public class HadoopRDD<K,V> extends RDD<scala.Tuple2<K,V>>
org.apache.hadoop.mapred
).
Note: Instantiating this class directly is not recommended, please use
org.apache.spark.SparkContext.hadoopRDD()
param: sc The SparkContext to associate the RDD with. param: broadcastedConf A general Hadoop Configuration, or a subclass of it. If the enclosed variable references an instance of JobConf, then that JobConf will be used for the Hadoop job. Otherwise, a new JobConf will be created on each slave using the enclosed Configuration. param: initLocalJobConfFuncOpt Optional closure used to initialize any JobConf that HadoopRDD creates. param: inputFormatClass Storage format of the data to be read. param: keyClass Class of the key associated with the inputFormatClass. param: valueClass Class of the value associated with the inputFormatClass. param: minPartitions Minimum number of HadoopRDD partitions (Hadoop Splits) to generate.
Modifier and Type | Class and Description |
---|---|
static class |
HadoopRDD.HadoopMapPartitionsWithSplitRDD$ |
Constructor and Description |
---|
HadoopRDD(SparkContext sc,
Broadcast<org.apache.spark.util.SerializableConfiguration> broadcastedConf,
scala.Option<scala.Function1<org.apache.hadoop.mapred.JobConf,scala.runtime.BoxedUnit>> initLocalJobConfFuncOpt,
java.lang.Class<? extends org.apache.hadoop.mapred.InputFormat<K,V>> inputFormatClass,
java.lang.Class<K> keyClass,
java.lang.Class<V> valueClass,
int minPartitions) |
HadoopRDD(SparkContext sc,
org.apache.hadoop.mapred.JobConf conf,
java.lang.Class<? extends org.apache.hadoop.mapred.InputFormat<K,V>> inputFormatClass,
java.lang.Class<K> keyClass,
java.lang.Class<V> valueClass,
int minPartitions) |
Modifier and Type | Method and Description |
---|---|
static RDD<T> |
$plus$plus(RDD<T> other) |
static void |
addLocalConfiguration(java.lang.String jobTrackerId,
int jobId,
int splitId,
int attemptId,
org.apache.hadoop.mapred.JobConf conf)
Add Hadoop configuration specific to a single partition and attempt.
|
static <U> U |
aggregate(U zeroValue,
scala.Function2<U,T,U> seqOp,
scala.Function2<U,U,U> combOp,
scala.reflect.ClassTag<U> evidence$29) |
static RDD<T> |
cache() |
static <U> RDD<scala.Tuple2<T,U>> |
cartesian(RDD<U> other,
scala.reflect.ClassTag<U> evidence$5) |
void |
checkpoint()
Mark this RDD for checkpointing.
|
protected static void |
clearDependencies() |
static RDD<T> |
coalesce(int numPartitions,
boolean shuffle,
scala.Option<PartitionCoalescer> partitionCoalescer,
scala.math.Ordering<T> ord) |
static boolean |
coalesce$default$2() |
static scala.Option<PartitionCoalescer> |
coalesce$default$3() |
static scala.math.Ordering<T> |
coalesce$default$4(int numPartitions,
boolean shuffle,
scala.Option<PartitionCoalescer> partitionCoalescer) |
static java.lang.Object |
collect() |
static <U> RDD<U> |
collect(scala.PartialFunction<T,U> f,
scala.reflect.ClassTag<U> evidence$28) |
InterruptibleIterator<scala.Tuple2<K,V>> |
compute(Partition theSplit,
TaskContext context)
:: DeveloperApi ::
Implemented by subclasses to compute a given partition.
|
static java.lang.Object |
CONFIGURATION_INSTANTIATION_LOCK()
Configuration's constructor is not threadsafe (see SPARK-1097 and HADOOP-10456).
