def __init__(self,
standardize=True,
family="gaussian",
link="family_default",
solver="AUTO",
tweedieVariancePower=0.0,
tweedieLinkPower=0.0,
alphaValue=None,
lambdaValue=None,
missingValuesHandling="MeanImputation",
prior=-1.0,
lambdaSearch=False,
nlambdas=-1,
nonNegative=False,
exactLambdas=False,
lambdaMinRatio=-1.0,
maxIterations=-1,
intercept=True,
betaEpsilon=1e-4,
objectiveEpsilon=-1.0,
gradientEpsilon=-1.0,
objReg=-1.0,
computePValues=False,
removeCollinearCols=False,
interactions=None,
interactionPairs=None,
earlyStopping=True,
modelId=None,
keepCrossValidationPredictions=False,
keepCrossValidationFoldAssignment=False,
parallelizeCrossValidation=True,
distribution="AUTO",
labelCol="label",
foldCol=None,
weightCol=None,
splitRatio=1.0,
seed=-1,
nfolds=0,
allStringColumnsToCategorical=True,
columnsToCategorical=[],
predictionCol="prediction",
detailedPredictionCol="detailed_prediction",
withDetailedPredictionCol=False,
featuresCols=[],
convertUnknownCategoricalLevelsToNa=False,
convertInvalidNumbersToNa=False,
namedMojoOutputColumns=True,
**DeprecatedParams):
Initializer.load_sparkling_jar()
super(H2OGLM, self).__init__()
self._java_obj = self._new_java_obj("ai.h2o.sparkling.ml.algos.H2OGLM", self.uid)
self._setDefaultValuesFromJava()
kwargs = Utils.getInputKwargs(self)
Utils.propagateValueFromDeprecatedProperty(kwargs, "alpha", "alphaValue")
Utils.propagateValueFromDeprecatedProperty(kwargs, "lambda_", "lambdaValue")
self._set(**kwargs)
def __init__(self,
algo=None,
hyperParameters={},
strategy="Cartesian",
maxRuntimeSecs=0.0,
maxModels=0,
stoppingRounds=0,
stoppingTolerance=0.001,
stoppingMetric="AUTO",
selectBestModelBy="AUTO",
parallelism=1,
labelCol="label",
foldCol=None,
weightCol=None,
offsetCol=None,
splitRatio=1.0,
seed=-1,
nfolds=0,
allStringColumnsToCategorical=True,
columnsToCategorical=[],
predictionCol="prediction",
detailedPredictionCol="detailed_prediction",
withDetailedPredictionCol=False,
featuresCols=[],
convertUnknownCategoricalLevelsToNa=False,
convertInvalidNumbersToNa=False,
namedMojoOutputColumns=True,
**DeprecatedParams):
Initializer.load_sparkling_jar()
super(H2OGridSearch, self).__init__()
self._java_obj = self._new_java_obj(
"ai.h2o.sparkling.ml.algos.H2OGridSearch", self.uid)
self._setDefaultValuesFromJava()
kwargs = Utils.getInputKwargs(self)
self._set(**kwargs)
def __init__(self,
epochs=10.0,
l1=0.0,
l2=0.0,
hidden=[200, 200],
reproducible=False,
modelId=None,
keepCrossValidationPredictions=False,
keepCrossValidationFoldAssignment=False,
parallelizeCrossValidation=True,
distribution="AUTO",
labelCol="label",
foldCol=None,
weightCol=None,
splitRatio=1.0,
seed=-1,
nfolds=0,
allStringColumnsToCategorical=True,
columnsToCategorical=[],
predictionCol="prediction",
detailedPredictionCol="detailed_prediction",
withDetailedPredictionCol=False,
featuresCols=[],
convertUnknownCategoricalLevelsToNa=False,
convertInvalidNumbersToNa=False,
namedMojoOutputColumns=True):
Initializer.load_sparkling_jar()
super(H2ODeepLearning, self).__init__()
self._java_obj = self._new_java_obj("ai.h2o.sparkling.ml.algos.H2ODeepLearning", self.uid)
