Move Scorers and Calibrators to use IComponentFactory.#671

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
eerhardt merged 6 commits into from
Aug 16, 2018
Merged

Move Scorers and Calibrators to use IComponentFactory. #671

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
c1bb9f4
Move Scorers and Calibrators to use IComponentFactory.
eerhardt Aug 6, 2018
92f5b7a
fix test issue
eerhardt Aug 9, 2018
446c72c
Remove last SubComponent usage from ScoreCommand.
eerhardt Aug 9, 2018
c0f1c3b
Keep the Create method's signature so DI can find it.
eerhardt Aug 9, 2018
f32af76
Respond to PR feedback.
eerhardt Aug 14, 2018
3688862
Change CmdParser ComponentFactoryFactory to not throw an exception du…
eerhardt Aug 14, 2018
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
13 changes: 11 additions & 2 deletions src/Microsoft.ML.Api/ComponentCreation.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -6,6 +6,7 @@
using System.IO;
using Microsoft.ML.Runtime.CommandLine;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.EntryPoints;
using Microsoft.ML.Runtime.Model;

namespace Microsoft.ML.Runtime.Api
Expand DownExpand Up@@ -304,12 +305,20 @@ public static IDataScorerTransform CreateScorer(this IHostEnvironment env, strin
env.CheckValue(predictor, nameof(predictor));
env.CheckValueOrNull(trainSchema);

var subComponent = SubComponent.Parse<IDataScorerTransform, SignatureDataScorer>(settings);
var bindable = ScoreUtils.GetSchemaBindableMapper(env, predictor.Pred, subComponent);
ICommandLineComponentFactory scorerFactorySettings = ParseScorerSettings(settings);
var bindable = ScoreUtils.GetSchemaBindableMapper(env, predictor.Pred, scorerFactorySettings: scorerFactorySettings);
var mapper = bindable.Bind(env, data.Schema);
return CreateCore<IDataScorerTransform, SignatureDataScorer>(env, settings, data.Data, mapper, trainSchema);
}

private static ICommandLineComponentFactory ParseScorerSettings(string settings)
{
return CmdParser.CreateComponentFactory(
typeof(IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform>),
typeof(SignatureDataScorer),
settings);
}

/// <summary>
/// Creates a default data scorer appropriate to the predictor's prediction kind.
/// </summary>
Expand Down
361 changes: 240 additions & 121 deletions src/Microsoft.ML.Core/CommandLine/CmdParser.cs
View file
Open in desktop

Large diffs are not rendered by default.

28 changes: 28 additions & 0 deletions src/Microsoft.ML.Core/EntryPoints/ComponentFactory.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -64,4 +64,32 @@ public interface IComponentFactory<in TArg1, in TArg2, out TComponent> : ICompon
{
TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2);
}

/// <summary>
/// An interface for creating a component when we take three extra parameters (and an <see cref="IHostEnvironment"/>).
/// </summary>
public interface IComponentFactory<in TArg1, in TArg2, in TArg3, out TComponent> : IComponentFactory
{
TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2, TArg3 argument3);
}

/// <summary>
/// A class for creating a component when we take three extra parameters
/// (and an <see cref="IHostEnvironment"/>) that simply wraps a delegate which
/// creates the component.
/// </summary>
public class SimpleComponentFactory<TArg1, TArg2, TArg3, TComponent> : IComponentFactory<TArg1, TArg2, TArg3, TComponent>

@TomFinleyTomFinleyAug 16, 2018

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

SimpleComponentFactory [](start = 17, length = 22)

Thanks @eerhardt. As we discussed in #681 perhaps we can hide these implementations of the interface, but we'll do that after we merge this I suppose.

@eerhardteerhardtAug 16, 2018

Copy link
Copy Markdown
MemberAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, I will take care of all the SimpleComponentFactory classes being hidden in #681.

{
private Func<IHostEnvironment, TArg1, TArg2, TArg3, TComponent> _factory;

public SimpleComponentFactory(Func<IHostEnvironment, TArg1, TArg2, TArg3, TComponent> factory)
{
_factory = factory;
}

public TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2, TArg3 argument3)
{
return _factory(env, argument1, argument2, argument3);
}
}
}
21 changes: 11 additions & 10 deletions src/Microsoft.ML.Data/Commands/CrossValidationCommand.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -28,8 +28,8 @@ public sealed class Arguments : DataCommand.ArgumentsBase
[Argument(ArgumentType.Multiple, HelpText = "Trainer to use", ShortName = "tr")]
public SubComponent<ITrainer, SignatureTrainer> Trainer = new SubComponent<ITrainer, SignatureTrainer>("AveragedPerceptron");

[Argument(ArgumentType.Multiple, HelpText = "Scorer to use", NullName = "<Auto>", SortOrder = 101)]
public SubComponent<IDataScorerTransform, SignatureDataScorer> Scorer;
[Argument(ArgumentType.Multiple, HelpText = "Scorer to use", NullName = "<Auto>", SortOrder = 101, SignatureType = typeof(SignatureDataScorer))]

@Zruty0Zruty0Aug 9, 2018•
edited
Loading

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

SignatureDataScorer [](start = 134, length = 19)

I wonder if the information contained in SignatureType is identical to the information contained in typeof(Scorer) ?
As in, aren't these the type parameters you want to invoke with? #Closed

@eerhardteerhardtAug 14, 2018•
edited by Zruty0
Loading

Copy link
Copy Markdown
MemberAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The parameter information definitely overlaps, but this isn't duplicate information.

For example, if there are two signature delegates:

publicdelegatevoidSignatureSweeper();publicdelegatevoidSignatureTrainer();

We can't discern which one we are trying to load from the component catalog solely on signature (both these signature delegates don't take any more parameters other than the Environment). #Closed

@Zruty0Zruty0Aug 15, 2018

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Oh, I see. So the signature is needed for subselecting a list.

