Skip to content

Scrub Latent Dirichlet Allocation Transform (Just Renaming) #2890

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Mar 11, 2019
Merged

Scrub Latent Dirichlet Allocation Transform (Just Renaming) #2890

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
bd68fde
Scrub LDA
wschin Mar 8, 2019
0212971
Rename static LDA API
wschin Mar 9, 2019
3eb12eb
Remove some advanced parameters in simple API
wschin Mar 9, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions docs/samples/Microsoft.ML.Samples/Dynamic/LdaTransform.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@

namespace Microsoft.ML.Samples.Dynamic
{
public static class LdaTransform
public static class LatentDirichletAllocationTransform
{
public static void Example()
{
Expand All @@ -30,7 +30,7 @@ public static void Example()

// A pipeline for featurizing the "Review" column
var pipeline = ml.Transforms.Text.ProduceWordBags(review).
Append(ml.Transforms.Text.LatentDirichletAllocation(review, ldaFeatures, numTopic:3));
Append(ml.Transforms.Text.LatentDirichletAllocation(review, ldaFeatures, numberOfTopics: 3));

// The transformed data
var transformer = pipeline.Fit(trainData);
Expand Down
94 changes: 47 additions & 47 deletions src/Microsoft.ML.StaticPipe/LdaStaticExtensions.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,65 +12,65 @@ namespace Microsoft.ML.StaticPipe
/// <summary>
/// Information on the result of fitting a LDA transform.
/// </summary>
public sealed class LdaFitResult
public sealed class LatentDirichletAllocationFitResult
{
/// <summary>
/// For user defined delegates that accept instances of the containing type.
/// </summary>
/// <param name="result"></param>
public delegate void OnFit(LdaFitResult result);
public delegate void OnFit(LatentDirichletAllocationFitResult result);

public LatentDirichletAllocationTransformer.LdaSummary LdaTopicSummary;
public LdaFitResult(LatentDirichletAllocationTransformer.LdaSummary ldaTopicSummary)
public LatentDirichletAllocationFitResult(LatentDirichletAllocationTransformer.LdaSummary ldaTopicSummary)
{
LdaTopicSummary = ldaTopicSummary;
}
}

public static class LdaStaticExtensions
public static class LatentDirichletAllocationStaticExtensions
{
private struct Config
{
public readonly int NumTopic;
public readonly int NumberOfTopics;
public readonly Single AlphaSum;
public readonly Single Beta;
public readonly int MHStep;
public readonly int NumIter;
public readonly int SamplingStepCount;
public readonly int MaximumNumberOfIterations;
public readonly int LikelihoodInterval;
public readonly int NumThread;
public readonly int NumMaxDocToken;
public readonly int NumSummaryTermPerTopic;
public readonly int NumBurninIter;
public readonly int NumberOfThreads;
public readonly int MaximumTokenCountPerDocument;
public readonly int NumberOfSummaryTermsPerTopic;
public readonly int NumberOfBurninIterations;
public readonly bool ResetRandomGenerator;

public readonly Action<LatentDirichletAllocationTransformer.LdaSummary> OnFit;

public Config(int numTopic, Single alphaSum, Single beta, int mhStep, int numIter, int likelihoodInterval,
int numThread, int numMaxDocToken, int numSummaryTermPerTopic, int numBurninIter, bool resetRandomGenerator,
public Config(int numberOfTopics, Single alphaSum, Single beta, int samplingStepCount, int maximumNumberOfIterations, int likelihoodInterval,
int numberOfThreads, int maximumTokenCountPerDocument, int numberOfSummaryTermsPerTopic, int numberOfBurninIterations, bool resetRandomGenerator,
Action<LatentDirichletAllocationTransformer.LdaSummary> onFit)
{
NumTopic = numTopic;
NumberOfTopics = numberOfTopics;
AlphaSum = alphaSum;
Beta = beta;
MHStep = mhStep;
NumIter = numIter;
SamplingStepCount = samplingStepCount;
MaximumNumberOfIterations = maximumNumberOfIterations;
LikelihoodInterval = likelihoodInterval;
NumThread = numThread;
NumMaxDocToken = numMaxDocToken;
NumSummaryTermPerTopic = numSummaryTermPerTopic;
NumBurninIter = numBurninIter;
NumberOfThreads = numberOfThreads;
MaximumTokenCountPerDocument = maximumTokenCountPerDocument;
NumberOfSummaryTermsPerTopic = numberOfSummaryTermsPerTopic;
NumberOfBurninIterations = numberOfBurninIterations;
ResetRandomGenerator = resetRandomGenerator;

OnFit = onFit;
}
}

private static Action<LatentDirichletAllocationTransformer.LdaSummary> Wrap(LdaFitResult.OnFit onFit)
private static Action<LatentDirichletAllocationTransformer.LdaSummary> Wrap(LatentDirichletAllocationFitResult.OnFit onFit)
{
if (onFit == null)
return null;

return ldaTopicSummary => onFit(new LdaFitResult(ldaTopicSummary));
return ldaTopicSummary => onFit(new LatentDirichletAllocationFitResult(ldaTopicSummary));
}

private interface ILdaCol
Expand Down Expand Up @@ -108,16 +108,16 @@ public override IEstimator<ITransformer> Reconcile(IHostEnvironment env,

