType column named id, containing elements in an range from 0 to end (exclusive) with step value 1.

Annotations
@Experimental()
Since
2.0.0
def read: DataFrameReader

:: Experimental :: Returns a DataFrameReader that can be used to read data and streams in as a DataFrame.
:: Experimental :: Returns a DataFrameReader that can be used to read data and streams in as a DataFrame.
```
sqlContext.read.parquet("/path/to/file.parquet")
sqlContext.read.schema(schema).json("/path/to/file.json")
```
Annotations
@Experimental()
Since
1.4.0
def runtimeConf: RuntimeConfig

Attributes
protected[org.apache.spark.sql]
def sessionState: SessionState

Attributes
protected[org.apache.spark.sql]
def setConf(key: String, value: String): Unit

Set the given Spark SQL configuration property.
Set the given Spark SQL configuration property.

Since
1.0.0
def setConf(props: Properties): Unit

Set Spark SQL configuration properties.
Set Spark SQL configuration properties.

Since
1.0.0
def sharedState: SharedState

Attributes
protected[org.apache.spark.sql]
def sparkContext: SparkContext
val sparkSession: SparkSession
def sql(sqlText: String): DataFrame

Executes a SQL query using Spark, returning the result as a DataFrame.
Executes a SQL query using Spark, returning the result as a DataFrame. The dialect that is used for SQL parsing can be configured with 'spark.sql.dialect'.

Since
1.3.0
def streams: ContinuousQueryManager

Returns a ContinuousQueryManager that allows managing all the ContinuousQueries active on this context.
Returns a ContinuousQueryManager that allows managing all the ContinuousQueries active on this context.

Since
2.0.0
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def table(tableName: String): DataFrame

Returns the specified table as a DataFrame.
Returns the specified table as a DataFrame.

Since
1.3.0
def tableNames(databaseName: String): Array[String]

Returns the names of tables in the given database as an array.
Returns the names of tables in the given database as an array.

Since
1.3.0
def tableNames(): Array[String]

Returns the names of tables in the current database as an array.
Returns the names of tables in the current database as an array.

Since
1.3.0
def tables(databaseName: String): DataFrame

Returns a DataFrame containing names of existing tables in the given database.
Returns a DataFrame containing names of existing tables in the given database. The returned DataFrame has two columns, tableName and isTemporary (a Boolean indicating if a table is a temporary one or not).

Since
1.3.0
def tables(): DataFrame

Returns a DataFrame containing names of existing tables in the current database.
Returns a DataFrame containing names of existing tables in the current database. The returned DataFrame has two columns, tableName and isTemporary (a Boolean indicating if a table is a temporary one or not).

Since
1.3.0
def toString(): String

Definition Classes
AnyRef → Any

def udf: UDFRegistration

A collection of methods for registering user-defined functions (UDF).

The following example registers a Scala closure as UDF:

sqlContext.udf.register("myUDF", (arg1: Int, arg2: String) => arg2 + arg1)

The following example registers a UDF in Java:

sqlContext.udf().register("myUDF",
    new UDF2<Integer, String, String>() {
        @Override
        public String call(Integer arg1, String arg2) {
            return arg2 + arg1;
        }
   }, DataTypes.StringType);

Or, to use Java 8 lambda syntax:

sqlContext.udf().register("myUDF",
    (Integer arg1, String arg2) -> arg2 + arg1,
    DataTypes.StringType);

Since: 1.3.0

def uncacheTable(tableName: String): Unit

Removes the specified table from the in-memory cache.
Removes the specified table from the in-memory cache.