In reply to: 210097300 [](ancestors = 210097300)

@eerhardteerhardtAug 15, 2018

Copy link
Copy Markdown
MemberAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The signature is needed in order to find the component in the ComponentCatalog. We can have multiple components with the same name, but are different based on their "signature type". So the components are keyed off both a name and a signature type:

machinelearning/src/Microsoft.ML.Core/ComponentModel/ComponentCatalog.cs

Lines 35 to 41 in e77f24e

/// <summary>
/// Used for dictionary lookup based on signature and name.
/// </summary>
internalstructKey:IEquatable<Key>
{
publicreadonlystringName;
publicreadonlyTypeSignature;

machinelearning/src/Microsoft.ML.Core/ComponentModel/ComponentCatalog.cs

Line 787 in e77f24e

privatestaticLoadableClassInfoFindClassCore(LoadableClassInfo.Keykey)

public IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> Scorer;

[Argument(ArgumentType.Multiple, HelpText = "Evaluator to use", ShortName = "eval", NullName = "<Auto>", SortOrder = 102)]
public SubComponent<IMamlEvaluator, SignatureMamlEvaluator> Evaluator;
Expand DownExpand Up@@ -76,8 +76,8 @@ public sealed class Arguments : DataCommand.ArgumentsBase
[Argument(ArgumentType.AtMostOnce, IsInputFileName = true, HelpText = "The validation data file", ShortName = "valid")]
public string ValidationFile;

[Argument(ArgumentType.Multiple, HelpText = "Output calibrator", ShortName = "cali", NullName = "<None>")]
public SubComponent<ICalibratorTrainer, SignatureCalibrator> Calibrator = new SubComponent<ICalibratorTrainer, SignatureCalibrator>("PlattCalibration");
[Argument(ArgumentType.Multiple, HelpText = "Output calibrator", ShortName = "cali", NullName = "<None>", SignatureType = typeof(SignatureCalibrator))]
public IComponentFactory<ICalibratorTrainer> Calibrator = new PlattCalibratorTrainerFactory();

[Argument(ArgumentType.LastOccurenceWins, HelpText = "Number of instances to train the calibrator", ShortName = "numcali")]
public int MaxCalibrationExamples = 1000000000;
Expand DownExpand Up@@ -383,9 +383,9 @@ public FoldResult(Dictionary<string, IDataView> metrics, ISchema scoreSchema, Ro
private readonly string _splitColumn;
private readonly int _numFolds;
private readonly SubComponent<ITrainer, SignatureTrainer> _trainer;
private readonly SubComponent<IDataScorerTransform, SignatureDataScorer> _scorer;
private readonly IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> _scorer;
private readonly SubComponent<IMamlEvaluator, SignatureMamlEvaluator> _evaluator;
private readonly SubComponent<ICalibratorTrainer, SignatureCalibrator> _calibrator;
private readonly IComponentFactory<ICalibratorTrainer> _calibrator;
private readonly int _maxCalibrationExamples;
private readonly bool _useThreads;
private readonly bool? _cacheData;
Expand DownExpand Up@@ -423,7 +423,7 @@ public FoldHelper(
Arguments args,
Func<IHostEnvironment, IChannel, IDataView, ITrainer, RoleMappedData> createExamples,
Func<IHostEnvironment, IChannel, IDataView, RoleMappedData, IDataView, RoleMappedData> applyTransformsToTestData,
SubComponent<IDataScorerTransform, SignatureDataScorer> scorer,
IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> scorer,
SubComponent<IMamlEvaluator, SignatureMamlEvaluator> evaluator,
Func<IDataView> getValidationDataView = null,
Func<IHostEnvironment, IChannel, IDataView, RoleMappedData, IDataView, RoleMappedData> applyTransformsToValidationData = null,
Expand DownExpand Up@@ -559,11 +559,12 @@ private FoldResult RunFold(int fold)

// Score.
ch.Trace("Scoring and evaluating");
var bindable = ScoreUtils.GetSchemaBindableMapper(host, predictor, _scorer);
ch.Assert(_scorer == null || _scorer is ICommandLineComponentFactory, "CrossValidationCommand should only be used from the command line.");
var bindable = ScoreUtils.GetSchemaBindableMapper(host, predictor, scorerFactorySettings: _scorer as ICommandLineComponentFactory);
ch.AssertValue(bindable);
var mapper = bindable.Bind(host, testData.Schema);
var scorerComp = _scorer.IsGood() ? _scorer : ScoreUtils.GetScorerComponent(mapper);
IDataScorerTransform scorePipe = scorerComp.CreateInstance(host, testData.Data, mapper, trainData.Schema);
var scorerComp = _scorer ?? ScoreUtils.GetScorerComponent(mapper);
IDataScorerTransform scorePipe = scorerComp.CreateComponent(host, testData.Data, mapper, trainData.Schema);

// Save per-fold model.
string modelFileName = ConstructPerFoldName(_outputModelFile, fold);
Expand Down
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
 Move Scorers and Calibrators to use IComponentFactory.#671

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

eerhardt
merged 6 commits into

from

Aug 16, 2018
 Merged


Move Scorers and Calibrators to use IComponentFactory.
#671
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


6 commits


Select commit
Hold shift + click to select a range
c1bb9f4

Move Scorers and Calibrators to use IComponentFactory.


eerhardt Aug 6, 2018
92f5b7a

fix test issue


eerhardt Aug 9, 2018
446c72c

Remove last SubComponent usage from ScoreCommand.


eerhardt Aug 9, 2018
c0f1c3b

Keep the Create method's signature so DI can find it.


eerhardt Aug 9, 2018
f32af76

Respond to PR feedback.


