Package edu.columbia.tjw.item.spark

Class ItemClassifier

java.lang.Object

org.apache.spark.ml.PipelineStage

org.apache.spark.ml.Estimator<M>

org.apache.spark.ml.Predictor<FeaturesType,E,M>

org.apache.spark.ml.classification.Classifier<FeaturesType,E,M>

org.apache.spark.ml.classification.ProbabilisticClassifier<org.apache.spark.ml.linalg.Vector,ItemClassifier,ItemClassificationModel>

edu.columbia.tjw.item.spark.ItemClassifier

All Implemented Interfaces:

Serializable, Cloneable, org.apache.spark.internal.Logging, org.apache.spark.ml.classification.ClassifierParams, org.apache.spark.ml.classification.ProbabilisticClassifierParams, org.apache.spark.ml.param.Params, org.apache.spark.ml.param.shared.HasFeaturesCol, org.apache.spark.ml.param.shared.HasLabelCol, org.apache.spark.ml.param.shared.HasPredictionCol, org.apache.spark.ml.param.shared.HasProbabilityCol, org.apache.spark.ml.param.shared.HasRawPredictionCol, org.apache.spark.ml.param.shared.HasThresholds, org.apache.spark.ml.PredictorParams, org.apache.spark.ml.util.Identifiable, scala.Serializable

public class ItemClassifier
extends org.apache.spark.ml.classification.ProbabilisticClassifier<org.apache.spark.ml.linalg.Vector,ItemClassifier,ItemClassificationModel>
implements Cloneable

Author:

tyler

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor	Description
ItemClassifier(ItemClassifierSettings settings_)
ItemClassifier(ItemClassifierSettings settings_, edu.columbia.tjw.item.ItemParameters<edu.columbia.tjw.item.base.SimpleStatus,edu.columbia.tjw.item.base.SimpleRegressor,edu.columbia.tjw.item.base.StandardCurveType> startingParams_)

Method Summary

Modifier and Type	Method	Description
edu.columbia.tjw.item.fit.FitResult<edu.columbia.tjw.item.base.SimpleStatus,edu.columbia.tjw.item.base.SimpleRegressor,edu.columbia.tjw.item.base.StandardCurveType>	computeFitResult(org.apache.spark.sql.Dataset<?> data_, ItemClassificationModel model_)
edu.columbia.tjw.item.fit.GradientResult	computeGradients(org.apache.spark.sql.Dataset<?> data_, ItemClassificationModel model_)
ItemClassifier	copy(org.apache.spark.ml.param.ParamMap paramMap_)
edu.columbia.tjw.item.base.raw.RawFittingGrid<edu.columbia.tjw.item.base.SimpleStatus,edu.columbia.tjw.item.base.SimpleRegressor>	generateMaterializedGrid(org.apache.spark.sql.Dataset<?> data_)
ItemClassifierSettings	getSettings()
static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>	prepareData(org.apache.spark.sql.Dataset<?> data_, ItemClassifierSettings settings_, String featuresColumn_)
static ItemClassifierSettings	prepareSettings(org.apache.spark.sql.Dataset<?> data_, String toStatusColumn_, List<String> featureList, Set<String> curveRegressors_, int maxParamCount_)
static ItemClassifierSettings	prepareSettings(org.apache.spark.sql.Dataset<?> data_, String toStatusColumn_, List<String> featureList, Set<String> curveRegressors_, int maxParamCount_, edu.columbia.tjw.item.ItemSettings settings_)
ItemClassificationModel	retrainModel(org.apache.spark.sql.Dataset<?> data_, ItemClassificationModel prevModel_)
ItemClassificationModel	runAnnealing(org.apache.spark.sql.Dataset<?> data_, ItemClassificationModel prevModel_)
ItemClassificationModel	train(org.apache.spark.sql.Dataset<?> data_)
String	uid()

Methods inherited from class org.apache.spark.ml.classification.ProbabilisticClassifier

getProbabilityCol, getThresholds, org$apache$spark$ml$param$shared$HasProbabilityCol$_setter_$probabilityCol_$eq, org$apache$spark$ml$param$shared$HasThresholds$_setter_$thresholds_$eq, probabilityCol, setProbabilityCol, setThresholds, thresholds, validateAndTransformSchema

Methods inherited from class org.apache.spark.ml.classification.Classifier

extractLabeledPoints, getNumClasses, getNumClasses$default$2, getRawPredictionCol, org$apache$spark$ml$param$shared$HasRawPredictionCol$_setter_$rawPredictionCol_$eq, rawPredictionCol, setRawPredictionCol

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

extractLabeledPoints, featuresCol, featuresDataType, fit, getFeaturesCol, getLabelCol, getPredictionCol, labelCol, org$apache$spark$ml$param$shared$HasFeaturesCol$_setter_$featuresCol_$eq, org$apache$spark$ml$param$shared$HasLabelCol$_setter_$labelCol_$eq, org$apache$spark$ml$param$shared$HasPredictionCol$_setter_$predictionCol_$eq, predictionCol, setFeaturesCol, setLabelCol, setPredictionCol, transformSchema

