hex.deeplearning

Class DeepLearningModel

java.lang.Object

water.Iced<T>

water.Keyed<T>

water.Lockable<M>

hex.Model<M,P,O>

hex.SupervisedModel<DeepLearningModel,DeepLearningModel.DeepLearningParameters,DeepLearningModel.DeepLearningModelOutput>

hex.deeplearning.DeepLearningModel

All Implemented Interfaces:

java.io.Externalizable, java.io.Serializable, java.lang.Cloneable, water.Freezable<DeepLearningModel>

public class DeepLearningModel
extends hex.SupervisedModel<DeepLearningModel,DeepLearningModel.DeepLearningParameters,DeepLearningModel.DeepLearningModelOutput>

The Deep Learning model It contains a DeepLearningModelInfo with the most up-to-date model, a scoring history, as well as some helpers to indicate the progress

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	DeepLearningModel.DeepLearningModelInfo
static class	DeepLearningModel.DeepLearningModelOutput
static class	DeepLearningModel.DeepLearningParameters
static class	DeepLearningModel.DeepLearningScoring

Nested classes/interfaces inherited from class hex.SupervisedModel

hex.SupervisedModel.SupervisedOutput, hex.SupervisedModel.SupervisedParameters

Nested classes/interfaces inherited from class hex.Model

hex.Model.ModelCategory, hex.Model.Output, hex.Model.Parameters

Field Summary

Fields

Modifier and Type	Field and Description
long	_timeLastScoreEnter
water.Key	actual_best_model_key
long	actual_train_samples_per_iteration
double	epoch_counter
double	time_for_communication_us
long	training_rows
long	validation_rows

Fields inherited from class hex.Model

_output, _parms, _warnings

Fields inherited from class water.Lockable

_lockers

Fields inherited from class water.Keyed

_key

Constructor Summary

Constructors

Constructor and Description
DeepLearningModel(water.Key destKey, DeepLearningModel.DeepLearningParameters parms, DeepLearningModel.DeepLearningModelOutput output, water.fvec.Frame train, water.fvec.Frame valid)
DeepLearningModel(water.Key destKey, DeepLearningModel cp, boolean store_best_model, FrameTask.DataInfo dataInfo) Constructor to restart from a checkpointed model

Method Summary

Methods

Modifier and Type	Method and Description
double	calcOutlierThreshold(water.fvec.Vec mse, double quantile) Compute quantile-based threshold (in reconstruction error) to find outliers
hex.ConfusionMatrix	cm() for grid search error reporting
int	compareTo(DeepLearningModel o)
void	delete_best_model()
void	delete_xval_models()
float	error()
DeepLearningModel.DeepLearningParameters	get_params()
boolean	isSupervised()
hex.ModelMetrics.MetricBuilder	makeMetricBuilder(java.lang.String[] domain)
protected double	missingColumnsType()
DeepLearningModel.DeepLearningModelInfo	model_info()
double	mse()
water.api.ModelSchema	schema()
water.fvec.Frame	score(water.fvec.Frame fr, java.lang.String destination_key)
float[]	score0(double[] data, float[] preds) Predict from raw double values representing the data
water.fvec.Frame	scoreAutoEncoder(water.fvec.Frame frame) Score auto-encoded reconstruction (on-the-fly, without allocating the reconstruction as done in Frame score(Frame fr))
protected water.fvec.Frame	scoreImpl(water.fvec.Frame orig, water.fvec.Frame adaptedFr, java.lang.String destination_key) Make either a prediction or a reconstruction.
DeepLearningModel.DeepLearningScoring[]	scoring_history()
java.lang.String	toString()
java.lang.String	toStringAll()
hex.VarImp	varimp()

Methods inherited from class hex.SupervisedModel

score0

Methods inherited from class hex.Model

adaptTestForTrain, adaptTestForTrain, addMetrics, addWarning, checksum_impl, remove_impl, score, score

Methods inherited from class water.Lockable

delete_and_lock, delete, delete, delete, read_lock, read_lock, unlock_all, unlock, update, write_lock

Methods inherited from class water.Keyed

checksum, remove, remove, remove, remove

Methods inherited from class water.Iced

clone, frozenType, read_impl, read, readExternal, readJSON_impl, readJSON, toJsonString, write_impl, write, writeExternal, writeHTML_impl, writeHTML, writeJSON_impl, writeJSON