eerhardt Aug 14, 2018
3688862

Change CmdParser ComponentFactoryFactory to not throw an exception du…


eerhardt Aug 14, 2018

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


13 changes: 11 additions & 2 deletions
src/Microsoft.ML.Api/ComponentCreation.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -6,6 +6,7 @@
using System.IO;
using Microsoft.ML.Runtime.CommandLine;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.EntryPoints;
using Microsoft.ML.Runtime.Model;

namespace Microsoft.ML.Runtime.Api
Expand DownExpand Up@@ -304,12 +305,20 @@ public static IDataScorerTransform CreateScorer(this IHostEnvironment env, strin
 env.CheckValue(predictor, nameof(predictor));
 env.CheckValueOrNull(trainSchema);

var subComponent = SubComponent.Parse<IDataScorerTransform, SignatureDataScorer>(settings);
 var bindable = ScoreUtils.GetSchemaBindableMapper(env, predictor.Pred, subComponent);
ICommandLineComponentFactory scorerFactorySettings = ParseScorerSettings(settings);
 var bindable = ScoreUtils.GetSchemaBindableMapper(env, predictor.Pred, scorerFactorySettings: scorerFactorySettings);
 var mapper = bindable.Bind(env, data.Schema);
 return CreateCore<IDataScorerTransform, SignatureDataScorer>(env, settings, data.Data, mapper, trainSchema);
 }

 private static ICommandLineComponentFactory ParseScorerSettings(string settings)
 {
 return CmdParser.CreateComponentFactory(
 typeof(IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform>),
 typeof(SignatureDataScorer),
 settings);
 }

 /// <summary>
 /// Creates a default data scorer appropriate to the predictor's prediction kind.
 /// </summary>
Expand Down

361 changes: 240 additions & 121 deletions
src/Microsoft.ML.Core/CommandLine/CmdParser.cs

View file


Open in desktop


Large diffs are not rendered by default.


28 changes: 28 additions & 0 deletions
src/Microsoft.ML.Core/EntryPoints/ComponentFactory.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -64,4 +64,32 @@ public interface IComponentFactory<in TArg1, in TArg2, out TComponent> : ICompon
 {
 TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2);
 }

 /// <summary>
 /// An interface for creating a component when we take three extra parameters (and an <see cref="IHostEnvironment"/>).
 /// </summary>
 public interface IComponentFactory<in TArg1, in TArg2, in TArg3, out TComponent> : IComponentFactory
 {
 TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2, TArg3 argument3);
 }

 /// <summary>
 /// A class for creating a component when we take three extra parameters
 /// (and an <see cref="IHostEnvironment"/>) that simply wraps a delegate which
 /// creates the component.
 /// </summary>
 public class SimpleComponentFactory<TArg1, TArg2, TArg3, TComponent> : IComponentFactory<TArg1, TArg2, TArg3, TComponent>
@TomFinleyTomFinleyAug 16, 2018

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

SimpleComponentFactory [](start = 17, length = 22)
Thanks @eerhardt. As we discussed in #681 perhaps we can hide these implementations of the interface, but we'll do that after we merge this I suppose.
@eerhardteerhardtAug 16, 2018

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, I will take care of all the SimpleComponentFactory classes being hidden in #681.
 {
 private Func<IHostEnvironment, TArg1, TArg2, TArg3, TComponent> _factory;

 public SimpleComponentFactory(Func<IHostEnvironment, TArg1, TArg2, TArg3, TComponent> factory)
 {
 _factory = factory;
 }

 public TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2, TArg3 argument3)
 {
 return _factory(env, argument1, argument2, argument3);
 }
 }
}

21 changes: 11 additions & 10 deletions
src/Microsoft.ML.Data/Commands/CrossValidationCommand.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -28,8 +28,8 @@ public sealed class Arguments : DataCommand.ArgumentsBase
 [Argument(ArgumentType.Multiple, HelpText = "Trainer to use", ShortName = "tr")]
 public SubComponent<ITrainer, SignatureTrainer> Trainer = new SubComponent<ITrainer, SignatureTrainer>("AveragedPerceptron");

 [Argument(ArgumentType.Multiple, HelpText = "Scorer to use", NullName = "<Auto>", SortOrder = 101)]
 public SubComponent<IDataScorerTransform, SignatureDataScorer> Scorer;
 [Argument(ArgumentType.Multiple, HelpText = "Scorer to use", NullName = "<Auto>", SortOrder = 101, SignatureType = typeof(SignatureDataScorer))]
@Zruty0Zruty0Aug 9, 2018•

edited

Loading

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

SignatureDataScorer [](start = 134, length = 19)
I wonder if the information contained in SignatureType is identical to the information contained in typeof(Scorer) ?

As in, aren't these the type parameters you want to invoke with? #Closed
@eerhardteerhardtAug 14, 2018•

edited by Zruty0

Loading

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The parameter information definitely overlaps, but this isn't duplicate information.
For example, if there are two signature delegates:
publicdelegatevoidSignatureSweeper();publicdelegatevoidSignatureTrainer();
We can't discern which one we are trying to load from the component catalog solely on signature (both these signature delegates don't take any more parameters other than the Environment). #Closed
@Zruty0Zruty0Aug 15, 2018

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Oh, I see. So the signature is needed for subselecting a list.
In reply to: 210097300 [](ancestors = 210097300)
@eerhardteerhardtAug 15, 2018

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The signature is needed in order to find the component in the ComponentCatalog. We can have multiple components with the same name, but are different based on their "signature type". So the components are keyed off both a name and a signature type:
machinelearning/src/Microsoft.ML.Core/ComponentModel/ComponentCatalog.cs

Lines 35 to 41
in
e77f24e
/// <summary>
/// Used for dictionary lookup based on signature and name.
/// </summary>
internalstructKey:IEquatable<Key>
{
publicreadonlystringName;
publicreadonlyTypeSignature;
machinelearning/src/Microsoft.ML.Core/ComponentModel/ComponentCatalog.cs

Line 787
in
e77f24e
privatestaticLoadableClassInfoFindClassCore(LoadableClassInfo.Keykey)
 public IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> Scorer;

 [Argument(ArgumentType.Multiple, HelpText = "Evaluator to use", ShortName = "eval", NullName = "<Auto>", SortOrder = 102)]
 public SubComponent<IMamlEvaluator, SignatureMamlEvaluator> Evaluator;
Expand DownExpand Up@@ -76,8 +76,8 @@ public sealed class Arguments : DataCommand.ArgumentsBase
 [Argument(ArgumentType.AtMostOnce, IsInputFileName = true, HelpText = "The validation data file", ShortName = "valid")]
 public string ValidationFile;