infos[i] = new LatentDirichletAllocationEstimator.ColumnOptions(outputNames[toOutput[i]],
inputNames[tcol.Input],
tcol.Config.NumTopic,
tcol.Config.NumberOfTopics,
tcol.Config.AlphaSum,
tcol.Config.Beta,
tcol.Config.MHStep,
tcol.Config.NumIter,
tcol.Config.SamplingStepCount,
tcol.Config.MaximumNumberOfIterations,
tcol.Config.LikelihoodInterval,
tcol.Config.NumThread,
tcol.Config.NumMaxDocToken,
tcol.Config.NumSummaryTermPerTopic,
tcol.Config.NumBurninIter,
tcol.Config.NumberOfThreads,
tcol.Config.MaximumTokenCountPerDocument,
tcol.Config.NumberOfSummaryTermsPerTopic,
tcol.Config.NumberOfBurninIterations,
tcol.Config.ResetRandomGenerator);

if (tcol.Config.OnFit != null)
Expand All @@ -137,36 +137,36 @@ public override IEstimator<ITransformer> Reconcile(IHostEnvironment env,

/// <include file='../Microsoft.ML.Transforms/Text/doc.xml' path='doc/members/member[@name="LightLDA"]/*' />
/// <param name="input">A vector of floats representing the document.</param>
/// <param name="numTopic">The number of topics.</param>
/// <param name="numberOfTopics">The number of topics.</param>
/// <param name="alphaSum">Dirichlet prior on document-topic vectors.</param>
/// <param name="beta">Dirichlet prior on vocab-topic vectors.</param>
/// <param name="mhstep">Number of Metropolis Hasting step.</param>
/// <param name="numIterations">Number of iterations.</param>
/// <param name="samplingStepCount">Number of Metropolis Hasting step.</param>
/// <param name="maximumNumberOfIterations">Number of iterations.</param>
/// <param name="likelihoodInterval">Compute log likelihood over local dataset on this iteration interval.</param>
/// <param name="numThreads">The number of training threads. Default value depends on number of logical processors.</param>
/// <param name="numMaxDocToken">The threshold of maximum count of tokens per doc.</param>
/// <param name="numSummaryTermPerTopic">The number of words to summarize the topic.</param>
/// <param name="numBurninIterations">The number of burn-in iterations.</param>
/// <param name="numberOfThreads">The number of training threads. Default value depends on number of logical processors.</param>
/// <param name="maximumTokenCountPerDocument">The threshold of maximum count of tokens per doc.</param>
/// <param name="numberOfSummaryTermsPerTopic">The number of words to summarize the topic.</param>
/// <param name="numberOfBurninIterations">The number of burn-in iterations.</param>
/// <param name="resetRandomGenerator">Reset the random number generator for each document.</param>
/// <param name="onFit">Called upon fitting with the learnt enumeration on the dataset.</param>
public static Vector<float> ToLdaTopicVector(this Vector<float> input,
int numTopic = LatentDirichletAllocationEstimator.Defaults.NumTopic,
public static Vector<float> LatentDirichletAllocation(this Vector<float> input,
int numberOfTopics = LatentDirichletAllocationEstimator.Defaults.NumberOfTopics,
Single alphaSum = LatentDirichletAllocationEstimator.Defaults.AlphaSum,
Single beta = LatentDirichletAllocationEstimator.Defaults.Beta,
int mhstep = LatentDirichletAllocationEstimator.Defaults.Mhstep,
int numIterations = LatentDirichletAllocationEstimator.Defaults.NumIterations,
int samplingStepCount = LatentDirichletAllocationEstimator.Defaults.SamplingStepCount,
int maximumNumberOfIterations = LatentDirichletAllocationEstimator.Defaults.MaximumNumberOfIterations,
int likelihoodInterval = LatentDirichletAllocationEstimator.Defaults.LikelihoodInterval,
int numThreads = LatentDirichletAllocationEstimator.Defaults.NumThreads,
int numMaxDocToken = LatentDirichletAllocationEstimator.Defaults.NumMaxDocToken,
int numSummaryTermPerTopic = LatentDirichletAllocationEstimator.Defaults.NumSummaryTermPerTopic,
int numBurninIterations = LatentDirichletAllocationEstimator.Defaults.NumBurninIterations,
int numberOfThreads = LatentDirichletAllocationEstimator.Defaults.NumberOfThreads,
int maximumTokenCountPerDocument = LatentDirichletAllocationEstimator.Defaults.MaximumTokenCountPerDocument,
int numberOfSummaryTermsPerTopic = LatentDirichletAllocationEstimator.Defaults.NumberOfSummaryTermsPerTopic,
int numberOfBurninIterations = LatentDirichletAllocationEstimator.Defaults.NumberOfBurninIterations,
bool resetRandomGenerator = LatentDirichletAllocationEstimator.Defaults.ResetRandomGenerator,
LdaFitResult.OnFit onFit = null)
LatentDirichletAllocationFitResult.OnFit onFit = null)
{
Contracts.CheckValue(input, nameof(input));
return new ImplVector(input,
new Config(numTopic, alphaSum, beta, mhstep, numIterations, likelihoodInterval, numThreads, numMaxDocToken, numSummaryTermPerTopic,
numBurninIterations, resetRandomGenerator, Wrap(onFit)));
new Config(numberOfTopics, alphaSum, beta, samplingStepCount, maximumNumberOfIterations, likelihoodInterval, numberOfThreads, maximumTokenCountPerDocument, numberOfSummaryTermsPerTopic,
numberOfBurninIterations, resetRandomGenerator, Wrap(onFit)));
}
}
}
Loading