Model (h2o-core 3.42.0 API)

java.lang.Object
- water.Iced<T>
- - water.Keyed<T>
  - - water.Lockable<M>
    - - hex.Model<M,P,O>

All Implemented Interfaces:

java.io.Externalizable, java.io.Serializable, java.lang.Cloneable, StreamWriter, Freezable<M>

Direct Known Subclasses:

ClusteringModel, QuantileModel
```
public abstract class Model<M extends Model<M,P,O>,P extends Model.Parameters,O extends Model.Output>
extends Lockable<M>
implements StreamWriter
```
A Model models reality (hopefully). A model can be used to 'score' a row (make a prediction), or a collection of rows on any compatible dataset - meaning the row has all the columns with the same names as used to build the mode and any categorical columns can be adapted.

See Also:

Serialized Form

Nested Class Summary

Nested Classes
Modifier and Type	Class and Description
`static interface`	`Model.AdaptFrameParameters`
`protected class`	`Model.BigScore`
`static interface`	`Model.BigScoreChunkPredict`
`static interface`	`Model.BigScorePredict`
`static interface`	`Model.Contributions`
`static interface`	`Model.DeepFeatures`
`static interface`	`Model.ExemplarMembers`
`static interface`	`Model.FeatureFrequencies`
`static interface`	`Model.GetMostImportantFeatures`
`static interface`	`Model.GetNTrees`
`static interface`	`Model.GLRMArchetypes`
`static class`	`Model.GridSortBy`
`protected class`	`Model.H2OModelDescriptor`
`static interface`	`Model.InteractionBuilder`
`static class`	`Model.InteractionPair` This class represents a pair of interacting columns plus some additional data about specific enums to be interacted when the vecs are categorical.
`static class`	`Model.InteractionSpec`
`class`	`Model.JavaModelStreamWriter` Model stream writer - output Java code representation of model.
`static class`	`Model.JavaScoringOptions`
`static interface`	`Model.LeafNodeAssignment`
`static class`	`Model.Output` Model-specific output class.
`static class`	`Model.Parameters` Model-specific parameter class.
`protected class`	`Model.PredictScoreResult`
`static interface`	`Model.RowToTreeAssignment`
`static interface`	`Model.StagedPredictions`
`static interface`	`Model.UpdateAuxTreeWeights`

Field Summary

Fields
Modifier and Type	Field and Description
`Distribution`	`_dist`
`P`	`_input_parms`
`O`	`_output`
`P`	`_parms`
`IcedHashMap<Key,java.lang.String>`	`_toDelete`
`java.lang.String[]`	`_warnings`
`java.lang.String[]`	`_warningsP`
`static java.lang.String`	`EVAL_AUTO_PARAMS_ENABLED`
`boolean`	`evalAutoParamsEnabled`
`protected ScoringInfo[]`	`scoringInfo`

Fields inherited from class water.Lockable
_lockers

Fields inherited from class water.Keyed
_key

Constructor Summary

Constructors
Constructor and Description

Model(Key<M> selfKey, P parms, O output)
Full constructor

Constructors
Constructor and Description
`Model(Key<M> selfKey, P parms, O output)` Full constructor

