- AccuracyValidation - Class in com.indeed.vw.wrapper.progvalidation
-
correct predictions / total
- AccuracyValidation(double) - Constructor for class com.indeed.vw.wrapper.progvalidation.AccuracyValidation
-
- active() - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
enable active learning
- activeCover() - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
enable active learning with cover
- adaptive() - Method in interface com.indeed.vw.wrapper.api.parameters.UpdatesOptions
-
use adaptive, individual learning rates.
- adaptive() - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
use adaptive, individual learning rates.
- addCategoricalFeature(Object) - Method in class com.indeed.vw.wrapper.api.example.ExampleBuilder.NamespaceBuilder
-
Add a categorical feature to this namespace (e.g.
- addCategoricalFeature(String, Object) - Method in class com.indeed.vw.wrapper.api.example.ExampleBuilder.NamespaceBuilder
-
Add a categorical feature to this namespace (e.g.
- addNumericalFeature(String, double) - Method in class com.indeed.vw.wrapper.api.example.ExampleBuilder.NamespaceBuilder
-
Add numerical feature to this namespace (e.g.
- addTextAsFeatures(String) - Method in class com.indeed.vw.wrapper.api.example.ExampleBuilder.NamespaceBuilder
-
Add text feature to this namespace (e.g.
- advancedBuilder() - Static method in class com.indeed.vw.wrapper.api.VowpalWabbit
-
Create advanced builder for Vowpal Wabbit learner
- affix(String) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
generate prefixes/suffixes of features; argument '+2a,-3b,+1'
- ANY_NAMESPACE - Static variable in class com.indeed.vw.wrapper.api.VowpalWabbit
-
Pass this constant as namespace parameter if you want to set some feature engineering for all namespaces.
- auditRegressor(Path) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
stores feature names and their regressor values.
- autolink(int) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
create link function with polynomial d
- cache() - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
Use a cache.
- cacheFile(Path) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
The location(s) of cacheFile.
- cb(int) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
Use contextual bandit learning with <k> costs
- cbAdf() - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
Do Contextual Bandit learning with multiline action dependent features.
- cbExplore(int) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
Online explore-exploit for a <k> action contextual bandit problem
- cbExploreAdf() - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
Online explore-exploit for a contextual bandit problem with multiline action dependent features
- cbify(int) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
Convert multiclass on <k> classes into a contextual bandit problem
- com.indeed.vw.wrapper.api - package com.indeed.vw.wrapper.api
-
This package contains OOP api for wowpal wabbit jni wrapper.
- com.indeed.vw.wrapper.api.example - package com.indeed.vw.wrapper.api.example
-
API for creating vowpal wabbit examples string.
- com.indeed.vw.wrapper.api.parameters - package com.indeed.vw.wrapper.api.parameters
-
API for creating vowpal wabbit parameters string.
- com.indeed.vw.wrapper.progvalidation - package com.indeed.vw.wrapper.progvalidation
-
Package with implementation of multiple quality metrics, calculated in progressive validation style.
- compressed() - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
use gzip format whenever possible.
- confidence() - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
Get confidence for binary predictions
- confidenceAfterTraining() - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
Confidence after training
- conjugateGradient() - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
use conjugate gradient based optimization
- constant(double) - Method in interface com.indeed.vw.wrapper.api.parameters.FeatureEngineeringFunctions
-
Set initial value of constant
- constant(double) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
Set initial value of constant
- countNumberOfNonZeroWeights(Path) - Static method in class com.indeed.vw.wrapper.api.parameters.VWUtility
-
Read vowpal wabbit model and count number of non-zero weights in it
- create() - Static method in class com.indeed.vw.wrapper.api.example.ExampleBuilder
-
Create method
- createAndDoNotCheckNamespace() - Static method in class com.indeed.vw.wrapper.api.example.ExampleBuilder
-
By default each namespace should start with unique character.
- createNamespace(String) - Method in class com.indeed.vw.wrapper.api.example.ExampleBuilder
-
- csoaa(int) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
One-against-all multiclass with <k> costs
- csoaaLdf(VowpalWabbit.LDF) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
Use one-against-all multiclass learning with label dependent features.
- cubic(String, String, String) - Method in interface com.indeed.vw.wrapper.api.parameters.FeatureEngineeringFunctions
-
Create and use cubic features
- cubic(String, String, String) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
Create and use cubic features
- l1(double) - Method in interface com.indeed.vw.wrapper.api.parameters.RegularizationOptions
-
l_1 lambda
- l1(double) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
l_1 lambda
- l2(double) - Method in interface com.indeed.vw.wrapper.api.parameters.RegularizationOptions
-
l_2 lambda
- l2(double) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
l_2 lambda
- label(double) - Method in class com.indeed.vw.wrapper.api.example.ExampleBuilder
-
Label is the real number that we are trying to predict for this example.
- lda(int) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
Run lda with <int> topics
- learningRate(double) - Method in interface com.indeed.vw.wrapper.api.parameters.UpdatesOptions
-
Set learning rate
- learningRate(double) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
Set learning rate
- leaveDuplicateInteractions() - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
Don't remove interactions with duplicate combinations of namespaces.