self._setDefaultValuesFromJava()
kwargs = Utils.getInputKwargs(self)
self._set(**kwargs)
def __init__(self,
maxIterations=10,
standardize=True,
init="Furthest",
userPoints=None,
estimateK=False,
k=2,
modelId=None,
keepCrossValidationPredictions=False,
keepCrossValidationFoldAssignment=False,
parallelizeCrossValidation=True,
distribution="AUTO",
foldCol=None,
weightCol=None,
splitRatio=1.0,
seed=-1,
nfolds=0,
allStringColumnsToCategorical=True,
columnsToCategorical=[],
predictionCol="prediction",
detailedPredictionCol="detailed_prediction",
withDetailedPredictionCol=False,
featuresCols=[],
convertUnknownCategoricalLevelsToNa=False,
convertInvalidNumbersToNa=False,
namedMojoOutputColumns=True):
Initializer.load_sparkling_jar()
super(H2OKMeans, self).__init__()
self._java_obj = self._new_java_obj(
"ai.h2o.sparkling.ml.algos.H2OKMeans", self.uid)
self._setDefaultValuesFromJava()
kwargs = Utils.getInputKwargs(self)
self._set(**kwargs)
def __init__(self, keep=False, columns=[]):
Initializer.load_sparkling_jar()
super(ColumnPruner, self).__init__()
self._java_obj = self._new_java_obj(
"ai.h2o.sparkling.ml.features.ColumnPruner", self.uid)
self._setDefaultValuesFromJava()
kwargs = Utils.getInputKwargs(self)
self._set(**kwargs)
def __init__(self,
learnRate=0.1,
learnRateAnnealing=1.0,
colSampleRate=1.0,
maxAbsLeafnodePred=Utils.javaDoubleMaxValue,
predNoiseBandwidth=0.0,
quantileAlpha=0.5,
ntrees=50,
maxDepth=5,
minRows=10.0,
nbins=20,
nbinsCats=1024,
minSplitImprovement=1e-5,
histogramType="AUTO",
nbinsTopLevel=1 << 10,
buildTreeOneNode=False,
scoreTreeInterval=0,
sampleRate=1.0,
sampleRatePerClass=None,
colSampleRateChangePerLevel=1.0,
colSampleRatePerTree=1.0,
modelId=None,
keepCrossValidationPredictions=False,
keepCrossValidationFoldAssignment=False,
parallelizeCrossValidation=True,
distribution="AUTO",
labelCol="label",
foldCol=None,
weightCol=None,
offsetCol=None,
splitRatio=1.0,
seed=-1,
nfolds=0,
allStringColumnsToCategorical=True,
columnsToCategorical=[],
predictionCol="prediction",
detailedPredictionCol="detailed_prediction",
withDetailedPredictionCol=False,
featuresCols=[],
convertUnknownCategoricalLevelsToNa=False,
convertInvalidNumbersToNa=False,
namedMojoOutputColumns=True,
monotoneConstraints={},
stoppingRounds=0,
stoppingMetric="AUTO",
stoppingTolerance=0.001):
Initializer.load_sparkling_jar()
super(H2OGBM, self).__init__()
self._java_obj = self._new_java_obj("ai.h2o.sparkling.ml.algos.H2OGBM",
self.uid)
self._setDefaultValuesFromJava()
kwargs = Utils.getInputKwargs(self)
self._set(**kwargs)
def __init__(self,
maxIterations=10,
standardize=True,
init="Furthest",
userPoints=None,
estimateK=False,
k=2,
modelId=None,
keepCrossValidationPredictions=False,
keepCrossValidationFoldAssignment=False,
keepCrossValidationModels=True,
parallelizeCrossValidation=True,
distribution="AUTO",
foldCol=None,
weightCol=None,
splitRatio=1.0,
seed=-1,
nfolds=0,
columnsToCategorical=[],
predictionCol="prediction",
detailedPredictionCol="detailed_prediction",
withDetailedPredictionCol=False,
featuresCols=[],
convertUnknownCategoricalLevelsToNa=False,