Method Summary

All Methods Static Methods Instance Methods Abstract Methods Concrete Methods Deprecated Methods
Modifier and Type	Method and Description
`protected Frame`	`adaptFrameForScore(Frame fr, boolean computeMetrics, java.util.List<Frame> tmpFrames)`
`protected java.lang.String[]`	`adaptTestForJavaScoring(Frame test, boolean computeMetrics)`
`java.lang.String[]`	`adaptTestForTrain(Frame test, boolean expensive, boolean computeMetrics)` Adapt a Test/Validation Frame to be compatible for a Training Frame.
`java.lang.String[]`	`adaptTestForTrain(Frame test, boolean expensive, boolean computeMetrics, boolean catEncoded)`
`static java.lang.String[]`	`adaptTestForTrain(Frame test, java.lang.String[] origNames, java.lang.String[][] origDomains, java.lang.String[] names, java.lang.String[][] domains, Model.AdaptFrameParameters parms, boolean expensive, boolean computeMetrics, Model.InteractionBuilder interactionBldr, ToEigenVec tev, IcedHashMap<Key,java.lang.String> toDelete, boolean catEncoded)`
`ModelMetrics`	`addMetrics(ModelMetrics mm)`
`ModelMetrics`	`addModelMetrics(ModelMetrics mm)`
`void`	`addWarning(java.lang.String s)`
`double`	`auc()`
`double`	`AUCPR()`
`protected long`	`checksum_impl()` High-quality 64-bit checksum of the content of the object.
`double`	`classification_error()`
`int`	`compareTo(M o)`
`Frame`	`computeDeviances(Frame valid, Frame predictions, java.lang.String outputName)` Compute the deviances for each observation
`boolean`	`containsResponse(java.lang.String s, java.lang.String responseName)`
`protected double`	`data(Chunk[] chks, int row, int col)`
`double`	`defaultThreshold()` Default threshold for assigning class labels to the target class (for binomial models)
`static <O extends Model.Output> double`	`defaultThreshold(O output)` Deprecated. use `Model.Output.defaultThreshold()` instead.
`void`	`deleteCrossValidationFoldAssignment()`
`void`	`deleteCrossValidationModels()` delete from the output all associated CV models from DKV.
`void`	`deleteCrossValidationPreds()` delete from the output all associated CV predictions from DKV.
`double`	`deviance()`
`double`	`deviance(double w, double y, double f)` Deviance of given distribution function at predicted value f
`static boolean`	`evaluateAutoModelParameters()` Whether to evaluate input parameters of value AUTO.
`java.net.URI`	`exportBinaryModel(java.lang.String location, boolean force, ModelExportOption... options)` Exports a binary model to a given location.
`java.net.URI`	`exportMojo(java.lang.String location, boolean force)` Exports a MOJO representation of a model to a given location.
`static Model[]`	`fetchAll()`
`void`	`fillScoringInfo(ScoringInfo scoringInfo)` Fill a ScoringInfo with data from the ModelMetrics for this model.
`Model.GridSortBy`	`getDefaultGridSortBy()` Identifies the default ordering method for models returned from Grid Search
`protected hex.genmodel.CategoricalEncoding`	`getGenModelEncoding()` Specify categorical encoding that should be applied before running score0 method of POJO/MOJO.
`ModelMojoWriter`	`getMojo()` Override this in models that support serialization into the MOJO format.
`protected java.lang.Class<?>[]`	`getPojoInterfaces()`
`ToEigenVec`	`getToEigenVec()`
`boolean`	`haveMojo()`
`boolean`	`havePojo()`
`static <M extends Model<?,?,?>> M`	`importBinaryModel(java.lang.String location)` Imports a binary model from a given location.
`void`	`initActualParamValues()`
`boolean`	`isDistributionHuber()`
`protected boolean`	`isFeatureUsedInPredict(int featureIdx)`
`boolean`	`isFeatureUsedInPredict(java.lang.String featureName)` Convenience method to find out if featureName is used for prediction, i.e., if it has beta == 0 in GLM, it is not considered to be used.
`boolean`	`isSupervised()`
`ScoringInfo`	`last_scored()`
`double`	`lift_top_group()`
`double`	`likelihood(double w, double y, double[] f)`
`double`	`logloss()`
`float`	`loss()`
`double`	`mae()`
`protected Model.AdaptFrameParameters`	`makeAdaptFrameParameters()`
`protected Model.BigScore`	`makeBigScoreTask(java.lang.String[][] domains, java.lang.String[] names, Frame adaptFrm, boolean computeMetrics, boolean makePrediction, Job j, CFuncRef customMetricFunc)` Allow subclasses to define their own BigScore class.
`static InteractionWrappedVec`	`makeInteraction(Frame fr, Model.InteractionPair ip, boolean useAllFactorLevels, boolean skipMissing, boolean standardize)`
`static Frame`	`makeInteractions(Frame fr, boolean valid, Model.InteractionPair[] interactions, boolean useAllFactorLevels, boolean skipMissing, boolean standardize)`
`static InteractionWrappedVec[]`	`makeInteractions(Frame fr, Model.InteractionPair[] interactions, boolean useAllFactorLevels, boolean skipMissing, boolean standardize)`
`abstract ModelMetrics.MetricBuilder`	`makeMetricBuilder(java.lang.String[] domain)`