Since
1.3.0
final def wait(): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long, arg1: Int): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )

Related Docs: object SQLContext | package sql

class SQLContext extends Logging with Serializable

Instance Constructors

new SQLContext(sparkContext: JavaSparkContext)

new SQLContext(sc: SparkContext)

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

def applySchemaToPythonRDD(rdd: RDD[Array[Any]], schema: StructType): DataFrame

def applySchemaToPythonRDD(rdd: RDD[Array[Any]], schemaString: String): DataFrame

final def asInstanceOf[T0]: T0

def baseRelationToDataFrame(baseRelation: BaseRelation): DataFrame

def cacheManager: CacheManager

def cacheTable(tableName: String): Unit

def clearCache(): Unit

def clone(): AnyRef

def conf: SQLConf

def createDataFrame(data: List[_], beanClass: Class[_]): DataFrame

def createDataFrame(rdd: JavaRDD[_], beanClass: Class[_]): DataFrame

def createDataFrame(rdd: RDD[_], beanClass: Class[_]): DataFrame

def createDataFrame(rows: List[Row], schema: StructType): DataFrame

def createDataFrame(rowRDD: JavaRDD[Row], schema: StructType): DataFrame

def createDataFrame(rowRDD: RDD[Row], schema: StructType): DataFrame

def createDataFrame[A <: Product](data: Seq[A])(implicit arg0: scala.reflect.api.JavaUniverse.TypeTag[A]): DataFrame

def createDataFrame[A <: Product](rdd: RDD[A])(implicit arg0: scala.reflect.api.JavaUniverse.TypeTag[A]): DataFrame

def createDataset[T](data: List[T])(implicit arg0: Encoder[T]): Dataset[T]

def createDataset[T](data: RDD[T])(implicit arg0: Encoder[T]): Dataset[T]

def createDataset[T](data: Seq[T])(implicit arg0: Encoder[T]): Dataset[T]

def createExternalTable(tableName: String, source: String, schema: StructType, options: Map[String, String]): DataFrame

def createExternalTable(tableName: String, source: String, schema: StructType, options: Map[String, String]): DataFrame

def createExternalTable(tableName: String, source: String, options: Map[String, String]): DataFrame

def createExternalTable(tableName: String, source: String, options: Map[String, String]): DataFrame

def createExternalTable(tableName: String, path: String, source: String): DataFrame

def createExternalTable(tableName: String, path: String): DataFrame

def dropTempTable(tableName: String): Unit

def emptyDataFrame: DataFrame

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def executePlan(plan: LogicalPlan): QueryExecution

def executeSql(sql: String): QueryExecution

def experimental: ExperimentalMethods

def externalCatalog: ExternalCatalog

def finalize(): Unit

def getAllConfs: Map[String, String]

final def getClass(): Class[_]

def getConf(key: String, defaultValue: String): String

def getConf(key: String): String

def hashCode(): Int

object implicits extends SQLImplicits with Serializable

def initializeLogIfNecessary(isInterpreter: Boolean): Unit

def isCached(tableName: String): Boolean

final def isInstanceOf[T0]: Boolean

val isRootContext: Boolean

def isTraceEnabled(): Boolean

def listener: SQLListener

def listenerManager: ExecutionListenerManager

def log: Logger

def logDebug(msg: ⇒ String, throwable: Throwable): Unit

def logDebug(msg: ⇒ String): Unit

def logError(msg: ⇒ String, throwable: Throwable): Unit

def logError(msg: ⇒ String): Unit

def logInfo(msg: ⇒ String, throwable: Throwable): Unit

def logInfo(msg: ⇒ String): Unit

def logName: String

def logTrace(msg: ⇒ String, throwable: Throwable): Unit

def logTrace(msg: ⇒ String): Unit

def logWarning(msg: ⇒ String, throwable: Throwable): Unit

def logWarning(msg: ⇒ String): Unit

final def ne(arg0: AnyRef): Boolean

def newSession(): SQLContext

final def notify(): Unit

final def notifyAll(): Unit

def parseDataType(dataTypeString: String): DataType

def parseSql(sql: String): LogicalPlan

def range(start: Long, end: Long, step: Long, numPartitions: Int): Dataset[Long]

def range(start: Long, end: Long, step: Long): Dataset[Long]

def range(start: Long, end: Long): Dataset[Long]

def range(end: Long): Dataset[Long]