public class Word2VecModel extends Model<Word2VecModel> implements MLWritable
Word2Vec
.Modifier and Type | Method and Description |
---|---|
protected static <T> T |
$(Param<T> param) |
static Params |
clear(Param<?> param) |
Word2VecModel |
copy(ParamMap extra)
Creates a copy of this instance with the same UID and some extra params.
|
protected static <T extends Params> |
copyValues(T to,
ParamMap extra) |
protected static <T extends Params> |
copyValues$default$2() |
protected static <T extends Params> |
defaultCopy(ParamMap extra) |
static java.lang.String |
explainParam(Param<?> param) |
static java.lang.String |
explainParams() |
static ParamMap |
extractParamMap() |
static ParamMap |
extractParamMap(ParamMap extra) |
Dataset<Row> |
findSynonyms(java.lang.String word,
int num)
Find "num" number of words closest in similarity to the given word.
|
Dataset<Row> |
findSynonyms(Vector word,
int num)
Find "num" number of words closest to similarity to the given vector representation
of the word.
|
static <T> scala.Option<T> |
get(Param<T> param) |
static <T> scala.Option<T> |
getDefault(Param<T> param) |
static java.lang.String |
getInputCol() |
java.lang.String |
getInputCol() |
static int |
getMaxIter() |
int |
getMaxIter() |
static int |
getMinCount() |
int |
getMinCount() |
static int |
getNumPartitions() |
int |
getNumPartitions() |
static <T> T |
getOrDefault(Param<T> param) |
static java.lang.String |
getOutputCol() |
java.lang.String |
getOutputCol() |
static Param<java.lang.Object> |
getParam(java.lang.String paramName) |
static long |
getSeed() |
long |
getSeed() |
static double |
getStepSize() |
double |
getStepSize() |
Dataset<Row> |
getVectors()
Returns a dataframe with two fields, "word" and "vector", with "word" being a String and
and the vector the DenseVector that it is mapped to.
|
static int |
getVectorSize() |
int |
getVectorSize() |
static int |
getWindowSize() |
int |
getWindowSize() |
static <T> boolean |
hasDefault(Param<T> param) |
static boolean |
hasParam(java.lang.String paramName) |
static boolean |
hasParent() |
protected static void |
initializeLogIfNecessary(boolean isInterpreter) |
static Param<java.lang.String> |
inputCol() |
Param<java.lang.String> |
inputCol()
Param for input column name.
|
static boolean |
isDefined(Param<?> param) |
static boolean |
isSet(Param<?> param) |
protected static boolean |
isTraceEnabled() |
static Word2VecModel |
load(java.lang.String path) |
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 IntParam |
maxIter() |
IntParam |
maxIter()
Param for maximum number of iterations (>= 0).
|
static IntParam |
minCount() |
IntParam |
minCount()
The minimum number of times a token must appear to be included in the word2vec model's
vocabulary.
|
static IntParam |
numPartitions() |
IntParam |
numPartitions()
Number of partitions for sentences of words.
|
static Param<java.lang.String> |
outputCol() |
Param<java.lang.String> |
outputCol()
Param for output column name.
|
static Param<?>[] |
params() |
static void |
parent_$eq(Estimator<M> x$1) |
static Estimator<M> |
parent() |
static MLReader<Word2VecModel> |
read() |
static void |
save(java.lang.String path) |
static LongParam |
seed() |
LongParam |
seed()
Param for random seed.
|
static <T> Params |
set(Param<T> param,
T value) |
protected static Params |
set(ParamPair<?> paramPair) |
protected static Params |
set(java.lang.String param,
java.lang.Object value) |
protected static <T> Params |
setDefault(Param<T> param,
T value) |
protected static Params |
setDefault(scala.collection.Seq<ParamPair<?>> paramPairs) |
Word2VecModel |
setInputCol(java.lang.String value) |
Word2VecModel |
setOutputCol(java.lang.String value) |
static M |
setParent(Estimator<M> parent) |
static DoubleParam |
stepSize() |
DoubleParam |
stepSize()
Param for Step size to be used for each iteration of optimization.
|
static java.lang.String |
toString() |
Dataset<Row> |
transform(Dataset<?> dataset)
Transform a sentence column to a vector column to represent the whole sentence.
|
StructType |
transformSchema(StructType schema)
:: DeveloperApi ::
|
java.lang.String |
uid()
An immutable unique ID for the object and its derivatives.
|
protected static StructType |
validateAndTransformSchema(StructType schema) |
StructType |
validateAndTransformSchema(StructType schema)
Validate and transform the input schema.
|
static void |
validateParams() |
static IntParam |
vectorSize() |
IntParam |
vectorSize()
The dimension of the code that you want to transform from words.
|
static IntParam |
windowSize() |
IntParam |
windowSize()
The window size (context words from [-window, window]) default 5.