`protected PojoWriter`	`makePojoWriter()`
`java.lang.Class<KeyV3.ModelKeyV3>`	`makeSchema()`
`protected java.lang.String[][]`	`makeScoringDomains(Frame adaptFrm, boolean computeMetrics, java.lang.String[] names)`
`protected java.lang.String[]`	`makeScoringNames()`
`static <O extends Model.Output> java.lang.String[]`	`makeScoringNames(O output)`
`double`	`mean_per_class_error()`
`hex.genmodel.descriptor.ModelDescriptor`	`modelDescriptor()`
`double`	`mse()`
`protected boolean`	`needsPostProcess()` Implementations can disable post-processing of predictions by overriding this method (eg.
`protected Frame`	`postProcessPredictions(Frame adaptFrm, Frame predictFr, Job j)` Post-process prediction frame.
`protected Model.PredictScoreResult`	`predictScoreImpl(Frame fr, Frame adaptFrm, java.lang.String destination_key, Job j, boolean computeMetrics, CFuncRef customMetricFunc)` Score an already adapted frame.
`double`	`r2()`
`protected Keyed`	`readAll_impl(AutoBuffer ab, Futures fs)`
`protected Futures`	`remove_impl(Futures fs, boolean cascade)` Override to remove subparts, but not self, of composite Keyed objects.
`void`	`resetThreshold(double value)`
`Frame`	`result()`
`double`	`rmsle()`
`double`	`score(double[] data)`
`Frame`	`score(Frame fr)` Bulk score the frame, and auto-name the resulting predictions frame.
`Frame`	`score(Frame fr, java.lang.String destination_key)`
`Frame`	`score(Frame fr, java.lang.String destination_key, CFuncRef customMetricFunc)` Bulk score the frame `fr`, producing a Frame result; the 1st Vec is the predicted class, the remaining Vecs are the probability distributions.
`Frame`	`score(Frame fr, java.lang.String destination_key, Job j)`
`Frame`	`score(Frame fr, java.lang.String destination_key, Job j, boolean computeMetrics)`
`Frame`	`score(Frame fr, java.lang.String destination_key, Job j, boolean computeMetrics, CFuncRef customMetricFunc)`
`double[]`	`score0(Chunk[] chks, double offset, int row_in_chunk, double[] tmp, double[] preds)`
`double[]`	`score0(Chunk[] chks, int row_in_chunk, double[] tmp, double[] preds)` Bulk scoring API for one row.
`protected abstract double[]`	`score0(double[] data, double[] preds)` Subclasses implement the scoring logic.
`protected double[]`	`score0(double[] data, double[] preds, double offset)` Override scoring logic for models that handle weight/offset
`protected void`	`score0PostProcessSupervised(double[] scored, double[] tmp)`
`protected ModelMetrics.MetricBuilder`	`scoreMetrics(Frame adaptFrm)` Score an already adapted frame.
`ScoringInfo[]`	`scoring_history()`
`protected java.lang.String[][]`	`scoringDomains()`
`void`	`setInputParms(P _input_parms)`
`protected Model.BigScorePredict`	`setupBigScorePredict(Model.BigScore bs)`
`boolean`	`testJavaScoring(Frame data, Frame model_predictions, double rel_epsilon)`
`boolean`	`testJavaScoring(Frame data, Frame model_predictions, double rel_epsilon, double abs_epsilon)`
`boolean`	`testJavaScoring(Frame data, Frame model_predictions, double rel_epsilon, double abs_epsilon, double fraction)`
`boolean`	`testJavaScoring(Frame data, Frame model_predictions, double rel_epsilon, Model.JavaScoringOptions options)`
`boolean`	`testJavaScoring(Frame data, Frame model_predictions, hex.genmodel.easy.EasyPredictModelWrapper.Config config, double rel_epsilon, double abs_epsilon, double fraction)`
`java.lang.String`	`toJava(boolean preview, boolean verboseCode)` Return a String which is a valid Java program representing a class that implements the Model.
`SBPrintStream`	`toJava(java.io.OutputStream os, boolean preview, boolean verboseCode)`
`protected SBPrintStream`	`toJava(SBPrintStream sb, boolean isGeneratingPreview, boolean verboseCode)`
`protected java.lang.String`	`toJavaAlgo()`
`protected boolean`	`toJavaCheckTooBig()`
`protected SBPrintStream`	`toJavaInit(SBPrintStream sb, CodeGeneratorPipeline fileContext)`
`protected java.lang.String`	`toJavaModelClassName()`
`protected void`	`toJavaPredictBody(SBPrintStream body, CodeGeneratorPipeline classCtx, CodeGeneratorPipeline fileCtx, boolean verboseCode)`
`protected SBPrintStream`	`toJavaTransform(SBPrintStream ccsb, CodeGeneratorPipeline fileCtx, boolean verboseCode)`
`protected java.lang.String`	`toJavaUUID()`
`hex.genmodel.MojoModel`	`toMojo()` Convenience method to convert Model to a MOJO representation.
`hex.genmodel.MojoModel`	`toMojo(boolean readMetadata)` Convenience method to convert Model to a MOJO representation.
`java.lang.String`	`toString()`
`Frame`	`transform(Frame fr)`
`static <M extends Model<?,?,?>> M`	`uploadBinaryModel(java.lang.String destinationFrame)` Uploads a binary model from a given frame.
`protected AutoBuffer`	`writeAll_impl(AutoBuffer ab)` Write out K/V pairs, in this case model metrics.
`void`	`writeTo(java.io.OutputStream os, StreamWriteOption... options)` The implementation write its content to given output stream.

