org.apache.spark.ml.feature

Class Tokenizer

Object

org.apache.spark.ml.PipelineStage

org.apache.spark.ml.Transformer

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

org.apache.spark.ml.feature.Tokenizer

All Implemented Interfaces:

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

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

A tokenizer that converts the input string to lowercase and then splits it by white spaces.

See Also:

RegexTokenizer, Serialized Form

Constructor Summary

Constructors

Constructor and Description
Tokenizer()
Tokenizer(String uid)

Method Summary

Modifier and Type	Method and Description
static Params	clear(Param<?> param)
Tokenizer	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)
static <T> scala.Option<T>	get(Param<T> param)
static <T> scala.Option<T>	getDefault(Param<T> param)
static String	getInputCol()
static <T> T	getOrDefault(Param<T> param)
static String	getOutputCol()
static Param<Object>	getParam(String paramName)
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 Tokenizer	load(String path)
static Param<String>	outputCol()
static Param<?>[]	params()
static void	save(String path)
static <T> Params	set(Param<T> param, T value)
static T	setInputCol(String value)
static T	setOutputCol(String value)
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

Tokenizer

public Tokenizer(String uid)

Tokenizer

public Tokenizer()

Method Detail

load

public static Tokenizer 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)

copy

public Tokenizer 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>,Tokenizer>

Parameters:

extra - (undocumented)

Returns:

(undocumented)