|
MLWriter |
write()
Returns an
MLWriter instance for this ML instance. |
transform, transform, transform
transformSchema
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
clear, copyValues, defaultCopy, defaultParamMap, explainParam, explainParams, extractParamMap, extractParamMap, get, getDefault, getOrDefault, getParam, hasDefault, hasParam, isDefined, isSet, paramMap, params, set, set, set, setDefault, setDefault, shouldOwn, validateParams
toString
save
public static MLReader<Word2VecModel> read()
public static Word2VecModel load(java.lang.String path)
public static java.lang.String toString()
public static Param<?>[] params()
public static void validateParams()
public static java.lang.String explainParam(Param<?> param)
public static java.lang.String explainParams()
public static final boolean isSet(Param<?> param)
public static final boolean isDefined(Param<?> param)
public static boolean hasParam(java.lang.String paramName)
public static Param<java.lang.Object> getParam(java.lang.String paramName)
protected static final Params set(java.lang.String param, java.lang.Object value)
public static final <T> scala.Option<T> get(Param<T> param)
public static final <T> T getOrDefault(Param<T> param)
protected static final <T> T $(Param<T> param)
public static final <T> scala.Option<T> getDefault(Param<T> param)
public static final <T> boolean hasDefault(Param<T> param)
public static final ParamMap extractParamMap()
protected static java.lang.String logName()
protected static org.slf4j.Logger log()
protected static void logInfo(scala.Function0<java.lang.String> msg)
protected static void logDebug(scala.Function0<java.lang.String> msg)
protected static void logTrace(scala.Function0<java.lang.String> msg)
protected static void logWarning(scala.Function0<java.lang.String> msg)
protected static void logError(scala.Function0<java.lang.String> msg)
protected static void logInfo(scala.Function0<java.lang.String> msg, java.lang.Throwable throwable)
protected static void logDebug(scala.Function0<java.lang.String> msg, java.lang.Throwable throwable)
protected static void logTrace(scala.Function0<java.lang.String> msg, java.lang.Throwable throwable)
protected static void logWarning(scala.Function0<java.lang.String> msg, java.lang.Throwable throwable)
protected static void logError(scala.Function0<java.lang.String> msg, java.lang.Throwable throwable)
protected static boolean isTraceEnabled()
protected static void initializeLogIfNecessary(boolean isInterpreter)
public static Estimator<M> parent()
public static void parent_$eq(Estimator<M> x$1)
public static M setParent(Estimator<M> parent)
public static boolean hasParent()
public static final Param<java.lang.String> inputCol()
public static final java.lang.String getInputCol()
public static final Param<java.lang.String> outputCol()
public static final java.lang.String getOutputCol()
public static final IntParam maxIter()
public static final int getMaxIter()
public static final DoubleParam stepSize()
public static final double getStepSize()
public static final LongParam seed()
public static final long getSeed()
public static final IntParam vectorSize()
public static int getVectorSize()
public static final IntParam windowSize()
public static int getWindowSize()
public static final IntParam numPartitions()
public static int getNumPartitions()
public static final IntParam minCount()
public static int getMinCount()
protected static StructType validateAndTransformSchema(StructType schema)
public static void save(java.lang.String path) throws java.io.IOException
java.io.IOException
public java.lang.String uid()
Identifiable
uid
in interface Identifiable
public Dataset<Row> getVectors()
public Dataset<Row> findSynonyms(java.lang.String word, int num)
word
- (undocumented)num
- (undocumented)public Dataset<Row> findSynonyms(Vector word, int num)
word
- (undocumented)num
- (undocumented)public Word2VecModel setInputCol(java.lang.String value)
public Word2VecModel setOutputCol(java.lang.String value)
public Dataset<Row> transform(Dataset<?> dataset)
transform
in class Transformer
dataset
- (undocumented)public StructType transformSchema(StructType schema)
PipelineStage
Derives the output schema from the input schema.
transformSchema
in class PipelineStage
schema
- (undocumented)public Word2VecModel copy(ParamMap extra)
Params
copy
in interface Params
copy
in class Model<Word2VecModel>
extra
- (undocumented)defaultCopy()
public MLWriter write()
MLWritable
MLWriter
instance for this ML instance.write
in interface MLWritable
public IntParam vectorSize()
public int getVectorSize()
public IntParam windowSize()
public int getWindowSize()
public IntParam numPartitions()
public int getNumPartitions()
public IntParam minCount()
public int getMinCount()
public StructType validateAndTransformSchema(StructType schema)
schema
- (undocumented)public Param<java.lang.String> inputCol()
public java.lang.String getInputCol()
public Param<java.lang.String> outputCol()
public java.lang.String getOutputCol()
public IntParam maxIter()
public int getMaxIter()
public DoubleParam stepSize()
public double getStepSize()
public LongParam seed()
public long getSeed()