Methods inherited from class water.Lockable
delete_and_lock, delete_and_lock, delete_and_lock, delete, delete, delete, delete, read_lock, read_lock, read_lock, unlock_all, unlock, unlock, unlock, unlock, update, update, update, write_lock_to_read_lock, write_lock, write_lock, write_lock

Methods inherited from class water.Keyed
checksum_impl, checksum, checksum, getKey, readAll, remove_impl, remove_self_key_impl, remove, remove, remove, remove, remove, remove, removeQuietly, writeAll

Methods inherited from class water.Iced
asBytes, clone, copyOver, frozenType, read, readExternal, readJSON, reloadFromBytes, toJsonBytes, toJsonString, write, writeExternal, writeJSON

Methods inherited from class java.lang.Object
equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Field Detail

EVAL_AUTO_PARAMS_ENABLED

public static final java.lang.String EVAL_AUTO_PARAMS_ENABLED

See Also:: Constant Field Values

_parms

public P extends Model.Parameters _parms

_input_parms

public P extends Model.Parameters _input_parms

_output
```
public O extends Model.Output _output
```

_warnings
```
public java.lang.String[] _warnings
```

_warningsP

public transient java.lang.String[] _warningsP

_dist
```
public Distribution _dist
```

scoringInfo
```
protected ScoringInfo[] scoringInfo
```

_toDelete

public IcedHashMap<Key,java.lang.String> _toDelete

evalAutoParamsEnabled
```
public boolean evalAutoParamsEnabled
```

Constructor Detail

Model

public Model(Key<M> selfKey,
             P parms,
             O output)

Full constructor

Method Detail

fetchAll
```
public static Model[] fetchAll()
```

evaluateAutoModelParameters
```
public static boolean evaluateAutoModelParameters()
```
Whether to evaluate input parameters of value AUTO.

setInputParms

public void setInputParms(P _input_parms)

defaultThreshold
```
public double defaultThreshold()
```
Default threshold for assigning class labels to the target class (for binomial models)

Returns:

threshold in 0...1

resetThreshold

public void resetThreshold(double value)

defaultThreshold

@Deprecated
public static <O extends Model.Output> double defaultThreshold(O output)

Deprecated. use Model.Output.defaultThreshold() instead.

isSupervised
```
public final boolean isSupervised()
```

havePojo
```
public boolean havePojo()
```

haveMojo
```
public boolean haveMojo()
```

getDefaultGridSortBy
```
public Model.GridSortBy getDefaultGridSortBy()
```
Identifies the default ordering method for models returned from Grid Search

Returns:

default sort-by

getToEigenVec
```
public ToEigenVec getToEigenVec()
```

addModelMetrics

public ModelMetrics addModelMetrics(ModelMetrics mm)

addWarning

public void addWarning(java.lang.String s)

scoringDomains

protected java.lang.String[][] scoringDomains()

addMetrics

public ModelMetrics addMetrics(ModelMetrics mm)

makeMetricBuilder

public abstract ModelMetrics.MetricBuilder makeMetricBuilder(java.lang.String[] domain)

initActualParamValues
```
public void initActualParamValues()
```

deviance
```
public double deviance(double w,
                       double y,
                       double f)
```
Deviance of given distribution function at predicted value f

Parameters:

w - observation weight

y - (actual) response

f - (predicted) response in original response space

Returns:

value of gradient

likelihood

public double likelihood(double w,
                         double y,
                         double[] f)

scoring_history

public ScoringInfo[] scoring_history()

fillScoringInfo
```
public void fillScoringInfo(ScoringInfo scoringInfo)
```
Fill a ScoringInfo with data from the ModelMetrics for this model.

Parameters:

scoringInfo -

last_scored
```
public ScoringInfo last_scored()
```

loss
```
public float loss()
```

compareTo
```
public int compareTo(M o)
```

classification_error
```
public double classification_error()
```

mse
```
public double mse()
```

r2
```
public double r2()
```

mae
```
public double mae()
```

rmsle
```
public double rmsle()
```

auc
```
public double auc()
```

AUCPR
```
public double AUCPR()
```

deviance
```
public double deviance()
```

logloss
```
public double logloss()
```

mean_per_class_error
```
public double mean_per_class_error()
```

lift_top_group
```
public double lift_top_group()
```

adaptTestForTrain
```
public java.lang.String[] adaptTestForTrain(Frame test,
                                            boolean expensive,
                                            boolean computeMetrics)
```
Adapt a Test/Validation Frame to be compatible for a Training Frame. The intention here is that ModelBuilders can assume the test set has the same count of columns, and within each factor column the same set of same-numbered levels. Extra levels are renumbered past those in the Train set but will still be present in the Test set, thus requiring range-checking. This routine is used before model building (with no Model made yet) to check for compatible datasets, and also used to prepare a large dataset for scoring (with a Model). Adaption does the following things: - Remove any "extra" Vecs appearing only in the test and not the train - Insert any "missing" Vecs appearing only in the train and not the test with all NAs (missingColumnsType). This will issue a warning, and if the "expensive" flag is false won't actually make the column replacement column but instead will bail-out on the whole adaption (but will continue looking for more warnings). - If all columns are missing, issue an error. - Renumber matching cat levels to match the Train levels; this might make "holes" in the Test set cat levels, if some are not in the Test set. - Extra Test levels are renumbered past the end of the Train set, hence the train and test levels match up to all the train levels; there might be extra Test levels past that. - For all mis-matched levels, issue a warning. The test frame is updated in-place to be compatible, by altering the names and Vecs; make a defensive copy if you do not want it modified. There is a fast-path cutout if the test set is already compatible. Since the test-set is conditionally modifed with extra CategoricalWrappedVec optionally added it is recommended to use a Scope enter/exit to track Vec lifetimes.