convertInvalidNumbersToNa=False,
namedMojoOutputColumns=True,
quantileAlpha=0.5,
tweediePower=1.5,
maxCategoricalLevels=10,
ignoredCols=None,
ignoreConstCols=True,
scoreEachIteration=False,
customDistributionFunc=None,
customMetricFunc=None,
exportCheckpointsDir=None,
stoppingRounds=0,
stoppingMetric="AUTO",
maxRuntimeSecs=0.0,
clusterSizeConstraints=None,
stoppingTolerance=0.001,
foldAssignment="AUTO",
categoricalEncoding="AUTO",
huberAlpha=0.9):
Initializer.load_sparkling_jar()
super(H2OKMeans, self).__init__()
self._java_obj = self._new_java_obj(
"ai.h2o.sparkling.ml.algos.H2OKMeans", self.uid)
self._setDefaultValuesFromJava()
kwargs = Utils.getInputKwargs(self)
self._set(**kwargs)
def __init__(self,
foldCol=None,
labelCol="label",
inputCols=[],
holdoutStrategy="None",
blendedAvgEnabled=False,
blendedAvgInflectionPoint=10.0,
blendedAvgSmoothing=20.0,
noise=0.01,
noiseSeed=-1):
Initializer.load_sparkling_jar()
super(H2OTargetEncoder, self).__init__()
self._java_obj = self._new_java_obj(
"ai.h2o.sparkling.ml.features.H2OTargetEncoder", self.uid)
self._setDefaultValuesFromJava()
kwargs = Utils.getInputKwargs(self)
self._set(**kwargs)
def __init__(self,
binomialDoubleTrees=False,
mtries=-1,
ntrees=50,
maxDepth=20,
minRows=1,
nbins=20,
nbinsCats=1024,
minSplitImprovement=1e-5,
histogramType="AUTO",
r2Stopping=Utils.javaDoubleMaxValue,
nbinsTopLevel=1 << 10,
buildTreeOneNode=False,
scoreTreeInterval=0,
sampleRate=1.0,
sampleRatePerClass=None,
colSampleRateChangePerLevel=1.0,
colSampleRatePerTree=1.0,
modelId=None,
keepCrossValidationPredictions=False,
keepCrossValidationFoldAssignment=False,
parallelizeCrossValidation=True,
distribution="AUTO",
labelCol="label",
foldCol=None,
weightCol=None,
splitRatio=1.0,
seed=-1,
nfolds=0,
allStringColumnsToCategorical=True,
columnsToCategorical=[],
predictionCol="prediction",
detailedPredictionCol="detailed_prediction",
withDetailedPredictionCol=False,
featuresCols=[],
convertUnknownCategoricalLevelsToNa=False,
convertInvalidNumbersToNa=False,
namedMojoOutputColumns=True):
Initializer.load_sparkling_jar()
super(H2ODRF, self).__init__()
self._java_obj = self._new_java_obj("ai.h2o.sparkling.ml.algos.H2ODRF",
self.uid)
self._setDefaultValuesFromJava()
kwargs = Utils.getInputKwargs(self)
self._set(**kwargs)
def __init__(self,
ignoredCols=[],
includeAlgos=[
"GLM", "DRF", "GBM", "DeepLearning", "StackedEnsemble",
"XGBoost"
],
excludeAlgos=[],
projectName=None,
maxRuntimeSecs=0.0,
stoppingRounds=3,
stoppingTolerance=0.001,
stoppingMetric="AUTO",
sortMetric="AUTO",
balanceClasses=False,
classSamplingFactors=None,
maxAfterBalanceSize=5.0,
keepCrossValidationPredictions=False,
keepCrossValidationModels=False,
maxModels=0,
labelCol="label",
foldCol=None,
weightCol=None,
offsetCol=None,
splitRatio=1.0,
seed=-1,
nfolds=5,
allStringColumnsToCategorical=True,
columnsToCategorical=[],
predictionCol="prediction",
detailedPredictionCol="detailed_prediction",
withDetailedPredictionCol=False,
featuresCols=[],
convertUnknownCategoricalLevelsToNa=False,
convertInvalidNumbersToNa=False,
namedMojoOutputColumns=True,
monotoneConstraints={}):