 [Argument(ArgumentType.Multiple, HelpText = "Output calibrator", ShortName = "cali", NullName = "<None>")]
 public SubComponent<ICalibratorTrainer, SignatureCalibrator> Calibrator = new SubComponent<ICalibratorTrainer, SignatureCalibrator>("PlattCalibration");
 [Argument(ArgumentType.Multiple, HelpText = "Output calibrator", ShortName = "cali", NullName = "<None>", SignatureType = typeof(SignatureCalibrator))]
 public IComponentFactory<ICalibratorTrainer> Calibrator = new PlattCalibratorTrainerFactory();

 [Argument(ArgumentType.LastOccurenceWins, HelpText = "Number of instances to train the calibrator", ShortName = "numcali")]
 public int MaxCalibrationExamples = 1000000000;
Expand DownExpand Up@@ -383,9 +383,9 @@ public FoldResult(Dictionary<string, IDataView> metrics, ISchema scoreSchema, Ro
 private readonly string _splitColumn;
 private readonly int _numFolds;
 private readonly SubComponent<ITrainer, SignatureTrainer> _trainer;
 private readonly SubComponent<IDataScorerTransform, SignatureDataScorer> _scorer;
 private readonly IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> _scorer;
 private readonly SubComponent<IMamlEvaluator, SignatureMamlEvaluator> _evaluator;
 private readonly SubComponent<ICalibratorTrainer, SignatureCalibrator> _calibrator;
 private readonly IComponentFactory<ICalibratorTrainer> _calibrator;
 private readonly int _maxCalibrationExamples;
 private readonly bool _useThreads;
 private readonly bool? _cacheData;
Expand DownExpand Up@@ -423,7 +423,7 @@ public FoldHelper(
 Arguments args,
 Func<IHostEnvironment, IChannel, IDataView, ITrainer, RoleMappedData> createExamples,
 Func<IHostEnvironment, IChannel, IDataView, RoleMappedData, IDataView, RoleMappedData> applyTransformsToTestData,
SubComponent<IDataScorerTransform, SignatureDataScorer> scorer,
IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> scorer,
 SubComponent<IMamlEvaluator, SignatureMamlEvaluator> evaluator,
 Func<IDataView> getValidationDataView = null,
 Func<IHostEnvironment, IChannel, IDataView, RoleMappedData, IDataView, RoleMappedData> applyTransformsToValidationData = null,
Expand DownExpand Up@@ -559,11 +559,12 @@ private FoldResult RunFold(int fold)

 // Score.
 ch.Trace("Scoring and evaluating");
 var bindable = ScoreUtils.GetSchemaBindableMapper(host, predictor, _scorer);
 ch.Assert(_scorer == null || _scorer is ICommandLineComponentFactory, "CrossValidationCommand should only be used from the command line.");
 var bindable = ScoreUtils.GetSchemaBindableMapper(host, predictor, scorerFactorySettings: _scorer as ICommandLineComponentFactory);
 ch.AssertValue(bindable);
 var mapper = bindable.Bind(host, testData.Schema);
 var scorerComp = _scorer.IsGood() ? _scorer : ScoreUtils.GetScorerComponent(mapper);
 IDataScorerTransform scorePipe = scorerComp.CreateInstance(host, testData.Data, mapper, trainData.Schema);
 var scorerComp = _scorer ?? ScoreUtils.GetScorerComponent(mapper);
 IDataScorerTransform scorePipe = scorerComp.CreateComponent(host, testData.Data, mapper, trainData.Schema);

 // Save per-fold model.
 string modelFileName = ConstructPerFoldName(_outputModelFile, fold);
Expand Down
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
 Move Scorers and Calibrators to use IComponentFactory.#671

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

eerhardt
merged 6 commits into

from

Aug 16, 2018
 Merged


Move Scorers and Calibrators to use IComponentFactory.
#671
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


6 commits


Select commit
Hold shift + click to select a range
c1bb9f4

Move Scorers and Calibrators to use IComponentFactory.


eerhardt Aug 6, 2018
92f5b7a

fix test issue


eerhardt Aug 9, 2018
446c72c

Remove last SubComponent usage from ScoreCommand.


eerhardt Aug 9, 2018
c0f1c3b

Keep the Create method's signature so DI can find it.


eerhardt Aug 9, 2018
f32af76

Respond to PR feedback.


eerhardt Aug 14, 2018
3688862

Change CmdParser ComponentFactoryFactory to not throw an exception du…


eerhardt Aug 14, 2018

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


13 changes: 11 additions & 2 deletions
src/Microsoft.ML.Api/ComponentCreation.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -6,6 +6,7 @@
using System.IO;
using Microsoft.ML.Runtime.CommandLine;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.EntryPoints;
using Microsoft.ML.Runtime.Model;

namespace Microsoft.ML.Runtime.Api
Expand DownExpand Up@@ -304,12 +305,20 @@ public static IDataScorerTransform CreateScorer(this IHostEnvironment env, strin
 env.CheckValue(predictor, nameof(predictor));
 env.CheckValueOrNull(trainSchema);

var subComponent = SubComponent.Parse<IDataScorerTransform, SignatureDataScorer>(settings);
 var bindable = ScoreUtils.GetSchemaBindableMapper(env, predictor.Pred, subComponent);
ICommandLineComponentFactory scorerFactorySettings = ParseScorerSettings(settings);
 var bindable = ScoreUtils.GetSchemaBindableMapper(env, predictor.Pred, scorerFactorySettings: scorerFactorySettings);
 var mapper = bindable.Bind(env, data.Schema);
 return CreateCore<IDataScorerTransform, SignatureDataScorer>(env, settings, data.Data, mapper, trainSchema);
 }

 private static ICommandLineComponentFactory ParseScorerSettings(string settings)
 {
 return CmdParser.CreateComponentFactory(
 typeof(IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform>),
 typeof(SignatureDataScorer),
 settings);
 }

 /// <summary>
 /// Creates a default data scorer appropriate to the predictor's prediction kind.
 /// </summary>
Expand Down

361 changes: 240 additions & 121 deletions
src/Microsoft.ML.Core/CommandLine/CmdParser.cs

View file


Open in desktop


Large diffs are not rendered by default.