- Link - Enum in com.indeed.vw.wrapper.api.parameters
-
Function applied on linear prediction.
- link(Link) - Method in interface com.indeed.vw.wrapper.api.parameters.LinkAndLossOptions
-
Specify the link function: identity, logistic, glf1 or poisson (=identity)
- link(Link) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
Specify the link function: identity, logistic, glf1 or poisson (=identity)
- LinkAndLossOptions - Interface in com.indeed.vw.wrapper.api.parameters
-
Link and Loss options.
- LogLossValidation - Class in com.indeed.vw.wrapper.progvalidation
-
- LogLossValidation() - Constructor for class com.indeed.vw.wrapper.progvalidation.LogLossValidation
-
- logMulti(int) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
Use online tree for multiclass
- Loss - Enum in com.indeed.vw.wrapper.api.parameters
-
Function that measures the discrepancy between the algorithm's prediction and the desired output.
- lossFunction(Loss) - Method in interface com.indeed.vw.wrapper.api.parameters.LinkAndLossOptions
-
Specify the loss function to be used, uses squared by default.
- lossFunction(Loss) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
Specify the loss function to be used, uses squared by default.
- lrq(String, String, int) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
use low rank quadratic features
- lrqdropout() - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
use dropout training for low rank quadratic features
- lrqfa(String, String, int) - Method in interface com.indeed.vw.wrapper.api.parameters.FeatureEngineeringFunctions
-
use low rank quadratic feature-aware weights
- lrqfa(String, String, int) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
use low rank quadratic features with field aware weights
- savePerPass() - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
Save the model after every pass over data
- saveResume() - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
save extra state so learning can be resumed later with new data
- search(int) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
Use learning to search, argument=maximum action id or 0 for LDF
- setLabelString(String) - Method in class com.indeed.vw.wrapper.api.example.ExampleBuilder
-
You can use it to pass labels for multi-class classification.
- sgd() - Method in interface com.indeed.vw.wrapper.api.parameters.UpdatesOptions
-
use regular stochastic gradient descent update.
- sgd() - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
use regular stochastic gradient descent update.
- SGDVowpalWabbitBuilder - Interface in com.indeed.vw.wrapper.api.parameters
-
This interface specify small subset of available options with some additional documentation.
- skips(String, int) - Method in interface com.indeed.vw.wrapper.api.parameters.FeatureEngineeringFunctions
-
Generate skips in N grams.
- skips(String, int) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
Generate skips in N grams.
- sortFeatures() - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
turn this on to disregard order in which features have been defined.
- sparseL2(double) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
use per feature normalized updates (=0)
- spelling(String) - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
compute spelling features for a give namespace (use '_' for default namespace)
- stagePoly() - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
use stagewise polynomial feature learning
- svrg() - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
Streaming Stochastic Variance Reduced Gradient
- valueOf(String) - Static method in enum com.indeed.vw.wrapper.api.parameters.Link
-
Returns the enum constant of this type with the specified name.
- valueOf(String) - Static method in enum com.indeed.vw.wrapper.api.parameters.Loss
-
Returns the enum constant of this type with the specified name.
- valueOf(String) - Static method in enum com.indeed.vw.wrapper.api.VowpalWabbit.Hash
-
Returns the enum constant of this type with the specified name.
- valueOf(String) - Static method in enum com.indeed.vw.wrapper.api.VowpalWabbit.LDF
-
Returns the enum constant of this type with the specified name.
- values() - Static method in enum com.indeed.vw.wrapper.api.parameters.Link
-
Returns an array containing the constants of this enum type, in
the order they are declared.
- values() - Static method in enum com.indeed.vw.wrapper.api.parameters.Loss
-
Returns an array containing the constants of this enum type, in
the order they are declared.
- values() - Static method in enum com.indeed.vw.wrapper.api.VowpalWabbit.Hash
-
Returns an array containing the constants of this enum type, in
the order they are declared.
- values() - Static method in enum com.indeed.vw.wrapper.api.VowpalWabbit.LDF
-
Returns an array containing the constants of this enum type, in
the order they are declared.
- verbose() - Method in interface com.indeed.vw.wrapper.api.parameters.DebuggingOptions
-
Make vowpal wabbit writing debug and performance information to stderr
- verbose() - Method in class com.indeed.vw.wrapper.api.VowpalWabbit.Builder
-
Make vowpal wabbit writing debug and performance information to stderr
- VowpalWabbit - Class in com.indeed.vw.wrapper.api
-
This class contains factory methods for VWLearner builder object.
- VowpalWabbit.Builder - Class in com.indeed.vw.wrapper.api
-
Builder for Vowpal Wabbit learner.
- VowpalWabbit.Hash - Enum in com.indeed.vw.wrapper.api
-
- VowpalWabbit.LDF - Enum in com.indeed.vw.wrapper.api
-
- VWUtility - Class in com.indeed.vw.wrapper.api.parameters
-
Set of useful methods