Initializer.load_sparkling_jar()
super(H2OAutoML, self).__init__()
self._java_obj = self._new_java_obj(
"ai.h2o.sparkling.ml.algos.H2OAutoML", self.uid)
self._setDefaultValuesFromJava()
kwargs = Utils.getInputKwargs(self)
self._set(**kwargs)
def __init__(self,
algo=None,
hyperParameters={},
strategy="Cartesian",
maxRuntimeSecs=0.0,
maxModels=0,
stoppingRounds=0,
stoppingTolerance=0.001,
stoppingMetric="AUTO",
selectBestModelBy="AUTO",
selectBestModelDecreasing=True,
labelCol="label",
foldCol=None,
weightCol=None,
splitRatio=1.0,
seed=-1,
nfolds=0,
allStringColumnsToCategorical=True,
columnsToCategorical=[],
predictionCol="prediction",
detailedPredictionCol="detailed_prediction",
withDetailedPredictionCol=False,
featuresCols=[],
convertUnknownCategoricalLevelsToNa=False,
convertInvalidNumbersToNa=False):
Initializer.load_sparkling_jar()
super(H2OGridSearch, self).__init__()
self._java_obj = self._new_java_obj(
"ai.h2o.sparkling.ml.algos.H2OGridSearch", self.uid)
self._setDefaultValuesFromJava(["algoParams"])
kwargs = Utils.getInputKwargs(self)
if "algo" in kwargs and kwargs["algo"] is not None:
tmp = kwargs["algo"]
del kwargs['algo']
self._java_obj.setAlgo(tmp._java_obj)
self._set(**kwargs)
def getAlpha(self):
Utils.deprecationWarning("getAlpha", "getAlphaValue")
return self.getAlphaValue()
def __init__(self,
binomialDoubleTrees=False,
mtries=-1,
ntrees=50,
maxDepth=20,
minRows=1,
nbins=20,
nbinsCats=1024,
minSplitImprovement=1e-5,
histogramType="AUTO",
nbinsTopLevel=1 << 10,
buildTreeOneNode=False,
scoreTreeInterval=0,
sampleRate=1.0,
sampleRatePerClass=None,
colSampleRateChangePerLevel=1.0,
colSampleRatePerTree=1.0,
modelId=None,
keepCrossValidationPredictions=False,
keepCrossValidationFoldAssignment=False,
parallelizeCrossValidation=True,
distribution="AUTO",
labelCol="label",
foldCol=None,
weightCol=None,
offsetCol=None,
splitRatio=1.0,
seed=-1,
nfolds=0,
columnsToCategorical=[],
predictionCol="prediction",
detailedPredictionCol="detailed_prediction",
withDetailedPredictionCol=False,
featuresCols=[],
convertUnknownCategoricalLevelsToNa=False,
convertInvalidNumbersToNa=False,
namedMojoOutputColumns=True,
stoppingRounds=0,
stoppingMetric="AUTO",
stoppingTolerance=0.001,
customDistributionFunc=None,
customMetricFunc=None,
maxRuntimeSecs=0.0,
exportCheckpointsDir=None,
classSamplingFactors=None,
huberAlpha=0.9,
tweediePower=1.5,
quantileAlpha=0.5,
ignoredCols=None,
ignoreConstCols=True,
scoreEachIteration=False,
maxCategoricalLevels=10,
maxAfterBalanceSize=5.0,
balanceClasses=False,
calibrateModel=False,
checkConstantResponse=True,
foldAssignment="AUTO",
categoricalEncoding="AUTO",
keepCrossValidationModels=True):
Initializer.load_sparkling_jar()
super(H2ODRF, self).__init__()
self._java_obj = self._new_java_obj("ai.h2o.sparkling.ml.algos.H2ODRF",
self.uid)
self._setDefaultValuesFromJava()
kwargs = Utils.getInputKwargs(self)
self._set(**kwargs)
def setLambda(self, value):
Utils.deprecationWarning("setLambda", "setLambdaValue")
return self.setLambdaValue(value)
def getNEstimators(self):
Utils.methodDeprecationWarning("getNEstimators")
return 0