28 changes: 28 additions & 0 deletions
src/Microsoft.ML.Core/EntryPoints/ComponentFactory.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -64,4 +64,32 @@ public interface IComponentFactory<in TArg1, in TArg2, out TComponent> : ICompon
 {
 TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2);
 }

 /// <summary>
 /// An interface for creating a component when we take three extra parameters (and an <see cref="IHostEnvironment"/>).
 /// </summary>
 public interface IComponentFactory<in TArg1, in TArg2, in TArg3, out TComponent> : IComponentFactory
 {
 TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2, TArg3 argument3);
 }

 /// <summary>
 /// A class for creating a component when we take three extra parameters
 /// (and an <see cref="IHostEnvironment"/>) that simply wraps a delegate which
 /// creates the component.
 /// </summary>
 public class SimpleComponentFactory<TArg1, TArg2, TArg3, TComponent> : IComponentFactory<TArg1, TArg2, TArg3, TComponent>
@TomFinleyTomFinleyAug 16, 2018

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

SimpleComponentFactory [](start = 17, length = 22)
Thanks @eerhardt. As we discussed in #681 perhaps we can hide these implementations of the interface, but we'll do that after we merge this I suppose.
@eerhardteerhardtAug 16, 2018

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, I will take care of all the SimpleComponentFactory classes being hidden in #681.
 {
 private Func<IHostEnvironment, TArg1, TArg2, TArg3, TComponent> _factory;

 public SimpleComponentFactory(Func<IHostEnvironment, TArg1, TArg2, TArg3, TComponent> factory)
 {
 _factory = factory;
 }

 public TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2, TArg3 argument3)
 {
 return _factory(env, argument1, argument2, argument3);
 }
 }
}

21 changes: 11 additions & 10 deletions
src/Microsoft.ML.Data/Commands/CrossValidationCommand.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -28,8 +28,8 @@ public sealed class Arguments : DataCommand.ArgumentsBase
 [Argument(ArgumentType.Multiple, HelpText = "Trainer to use", ShortName = "tr")]
 public SubComponent<ITrainer, SignatureTrainer> Trainer = new SubComponent<ITrainer, SignatureTrainer>("AveragedPerceptron");

 [Argument(ArgumentType.Multiple, HelpText = "Scorer to use", NullName = "<Auto>", SortOrder = 101)]
 public SubComponent<IDataScorerTransform, SignatureDataScorer> Scorer;
 [Argument(ArgumentType.Multiple, HelpText = "Scorer to use", NullName = "<Auto>", SortOrder = 101, SignatureType = typeof(SignatureDataScorer))]
@Zruty0Zruty0Aug 9, 2018•

edited

Loading

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

SignatureDataScorer [](start = 134, length = 19)
I wonder if the information contained in SignatureType is identical to the information contained in typeof(Scorer) ?

As in, aren't these the type parameters you want to invoke with? #Closed
@eerhardteerhardtAug 14, 2018•

edited by Zruty0

Loading

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The parameter information definitely overlaps, but this isn't duplicate information.
For example, if there are two signature delegates:
publicdelegatevoidSignatureSweeper();publicdelegatevoidSignatureTrainer();
We can't discern which one we are trying to load from the component catalog solely on signature (both these signature delegates don't take any more parameters other than the Environment). #Closed
@Zruty0Zruty0Aug 15, 2018

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Oh, I see. So the signature is needed for subselecting a list.
In reply to: 210097300 [](ancestors = 210097300)
@eerhardteerhardtAug 15, 2018

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The signature is needed in order to find the component in the ComponentCatalog. We can have multiple components with the same name, but are different based on their "signature type". So the components are keyed off both a name and a signature type:
machinelearning/src/Microsoft.ML.Core/ComponentModel/ComponentCatalog.cs

Lines 35 to 41
in
e77f24e
/// <summary>
/// Used for dictionary lookup based on signature and name.
/// </summary>
internalstructKey:IEquatable<Key>
{
publicreadonlystringName;
publicreadonlyTypeSignature;
machinelearning/src/Microsoft.ML.Core/ComponentModel/ComponentCatalog.cs

Line 787
in
e77f24e
privatestaticLoadableClassInfoFindClassCore(LoadableClassInfo.Keykey)
 public IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> Scorer;

 [Argument(ArgumentType.Multiple, HelpText = "Evaluator to use", ShortName = "eval", NullName = "<Auto>", SortOrder = 102)]
 public SubComponent<IMamlEvaluator, SignatureMamlEvaluator> Evaluator;
Expand DownExpand Up@@ -76,8 +76,8 @@ public sealed class Arguments : DataCommand.ArgumentsBase
 [Argument(ArgumentType.AtMostOnce, IsInputFileName = true, HelpText = "The validation data file", ShortName = "valid")]
 public string ValidationFile;

 [Argument(ArgumentType.Multiple, HelpText = "Output calibrator", ShortName = "cali", NullName = "<None>")]
 public SubComponent<ICalibratorTrainer, SignatureCalibrator> Calibrator = new SubComponent<ICalibratorTrainer, SignatureCalibrator>("PlattCalibration");
 [Argument(ArgumentType.Multiple, HelpText = "Output calibrator", ShortName = "cali", NullName = "<None>", SignatureType = typeof(SignatureCalibrator))]
 public IComponentFactory<ICalibratorTrainer> Calibrator = new PlattCalibratorTrainerFactory();

