org.apache.spark.ml.fpm

Class PrefixSpan

Object

org.apache.spark.ml.fpm.PrefixSpan

All Implemented Interfaces:

java.io.Serializable, Params, Identifiable

public final class PrefixSpan
extends Object
implements Params

A parallel PrefixSpan algorithm to mine frequent sequential patterns. The PrefixSpan algorithm is described in J. Pei, et al., PrefixSpan: Mining Sequential Patterns Efficiently by Prefix-Projected Pattern Growth (see here). This class is not yet an Estimator/Transformer, use findFrequentSequentialPatterns method to run the PrefixSpan algorithm.

See Also:

Sequential Pattern Mining (Wikipedia), Serialized Form

Constructor Summary

Constructors

Constructor and Description
PrefixSpan()
PrefixSpan(String uid)

Method Summary

Modifier and Type	Method and Description
PrefixSpan	copy(ParamMap extra) Creates a copy of this instance with the same UID and some extra params.
Dataset<Row>	findFrequentSequentialPatterns(Dataset<?> dataset) Finds the complete set of frequent sequential patterns in the input sequences of itemsets.
long	getMaxLocalProjDBSize()
int	getMaxPatternLength()
double	getMinSupport()
String	getSequenceCol()
LongParam	maxLocalProjDBSize() Param for the maximum number of items (including delimiters used in the internal storage format) allowed in a projected database before local processing (default: 32000000).
IntParam	maxPatternLength() Param for the maximal pattern length (default: 10).
DoubleParam	minSupport() Param for the minimal support level (default: 0.1).
Param<?>[]	params() Returns all params sorted by their names.
Param<String>	sequenceCol() Param for the name of the sequence column in dataset (default "sequence"), rows with nulls in this column are ignored.
PrefixSpan	setMaxLocalProjDBSize(long value)
PrefixSpan	setMaxPatternLength(int value)
PrefixSpan	setMinSupport(double value)
PrefixSpan	setSequenceCol(String value)
String	uid() An immutable unique ID for the object and its derivatives.

Methods inherited from class Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface org.apache.spark.ml.param.Params

clear, copyValues, defaultCopy, explainParam, explainParams, extractParamMap, extractParamMap, get, getDefault, getOrDefault, getParam, hasDefault, hasParam, isDefined, isSet, onParamChange, set, set, set, setDefault, setDefault, shouldOwn

Methods inherited from interface org.apache.spark.ml.util.Identifiable

toString

Constructor Detail

PrefixSpan

public PrefixSpan(String uid)

PrefixSpan

public PrefixSpan()

Method Detail

copy

public PrefixSpan copy(ParamMap extra)

Description copied from interface: Params

Creates a copy of this instance with the same UID and some extra params. Subclasses should implement this method and set the return type properly. See defaultCopy().

Specified by:

copy in interface Params

Parameters:

extra - (undocumented)

Returns:

(undocumented)

findFrequentSequentialPatterns

public Dataset<Row> findFrequentSequentialPatterns(Dataset<?> dataset)

Finds the complete set of frequent sequential patterns in the input sequences of itemsets.

Parameters:

dataset - A dataset or a dataframe containing a sequence column which is

ArrayType(ArrayType(T))

type, T is the item type for the input dataset. @return A `DataFrame` that contains columns of sequence and corresponding frequency. The schema of it will be: - `sequence: ArrayType(ArrayType(T))` (T is the item type) - `freq: Long`

Returns:

(undocumented)

getMaxLocalProjDBSize

public long getMaxLocalProjDBSize()

getMaxPatternLength

public int getMaxPatternLength()

getMinSupport

public double getMinSupport()

getSequenceCol

public String getSequenceCol()

maxLocalProjDBSize

public LongParam maxLocalProjDBSize()

Param for the maximum number of items (including delimiters used in the internal storage format) allowed in a projected database before local processing (default: 32000000). If a projected database exceeds this size, another iteration of distributed prefix growth is run.

Returns:

(undocumented)

maxPatternLength

public IntParam maxPatternLength()

Param for the maximal pattern length (default: 10).

Returns:

(undocumented)

minSupport

public DoubleParam minSupport()

Param for the minimal support level (default: 0.1). Sequential patterns that appear more than (minSupport * size-of-the-dataset) times are identified as frequent sequential patterns.

Returns:

(undocumented)

params

public Param<?>[] params()

Description copied from interface: Params

Returns all params sorted by their names. The default implementation uses Java reflection to list all public methods that have no arguments and return Param.

Specified by:

params in interface Params

Returns:

(undocumented)

sequenceCol

public Param<String> sequenceCol()

Param for the name of the sequence column in dataset (default "sequence"), rows with nulls in this column are ignored.

Returns:

(undocumented)

setMaxLocalProjDBSize

public PrefixSpan setMaxLocalProjDBSize(long value)

setMaxPatternLength

public PrefixSpan setMaxPatternLength(int value)

setMinSupport

public PrefixSpan setMinSupport(double value)

setSequenceCol

public PrefixSpan setSequenceCol(String value)

uid

public String uid()

Description copied from interface: Identifiable

An immutable unique ID for the object and its derivatives.

Specified by:

uid in interface Identifiable

Returns:

(undocumented)