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

fit, fit, fit, fit

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

$, clear, copyValues, copyValues$default$2, defaultCopy, defaultParamMap, explainParam, explainParams, extractParamMap, extractParamMap, get, getDefault, getOrDefault, getParam, hasDefault, hasParam, initializeLogIfNecessary, initializeLogIfNecessary, initializeLogIfNecessary$default$2, isDefined, isSet, isTraceEnabled, log, logDebug, logDebug, logError, logError, logInfo, logInfo, logName, logTrace, logTrace, logWarning, logWarning, org$apache$spark$internal$Logging$$log_, org$apache$spark$internal$Logging$$log__$eq, org$apache$spark$ml$param$Params$_setter_$defaultParamMap_$eq, org$apache$spark$ml$param$Params$_setter_$paramMap_$eq, paramMap, params, set, set, set, setDefault, setDefault, toString, transformSchema

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

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

featuresCol, getFeaturesCol, org$apache$spark$ml$param$shared$HasFeaturesCol$_setter_$featuresCol_$eq

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

getLabelCol, labelCol, org$apache$spark$ml$param$shared$HasLabelCol$_setter_$labelCol_$eq

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

getPredictionCol, org$apache$spark$ml$param$shared$HasPredictionCol$_setter_$predictionCol_$eq, predictionCol

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

getRawPredictionCol, org$apache$spark$ml$param$shared$HasRawPredictionCol$_setter_$rawPredictionCol_$eq, rawPredictionCol

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

toString

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

$, clear, copyValues, copyValues$default$2, defaultCopy, defaultParamMap, explainParam, explainParams, extractParamMap, extractParamMap, get, getDefault, getOrDefault, getParam, hasDefault, hasParam, isDefined, isSet, org$apache$spark$ml$param$Params$_setter_$defaultParamMap_$eq, org$apache$spark$ml$param$Params$_setter_$paramMap_$eq, paramMap, params, set, set, set, setDefault, setDefault

Constructor Detail

ItemClassifier

public ItemClassifier(ItemClassifierSettings settings_)

ItemClassifier

public ItemClassifier(ItemClassifierSettings settings_,
                      edu.columbia.tjw.item.ItemParameters<edu.columbia.tjw.item.base.SimpleStatus,edu.columbia.tjw.item.base.SimpleRegressor,edu.columbia.tjw.item.base.StandardCurveType> startingParams_)

Method Detail

copy

public ItemClassifier copy(org.apache.spark.ml.param.ParamMap paramMap_)

Specified by:

copy in interface org.apache.spark.ml.param.Params

Specified by:

copy in class org.apache.spark.ml.Predictor<org.apache.spark.ml.linalg.Vector,ItemClassifier,ItemClassificationModel>

getSettings

public ItemClassifierSettings getSettings()

generateMaterializedGrid

public edu.columbia.tjw.item.base.raw.RawFittingGrid<edu.columbia.tjw.item.base.SimpleStatus,edu.columbia.tjw.item.base.SimpleRegressor> generateMaterializedGrid(org.apache.spark.sql.Dataset<?> data_)

prepareData

public static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> prepareData(org.apache.spark.sql.Dataset<?> data_,
                                                                                 ItemClassifierSettings settings_,
                                                                                 String featuresColumn_)

prepareSettings

public static ItemClassifierSettings prepareSettings(org.apache.spark.sql.Dataset<?> data_,
                                                     String toStatusColumn_,
                                                     List<String> featureList,
                                                     Set<String> curveRegressors_,
                                                     int maxParamCount_)

prepareSettings

public static ItemClassifierSettings prepareSettings(org.apache.spark.sql.Dataset<?> data_,
                                                     String toStatusColumn_,
                                                     List<String> featureList,
                                                     Set<String> curveRegressors_,
                                                     int maxParamCount_,
                                                     edu.columbia.tjw.item.ItemSettings settings_)

computeGradients

public edu.columbia.tjw.item.fit.GradientResult computeGradients(org.apache.spark.sql.Dataset<?> data_,
                                                                 ItemClassificationModel model_)

computeFitResult

public edu.columbia.tjw.item.fit.FitResult<edu.columbia.tjw.item.base.SimpleStatus,edu.columbia.tjw.item.base.SimpleRegressor,edu.columbia.tjw.item.base.StandardCurveType> computeFitResult(org.apache.spark.sql.Dataset<?> data_,
                                                                                                                                                                                                         ItemClassificationModel model_)

runAnnealing

public ItemClassificationModel runAnnealing(org.apache.spark.sql.Dataset<?> data_,
                                            ItemClassificationModel prevModel_)

retrainModel

public ItemClassificationModel retrainModel(org.apache.spark.sql.Dataset<?> data_,
                                            ItemClassificationModel prevModel_)

train

public ItemClassificationModel train(org.apache.spark.sql.Dataset<?> data_)

Specified by:

train in class org.apache.spark.ml.Predictor<org.apache.spark.ml.linalg.Vector,ItemClassifier,ItemClassificationModel>

uid

public String uid()

Specified by:

uid in interface org.apache.spark.ml.util.Identifiable