 [Argument(ArgumentType.LastOccurenceWins, HelpText = "Number of instances to train the calibrator", ShortName = "numcali")]
 public int MaxCalibrationExamples = 1000000000;
Expand DownExpand Up@@ -383,9 +383,9 @@ public FoldResult(Dictionary<string, IDataView> metrics, ISchema scoreSchema, Ro
 private readonly string _splitColumn;
 private readonly int _numFolds;
 private readonly SubComponent<ITrainer, SignatureTrainer> _trainer;
 private readonly SubComponent<IDataScorerTransform, SignatureDataScorer> _scorer;
 private readonly IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> _scorer;
 private readonly SubComponent<IMamlEvaluator, SignatureMamlEvaluator> _evaluator;
 private readonly SubComponent<ICalibratorTrainer, SignatureCalibrator> _calibrator;
 private readonly IComponentFactory<ICalibratorTrainer> _calibrator;
 private readonly int _maxCalibrationExamples;
 private readonly bool _useThreads;
 private readonly bool? _cacheData;
Expand DownExpand Up@@ -423,7 +423,7 @@ public FoldHelper(
 Arguments args,
 Func<IHostEnvironment, IChannel, IDataView, ITrainer, RoleMappedData> createExamples,
 Func<IHostEnvironment, IChannel, IDataView, RoleMappedData, IDataView, RoleMappedData> applyTransformsToTestData,
SubComponent<IDataScorerTransform, SignatureDataScorer> scorer,
IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> scorer,
 SubComponent<IMamlEvaluator, SignatureMamlEvaluator> evaluator,
 Func<IDataView> getValidationDataView = null,
 Func<IHostEnvironment, IChannel, IDataView, RoleMappedData, IDataView, RoleMappedData> applyTransformsToValidationData = null,
Expand DownExpand Up@@ -559,11 +559,12 @@ private FoldResult RunFold(int fold)

 // Score.
 ch.Trace("Scoring and evaluating");
 var bindable = ScoreUtils.GetSchemaBindableMapper(host, predictor, _scorer);
 ch.Assert(_scorer == null || _scorer is ICommandLineComponentFactory, "CrossValidationCommand should only be used from the command line.");
 var bindable = ScoreUtils.GetSchemaBindableMapper(host, predictor, scorerFactorySettings: _scorer as ICommandLineComponentFactory);
 ch.AssertValue(bindable);
 var mapper = bindable.Bind(host, testData.Schema);
 var scorerComp = _scorer.IsGood() ? _scorer : ScoreUtils.GetScorerComponent(mapper);
 IDataScorerTransform scorePipe = scorerComp.CreateInstance(host, testData.Data, mapper, trainData.Schema);
 var scorerComp = _scorer ?? ScoreUtils.GetScorerComponent(mapper);
 IDataScorerTransform scorePipe = scorerComp.CreateComponent(host, testData.Data, mapper, trainData.Schema);

 // Save per-fold model.
 string modelFileName = ConstructPerFoldName(_outputModelFile, fold);
Expand Down
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
 Move Scorers and Calibrators to use IComponentFactory.#671

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

eerhardt
merged 6 commits into

from

Aug 16, 2018
 Merged


Move Scorers and Calibrators to use IComponentFactory.
#671
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


6 commits


Select commit
Hold shift + click to select a range
c1bb9f4

Move Scorers and Calibrators to use IComponentFactory.


eerhardt Aug 6, 2018
92f5b7a

fix test issue


eerhardt Aug 9, 2018
446c72c

Remove last SubComponent usage from ScoreCommand.


eerhardt Aug 9, 2018
c0f1c3b

Keep the Create method's signature so DI can find it.


eerhardt Aug 9, 2018
f32af76

Respond to PR feedback.


eerhardt Aug 14, 2018
3688862

Change CmdParser ComponentFactoryFactory to not throw an exception du…


eerhardt Aug 14, 2018

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


13 changes: 11 additions & 2 deletions
src/Microsoft.ML.Api/ComponentCreation.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -6,6 +6,7 @@
using System.IO;
using Microsoft.ML.Runtime.CommandLine;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.EntryPoints;
using Microsoft.ML.Runtime.Model;

namespace Microsoft.ML.Runtime.Api
Expand DownExpand Up@@ -304,12 +305,20 @@ public static IDataScorerTransform CreateScorer(this IHostEnvironment env, strin
 env.CheckValue(predictor, nameof(predictor));
 env.CheckValueOrNull(trainSchema);

var subComponent = SubComponent.Parse<IDataScorerTransform, SignatureDataScorer>(settings);
 var bindable = ScoreUtils.GetSchemaBindableMapper(env, predictor.Pred, subComponent);
ICommandLineComponentFactory scorerFactorySettings = ParseScorerSettings(settings);
 var bindable = ScoreUtils.GetSchemaBindableMapper(env, predictor.Pred, scorerFactorySettings: scorerFactorySettings);
 var mapper = bindable.Bind(env, data.Schema);
 return CreateCore<IDataScorerTransform, SignatureDataScorer>(env, settings, data.Data, mapper, trainSchema);
 }

 private static ICommandLineComponentFactory ParseScorerSettings(string settings)
 {
 return CmdParser.CreateComponentFactory(
 typeof(IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform>),
 typeof(SignatureDataScorer),
 settings);
 }

 /// <summary>
 /// Creates a default data scorer appropriate to the predictor's prediction kind.
 /// </summary>
Expand Down

361 changes: 240 additions & 121 deletions
src/Microsoft.ML.Core/CommandLine/CmdParser.cs

View file


Open in desktop


Large diffs are not rendered by default.