Methods inherited from class java.lang.Object

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

Field Detail

actual_train_samples_per_iteration

public long actual_train_samples_per_iteration

time_for_communication_us

public double time_for_communication_us

epoch_counter

public double epoch_counter

training_rows

public long training_rows

validation_rows

public long validation_rows

actual_best_model_key

public water.Key actual_best_model_key

_timeLastScoreEnter

public long _timeLastScoreEnter

Constructor Detail

DeepLearningModel

public DeepLearningModel(water.Key destKey,
                 DeepLearningModel cp,
                 boolean store_best_model,
                 FrameTask.DataInfo dataInfo)

Constructor to restart from a checkpointed model

Parameters:

destKey - New destination key for the model

cp - Checkpoint to restart from

store_best_model - Store only the best model instead of the latest one

DeepLearningModel

public DeepLearningModel(water.Key destKey,
                 DeepLearningModel.DeepLearningParameters parms,
                 DeepLearningModel.DeepLearningModelOutput output,
                 water.fvec.Frame train,
                 water.fvec.Frame valid)

Method Detail

schema

public water.api.ModelSchema schema()

Specified by:

schema in class hex.Model<DeepLearningModel,DeepLearningModel.DeepLearningParameters,DeepLearningModel.DeepLearningModelOutput>

model_info

public final DeepLearningModel.DeepLearningModelInfo model_info()

scoring_history

public DeepLearningModel.DeepLearningScoring[] scoring_history()

get_params

public final DeepLearningModel.DeepLearningParameters get_params()

missingColumnsType

protected double missingColumnsType()

error

public float error()

isSupervised

public boolean isSupervised()

Overrides:

isSupervised in class hex.SupervisedModel<DeepLearningModel,DeepLearningModel.DeepLearningParameters,DeepLearningModel.DeepLearningModelOutput>

makeMetricBuilder

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

Specified by:

makeMetricBuilder in class hex.Model<DeepLearningModel,DeepLearningModel.DeepLearningParameters,DeepLearningModel.DeepLearningModelOutput>

compareTo

public int compareTo(DeepLearningModel o)

cm

public hex.ConfusionMatrix cm()

for grid search error reporting

mse

public double mse()

varimp

public hex.VarImp varimp()

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object

toStringAll

public java.lang.String toStringAll()

scoreImpl

protected water.fvec.Frame scoreImpl(water.fvec.Frame orig,
                         water.fvec.Frame adaptedFr,
                         java.lang.String destination_key)

Make either a prediction or a reconstruction.

Overrides:

scoreImpl in class hex.Model<DeepLearningModel,DeepLearningModel.DeepLearningParameters,DeepLearningModel.DeepLearningModelOutput>

Parameters:

orig - Test dataset

adaptedFr - Test dataset, adapted to the model

Returns:

A frame containing the prediction or reconstruction

score0

public float[] score0(double[] data,
             float[] preds)

Predict from raw double values representing the data

Specified by:

score0 in class hex.Model<DeepLearningModel,DeepLearningModel.DeepLearningParameters,DeepLearningModel.DeepLearningModelOutput>

Parameters:

data - raw array containing categorical values (horizontalized to 1,0,0,1,0,0 etc.) and numerical values (0.35,1.24,5.3234,etc), both can contain NaNs

preds - predicted label and per-class probabilities (for classification), predicted target (regression), can contain NaNs

Returns:

preds, can contain NaNs

scoreAutoEncoder

public water.fvec.Frame scoreAutoEncoder(water.fvec.Frame frame)

Score auto-encoded reconstruction (on-the-fly, without allocating the reconstruction as done in Frame score(Frame fr))

Parameters:

frame - Original data (can contain response, will be ignored)

Returns:

Frame containing one Vec with reconstruction error (MSE) of each reconstructed row, caller is responsible for deletion

score

public water.fvec.Frame score(water.fvec.Frame fr,
                     java.lang.String destination_key)

Overrides:

score in class hex.Model<DeepLearningModel,DeepLearningModel.DeepLearningParameters,DeepLearningModel.DeepLearningModelOutput>

calcOutlierThreshold

public double calcOutlierThreshold(water.fvec.Vec mse,
                          double quantile)

Compute quantile-based threshold (in reconstruction error) to find outliers

Parameters:

mse - Vector containing reconstruction errors

quantile - Quantile for cut-off

Returns:

Threshold in MSE value for a point to be above the quantile

delete_best_model

public void delete_best_model()

delete_xval_models

public void delete_xval_models()