.. _parameters_H2OGLRM:
Parameters of H2OGLRM
---------------------
Affected Class
##############
- ``ai.h2o.sparkling.ml.features.H2OGLRM``
Parameters
##########
- *Each parameter has also a corresponding getter and setter method.*
*(E.g.:* ``label`` *->* ``getLabel()`` *,* ``setLabel(...)`` *)*
maxScoringIterations
The maximum number of iterations used in MOJO scoring to update X
*Default value:* ``100``
*Also available on the trained model.*
reconstructedCol
Reconstructed column name. This column contains reconstructed input values (A_hat=X*Y instead of just X).
*Default value:* ``"H2OGLRM_d376573593d2__reconstructed"``
*Also available on the trained model.*
withReconstructedCol
A flag identifying whether a column with reconstructed input values will be produced or not.
*Scala default value:* ``false`` *; Python default value:* ``False``
*Also available on the trained model.*
lossByColNames
Columns names for which loss function will be overridden by the 'lossByCol' parameter
*Scala default value:* ``null`` *; Python default value:* ``None``
outputCol
Output column name
*Default value:* ``"H2OGLRM_d376573593d2__output"``
*Also available on the trained model.*
userX
User-specified initial matrix X.
*Scala default value:* ``null`` *; Python default value:* ``None``
userY
User-specified initial matrix Y.
*Scala default value:* ``null`` *; Python default value:* ``None``
columnsToCategorical
List of columns to convert to categorical before modelling
*Scala default value:* ``Array()`` *; Python default value:* ``[]``
convertInvalidNumbersToNa
If set to 'true', the model converts invalid numbers to NA during making predictions.
*Scala default value:* ``false`` *; Python default value:* ``False``
*Also available on the trained model.*
convertUnknownCategoricalLevelsToNa
If set to 'true', the model converts unknown categorical levels to NA during making predictions.
*Scala default value:* ``false`` *; Python default value:* ``False``
*Also available on the trained model.*
dataFrameSerializer
A full name of a serializer used for serialization and deserialization of Spark DataFrames to a JSON value within NullableDataFrameParam.
*Default value:* ``"ai.h2o.sparkling.utils.JSONDataFrameSerializer"``
*Also available on the trained model.*
expandUserY
Expand categorical columns in user-specified initial Y.
*Scala default value:* ``true`` *; Python default value:* ``True``
*Also available on the trained model.*
exportCheckpointsDir
Automatically export generated models to this directory.
*Scala default value:* ``null`` *; Python default value:* ``None``
*Also available on the trained model.*
gammaX
Regularization weight on X matrix.
*Default value:* ``0.0``
*Also available on the trained model.*
gammaY
Regularization weight on Y matrix.
*Default value:* ``0.0``
*Also available on the trained model.*
ignoreConstCols
Ignore constant columns.
*Scala default value:* ``true`` *; Python default value:* ``True``
*Also available on the trained model.*
ignoredCols
Names of columns to ignore for training.
*Scala default value:* ``null`` *; Python default value:* ``None``
*Also available on the trained model.*
imputeOriginal
Reconstruct original training data by reversing transform.
*Scala default value:* ``false`` *; Python default value:* ``False``
*Also available on the trained model.*
init
Initialization mode. Possible values are ``"Random"``, ``"SVD"``, ``"PlusPlus"``, ``"User"``, ``"Power"``.
*Default value:* ``"PlusPlus"``
*Also available on the trained model.*
initStepSize
Initial step size.
*Default value:* ``1.0``
*Also available on the trained model.*
inputCols
The array of input columns
*Scala default value:* ``Array()`` *; Python default value:* ``[]``
*Also available on the trained model.*
k
Rank of matrix approximation.
*Default value:* ``1``
*Also available on the trained model.*
keepBinaryModels
If set to true, all binary models created during execution of the ``fit`` method will be kept in DKV of H2O-3 cluster.
*Scala default value:* ``false`` *; Python default value:* ``False``
loadingName
[Deprecated] Use representation_name instead. Frame key to save resulting X.