28 changes: 28 additions & 0 deletions
src/Microsoft.ML.Core/EntryPoints/ComponentFactory.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -64,4 +64,32 @@ public interface IComponentFactory<in TArg1, in TArg2, out TComponent> : ICompon
 {
 TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2);
 }

 /// <summary>
 /// An interface for creating a component when we take three extra parameters (and an <see cref="IHostEnvironment"/>).
 /// </summary>
 public interface IComponentFactory<in TArg1, in TArg2, in TArg3, out TComponent> : IComponentFactory
 {
 TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2, TArg3 argument3);
 }

 /// <summary>
 /// A class for creating a component when we take three extra parameters
 /// (and an <see cref="IHostEnvironment"/>) that simply wraps a delegate which
 /// creates the component.
 /// </summary>
 public class SimpleComponentFactory<TArg1, TArg2, TArg3, TComponent> : IComponentFactory<TArg1, TArg2, TArg3, TComponent>
@TomFinleyTomFinleyAug 16, 2018

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

SimpleComponentFactory [](start = 17, length = 22)
Thanks @eerhardt. As we discussed in #681 perhaps we can hide these implementations of the interface, but we'll do that after we merge this I suppose.
@eerhardteerhardtAug 16, 2018

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, I will take care of all the SimpleComponentFactory classes being hidden in #681.
 {
 private Func<IHostEnvironment, TArg1, TArg2, TArg3, TComponent> _factory;

 public SimpleComponentFactory(Func<IHostEnvironment, TArg1, TArg2, TArg3, TComponent> factory)
 {
 _factory = factory;
 }

 public TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2, TArg3 argument3)
 {
 return _factory(env, argument1, argument2, argument3);
 }
 }
}

21 changes: 11 additions & 10 deletions
src/Microsoft.ML.Data/Commands/CrossValidationCommand.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -28,8 +28,8 @@ public sealed class Arguments : DataCommand.ArgumentsBase
 [Argument(ArgumentType.Multiple, HelpText = "Trainer to use", ShortName = "tr")]
 public SubComponent<ITrainer, SignatureTrainer> Trainer = new SubComponent<ITrainer, SignatureTrainer>("AveragedPerceptron");

 [Argument(ArgumentType.Multiple, HelpText = "Scorer to use", NullName = "<Auto>", SortOrder = 101)]
 public SubComponent<IDataScorerTransform, SignatureDataScorer> Scorer;
 [Argument(ArgumentType.Multiple, HelpText = "Scorer to use", NullName = "<Auto>", SortOrder = 101, SignatureType = typeof(SignatureDataScorer))]
@Zruty0Zruty0Aug 9, 2018•

edited

Loading

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

SignatureDataScorer [](start = 134, length = 19)
I wonder if the information contained in SignatureType is identical to the information contained in typeof(Scorer) ?

As in, aren't these the type parameters you want to invoke with? #Closed
@eerhardteerhardtAug 14, 2018•

edited by Zruty0

Loading

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The parameter information definitely overlaps, but this isn't duplicate information.
For example, if there are two signature delegates:
publicdelegatevoidSignatureSweeper();publicdelegatevoidSignatureTrainer();
We can't discern which one we are trying to load from the component catalog solely on signature (both these signature delegates don't take any more parameters other than the Environment). #Closed
@Zruty0Zruty0Aug 15, 2018

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Oh, I see. So the signature is needed for subselecting a list.
In reply to: 210097300 [](ancestors = 210097300)
@eerhardteerhardtAug 15, 2018

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The signature is needed in order to find the component in the ComponentCatalog. We can have multiple components with the same name, but are different based on their "signature type". So the components are keyed off both a name and a signature type:
machinelearning/src/Microsoft.ML.Core/ComponentModel/ComponentCatalog.cs

Lines 35 to 41
in
e77f24e
/// <summary>
/// Used for dictionary lookup based on signature and name.
/// </summary>
internalstructKey:IEquatable<Key>
{
publicreadonlystringName;
publicreadonlyTypeSignature;
machinelearning/src/Microsoft.ML.Core/ComponentModel/ComponentCatalog.cs

Line 787
in
e77f24e
privatestaticLoadableClassInfoFindClassCore(LoadableClassInfo.Keykey)
 public IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> Scorer;

 [Argument(ArgumentType.Multiple, HelpText = "Evaluator to use", ShortName = "eval", NullName = "<Auto>", SortOrder = 102)]
 public SubComponent<IMamlEvaluator, SignatureMamlEvaluator> Evaluator;
Expand DownExpand Up@@ -76,8 +76,8 @@ public sealed class Arguments : DataCommand.ArgumentsBase
 [Argument(ArgumentType.AtMostOnce, IsInputFileName = true, HelpText = "The validation data file", ShortName = "valid")]
 public string ValidationFile;

 [Argument(ArgumentType.Multiple, HelpText = "Output calibrator", ShortName = "cali", NullName = "<None>")]
 public SubComponent<ICalibratorTrainer, SignatureCalibrator> Calibrator = new SubComponent<ICalibratorTrainer, SignatureCalibrator>("PlattCalibration");
 [Argument(ArgumentType.Multiple, HelpText = "Output calibrator", ShortName = "cali", NullName = "<None>", SignatureType = typeof(SignatureCalibrator))]
 public IComponentFactory<ICalibratorTrainer> Calibrator = new PlattCalibratorTrainerFactory();

 [Argument(ArgumentType.LastOccurenceWins, HelpText = "Number of instances to train the calibrator", ShortName = "numcali")]
 public int MaxCalibrationExamples = 1000000000;
Expand DownExpand Up@@ -383,9 +383,9 @@ public FoldResult(Dictionary<string, IDataView> metrics, ISchema scoreSchema, Ro
 private readonly string _splitColumn;
 private readonly int _numFolds;
 private readonly SubComponent<ITrainer, SignatureTrainer> _trainer;
 private readonly SubComponent<IDataScorerTransform, SignatureDataScorer> _scorer;
 private readonly IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> _scorer;
 private readonly SubComponent<IMamlEvaluator, SignatureMamlEvaluator> _evaluator;
 private readonly SubComponent<ICalibratorTrainer, SignatureCalibrator> _calibrator;
 private readonly IComponentFactory<ICalibratorTrainer> _calibrator;
 private readonly int _maxCalibrationExamples;
 private readonly bool _useThreads;
 private readonly bool? _cacheData;
Expand DownExpand Up@@ -423,7 +423,7 @@ public FoldHelper(
 Arguments args,
 Func<IHostEnvironment, IChannel, IDataView, ITrainer, RoleMappedData> createExamples,
 Func<IHostEnvironment, IChannel, IDataView, RoleMappedData, IDataView, RoleMappedData> applyTransformsToTestData,
SubComponent<IDataScorerTransform, SignatureDataScorer> scorer,
IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> scorer,
 SubComponent<IMamlEvaluator, SignatureMamlEvaluator> evaluator,
 Func<IDataView> getValidationDataView = null,
 Func<IHostEnvironment, IChannel, IDataView, RoleMappedData, IDataView, RoleMappedData> applyTransformsToValidationData = null,
Expand DownExpand Up@@ -559,11 +559,12 @@ private FoldResult RunFold(int fold)

