class H2OCommonSupervisedParams(H2OCommonParams):
labelCol = Param(
Params._dummy(),
"labelCol",
"Label column name",
H2OTypeConverters.toString())
def getLabelCol(self):
return self.getOrDefault(self.labelCol)
def setLabelCol(self, value):
return self._set(labelCol=value)
class HasValidationLabelCol(Params):
validationLabelCol = Param(
Params._dummy(), "validationLabelCol",
"(experimental) Name of the label column in the validation data frame. "
"The label column should be a string column with two distinct values indicating the anomaly. "
"The negative value must be alphabetically smaller than the positive value. (E.g. '0'/'1', 'False'/'True')",
H2OTypeConverters.toString())
def getValidationLabelCol(self):
return self.getOrDefault(self.validationLabelCol)
def setValidationLabelCol(self, value):
return self._set(validationLabelCol=value)
class H2OMOJOAlgoSharedParams(Params):
predictionCol = Param(
Params._dummy(),
"predictionCol",
"Prediction column name",
H2OTypeConverters.toString())
detailedPredictionCol = Param(
Params._dummy(),
"detailedPredictionCol",
"Column containing additional prediction details, its content depends on the model type.",
H2OTypeConverters.toString())
withDetailedPredictionCol = Param(
Params._dummy(),
"withDetailedPredictionCol",
"Enables or disables generating additional prediction column, but with more details",
H2OTypeConverters.toBoolean())
featuresCols = Param(
Params._dummy(),
"featuresCols",
"Name of feature columns",
H2OTypeConverters.toListString())
convertUnknownCategoricalLevelsToNa = Param(
Params._dummy(),
"convertUnknownCategoricalLevelsToNa",
"If set to 'true', the model converts unknown categorical levels to NA during making predictions.",
H2OTypeConverters.toBoolean())
convertInvalidNumbersToNa = Param(
Params._dummy(),
"convertInvalidNumbersToNa",
"If set to 'true', the model converts invalid numbers to NA during making predictions.",
H2OTypeConverters.toBoolean())
namedMojoOutputColumns = Param(
Params._dummy(),
"namedMojoOutputColumns",
"Mojo Output is not stored in the array but in the properly named columns",
H2OTypeConverters.toBoolean())
##
# Getters
##
def getPredictionCol(self):
return self.getOrDefault(self.predictionCol)
def getDetailedPredictionCol(self):
return self.getOrDefault(self.detailedPredictionCol)
def getWithDetailedPredictionCol(self):
return self.getOrDefault(self.withDetailedPredictionCol)
def getFeaturesCols(self):
return self.getOrDefault(self.featuresCols)
def getConvertUnknownCategoricalLevelsToNa(self):
return self.getOrDefault(self.convertUnknownCategoricalLevelsToNa)
def getConvertInvalidNumbersToNa(self):
return self.getOrDefault(self.convertInvalidNumbersToNa)
def getNamedMojoOutputColumns(self):
return self.getOrDefault(self.namedMojoOutputColumns)
class H2OTargetEncoderParams(Params):
##
# Param definitions
##
foldCol = Param(Params._dummy(), "foldCol", "Fold column name",
H2OTypeConverters.toNullableString())
labelCol = Param(Params._dummy(), "labelCol", "Label column name",
H2OTypeConverters.toString())
inputCols = Param(Params._dummy(), "inputCols",
"Names of columns that will be transformed",
H2OTypeConverters.toListString())
outputCols = Param(
Params._dummy(), "outputCols",
"Names of columns representing the result of target encoding",
H2OTypeConverters.toListString())
holdoutStrategy = Param(
Params._dummy(), "holdoutStrategy",
"""A strategy deciding what records will be excluded when calculating the target average on the training dataset.
Options:
None - All rows are considered for the calculation
LeaveOneOut - All rows except the row the calculation is made for
KFold - Only out-of-fold data is considered (The option requires foldCol to be set.""",
H2OTypeConverters.toEnumString(
"ai.h2o.targetencoding.TargetEncoder$DataLeakageHandlingStrategy"))
blendedAvgEnabled = Param(
Params._dummy(), "blendedAvgEnabled",
"If set, the target average becomes a weighted average of the posterior average for a given "
"categorical level and the prior average of the target. The weight is determined by the size "
"of the given group that the row belongs to. By default, the blended average is disabled.",
H2OTypeConverters.toBoolean())
blendedAvgInflectionPoint = Param(
Params._dummy(), "blendedAvgInflectionPoint",
"A parameter of the blended average. The bigger number is set, the groups relatively bigger to the "
"overall data set size will consider the global target value as a component in the weighted average. "
"The default value is 10."