|
static boolean |
containsCachedMetadata(java.lang.String key) |
static SparkContext |
context() |
static long |
count() |
static PartialResult<BoundedDouble> |
countApprox(long timeout,
double confidence) |
static double |
countApprox$default$2() |
static long |
countApproxDistinct(double relativeSD) |
static long |
countApproxDistinct(int p,
int sp) |
static double |
countApproxDistinct$default$1() |
static scala.collection.Map<T,java.lang.Object> |
countByValue(scala.math.Ordering<T> ord) |
static scala.math.Ordering<T> |
countByValue$default$1() |
static PartialResult<scala.collection.Map<T,BoundedDouble>> |
countByValueApprox(long timeout,
double confidence,
scala.math.Ordering<T> ord) |
static double |
countByValueApprox$default$2() |
static scala.math.Ordering<T> |
countByValueApprox$default$3(long timeout,
double confidence) |
static scala.collection.Seq<Dependency<?>> |
dependencies() |
static RDD<T> |
distinct() |
static RDD<T> |
distinct(int numPartitions,
scala.math.Ordering<T> ord) |
static scala.math.Ordering<T> |
distinct$default$2(int numPartitions) |
static RDD<T> |
filter(scala.Function1<T,java.lang.Object> f) |
static T |
first() |
protected static <U> RDD<U> |
firstParent(scala.reflect.ClassTag<U> evidence$31) |
static <U> RDD<U> |
flatMap(scala.Function1<T,scala.collection.TraversableOnce<U>> f,
scala.reflect.ClassTag<U> evidence$4) |
static T |
fold(T zeroValue,
scala.Function2<T,T,T> op) |
static void |
foreach(scala.Function1<T,scala.runtime.BoxedUnit> f) |
static void |
foreachPartition(scala.Function1<scala.collection.Iterator<T>,scala.runtime.BoxedUnit> f) |
static java.lang.Object |
getCachedMetadata(java.lang.String key)
The three methods below are helpers for accessing the local map, a property of the SparkEnv of
the local process.
|
static scala.Option<java.lang.String> |
getCheckpointFile() |
org.apache.hadoop.conf.Configuration |
getConf() |
protected static scala.collection.Seq<Dependency<?>> |
getDependencies() |
protected org.apache.hadoop.mapred.InputFormat<K,V> |
getInputFormat(org.apache.hadoop.mapred.JobConf conf) |
protected org.apache.hadoop.mapred.JobConf |
getJobConf() |
static int |
getNumPartitions() |
Partition[] |
getPartitions()
Implemented by subclasses to return the set of partitions in this RDD.
|
scala.collection.Seq<java.lang.String> |
getPreferredLocations(Partition split)
Optionally overridden by subclasses to specify placement preferences.
|
static StorageLevel |
getStorageLevel() |
static RDD<java.lang.Object> |
glom() |
static <K> RDD<scala.Tuple2<K,scala.collection.Iterable<T>>> |
groupBy(scala.Function1<T,K> f,
scala.reflect.ClassTag<K> kt) |
static <K> RDD<scala.Tuple2<K,scala.collection.Iterable<T>>> |
groupBy(scala.Function1<T,K> f,
int numPartitions,
scala.reflect.ClassTag<K> kt) |
static <K> RDD<scala.Tuple2<K,scala.collection.Iterable<T>>> |
groupBy(scala.Function1<T,K> f,
Partitioner p,
scala.reflect.ClassTag<K> kt,
scala.math.Ordering<K> ord) |
static <K> scala.runtime.Null$ |
groupBy$default$4(scala.Function1<T,K> f,
Partitioner p) |
static int |
id() |
protected static void |
initializeLogIfNecessary(boolean isInterpreter) |
protected java.lang.String |
inputFormatCacheKey() |
static RDD<T> |
intersection(RDD<T> other) |
static RDD<T> |
intersection(RDD<T> other,
int numPartitions) |
static RDD<T> |
intersection(RDD<T> other,
Partitioner partitioner,
scala.math.Ordering<T> ord) |
static scala.math.Ordering<T> |
intersection$default$3(RDD<T> other,
Partitioner partitioner) |
static boolean |
isCheckpointed() |
static boolean |
isEmpty() |
protected static boolean |
isTraceEnabled() |
static scala.collection.Iterator<T> |
iterator(Partition split,
TaskContext context) |
protected java.lang.String |
jobConfCacheKey() |
static <K> RDD<scala.Tuple2<K,T>> |
keyBy(scala.Function1<T,K> f) |
static RDD<T> |
localCheckpoint() |