Parameters:

test - Testing Frame, updated in-place

expensive - Try hard to adapt; this might involve the creation of whole Vecs and thus get expensive. If false, then only adapt if no warnings and errors; otherwise just the messages are produced. Created Vecs have to be deleted by the caller (e.g. Scope.enter/exit).

Returns:

Array of warnings; zero length (never null) for no warnings. Throws IllegalArgumentException if no columns are in common, or if any factor column has no levels in common.

adaptTestForTrain

public java.lang.String[] adaptTestForTrain(Frame test,
                                            boolean expensive,
                                            boolean computeMetrics,
                                            boolean catEncoded)

makeAdaptFrameParameters

protected Model.AdaptFrameParameters makeAdaptFrameParameters()

adaptTestForTrain

public static java.lang.String[] adaptTestForTrain(Frame test,
                                                   java.lang.String[] origNames,
                                                   java.lang.String[][] origDomains,
                                                   java.lang.String[] names,
                                                   java.lang.String[][] domains,
                                                   Model.AdaptFrameParameters parms,
                                                   boolean expensive,
                                                   boolean computeMetrics,
                                                   Model.InteractionBuilder interactionBldr,
                                                   ToEigenVec tev,
                                                   IcedHashMap<Key,java.lang.String> toDelete,
                                                   boolean catEncoded)
                                            throws java.lang.IllegalArgumentException

Parameters:: test - Frame to be adapted; origNames - Training column names before categorical column encoding - can be the same as names; origDomains - Training column levels before categorical column encoding - can be the same as domains; names - Training column names; domains - Training column levels; parms - Model parameters; expensive - Whether to actually do the hard work; computeMetrics - Whether metrics can be (and should be) computed; interactionBldr - Column names to create pairwise interactions with; catEncoded - Whether the categorical columns of the test frame were already transformed via categorical_encoding
Throws:: java.lang.IllegalArgumentException

score
```
public Frame score(Frame fr)
            throws java.lang.IllegalArgumentException
```
Bulk score the frame, and auto-name the resulting predictions frame.

Parameters:

fr - frame which should be scored

Returns:

A new frame containing a predicted values. For classification it contains a column with prediction and distribution for all response classes. For regression it contains only one column with predicted values.

Throws:

java.lang.IllegalArgumentException

See Also:

score(Frame, String)

result
```
public Frame result()
```

transform
```
public Frame transform(Frame fr)
```

score
```
public Frame score(Frame fr,
                   java.lang.String destination_key,
                   CFuncRef customMetricFunc)
            throws java.lang.IllegalArgumentException
```
Bulk score the frame fr, producing a Frame result; the 1st Vec is the predicted class, the remaining Vecs are the probability distributions. For Regression (single-class) models, the 1st and only Vec is the prediction value. The result is in the DKV; caller is responsible for deleting.

Parameters:

fr - frame which should be scored

destination_key - store prediction frame under give key

customMetricFunc - function to produce adhoc scoring metrics if actuals are presented

Returns:

A new frame containing a predicted values. For classification it contains a column with prediction and distribution for all response classes. For regression it contains only one column with predicted values.

Throws:

java.lang.IllegalArgumentException

score

public Frame score(Frame fr,
                   java.lang.String destination_key)
            throws java.lang.IllegalArgumentException

Throws:: java.lang.IllegalArgumentException

score

public Frame score(Frame fr,
                   java.lang.String destination_key,
                   Job j)
            throws java.lang.IllegalArgumentException

Throws:: java.lang.IllegalArgumentException

containsResponse

public boolean containsResponse(java.lang.String s,
                                java.lang.String responseName)

score

public Frame score(Frame fr,
                   java.lang.String destination_key,
                   Job j,
                   boolean computeMetrics)
            throws java.lang.IllegalArgumentException

Throws:: java.lang.IllegalArgumentException

adaptFrameForScore

protected Frame adaptFrameForScore(Frame fr,
                                   boolean computeMetrics,
                                   java.util.List<Frame> tmpFrames)

score

public Frame score(Frame fr,
                   java.lang.String destination_key,
                   Job j,
                   boolean computeMetrics,
                   CFuncRef customMetricFunc)
            throws java.lang.IllegalArgumentException

Throws:: java.lang.IllegalArgumentException

computeDeviances
```
public Frame computeDeviances(Frame valid,
                              Frame predictions,
                              java.lang.String outputName)
```
Compute the deviances for each observation

Parameters:

valid - Validation Frame (must contain the response)

predictions - Predictions made by the model

outputName - Name of the output frame

Returns:

Frame containing 1 column with the per-row deviances

makeScoringNames

protected java.lang.String[] makeScoringNames()

makeScoringDomains

protected java.lang.String[][] makeScoringDomains(Frame adaptFrm,
                                                  boolean computeMetrics,
                                                  java.lang.String[] names)

makeScoringNames

public static <O extends Model.Output> java.lang.String[] makeScoringNames(O output)

makeBigScoreTask

protected Model.BigScore makeBigScoreTask(java.lang.String[][] domains,
                                          java.lang.String[] names,
                                          Frame adaptFrm,
                                          boolean computeMetrics,
                                          boolean makePrediction,
                                          Job j,
                                          CFuncRef customMetricFunc)

Allow subclasses to define their own BigScore class.

predictScoreImpl

protected Model.PredictScoreResult predictScoreImpl(Frame fr,
                                                    Frame adaptFrm,
                                                    java.lang.String destination_key,
                                                    Job j,
                                                    boolean computeMetrics,
                                                    CFuncRef customMetricFunc)

Score an already adapted frame. Returns a new Frame with new result vectors, all in the DKV. Caller responsible for deleting. Input is already adapted to the Model's domain, so the output is also. Also computes the metrics for this frame.

Parameters:: adaptFrm - Already adapted frame; computeMetrics -
Returns:: A Frame containing the prediction column, and class distribution

postProcessPredictions

protected Frame postProcessPredictions(Frame adaptFrm,
                                       Frame predictFr,
                                       Job j)

Post-process prediction frame.

Parameters:: adaptFrm -; predictFr -
Returns:

scoreMetrics
```
protected ModelMetrics.MetricBuilder scoreMetrics(Frame adaptFrm)
```
Score an already adapted frame. Returns a MetricBuilder that can be used to make a model metrics.

Parameters:

adaptFrm - Already adapted frame

Returns:

MetricBuilder

setupBigScorePredict

protected Model.BigScorePredict setupBigScorePredict(Model.BigScore bs)

data

protected double data(Chunk[] chks,
                      int row,
                      int col)

score0
```
public double[] score0(Chunk[] chks,
                       int row_in_chunk,
                       double[] tmp,
                       double[] preds)
```
Bulk scoring API for one row. Chunks are all compatible with the model, and expect the last Chunks are for the final distribution and prediction. Default method is to just load the data into the tmp array, then call subclass scoring logic.

score0

public double[] score0(Chunk[] chks,
                       double offset,
                       int row_in_chunk,
                       double[] tmp,
                       double[] preds)

needsPostProcess
```
protected boolean needsPostProcess()
```
Implementations can disable post-processing of predictions by overriding this method (eg. GLM)

Returns:

true, if output of score0 needs post-processing, false if the output is final

score0PostProcessSupervised

protected final void score0PostProcessSupervised(double[] scored,
                                                 double[] tmp)

score0
```
protected abstract double[] score0(double[] data,
                                   double[] preds)
```
Subclasses implement the scoring logic. The data is pre-loaded into a re-used temp array, in the order the model expects. The predictions are loaded into the re-used temp array, which is also returned.

score0

protected double[] score0(double[] data,
                          double[] preds,
                          double offset)

Override scoring logic for models that handle weight/offset

score
```
public double score(double[] data)
```

remove_impl
```
protected Futures remove_impl(Futures fs,
                              boolean cascade)
```
Description copied from class: Keyed

Override to remove subparts, but not self, of composite Keyed objects. Examples include Vec (removing associated Chunk keys) and Frame (removing associated Vec keys.)

Overrides:

remove_impl in class Keyed<M extends Model<M,P,O>>

writeAll_impl
```
protected AutoBuffer writeAll_impl(AutoBuffer ab)
```
Write out K/V pairs, in this case model metrics.

Overrides:

writeAll_impl in class Keyed<M extends Model<M,P,O>>

readAll_impl

protected Keyed readAll_impl(AutoBuffer ab,
                             Futures fs)

Overrides:: readAll_impl in class Keyed<M extends Model<M,P,O>>

checksum_impl
```
protected long checksum_impl()
```
Description copied from class: Keyed

High-quality 64-bit checksum of the content of the object. Similar to hashcode(), but a long to reduce the chance of hash clashes. For composite objects this should be defined using the subcomponents' checksums (or hashcodes if not available). If two Keyed objects have the same checksum() there should be a 1 - 1/2^64 chance that they are the same object by value.

Overrides:

checksum_impl in class Keyed<M extends Model<M,P,O>>

getMojo
```
public ModelMojoWriter getMojo()
```
Override this in models that support serialization into the MOJO format.

Returns:

a class that inherits from ModelMojoWriter

getGenModelEncoding
```
protected hex.genmodel.CategoricalEncoding getGenModelEncoding()
```
Specify categorical encoding that should be applied before running score0 method of POJO/MOJO. Default: AUTO - POJO/MOJO handles encoding or no transformation of input is needed.

