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
TomFinley 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 numberDiff line numberDiff 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 numberDiff line numberDiff 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 DownExpand 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
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all 
 blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks");
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

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

TomFinley
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 numberDiff line numberDiff 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 numberDiff line numberDiff 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 DownExpand 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

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Force GitHub README to respect dark mode\n(function() {\n var style = document.createElement('style');\n style.textContent = '\n .markdown-body {\n color-scheme: dark light;\n }\n .markdown-body pre { background: #161b22 !important; }\n .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }\n .markdown-body table th, .markdown-body table td { border-color: #30363d !important; }\n .markdown-body img { background: #0d1117; }\n .markdown-body blockquote { border-left-color: #8b949e; }\n .markdown-body hr { border-color: #30363d; }\n ';\n document.head.appendChild(style);\n})();", "GitHub Dark Mode README Fix");
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

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

TomFinley
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 numberDiff line numberDiff 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 numberDiff line numberDiff 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 DownExpand 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

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Highlight search terms from Google/DuckDuckGo/Bing referrer\n(function() {\n var ref = document.referrer;\n var terms = [];\n \n if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {\n var url = new URL(ref);\n var q = url.searchParams.get('q') || url.searchParams.get('p');\n if (q) {\n terms = q.split(/\\s+/).filter(function(t) { return t.length > 2; });\n }\n }\n \n if (terms.length === 0) return;\n \n var style = document.createElement('style');\n style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';\n document.head.appendChild(style);\n \n function highlight(node) {\n if (node.nodeType === 3) { // text node\n var text = node.textContent;\n var found = false;\n terms.forEach(function(term) {\n var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\\]\\\\]/g, '\\\\') + ')', 'gi');\n if (regex.test(text)) {\n found = true;\n var frag = document.createDocumentFragment();\n var parts = text.split(regex);\n parts.forEach(function(part, i) {\n if (i % 2 === 0) {\n frag.appendChild(document.createTextNode(part));\n } else {\n var span = document.createElement('span');\n span.className = 'userscript-highlight';\n span.textContent = part;\n frag.appendChild(span);\n }\n });\n node.parentNode.replaceChild(frag, node);\n }\n });\n } else if (node.nodeType === 1 && node.childNodes) { // element\n var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];\n if (!skipTags.includes(node.tagName)) {\n Array.from(node.childNodes).forEach(highlight);\n }\n }\n }\n \n highlight(document.body);\n \n // Re-highlight on dynamic content\n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1 || node.nodeType === 3) highlight(node);\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Highlight Search Terms");
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

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

TomFinley
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 numberDiff line numberDiff 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 numberDiff line numberDiff 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 DownExpand 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

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Strip utm_, fbclid, gclid, etc. from all links on page\n(function() {\n var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',\n 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',\n 'ref', 'ref_src', 'source', 'medium', 'campaign'];\n \n function cleanUrl(url) {\n try {\n var u = new URL(url, window.location.origin);\n var changed = false;\n trackingParams.forEach(function(p) {\n if (u.searchParams.has(p)) {\n u.searchParams.delete(p);\n changed = true;\n }\n });\n return changed ? u.toString() : url;\n } catch (e) {\n return url;\n }\n }\n \n function cleanLinks() {\n document.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n \n cleanLinks();\n \n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1) {\n if (node.tagName === 'A') cleanLinks();\n node.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Remove Tracking Parameters from Links");
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '

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

TomFinley
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 numberDiff line numberDiff 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 numberDiff line numberDiff 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 DownExpand 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

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Auto-enable theater mode on YouTube\n(function() {\n function tryTheater() {\n var btn = document.querySelector('button[aria-label=\"Theater mode\"], ytd-player #player button[title=\"Theater mode\"]');\n if (btn && !btn.classList.contains('activated')) {\n btn.click();\n }\n }\n \n // Try immediately\n tryTheater();\n \n // Try after navigation (SPA)\n var lastUrl = location.href;\n setInterval(function() {\n if (location.href !== lastUrl) {\n lastUrl = location.href;\n setTimeout(tryTheater, 500);\n }\n }, 1000);\n \n // Also try on player load\n var observer = new MutationObserver(tryTheater);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "YouTube Theater Mode Default");
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