protected static org.slf4j.Logger |
log() |
protected static void |
logDebug(scala.Function0<java.lang.String> msg) |
protected static void |
logDebug(scala.Function0<java.lang.String> msg,
java.lang.Throwable throwable) |
protected static void |
logError(scala.Function0<java.lang.String> msg) |
protected static void |
logError(scala.Function0<java.lang.String> msg,
java.lang.Throwable throwable) |
protected static void |
logInfo(scala.Function0<java.lang.String> msg) |
protected static void |
logInfo(scala.Function0<java.lang.String> msg,
java.lang.Throwable throwable) |
protected static java.lang.String |
logName() |
protected static void |
logTrace(scala.Function0<java.lang.String> msg) |
protected static void |
logTrace(scala.Function0<java.lang.String> msg,
java.lang.Throwable throwable) |
protected static void |
logWarning(scala.Function0<java.lang.String> msg) |
protected static void |
logWarning(scala.Function0<java.lang.String> msg,
java.lang.Throwable throwable) |
static <U> RDD<U> |
map(scala.Function1<T,U> f,
scala.reflect.ClassTag<U> evidence$3) |
static <U> RDD<U> |
mapPartitions(scala.Function1<scala.collection.Iterator<T>,scala.collection.Iterator<U>> f,
boolean preservesPartitioning,
scala.reflect.ClassTag<U> evidence$6) |
static <U> boolean |
mapPartitions$default$2() |
static <U> boolean |
mapPartitionsInternal$default$2() |
static <U> RDD<U> |
mapPartitionsWithIndex(scala.Function2<java.lang.Object,scala.collection.Iterator<T>,scala.collection.Iterator<U>> f,
boolean preservesPartitioning,
scala.reflect.ClassTag<U> evidence$8) |
static <U> boolean |
mapPartitionsWithIndex$default$2() |
<U> RDD<U> |
mapPartitionsWithInputSplit(scala.Function2<org.apache.hadoop.mapred.InputSplit,scala.collection.Iterator<scala.Tuple2<K,V>>,scala.collection.Iterator<U>> f,
boolean preservesPartitioning,
scala.reflect.ClassTag<U> evidence$1)
Maps over a partition, providing the InputSplit that was used as the base of the partition.
|
static T |
max(scala.math.Ordering<T> ord) |
static T |
min(scala.math.Ordering<T> ord) |
static void |
name_$eq(java.lang.String x$1) |
static java.lang.String |
name() |
protected static <U> RDD<U> |
parent(int j,
scala.reflect.ClassTag<U> evidence$32) |
static scala.Option<Partitioner> |
partitioner() |
static Partition[] |
partitions() |
HadoopRDD<K,V> |
persist(StorageLevel storageLevel)
Set this RDD's storage level to persist its values across operations after the first time
it is computed.
|
static RDD<java.lang.String> |
pipe(scala.collection.Seq<java.lang.String> command,
scala.collection.Map<java.lang.String,java.lang.String> env,
scala.Function1<scala.Function1<java.lang.String,scala.runtime.BoxedUnit>,scala.runtime.BoxedUnit> printPipeContext,
scala.Function2<T,scala.Function1<java.lang.String,scala.runtime.BoxedUnit>,scala.runtime.BoxedUnit> printRDDElement,
boolean separateWorkingDir,
int bufferSize) |
static RDD<java.lang.String> |
pipe(java.lang.String command) |
static RDD<java.lang.String> |
pipe(java.lang.String command,
scala.collection.Map<java.lang.String,java.lang.String> env) |
static scala.collection.Map<java.lang.String,java.lang.String> |
pipe$default$2() |
static scala.Function1<scala.Function1<java.lang.String,scala.runtime.BoxedUnit>,scala.runtime.BoxedUnit> |
pipe$default$3() |
static scala.Function2<T,scala.Function1<java.lang.String,scala.runtime.BoxedUnit>,scala.runtime.BoxedUnit> |
pipe$default$4() |
static boolean |
pipe$default$5() |
static int |
pipe$default$6() |
static scala.collection.Seq<java.lang.String> |
preferredLocations(Partition split) |
static RDD<T>[] |
randomSplit(double[] weights,
long seed) |
static long |
randomSplit$default$2() |
static int |
RECORDS_BETWEEN_BYTES_READ_METRIC_UPDATES()
Update the input bytes read metric each time this number of records has been read
|
static T |
reduce(scala.Function2<T,T,T> f) |
static RDD<T> |
