public final class VectorSlicer extends Transformer
The subset of features can be specified with either indices (setIndices()
)
or names (setNames()
). At least one feature must be selected. Duplicate features
are not allowed, so there can be no overlap between selected indices and names.
The output vector will order features with the selected indices first (in the order given), followed by the selected names (in the order given).
Constructor and Description |
---|
VectorSlicer() |
VectorSlicer(java.lang.String uid) |
Modifier and Type | Method and Description |
---|---|
protected static <T> T |
$(Param<T> param) |
static Params |
clear(Param<?> param) |
VectorSlicer |
copy(ParamMap extra)
Creates a copy of this instance with the same UID and some extra params.
|
protected static <T extends Params> |
copyValues(T to,
ParamMap extra) |
protected static <T extends Params> |
copyValues$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) |
static <T> scala.Option<T> |
get(Param<T> param) |
static <T> scala.Option<T> |
getDefault(Param<T> param) |
int[] |
getIndices() |
static java.lang.String |
getInputCol() |
java.lang.String[] |
getNames() |
static <T> T |
getOrDefault(Param<T> param) |
static java.lang.String |
getOutputCol() |
static Param<java.lang.Object> |
getParam(java.lang.String paramName) |
static <T> boolean |
hasDefault(Param<T> param) |
static boolean |
hasParam(java.lang.String paramName) |
IntArrayParam |
indices()
An array of indices to select features from a vector column.
|
protected static void |
initializeLogIfNecessary(boolean isInterpreter) |
static Param<java.lang.String> |
inputCol() |
static boolean |
isDefined(Param<?> param) |
static boolean |
isSet(Param<?> param) |
protected static boolean |
isTraceEnabled() |
static VectorSlicer |
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) |
StringArrayParam |
names()
An array of feature names to select features from a vector column.
|
static Param<java.lang.String> |
outputCol() |
static Param<?>[] |
params() |
static void |
save(java.lang.String path) |
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) |
VectorSlicer |
setIndices(int[] value) |
VectorSlicer |
setInputCol(java.lang.String value) |
VectorSlicer |
setNames(java.lang.String[] value) |
VectorSlicer |
setOutputCol(java.lang.String value) |
static java.lang.String |
toString() |
Dataset<Row> |
transform(Dataset<?> dataset)
Transforms the input dataset.
|
StructType |
transformSchema(StructType schema)
:: DeveloperApi ::
|
java.lang.String |
uid()
An immutable unique ID for the object and its derivatives.
|
static void |
validateParams() |
static MLWriter |
write() |
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
public VectorSlicer(java.lang.String uid)
public VectorSlicer()
public static VectorSlicer 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 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 void save(java.lang.String path) throws java.io.IOException
java.io.IOException
public static MLWriter write()
public java.lang.String uid()
Identifiable
public IntArrayParam indices()
names
.
Default: Empty arraypublic int[] getIndices()
public VectorSlicer setIndices(int[] value)
public StringArrayParam names()
Attribute
s.
There can be no overlap with indices
.
Default: Empty Arraypublic java.lang.String[] getNames()
public VectorSlicer setNames(java.lang.String[] value)
public VectorSlicer setInputCol(java.lang.String value)
public VectorSlicer setOutputCol(java.lang.String value)
public Dataset<Row> transform(Dataset<?> dataset)
Transformer
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 VectorSlicer copy(ParamMap extra)
Params
copy
in interface Params
copy
in class Transformer
extra
- (undocumented)defaultCopy()