org.apache.spark.ml.feature

Class RegexTokenizer

Object

org.apache.spark.ml.PipelineStage

org.apache.spark.ml.Transformer

org.apache.spark.ml.UnaryTransformer<String,scala.collection.Seq<String>,RegexTokenizer>

org.apache.spark.ml.feature.RegexTokenizer

All Implemented Interfaces:

java.io.Serializable, Logging, Params, HasInputCol, HasOutputCol, DefaultParamsWritable, Identifiable, MLWritable

public class RegexTokenizer
extends UnaryTransformer<String,scala.collection.Seq<String>,RegexTokenizer>
implements DefaultParamsWritable

A regex based tokenizer that extracts tokens either by using the provided regex pattern to split the text (default) or repeatedly matching the regex (if gaps is false). Optional parameters also allow filtering tokens using a minimal length. It returns an array of strings that can be empty.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
RegexTokenizer()
RegexTokenizer(String uid)

Method Summary

Modifier and Type	Method and Description
static Params	clear(Param<?> param)
RegexTokenizer	copy(ParamMap extra) Creates a copy of this instance with the same UID and some extra params.
static String	explainParam(Param<?> param)
static String	explainParams()
static ParamMap	extractParamMap()
static ParamMap	extractParamMap(ParamMap extra)
BooleanParam	gaps() Indicates whether regex splits on gaps (true) or matches tokens (false).
static <T> scala.Option<T>	get(Param<T> param)
static <T> scala.Option<T>	getDefault(Param<T> param)
boolean	getGaps()
static String	getInputCol()
int	getMinTokenLength()
static <T> T	getOrDefault(Param<T> param)
static String	getOutputCol()
static Param<Object>	getParam(String paramName)
String	getPattern()
boolean	getToLowercase()
static <T> boolean	hasDefault(Param<T> param)
static boolean	hasParam(String paramName)
static Param<String>	inputCol()
static boolean	isDefined(Param<?> param)
static boolean	isSet(Param<?> param)
static RegexTokenizer	load(String path)
IntParam	minTokenLength() Minimum token length, greater than or equal to 0.
static Param<String>	outputCol()
static Param<?>[]	params()
Param<String>	pattern() Regex pattern used to match delimiters if gaps is true or tokens if gaps is false.
static void	save(String path)
static <T> Params	set(Param<T> param, T value)
RegexTokenizer	setGaps(boolean value)
static T	setInputCol(String value)
RegexTokenizer	setMinTokenLength(int value)
static T	setOutputCol(String value)
RegexTokenizer	setPattern(String value)
RegexTokenizer	setToLowercase(boolean value)
BooleanParam	toLowercase() Indicates whether to convert all characters to lowercase before tokenizing.
static String	toString()
static Dataset<Row>	transform(Dataset<?> dataset)
static Dataset<Row>	transform(Dataset<?> dataset, ParamMap paramMap)
static Dataset<Row>	transform(Dataset<?> dataset, ParamPair<?> firstParamPair, ParamPair<?>... otherParamPairs)
static Dataset<Row>	transform(Dataset<?> dataset, ParamPair<?> firstParamPair, scala.collection.Seq<ParamPair<?>> otherParamPairs)
static StructType	transformSchema(StructType schema)
String	uid() An immutable unique ID for the object and its derivatives.
static MLWriter	write()

Methods inherited from class org.apache.spark.ml.UnaryTransformer

setInputCol, setOutputCol, transform, transformSchema

Methods inherited from class org.apache.spark.ml.Transformer

transform, transform, transform

Methods inherited from class Object

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

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

write

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

save

Methods inherited from interface org.apache.spark.ml.param.shared.HasInputCol

getInputCol, inputCol

Methods inherited from interface org.apache.spark.ml.param.shared.HasOutputCol

getOutputCol, outputCol

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

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

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

toString

Methods inherited from interface org.apache.spark.internal.Logging

initializeLogging, initializeLogIfNecessary, initializeLogIfNecessary, isTraceEnabled, log_, log, logDebug, logDebug, logError, logError, logInfo, logInfo, logName, logTrace, logTrace, logWarning, logWarning

Constructor Detail

RegexTokenizer

public RegexTokenizer(String uid)

RegexTokenizer

public RegexTokenizer()

Method Detail

load

public static RegexTokenizer load(String path)

toString

public static String toString()

params

public static Param<?>[] params()

explainParam

public static String explainParam(Param<?> param)

explainParams

public static String explainParams()

isSet

public static final boolean isSet(Param<?> param)

isDefined

public static final boolean isDefined(Param<?> param)

hasParam

public static boolean hasParam(String paramName)

getParam

public static Param<Object> getParam(String paramName)

set

public static final <T> Params set(Param<T> param,
                                   T value)

get

public static final <T> scala.Option<T> get(Param<T> param)

clear

public static final Params clear(Param<?> param)

getOrDefault

public static final <T> T getOrDefault(Param<T> param)

getDefault

public static final <T> scala.Option<T> getDefault(Param<T> param)

hasDefault

public static final <T> boolean hasDefault(Param<T> param)

extractParamMap

public static final ParamMap extractParamMap(ParamMap extra)

extractParamMap

public static final ParamMap extractParamMap()

transform

public static Dataset<Row> transform(Dataset<?> dataset,
                                     ParamPair<?> firstParamPair,
                                     scala.collection.Seq<ParamPair<?>> otherParamPairs)

transform

public static Dataset<Row> transform(Dataset<?> dataset,
                                     ParamMap paramMap)

transform

public static Dataset<Row> transform(Dataset<?> dataset,
                                     ParamPair<?> firstParamPair,
                                     ParamPair<?>... otherParamPairs)

inputCol

public static final Param<String> inputCol()

getInputCol

public static final String getInputCol()

outputCol

public static final Param<String> outputCol()

getOutputCol

public static final String getOutputCol()

setInputCol

public static T setInputCol(String value)

setOutputCol

public static T setOutputCol(String value)

transformSchema

public static StructType transformSchema(StructType schema)

transform

public static Dataset<Row> transform(Dataset<?> dataset)

save

public static void save(String path)
                 throws java.io.IOException

Throws:

java.io.IOException

write

public static MLWriter write()

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)

minTokenLength

public IntParam minTokenLength()

Minimum token length, greater than or equal to 0. Default: 1, to avoid returning empty strings

Returns:

(undocumented)

setMinTokenLength

public RegexTokenizer setMinTokenLength(int value)

getMinTokenLength

public int getMinTokenLength()

gaps

public BooleanParam gaps()

Indicates whether regex splits on gaps (true) or matches tokens (false). Default: true

Returns:

(undocumented)

setGaps

public RegexTokenizer setGaps(boolean value)

getGaps

public boolean getGaps()

pattern

public Param<String> pattern()

Regex pattern used to match delimiters if gaps is true or tokens if gaps is false. Default: "\\s+"

Returns:

(undocumented)

setPattern

public RegexTokenizer setPattern(String value)

getPattern

public String getPattern()

toLowercase

public final BooleanParam toLowercase()

Indicates whether to convert all characters to lowercase before tokenizing. Default: true

Returns:

(undocumented)

setToLowercase

public RegexTokenizer setToLowercase(boolean value)

getToLowercase

public boolean getToLowercase()

copy

public RegexTokenizer 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

Overrides:

copy in class UnaryTransformer<String,scala.collection.Seq<String>,RegexTokenizer>

Parameters:

extra - (undocumented)

Returns:

(undocumented)