def __init__(self,
standardize=True,
family="gaussian",
link="family_default",
solver="AUTO",
tweedieVariancePower=0.0,
tweedieLinkPower=0.0,
alphaValue=None,
lambdaValue=None,
missingValuesHandling="MeanImputation",
prior=-1.0,
lambdaSearch=False,
nlambdas=-1,
nonNegative=False,
lambdaMinRatio=-1.0,
maxIterations=-1,
intercept=True,
betaEpsilon=1e-4,
objectiveEpsilon=-1.0,
gradientEpsilon=-1.0,
objReg=-1.0,
computePValues=False,
removeCollinearCols=False,
interactions=None,
interactionPairs=None,
earlyStopping=True,
modelId=None,
keepCrossValidationPredictions=False,
keepCrossValidationFoldAssignment=False,
keepCrossValidationModels=True,
parallelizeCrossValidation=True,
distribution="AUTO",
labelCol="label",
foldCol=None,
weightCol=None,
offsetCol=None,
splitRatio=1.0,
seed=-1,
nfolds=0,
columnsToCategorical=[],
predictionCol="prediction",
detailedPredictionCol="detailed_prediction",
withDetailedPredictionCol=False,
featuresCols=[],
convertUnknownCategoricalLevelsToNa=False,
convertInvalidNumbersToNa=False,
namedMojoOutputColumns=True,
balanceClasses=False,
quantileAlpha=0.5,
stoppingMetric="AUTO",
stoppingTolerance=0.0001,
stoppingRounds=3,
categoricalEncoding="AUTO",
exportCheckpointsDir=None,
ignoredCols=None,
ignoreConstCols=True,
classSamplingFactors=None,
maxAfterBalanceSize=5.0,
maxCategoricalLevels=10,
HGLM=False,
customDistributionFunc=None,
customMetricFunc=None,
startval=None,
theta=0.0000000001,
tweediePower=1.5,
scoreEachIteration=False,
huberAlpha=0.9,
maxActivePredictors=-1,
foldAssignment="AUTO",
calcLike=False,
maxRuntimeSecs=0.0,
**DeprecatedParams):
Initializer.load_sparkling_jar()
super(H2OGLM, self).__init__()
self._java_obj = self._new_java_obj("ai.h2o.sparkling.ml.algos.H2OGLM",
self.uid)
self._setDefaultValuesFromJava()
kwargs = Utils.getInputKwargs(self)
self._set(**kwargs)
def setNEstimators(self, value):
Utils.methodDeprecationWarning("setNEstimators")
return self
def getLambda(self):
Utils.deprecationWarning("getLambda", "getLambdaValue")
return self.getLambdaValue()
def setAlpha(self, value):
Utils.deprecationWarning("setAlpha", "setAlphaValue")
return self.setAlphaValue(value)
def __init__(self,
quietMode=True,
ntrees=50,
maxDepth=6,
minRows=1.0,
minChildWeight=1.0,
learnRate=0.3,
eta=0.3,
learnRateAnnealing=1.0,
sampleRate=1.0,
subsample=1.0,
colSampleRate=1.0,
colSampleByLevel=1.0,
colSampleRatePerTree=1.0,
colSampleByTree=1.0,
maxAbsLeafnodePred=0.0,
maxDeltaStep=0.0,
scoreTreeInterval=0,
initialScoreInterval=4000,
scoreInterval=4000,
minSplitImprovement=0.0,
gamma=0.0,
nthread=-1,
maxBins=256,
maxLeaves=0,
minSumHessianInLeaf=100.0,
minDataInLeaf=0.0,
treeMethod="auto",
growPolicy="depthwise",
booster="gbtree",
dmatrixType="auto",
regLambda=0.0,
regAlpha=0.0,
sampleType="uniform",
normalizeType="tree",
rateDrop=0.0,
oneDrop=False,
skipDrop=0.0,
gpuId=0,
backend="auto",
modelId=None,
keepCrossValidationPredictions=False,
keepCrossValidationFoldAssignment=False,
parallelizeCrossValidation=True,
distribution="AUTO",
labelCol="label",
foldCol=None,
weightCol=None,
offsetCol=None,
splitRatio=1.0,
seed=-1,
nfolds=0,