repartition(int numPartitions,
scala.math.Ordering<T> ord) |
static scala.math.Ordering<T> |
repartition$default$2(int numPartitions) |
static RDD<T> |
sample(boolean withReplacement,
double fraction,
long seed) |
static long |
sample$default$3() |
static void |
saveAsObjectFile(java.lang.String path) |
static void |
saveAsTextFile(java.lang.String path) |
static void |
saveAsTextFile(java.lang.String path,
java.lang.Class<? extends org.apache.hadoop.io.compress.CompressionCodec> codec) |
static RDD<T> |
setName(java.lang.String _name) |
static <K> RDD<T> |
sortBy(scala.Function1<T,K> f,
boolean ascending,
int numPartitions,
scala.math.Ordering<K> ord,
scala.reflect.ClassTag<K> ctag) |
static <K> boolean |
sortBy$default$2() |
static <K> int |
sortBy$default$3() |
static SparkContext |
sparkContext() |
static RDD<T> |
subtract(RDD<T> other) |
static RDD<T> |
subtract(RDD<T> other,
int numPartitions) |
static RDD<T> |
subtract(RDD<T> other,
Partitioner p,
scala.math.Ordering<T> ord) |
static scala.math.Ordering<T> |
subtract$default$3(RDD<T> other,
Partitioner p) |
static java.lang.Object |
take(int num) |
static java.lang.Object |
takeOrdered(int num,
scala.math.Ordering<T> ord) |
static java.lang.Object |
takeSample(boolean withReplacement,
int num,
long seed) |
static long |
takeSample$default$3() |
static java.lang.String |
toDebugString() |
static JavaRDD<T> |
toJavaRDD() |
static scala.collection.Iterator<T> |
toLocalIterator() |
static java.lang.Object |
top(int num,
scala.math.Ordering<T> ord) |
static java.lang.String |
toString() |
static <U> U |
treeAggregate(U zeroValue,
scala.Function2<U,T,U> seqOp,
scala.Function2<U,U,U> combOp,
int depth,
scala.reflect.ClassTag<U> evidence$30) |
static <U> int |
treeAggregate$default$4(U zeroValue) |
static T |
treeReduce(scala.Function2<T,T,T> f,
int depth) |
static int |
treeReduce$default$2() |
static RDD<T> |
union(RDD<T> other) |
static RDD<T> |
unpersist(boolean blocking) |
static boolean |
unpersist$default$1() |
static <U> RDD<scala.Tuple2<T,U>> |
zip(RDD<U> other,
scala.reflect.ClassTag<U> evidence$9) |
static <B,V> RDD<V> |
zipPartitions(RDD<B> rdd2,
boolean preservesPartitioning,
scala.Function2<scala.collection.Iterator<T>,scala.collection.Iterator<B>,scala.collection.Iterator<V>> f,
scala.reflect.ClassTag<B> evidence$10,
scala.reflect.ClassTag<V> evidence$11) |
static <B,V> RDD<V> |
zipPartitions(RDD<B> rdd2,
scala.Function2<scala.collection.Iterator<T>,scala.collection.Iterator<B>,scala.collection.Iterator<V>> f,
scala.reflect.ClassTag<B> evidence$12,
scala.reflect.ClassTag<V> evidence$13) |
static <B,C,V> RDD<V> |
zipPartitions(RDD<B> rdd2,
RDD<C> rdd3,
boolean preservesPartitioning,
scala.Function3<scala.collection.Iterator<T>,scala.collection.Iterator<B>,scala.collection.Iterator<C>,scala.collection.Iterator<V>> f,
scala.reflect.ClassTag<B> evidence$14,
scala.reflect.ClassTag<C> evidence$15,
scala.reflect.ClassTag<V> evidence$16) |
static <B,C,V> RDD<V> |
zipPartitions(RDD<B> rdd2,
RDD<C> rdd3,
scala.Function3<scala.collection.Iterator<T>,scala.collection.Iterator<B>,scala.collection.Iterator<C>,scala.collection.Iterator<V>> f,
scala.reflect.ClassTag<B> evidence$17,
scala.reflect.ClassTag<C> evidence$18,
scala.reflect.ClassTag<V> evidence$19) |
static <B,C,D,V> RDD<V> |
zipPartitions(RDD<B> rdd2,
RDD<C> rdd3,
RDD<D> rdd4,
boolean preservesPartitioning,
scala.Function4<scala.collection.Iterator<T>,scala.collection.Iterator<B>,scala.collection.Iterator<C>,scala.collection.Iterator<D>,scala.collection.Iterator<V>> f,
scala.reflect.ClassTag<B> evidence$20,
scala.reflect.ClassTag<C> evidence$21,
scala.reflect.ClassTag<D> evidence$22,
scala.reflect.ClassTag<V> evidence$23) |
static <B,C,D,V> RDD<V> |
zipPartitions(RDD<B> rdd2,
RDD<C> rdd3,
RDD<D> rdd4,
scala.Function4<scala.collection.Iterator<T>,scala.collection.Iterator<B>,scala.collection.Iterator<C>,scala.collection.Iterator<D>,scala.collection.Iterator<V>> f,