Returns:

instance of CategoricalEncoding supported by GenModel or null if encoding is not supported.

toJava

public final java.lang.String toJava(boolean preview,
                                     boolean verboseCode)

Return a String which is a valid Java program representing a class that implements the Model. The Java is of the form:

    class UUIDxxxxModel {
      public static final String NAMES[] = { ....column names... }
      public static final String DOMAINS[][] = { ....domain names... }
      // Pass in data in a double[], pre-aligned to the Model's requirements.
      // Jam predictions into the preds[] array; preds[0] is reserved for the
      // main prediction (class for classifiers or value for regression),
      // and remaining columns hold a probability distribution for classifiers.
      double[] predict( double data[], double preds[] );
      double[] map( HashMap < String,Double > row, double data[] );
      // Does the mapping lookup for every row, no allocation
      double[] predict( HashMap < String,Double > row, double data[], double preds[] );
      // Allocates a double[] for every row
      double[] predict( HashMap < String,Double > row, double preds[] );
      // Allocates a double[] and a double[] for every row
      double[] predict( HashMap < String,Double > row );
    }

toJava

public final SBPrintStream toJava(java.io.OutputStream os,
                                  boolean preview,
                                  boolean verboseCode)

toJava

protected SBPrintStream toJava(SBPrintStream sb,
                               boolean isGeneratingPreview,
                               boolean verboseCode)

makePojoWriter
```
protected PojoWriter makePojoWriter()
```

toJavaModelClassName

protected java.lang.String toJavaModelClassName()

toJavaAlgo

protected java.lang.String toJavaAlgo()

toJavaUUID

protected java.lang.String toJavaUUID()

getPojoInterfaces

protected java.lang.Class<?>[] getPojoInterfaces()

toJavaCheckTooBig
```
protected boolean toJavaCheckTooBig()
```

toJavaInit

protected SBPrintStream toJavaInit(SBPrintStream sb,
                                   CodeGeneratorPipeline fileContext)

toJavaPredictBody

protected void toJavaPredictBody(SBPrintStream body,
                                 CodeGeneratorPipeline classCtx,
                                 CodeGeneratorPipeline fileCtx,
                                 boolean verboseCode)

toJavaTransform

protected SBPrintStream toJavaTransform(SBPrintStream ccsb,
                                        CodeGeneratorPipeline fileCtx,
                                        boolean verboseCode)

testJavaScoring

public boolean testJavaScoring(Frame data,
                               Frame model_predictions,
                               double rel_epsilon)

testJavaScoring

public boolean testJavaScoring(Frame data,
                               Frame model_predictions,
                               double rel_epsilon,
                               double abs_epsilon)

testJavaScoring

public boolean testJavaScoring(Frame data,
                               Frame model_predictions,
                               double rel_epsilon,
                               double abs_epsilon,
                               double fraction)

testJavaScoring

public boolean testJavaScoring(Frame data,
                               Frame model_predictions,
                               hex.genmodel.easy.EasyPredictModelWrapper.Config config,
                               double rel_epsilon,
                               double abs_epsilon,
                               double fraction)

testJavaScoring

public boolean testJavaScoring(Frame data,
                               Frame model_predictions,
                               double rel_epsilon,
                               Model.JavaScoringOptions options)

adaptTestForJavaScoring

protected java.lang.String[] adaptTestForJavaScoring(Frame test,
                                                     boolean computeMetrics)

deleteCrossValidationModels
```
public void deleteCrossValidationModels()
```
delete from the output all associated CV models from DKV.

deleteCrossValidationPreds
```
public void deleteCrossValidationPreds()
```
delete from the output all associated CV predictions from DKV.

deleteCrossValidationFoldAssignment

public void deleteCrossValidationFoldAssignment()

toString
```
public java.lang.String toString()
```
Overrides:

toString in class java.lang.Object

makeSchema
```
public java.lang.Class<KeyV3.ModelKeyV3> makeSchema()
```
Overrides:

makeSchema in class Keyed<M extends Model<M,P,O>>

makeInteractions

public static Frame makeInteractions(Frame fr,
                                     boolean valid,
                                     Model.InteractionPair[] interactions,
                                     boolean useAllFactorLevels,
                                     boolean skipMissing,
                                     boolean standardize)

makeInteractions

public static InteractionWrappedVec[] makeInteractions(Frame fr,
                                                       Model.InteractionPair[] interactions,
                                                       boolean useAllFactorLevels,
                                                       boolean skipMissing,
                                                       boolean standardize)

makeInteraction

public static InteractionWrappedVec makeInteraction(Frame fr,
                                                    Model.InteractionPair ip,
                                                    boolean useAllFactorLevels,
                                                    boolean skipMissing,
                                                    boolean standardize)

importBinaryModel
```
public static <M extends Model<?,?,?>> M importBinaryModel(java.lang.String location)
                                                    throws java.io.IOException
```
Imports a binary model from a given location. Note: binary model has to be created by the same version of H2O, import of a model from a different version will fail

Parameters:

location - path to the binary representation of the model on a local filesystem, HDFS, S3...