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

TomFinley
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 numberDiff line numberDiff 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 numberDiff line numberDiff 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 DownExpand 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

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Remove or un-stick sticky/fixed headers that block content\n(function() {\n function unstick() {\n document.querySelectorAll('header, nav, [role=\"banner\"], .header, .navbar, .sticky, .fixed-top, [style*=\"position: fixed\"], [style*=\"position:sticky\"]').forEach(function(el) {\n if (el.style.position === 'fixed' || el.style.position === 'sticky' || \n getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {\n el.style.position = 'static';\n el.style.top = 'auto';\n el.style.zIndex = 'auto';\n }\n });\n }\n \n unstick();\n \n var observer = new MutationObserver(unstick);\n observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });\n})();", "Kill Sticky Headers");
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

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

TomFinley
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 numberDiff line numberDiff 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 numberDiff line numberDiff 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 DownExpand 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

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Universal Dark Mode - works on any site\n(function() {\n var enabled = true;\n \n function applyDarkMode() {\n if (!enabled) return;\n \n // Create style element if it doesn't exist\n var style = document.getElementById('universal-dark-mode-style');\n if (!style) {\n style = document.createElement('style');\n style.id = 'universal-dark-mode-style';\n document.head.appendChild(style);\n }\n \n // Dark mode CSS - inverts colors but preserves images/video\n style.textContent = '\n /* Invert everything except media */\n html {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #1a1a2e !important;\n }\n \n /* Restore images, videos, iframes, canvas */\n img, video, iframe, canvas, svg, picture, [style*=\"background-image\"] {\n filter: invert(1) hue-rotate(180deg) !important;\n }\n \n /* Preserve specific elements that should not be inverted */\n .no-dark-mode, .no-dark-mode *,\n [data-theme=\"light\"], [data-theme=\"light\"],\n .ace_editor, .ace_editor *,\n .CodeMirror, .CodeMirror *,\n .monaco-editor, .monaco-editor *,\n .markdown-body pre, .markdown-body pre *,\n .highlight, .highlight *,\n pre code, pre code * {\n filter: none !important;\n }\n \n /* Fix common UI elements */\n .modal, .popup, .dropdown-menu, .tooltip, .popover {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #2d2d44 !important;\n border-color: #444 !important;\n }\n \n /* Scrollbars */\n ::-webkit-scrollbar { background: #1a1a2e !important; }\n ::-webkit-scrollbar-thumb { background: #444 !important; }\n ::-webkit-scrollbar-thumb:hover { background: #555 !important; }\n \n /* Selection */\n ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ';\n }\n \n function removeDarkMode() {\n var style = document.getElementById('universal-dark-mode-style');\n if (style) style.remove();\n }\n \n // Toggle with Alt+Shift+D\n document.addEventListener('keydown', function(e) {\n if (e.altKey && e.shiftKey && e.key === 'D') {\n e.preventDefault();\n enabled = !enabled;\n if (enabled) {\n applyDarkMode();\n console.log('[Universal Dark Mode] Enabled');\n } else {\n removeDarkMode();\n console.log('[Universal Dark Mode] Disabled');\n }\n }\n });\n \n // Apply on load\n applyDarkMode();\n \n // Re-apply on dynamic content\n var observer = new MutationObserver(function(mutations) {\n if (enabled && !document.getElementById('universal-dark-mode-style')) {\n applyDarkMode();\n }\n });\n observer.observe(document.head, { childList: true });\n \n console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');\n})();", "Universal Dark Mode");
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();

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

TomFinley
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 numberDiff line numberDiff 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 numberDiff line numberDiff 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 DownExpand 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