scala.reflect.ClassTag<B> evidence$24,
scala.reflect.ClassTag<C> evidence$25,
scala.reflect.ClassTag<D> evidence$26,
scala.reflect.ClassTag<V> evidence$27) |
static RDD<scala.Tuple2<T,java.lang.Object>> |
zipWithIndex() |
static RDD<scala.Tuple2<T,java.lang.Object>> |
zipWithUniqueId() |
aggregate, cache, cartesian, clearDependencies, coalesce, collect, collect, context, count, countApprox, countApproxDistinct, countApproxDistinct, countByValue, countByValueApprox, dependencies, distinct, distinct, doubleRDDToDoubleRDDFunctions, filter, first, firstParent, flatMap, fold, foreach, foreachPartition, getCheckpointFile, getDependencies, getNumPartitions, getStorageLevel, glom, groupBy, groupBy, groupBy, id, intersection, intersection, intersection, isCheckpointed, isEmpty, iterator, keyBy, localCheckpoint, map, mapPartitions, mapPartitionsWithIndex, max, min, name, numericRDDToDoubleRDDFunctions, parent, partitioner, partitions, persist, pipe, pipe, pipe, preferredLocations, randomSplit, rddToAsyncRDDActions, rddToOrderedRDDFunctions, rddToPairRDDFunctions, rddToSequenceFileRDDFunctions, reduce, repartition, sample, saveAsObjectFile, saveAsTextFile, saveAsTextFile, setName, sortBy, sparkContext, subtract, subtract, subtract, take, takeOrdered, takeSample, toDebugString, toJavaRDD, toLocalIterator, top, toString, treeAggregate, treeReduce, union, unpersist, zip, zipPartitions, zipPartitions, zipPartitions, zipPartitions, zipPartitions, zipPartitions, zipWithIndex, zipWithUniqueId
public HadoopRDD(SparkContext sc, Broadcast<org.apache.spark.util.SerializableConfiguration> broadcastedConf, scala.Option<scala.Function1<org.apache.hadoop.mapred.JobConf,scala.runtime.BoxedUnit>> initLocalJobConfFuncOpt, java.lang.Class<? extends org.apache.hadoop.mapred.InputFormat<K,V>> inputFormatClass, java.lang.Class<K> keyClass, java.lang.Class<V> valueClass, int minPartitions)
public HadoopRDD(SparkContext sc, org.apache.hadoop.mapred.JobConf conf, java.lang.Class<? extends org.apache.hadoop.mapred.InputFormat<K,V>> inputFormatClass, java.lang.Class<K> keyClass, java.lang.Class<V> valueClass, int minPartitions)
public static java.lang.Object CONFIGURATION_INSTANTIATION_LOCK()
public static int RECORDS_BETWEEN_BYTES_READ_METRIC_UPDATES()
public static java.lang.Object getCachedMetadata(java.lang.String key)
key
- (undocumented)public static boolean containsCachedMetadata(java.lang.String key)
public static void addLocalConfiguration(java.lang.String jobTrackerId, int jobId, int splitId, int attemptId, org.apache.hadoop.mapred.JobConf conf)
protected static java.lang.String logName()
protected static org.slf4j.Logger log()
protected static void logInfo(scala.Function0<java.lang.String> msg)
protected static void logDebug(scala.Function0<java.lang.String> msg)
protected static void logTrace(scala.Function0<java.lang.String> msg)
protected static void logWarning(scala.Function0<java.lang.String> msg)
protected static void logError(scala.Function0<java.lang.String> msg)
protected static void logInfo(scala.Function0<java.lang.String> msg, java.lang.Throwable throwable)
protected static void logDebug(scala.Function0<java.lang.String> msg, java.lang.Throwable throwable)
protected static void logTrace(scala.Function0<java.lang.String> msg, java.lang.Throwable throwable)
protected static void logWarning(scala.Function0<java.lang.String> msg, java.lang.Throwable throwable)
protected static void logError(scala.Function0<java.lang.String> msg, java.lang.Throwable throwable)
protected static boolean isTraceEnabled()
protected static void initializeLogIfNecessary(boolean isInterpreter)
protected static scala.collection.Seq<Dependency<?>> getDependencies()
public static scala.Option<Partitioner> partitioner()
public static SparkContext sparkContext()
public static int id()
