public final class QuantileDiscretizer extends Estimator<Bucketizer>
QuantileDiscretizer
takes a column with continuous features and outputs a column with binned
categorical features. The bin ranges are chosen by taking a sample of the data and dividing it
into roughly equal parts. The lower and upper bin bounds will be -Infinity and +Infinity,
covering all real values.Constructor and Description |
---|
QuantileDiscretizer() |
QuantileDiscretizer(java.lang.String uid) |
Modifier and Type | Method and Description |
---|---|
protected static <T> T |
$(Param<T> param) |
static Params |
clear(Param<?> param) |
QuantileDiscretizer |
copy(ParamMap extra)
Creates a copy of this instance with the same UID and some extra params.
|
protected static <T extends Params> |
copyValues(T to,
ParamMap extra) |
protected static <T extends Params> |
copyValues$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) |
Bucketizer |
fit(Dataset<?> dataset)
Fits a model to the input data.
|
static <T> scala.Option<T> |
get(Param<T> param) |
static <T> scala.Option<T> |
getDefault(Param<T> param) |
static java.lang.String |
getInputCol() |
static int |
getNumBuckets() |
int |
getNumBuckets() |
static <T> T |
getOrDefault(Param<T> param) |
static java.lang.String |
getOutputCol() |
static Param<java.lang.Object> |
getParam(java.lang.String paramName) |
static double |
getRelativeError() |
double |
getRelativeError() |
static long |
getSeed() |
static <T> boolean |
hasDefault(Param<T> param) |
static boolean |
hasParam(java.lang.String paramName) |
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 QuantileDiscretizer |
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 |
numBuckets() |
IntParam |
numBuckets()
Number of buckets (quantiles, or categories) into which data points are grouped.
|
static Param<java.lang.String> |
outputCol() |
static Param<?>[] |
params() |
static DoubleParam |
relativeError() |
DoubleParam |
relativeError()
Relative error (see documentation for
approxQuantile for description)
Must be a number in [0, 1]. |
static void |
save(java.lang.String path) |
static LongParam |
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) |
QuantileDiscretizer |
setInputCol(java.lang.String value) |
QuantileDiscretizer |
setNumBuckets(int value) |
QuantileDiscretizer |
setOutputCol(java.lang.String value) |
QuantileDiscretizer |
setRelativeError(double value) |
QuantileDiscretizer |
setSeed(long value) |
static java.lang.String |
toString() |
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() |
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 QuantileDiscretizer(java.lang.String uid)
public QuantileDiscretizer()
public static QuantileDiscretizer 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 final LongParam seed()
public static final long getSeed()
public static IntParam numBuckets()
public static int getNumBuckets()
public static DoubleParam relativeError()
public static double getRelativeError()
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
uid
in interface Identifiable
public QuantileDiscretizer setRelativeError(double value)
public QuantileDiscretizer setNumBuckets(int value)
public QuantileDiscretizer setInputCol(java.lang.String value)
public QuantileDiscretizer setOutputCol(java.lang.String value)
public QuantileDiscretizer setSeed(long value)
public StructType transformSchema(StructType schema)
PipelineStage
Derives the output schema from the input schema.
transformSchema
in class PipelineStage
schema
- (undocumented)public Bucketizer fit(Dataset<?> dataset)
Estimator
fit
in class Estimator<Bucketizer>
dataset
- (undocumented)public QuantileDiscretizer copy(ParamMap extra)
Params
copy
in interface Params
copy
in class Estimator<Bucketizer>
extra
- (undocumented)defaultCopy()
public IntParam numBuckets()
public int getNumBuckets()
public DoubleParam relativeError()
approxQuantile
for description)
Must be a number in [0, 1].
default: 0.001public double getRelativeError()