*Scala default value:* ``null`` *; Python default value:* ``None``
*Also available on the trained model.*
loss
Numeric loss function. Possible values are ``"Quadratic"``, ``"Absolute"``, ``"Huber"``, ``"Poisson"``, ``"Periodic(0)"``, ``"Logistic"``, ``"Hinge"``, ``"Categorical"``, ``"Ordinal"``.
*Default value:* ``"Quadratic"``
*Also available on the trained model.*
lossByCol
Loss function by column (override). Possible values are ``"Quadratic"``, ``"Absolute"``, ``"Huber"``, ``"Poisson"``, ``"Periodic(0)"``, ``"Logistic"``, ``"Hinge"``, ``"Categorical"``, ``"Ordinal"``.
*Scala default value:* ``null`` *; Python default value:* ``None``
*Also available on the trained model.*
maxIterations
Maximum number of iterations.
*Default value:* ``1000``
*Also available on the trained model.*
maxRuntimeSecs
Maximum allowed runtime in seconds for model training. Use 0 to disable.
*Default value:* ``0.0``
*Also available on the trained model.*
maxUpdates
Maximum number of updates, defaults to 2*max_iterations.
*Default value:* ``2000``
*Also available on the trained model.*
minStepSize
Minimum step size.
*Scala default value:* ``1.0e-4`` *; Python default value:* ``1.0E-4``
*Also available on the trained model.*
modelId
Destination id for this model; auto-generated if not specified.
*Scala default value:* ``null`` *; Python default value:* ``None``
multiLoss
Categorical loss function. Possible values are ``"Quadratic"``, ``"Absolute"``, ``"Huber"``, ``"Poisson"``, ``"Periodic(0)"``, ``"Logistic"``, ``"Hinge"``, ``"Categorical"``, ``"Ordinal"``.
*Default value:* ``"Categorical"``
*Also available on the trained model.*
period
Length of period (only used with periodic loss function).
*Default value:* ``1``
*Also available on the trained model.*
recoverSvd
Recover singular values and eigenvectors of XY.
*Scala default value:* ``false`` *; Python default value:* ``False``
*Also available on the trained model.*
regularizationX
Regularization function for X matrix. Possible values are ``"None"``, ``"Quadratic"``, ``"L2"``, ``"L1"``, ``"NonNegative"``, ``"OneSparse"``, ``"UnitOneSparse"``, ``"Simplex"``.
*Default value:* ``"None"``
*Also available on the trained model.*
regularizationY
Regularization function for Y matrix. Possible values are ``"None"``, ``"Quadratic"``, ``"L2"``, ``"L1"``, ``"NonNegative"``, ``"OneSparse"``, ``"UnitOneSparse"``, ``"Simplex"``.
*Default value:* ``"None"``
*Also available on the trained model.*
representationName
Frame key to save resulting X.
*Scala default value:* ``null`` *; Python default value:* ``None``
*Also available on the trained model.*
scoreEachIteration
Whether to score during each iteration of model training.
*Scala default value:* ``false`` *; Python default value:* ``False``
*Also available on the trained model.*
seed
RNG seed for initialization.
*Scala default value:* ``-1L`` *; Python default value:* ``-1``
*Also available on the trained model.*
splitRatio
Accepts values in range [0, 1.0] which determine how large part of dataset is used for training and for validation. For example, 0.8 -> 80% training 20% validation. This parameter is ignored when validationDataFrame is set.
*Default value:* ``1.0``
svdMethod
Method for computing SVD during initialization (Caution: Randomized is currently experimental and unstable). Possible values are ``"GramSVD"``, ``"Power"``, ``"Randomized"``.
*Default value:* ``"Randomized"``
*Also available on the trained model.*
transform
Transformation of training data. Possible values are ``"NONE"``, ``"STANDARDIZE"``, ``"NORMALIZE"``, ``"DEMEAN"``, ``"DESCALE"``.
*Default value:* ``"NONE"``
*Also available on the trained model.*
validationDataFrame
A data frame dedicated for a validation of the trained model. If the parameters is not set,a validation frame created via the 'splitRatio' parameter. The parameter is not serializable!
*Scala default value:* ``null`` *; Python default value:* ``None``