public static java.lang.String name()
public static void name_$eq(java.lang.String x$1)
public static RDD<T> setName(java.lang.String _name)
public static RDD<T> cache()
public static RDD<T> unpersist(boolean blocking)
public static StorageLevel getStorageLevel()
public static final scala.collection.Seq<Dependency<?>> dependencies()
public static final Partition[] partitions()
public static final int getNumPartitions()
public static final scala.collection.Seq<java.lang.String> preferredLocations(Partition split)
public static final scala.collection.Iterator<T> iterator(Partition split, TaskContext context)
public static <U> RDD<U> map(scala.Function1<T,U> f, scala.reflect.ClassTag<U> evidence$3)
public static <U> RDD<U> flatMap(scala.Function1<T,scala.collection.TraversableOnce<U>> f, scala.reflect.ClassTag<U> evidence$4)
public static RDD<T> filter(scala.Function1<T,java.lang.Object> f)
public static RDD<T> distinct(int numPartitions, scala.math.Ordering<T> ord)
public static RDD<T> distinct()
public static RDD<T> repartition(int numPartitions, scala.math.Ordering<T> ord)
public static RDD<T> coalesce(int numPartitions, boolean shuffle, scala.Option<PartitionCoalescer> partitionCoalescer, scala.math.Ordering<T> ord)
public static RDD<T> sample(boolean withReplacement, double fraction, long seed)
public static RDD<T>[] randomSplit(double[] weights, long seed)
public static java.lang.Object takeSample(boolean withReplacement, int num, long seed)
public static <K> RDD<T> sortBy(scala.Function1<T,K> f, boolean ascending, int numPartitions, scala.math.Ordering<K> ord, scala.reflect.ClassTag<K> ctag)
public static RDD<T> intersection(RDD<T> other, Partitioner partitioner, scala.math.Ordering<T> ord)
public static RDD<java.lang.Object> glom()
public static <U> RDD<scala.Tuple2<T,U>> cartesian(RDD<U> other, scala.reflect.ClassTag<U> evidence$5)
public static <K> RDD<scala.Tuple2<K,scala.collection.Iterable<T>>> groupBy(scala.Function1<T,K> f, scala.reflect.ClassTag<K> kt)
public static <K> RDD<scala.Tuple2<K,scala.collection.Iterable<T>>> groupBy(scala.Function1<T,K> f, int numPartitions, scala.reflect.ClassTag<K> kt)
public static <K> RDD<scala.Tuple2<K,scala.collection.Iterable<T>>> groupBy(scala.Function1<T,K> f, Partitioner p, scala.reflect.ClassTag<K> kt, scala.math.Ordering<K> ord)
public static RDD<java.lang.String> pipe(java.lang.String command)
public static RDD<java.lang.String> pipe(java.lang.String command, scala.collection.Map<java.lang.String,java.lang.String> env)
public static RDD<java.lang.String> pipe(scala.collection.Seq<java.lang.String> command, scala.collection.Map<java.lang.String,java.lang.String> env, scala.Function1<scala.Function1<java.lang.String,scala.runtime.BoxedUnit>,scala.runtime.BoxedUnit> printPipeContext, scala.Function2<T,scala.Function1<java.lang.String,scala.runtime.BoxedUnit>,scala.runtime.BoxedUnit> printRDDElement, boolean separateWorkingDir, int bufferSize)
public static <U> RDD<U> mapPartitions(scala.Function1<scala.collection.Iterator<T>,scala.collection.Iterator<U>> f, boolean preservesPartitioning, scala.reflect.ClassTag<U> evidence$6)
public static <U> RDD<U> mapPartitionsWithIndex(scala.Function2<java.lang.Object,scala.collection.Iterator<T>,scala.collection.Iterator<U>> f, boolean preservesPartitioning, scala.reflect.ClassTag<U> evidence$8)
public static <U> RDD<scala.Tuple2<T,U>> zip(RDD<U> other, scala.reflect.ClassTag<U> evidence$9)
public static <B,V> RDD<V> zipPartitions(RDD<B> rdd2, boolean preservesPartitioning, scala.Function2<scala.collection.Iterator<T>,scala.collection.Iterator<B>,scala.collection.Iterator<V>> f, scala.reflect.ClassTag<B> evidence$10, scala.reflect.ClassTag<V> evidence$11)
public static <B,V> RDD<V> zipPartitions(RDD<B> rdd2, scala.Function2<scala.collection.Iterator<T>,scala.collection.Iterator<B>,scala.collection.Iterator<V>> f, scala.reflect.ClassTag<B> evidence$12, scala.reflect.ClassTag<V> evidence$13)