Returns:

instance of an H2O Model

Throws:

java.io.IOException - when reading fails

uploadBinaryModel
```
public static <M extends Model<?,?,?>> M uploadBinaryModel(java.lang.String destinationFrame)
                                                    throws java.io.IOException
```
Uploads a binary model from a given frame. Note: binary model has to be created by the same version of H2O, import of a model from a different version will fail

Parameters:

destinationFrame - key of the frame containing the binary representation of the model on a local filesystem, HDFS, S3...

Returns:

instance of an H2O Model

Throws:

java.io.IOException - when reading fails

exportBinaryModel

public final java.net.URI exportBinaryModel(java.lang.String location,
                                            boolean force,
                                            ModelExportOption... options)
                                     throws java.io.IOException

Exports a binary model to a given location.

Parameters:: location - target path, it can be on local filesystem, HDFS, S3...; force - If true, overwrite already existing file
Returns:: URI representation of the target location
Throws:: FSIOException - when writing fails; java.io.IOException

writeTo
```
public final void writeTo(java.io.OutputStream os,
                          StreamWriteOption... options)
```
Description copied from interface: StreamWriter

The implementation write its content to given output stream.

Specified by:

writeTo in interface StreamWriter

Parameters:

os - output stream provided by framework

exportMojo
```
public java.net.URI exportMojo(java.lang.String location,
                               boolean force)
                        throws java.io.IOException
```
Exports a MOJO representation of a model to a given location.

Parameters:

location - target path, it can be on local filesystem, HDFS, S3...

force - If true, overwrite already existing file

Returns:

URI representation of the target location

Throws:

java.io.IOException - when writing fails

toMojo
```
public hex.genmodel.MojoModel toMojo()
                              throws java.io.IOException
```
Convenience method to convert Model to a MOJO representation. Please be aware that converting models to MOJOs using this function will require sufficient memory (to hold the mojo representation and interim serialized representation as well).

Returns:

instance of MojoModel

Throws:

java.io.IOException - when writing MOJO fails

toMojo
```
public hex.genmodel.MojoModel toMojo(boolean readMetadata)
                              throws java.io.IOException
```
Convenience method to convert Model to a MOJO representation. Please be aware that converting models to MOJOs using this function will require sufficient memory (to hold the mojo representation and interim serialized representation as well).

Parameters:

readMetadata - If true, parses also model metadata (model performance metrics... ModelAttributes) Model metadata are not required for scoring, it is advised to leave this option disabled if you want to use MOJO for inference only.

Returns:

instance of MojoModel

Throws:

java.io.IOException - when writing MOJO fails

modelDescriptor

public hex.genmodel.descriptor.ModelDescriptor modelDescriptor()

isFeatureUsedInPredict
```
public boolean isFeatureUsedInPredict(java.lang.String featureName)
```
Convenience method to find out if featureName is used for prediction, i.e., if it has beta == 0 in GLM, it is not considered to be used. This is mainly intended for optimizing prediction speed in StackedEnsemble.

Parameters:

featureName -

isFeatureUsedInPredict

protected boolean isFeatureUsedInPredict(int featureIdx)

isDistributionHuber
```
public boolean isDistributionHuber()
```

Class Model<M extends Model<M,P,O>,P extends Model.Parameters,O extends Model.Output>

Nested Class Summary

Field Summary

Fields inherited from class water.Lockable

Fields inherited from class water.Keyed

Constructor Summary

Method Summary

Methods inherited from class water.Lockable

Methods inherited from class water.Keyed

Methods inherited from class water.Iced

Methods inherited from class java.lang.Object

Field Detail

EVAL_AUTO_PARAMS_ENABLED

_parms

_input_parms

_output

_warnings

_warningsP

_dist

scoringInfo

_toDelete

evalAutoParamsEnabled

Constructor Detail

Model

Method Detail

fetchAll

evaluateAutoModelParameters

setInputParms

defaultThreshold

resetThreshold

defaultThreshold

isSupervised

havePojo

haveMojo

getDefaultGridSortBy

getToEigenVec

addModelMetrics

addWarning

scoringDomains

addMetrics

makeMetricBuilder

initActualParamValues

deviance

likelihood

scoring_history

fillScoringInfo

last_scored

loss

compareTo

classification_error

mse

r2

mae

rmsle

auc

AUCPR

deviance

logloss

mean_per_class_error

lift_top_group

adaptTestForTrain

adaptTestForTrain

makeAdaptFrameParameters

adaptTestForTrain

score

result

transform

score

score

score

containsResponse

score

adaptFrameForScore

score

computeDeviances

makeScoringNames

makeScoringDomains

makeScoringNames

makeBigScoreTask

predictScoreImpl