"", H2OTypeConverters.toFloat())
blendedAvgSmoothing = Param(
Params._dummy(), "blendedAvgSmoothing",
"A parameter of blended average. Controls the rate of transition between a group target value "
"and a global target value. The default value is 20.",
H2OTypeConverters.toFloat())
noise = Param(
Params._dummy(), "noise",
"Amount of random noise added to output values. The default value is 0.01",
H2OTypeConverters.toFloat())
noiseSeed = Param(Params._dummy(), "noiseSeed",
"A seed of the generator producing the random noise",
H2OTypeConverters.toInt())
##
# Getters
##
def getFoldCol(self):
return self.getOrDefault(self.foldCol)
def getLabelCol(self):
return self.getOrDefault(self.labelCol)
def getInputCols(self):
return self.getOrDefault(self.inputCols)
def getOutputCols(self):
columns = self.getOrDefault(self.outputCols)
if not columns:
return list(map(lambda c: c + "_te", self.getInputCols()))
else:
return columns
def getHoldoutStrategy(self):
return self.getOrDefault(self.holdoutStrategy)
def getBlendedAvgEnabled(self):
return self.getOrDefault(self.blendedAvgEnabled)
def getBlendedAvgInflectionPoint(self):
return self.getOrDefault(self.blendedAvgInflectionPoint)
def getBlendedAvgSmoothing(self):
return self.getOrDefault(self.blendedAvgSmoothing)
def getNoise(self):
return self.getOrDefault(self.noise)
def getNoiseSeed(self):
return self.getOrDefault(self.noiseSeed)
class H2OBaseMOJOParams(Params):
predictionCol = Param(
Params._dummy(),
"predictionCol",
"Prediction column name",
H2OTypeConverters.toString())
detailedPredictionCol = Param(
Params._dummy(),
"detailedPredictionCol",
"Column containing additional prediction details, its content depends on the model type.",
H2OTypeConverters.toString())
withDetailedPredictionCol = Param(
Params._dummy(),
"withDetailedPredictionCol",
"Enables or disables generating additional prediction column, but with more details",
H2OTypeConverters.toBoolean())
withContributions = Param(
Params._dummy(),
"withContributions",
"Enables or disables generating a sub-column of detailedPredictionCol containing Shapley values.",
H2OTypeConverters.toBoolean())
featuresCols = Param(
Params._dummy(),
"featuresCols",
"Name of feature columns",
H2OTypeConverters.toListString())
convertUnknownCategoricalLevelsToNa = Param(
Params._dummy(),
"convertUnknownCategoricalLevelsToNa",
"If set to 'true', the model converts unknown categorical levels to NA during making predictions.",
H2OTypeConverters.toBoolean())
convertInvalidNumbersToNa = Param(
Params._dummy(),
"convertInvalidNumbersToNa",
"If set to 'true', the model converts invalid numbers to NA during making predictions.",
H2OTypeConverters.toBoolean())
namedMojoOutputColumns = Param(
Params._dummy(),
"namedMojoOutputColumns",
"Mojo Output is not stored in the array but in the properly named columns",
H2OTypeConverters.toBoolean())
withLeafNodeAssignments = Param(
Params._dummy(),
"withLeafNodeAssignments",
"Enables or disables computation of leaf node assignments.",
H2OTypeConverters.toBoolean())
withStageResults = Param(
Params._dummy(),
"withStageResults",
"Enables or disables computation of stage results.",
H2OTypeConverters.toBoolean())
##
# Getters
##
def getPredictionCol(self):
return self.getOrDefault(self.predictionCol)
def getDetailedPredictionCol(self):
return self.getOrDefault(self.detailedPredictionCol)
def getWithDetailedPredictionCol(self):
warnings.warn("The method will be removed without a replacement in the version 3.34."
"Detailed prediction columns is always enabled.", DeprecationWarning)
return True
def getWithContributions(self):
return self.getOrDefault(self.withContributions)
def getFeaturesCols(self):
return self.getOrDefault(self.featuresCols)
def getConvertUnknownCategoricalLevelsToNa(self):
return self.getOrDefault(self.convertUnknownCategoricalLevelsToNa)
def getConvertInvalidNumbersToNa(self):
return self.getOrDefault(self.convertInvalidNumbersToNa)
def getNamedMojoOutputColumns(self):
return self.getOrDefault(self.namedMojoOutputColumns)
def getWithLeafNodeAssignments(self):
return self.getOrDefault(self.withLeafNodeAssignments)
def getWithStageResults(self):
return self.getOrDefault(self.withStageResults)