public static <B,C,V> RDD<V> zipPartitions(RDD<B> rdd2, RDD<C> rdd3, boolean preservesPartitioning, scala.Function3<scala.collection.Iterator<T>,scala.collection.Iterator<B>,scala.collection.Iterator<C>,scala.collection.Iterator<V>> f, scala.reflect.ClassTag<B> evidence$14, scala.reflect.ClassTag<C> evidence$15, scala.reflect.ClassTag<V> evidence$16)
public static <B,C,V> RDD<V> zipPartitions(RDD<B> rdd2, RDD<C> rdd3, scala.Function3<scala.collection.Iterator<T>,scala.collection.Iterator<B>,scala.collection.Iterator<C>,scala.collection.Iterator<V>> f, scala.reflect.ClassTag<B> evidence$17, scala.reflect.ClassTag<C> evidence$18, scala.reflect.ClassTag<V> evidence$19)
public static <B,C,D,V> RDD<V> zipPartitions(RDD<B> rdd2, RDD<C> rdd3, RDD<D> rdd4, boolean preservesPartitioning, scala.Function4<scala.collection.Iterator<T>,scala.collection.Iterator<B>,scala.collection.Iterator<C>,scala.collection.Iterator<D>,scala.collection.Iterator<V>> f, scala.reflect.ClassTag<B> evidence$20, scala.reflect.ClassTag<C> evidence$21, scala.reflect.ClassTag<D> evidence$22, scala.reflect.ClassTag<V> evidence$23)
public static <B,C,D,V> RDD<V> zipPartitions(RDD<B> rdd2, RDD<C> rdd3, RDD<D> rdd4, scala.Function4<scala.collection.Iterator<T>,scala.collection.Iterator<B>,scala.collection.Iterator<C>,scala.collection.Iterator<D>,scala.collection.Iterator<V>> f, scala.reflect.ClassTag<B> evidence$24, scala.reflect.ClassTag<C> evidence$25, scala.reflect.ClassTag<D> evidence$26, scala.reflect.ClassTag<V> evidence$27)
public static void foreach(scala.Function1<T,scala.runtime.BoxedUnit> f)
public static void foreachPartition(scala.Function1<scala.collection.Iterator<T>,scala.runtime.BoxedUnit> f)
public static java.lang.Object collect()
public static scala.collection.Iterator<T> toLocalIterator()
public static <U> RDD<U> collect(scala.PartialFunction<T,U> f, scala.reflect.ClassTag<U> evidence$28)
public static RDD<T> subtract(RDD<T> other, Partitioner p, scala.math.Ordering<T> ord)
public static T reduce(scala.Function2<T,T,T> f)
public static T treeReduce(scala.Function2<T,T,T> f, int depth)
public static T fold(T zeroValue, scala.Function2<T,T,T> op)
public static <U> U aggregate(U zeroValue, scala.Function2<U,T,U> seqOp, scala.Function2<U,U,U> combOp, scala.reflect.ClassTag<U> evidence$29)
public static <U> U treeAggregate(U zeroValue, scala.Function2<U,T,U> seqOp, scala.Function2<U,U,U> combOp, int depth, scala.reflect.ClassTag<U> evidence$30)
public static long count()
public static PartialResult<BoundedDouble> countApprox(long timeout, double confidence)
public static scala.collection.Map<T,java.lang.Object> countByValue(scala.math.Ordering<T> ord)
public static PartialResult<scala.collection.Map<T,BoundedDouble>> countByValueApprox(long timeout, double confidence, scala.math.Ordering<T> ord)
public static long countApproxDistinct(int p, int sp)
public static long countApproxDistinct(double relativeSD)
public static RDD<scala.Tuple2<T,java.lang.Object>> zipWithIndex()
public static RDD<scala.Tuple2<T,java.lang.Object>> zipWithUniqueId()
public static java.lang.Object take(int num)
public static T first()
public static java.lang.Object top(int num, scala.math.Ordering<T> ord)
public static java.lang.Object takeOrdered(int num, scala.math.Ordering<T> ord)
public static T max(scala.math.Ordering<T> ord)
public static T min(scala.math.Ordering<T> ord)
public static boolean isEmpty()
public static void saveAsTextFile(java.lang.String path)
public static void saveAsTextFile(java.lang.String path, java.lang.Class<? extends org.apache.hadoop.io.compress.CompressionCodec> codec)
public static void saveAsObjectFile(java.lang.String path)
public static <K> RDD<scala.Tuple2<K,T>> keyBy(scala.Function1<T,K> f)
public static RDD<T> localCheckpoint()