allStringColumnsToCategorical=True,
columnsToCategorical=[],
predictionCol="prediction",
detailedPredictionCol="detailed_prediction",
withDetailedPredictionCol=False,
featuresCols=[],
convertUnknownCategoricalLevelsToNa=False,
convertInvalidNumbersToNa=False,
namedMojoOutputColumns=True,
monotoneConstraints={},
stoppingRounds=0,
stoppingMetric="AUTO",
stoppingTolerance=0.001,
**DeprecatedParams):
Initializer.load_sparkling_jar()
super(H2OXGBoost, self).__init__()
self._java_obj = self._new_java_obj(
"ai.h2o.sparkling.ml.algos.H2OXGBoost", self.uid)
self._setDefaultValuesFromJava()
kwargs = Utils.getInputKwargs(self)
self._set(**kwargs)
def __init__(self,
epochs=10.0,
l1=0.0,
l2=0.0,
hidden=[200, 200],
reproducible=False,
activation="Rectifier",
quantileAlpha=0.5,
modelId=None,
keepCrossValidationPredictions=False,
keepCrossValidationFoldAssignment=False,
keepCrossValidationModels=True,
parallelizeCrossValidation=True,
distribution="AUTO",
labelCol="label",
foldCol=None,
weightCol=None,
offsetCol=None,
splitRatio=1.0,
seed=-1,
nfolds=0,
columnsToCategorical=[],
predictionCol="prediction",
detailedPredictionCol="detailed_prediction",
withDetailedPredictionCol=False,
featuresCols=[],
convertUnknownCategoricalLevelsToNa=False,
convertInvalidNumbersToNa=False,
namedMojoOutputColumns=True,
stoppingRounds=5,
stoppingMetric="AUTO",
stoppingTolerance=0.001,
inputDropoutRatio=0.0,
shuffleTrainingData=False,
rateDecay=1.0,
singleNodeMode=False,
ignoredCols=None,
ignoreConstCols=True,
hiddenDropoutRatios=None,
useAllFactorLevels=True,
missingValuesHandling="MeanImputation",
maxCategoricalFeatures=2147483647,
fastMode=True,
sparse=False,
scoreTrainingSamples=10000,
adaptiveRate=True,
initialWeightScale=1.0,
customMetricFunc=None,
customDistributionFunc=None,
autoencoder=False,
classificationStop=0.0,
standardize=True,
targetRatioCommToComp=0.05,
classSamplingFactors=None,
elasticAveragingMovingRate=0.9,
quietMode=False,
scoreValidationSampling="Uniform",
epsilon=.00000001,
trainSamplesPerIteration=-2,
diagnostics=True,
momentumStable=0.0,
rate=0.005,
regressionStop=0.000001,
initialWeightDistribution="UniformAdaptive",
sparsityBeta=0.0,
variableImportances=True,
loss="Automatic",
rateAnnealing=0.000001,
scoreDutyCycle=0.1,
maxRuntimeSecs=0.0,
exportCheckpointsDir=None,
nesterovAcceleratedGradient=True,
momentumRamp=1000000.0,
rho=0.99,
scoreInterval=5.0,
balanceClasses=False,
elasticAveraging=False,
averageActivation=0.0,
forceLoadBalance=True,
categoricalEncoding="AUTO",
momentumStart=0.0,
maxAfterBalanceSize=5.0,
tweediePower=1.5,
huberAlpha=0.9,
overwriteWithBestModel=True,
scoreEachIteration=False,
exportWeightsAndBiases=False,
foldAssignment="AUTO",
maxW2=sys.float_info.max,
elasticAveragingRegularization=0.001,
replicateTrainingData=True,
miniBatchSize=1,
scoreValidationSamples=0,
maxCategoricalLevels=10):
Initializer.load_sparkling_jar()
super(H2ODeepLearning, self).__init__()
self._java_obj = self._new_java_obj(
"ai.h2o.sparkling.ml.algos.H2ODeepLearning", self.uid)
self._setDefaultValuesFromJava()
kwargs = Utils.getInputKwargs(self)
self._set(**kwargs)