public static boolean isCheckpointed()
public static scala.Option<java.lang.String> getCheckpointFile()
protected static <U> RDD<U> firstParent(scala.reflect.ClassTag<U> evidence$31)
protected static <U> RDD<U> parent(int j, scala.reflect.ClassTag<U> evidence$32)
public static SparkContext context()
protected static void clearDependencies()
public static java.lang.String toDebugString()
public static java.lang.String toString()
public static JavaRDD<T> toJavaRDD()
public static long sample$default$3()
public static <U> boolean mapPartitionsWithIndex$default$2()
public static boolean unpersist$default$1()
public static scala.math.Ordering<T> distinct$default$2(int numPartitions)
public static boolean coalesce$default$2()
public static scala.Option<PartitionCoalescer> coalesce$default$3()
public static scala.math.Ordering<T> coalesce$default$4(int numPartitions, boolean shuffle, scala.Option<PartitionCoalescer> partitionCoalescer)
public static scala.math.Ordering<T> repartition$default$2(int numPartitions)
public static scala.math.Ordering<T> subtract$default$3(RDD<T> other, Partitioner p)
public static scala.math.Ordering<T> intersection$default$3(RDD<T> other, Partitioner partitioner)
public static long randomSplit$default$2()
public static <K> boolean sortBy$default$2()
public static <K> int sortBy$default$3()
public static <U> boolean mapPartitions$default$2()
public static <K> scala.runtime.Null$ groupBy$default$4(scala.Function1<T,K> f, Partitioner p)
public static scala.collection.Map<java.lang.String,java.lang.String> pipe$default$2()
public static scala.Function1<scala.Function1<java.lang.String,scala.runtime.BoxedUnit>,scala.runtime.BoxedUnit> pipe$default$3()
public static scala.Function2<T,scala.Function1<java.lang.String,scala.runtime.BoxedUnit>,scala.runtime.BoxedUnit> pipe$default$4()
public static boolean pipe$default$5()
public static int pipe$default$6()
public static int treeReduce$default$2()
public static <U> int treeAggregate$default$4(U zeroValue)
public static double countApprox$default$2()
public static scala.math.Ordering<T> countByValue$default$1()
public static double countByValueApprox$default$2()
public static scala.math.Ordering<T> countByValueApprox$default$3(long timeout, double confidence)
public static long takeSample$default$3()
public static double countApproxDistinct$default$1()
public static <U> boolean mapPartitionsInternal$default$2()
protected java.lang.String jobConfCacheKey()
protected java.lang.String inputFormatCacheKey()
protected org.apache.hadoop.mapred.JobConf getJobConf()
protected org.apache.hadoop.mapred.InputFormat<K,V> getInputFormat(org.apache.hadoop.mapred.JobConf conf)
public Partition[] getPartitions()
RDD
The partitions in this array must satisfy the following property:
rdd.partitions.zipWithIndex.forall { case (partition, index) => partition.index == index }
getPartitions
in class RDD<scala.Tuple2<K,V>>
public InterruptibleIterator<scala.Tuple2<K,V>> compute(Partition theSplit, TaskContext context)
RDD
public <U> RDD<U> mapPartitionsWithInputSplit(scala.Function2<org.apache.hadoop.mapred.InputSplit,scala.collection.Iterator<scala.Tuple2<K,V>>,scala.collection.Iterator<U>> f, boolean preservesPartitioning, scala.reflect.ClassTag<U> evidence$1)
public scala.collection.Seq<java.lang.String> getPreferredLocations(Partition split)
RDD
getPreferredLocations
in class RDD<scala.Tuple2<K,V>>
split
- (undocumented)public void checkpoint()
RDD
SparkContext#setCheckpointDir
and all references to its parent
RDDs will be removed. This function must be called before any job has been
executed on this RDD. It is strongly recommended that this RDD is persisted in
memory, otherwise saving it on a file will require recomputation.checkpoint
in class RDD<scala.Tuple2<K,V>>
public HadoopRDD<K,V> persist(StorageLevel storageLevel)
RDD
public org.apache.hadoop.conf.Configuration getConf()