 // Score.
 ch.Trace("Scoring and evaluating");
 var bindable = ScoreUtils.GetSchemaBindableMapper(host, predictor, _scorer);
 ch.Assert(_scorer == null || _scorer is ICommandLineComponentFactory, "CrossValidationCommand should only be used from the command line.");
 var bindable = ScoreUtils.GetSchemaBindableMapper(host, predictor, scorerFactorySettings: _scorer as ICommandLineComponentFactory);
 ch.AssertValue(bindable);
 var mapper = bindable.Bind(host, testData.Schema);
 var scorerComp = _scorer.IsGood() ? _scorer : ScoreUtils.GetScorerComponent(mapper);
 IDataScorerTransform scorePipe = scorerComp.CreateInstance(host, testData.Data, mapper, trainData.Schema);
 var scorerComp = _scorer ?? ScoreUtils.GetScorerComponent(mapper);
 IDataScorerTransform scorePipe = scorerComp.CreateComponent(host, testData.Data, mapper, trainData.Schema);

 // Save per-fold model.
 string modelFileName = ConstructPerFoldName(_outputModelFile, fold);
Expand Down
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
 Move Scorers and Calibrators to use IComponentFactory.#671

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

eerhardt
merged 6 commits into

from

Aug 16, 2018
 Merged


Move Scorers and Calibrators to use IComponentFactory.
#671
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


6 commits


Select commit
Hold shift + click to select a range
c1bb9f4

Move Scorers and Calibrators to use IComponentFactory.


eerhardt Aug 6, 2018
92f5b7a

fix test issue


eerhardt Aug 9, 2018
446c72c

Remove last SubComponent usage from ScoreCommand.


eerhardt Aug 9, 2018
c0f1c3b

Keep the Create method's signature so DI can find it.


eerhardt Aug 9, 2018
f32af76

Respond to PR feedback.


eerhardt Aug 14, 2018
3688862

Change CmdParser ComponentFactoryFactory to not throw an exception du…


eerhardt Aug 14, 2018

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


13 changes: 11 additions & 2 deletions
src/Microsoft.ML.Api/ComponentCreation.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -6,6 +6,7 @@
using System.IO;
using Microsoft.ML.Runtime.CommandLine;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.EntryPoints;
using Microsoft.ML.Runtime.Model;

namespace Microsoft.ML.Runtime.Api
Expand DownExpand Up@@ -304,12 +305,20 @@ public static IDataScorerTransform CreateScorer(this IHostEnvironment env, strin
 env.CheckValue(predictor, nameof(predictor));
 env.CheckValueOrNull(trainSchema);

var subComponent = SubComponent.Parse<IDataScorerTransform, SignatureDataScorer>(settings);
 var bindable = ScoreUtils.GetSchemaBindableMapper(env, predictor.Pred, subComponent);
ICommandLineComponentFactory scorerFactorySettings = ParseScorerSettings(settings);
 var bindable = ScoreUtils.GetSchemaBindableMapper(env, predictor.Pred, scorerFactorySettings: scorerFactorySettings);
 var mapper = bindable.Bind(env, data.Schema);
 return CreateCore<IDataScorerTransform, SignatureDataScorer>(env, settings, data.Data, mapper, trainSchema);
 }

 private static ICommandLineComponentFactory ParseScorerSettings(string settings)
 {
 return CmdParser.CreateComponentFactory(
 typeof(IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform>),
 typeof(SignatureDataScorer),
 settings);
 }

 /// <summary>
 /// Creates a default data scorer appropriate to the predictor's prediction kind.
 /// </summary>
Expand Down

361 changes: 240 additions & 121 deletions
src/Microsoft.ML.Core/CommandLine/CmdParser.cs

View file


Open in desktop


Large diffs are not rendered by default.


28 changes: 28 additions & 0 deletions
src/Microsoft.ML.Core/EntryPoints/ComponentFactory.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -64,4 +64,32 @@ public interface IComponentFactory<in TArg1, in TArg2, out TComponent> : ICompon
 {
 TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2);
 }

 /// <summary>
 /// An interface for creating a component when we take three extra parameters (and an <see cref="IHostEnvironment"/>).
 /// </summary>
 public interface IComponentFactory<in TArg1, in TArg2, in TArg3, out TComponent> : IComponentFactory
 {
 TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2, TArg3 argument3);
 }

 /// <summary>
 /// A class for creating a component when we take three extra parameters
 /// (and an <see cref="IHostEnvironment"/>) that simply wraps a delegate which
 /// creates the component.
 /// </summary>
 public class SimpleComponentFactory<TArg1, TArg2, TArg3, TComponent> : IComponentFactory<TArg1, TArg2, TArg3, TComponent>
@TomFinleyTomFinleyAug 16, 2018

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

SimpleComponentFactory [](start = 17, length = 22)
Thanks @eerhardt. As we discussed in #681 perhaps we can hide these implementations of the interface, but we'll do that after we merge this I suppose.
@eerhardteerhardtAug 16, 2018

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, I will take care of all the SimpleComponentFactory classes being hidden in #681.
 {
 private Func<IHostEnvironment, TArg1, TArg2, TArg3, TComponent> _factory;

 public SimpleComponentFactory(Func<IHostEnvironment, TArg1, TArg2, TArg3, TComponent> factory)
 {
 _factory = factory;
 }

 public TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2, TArg3 argument3)
 {
 return _factory(env, argument1, argument2, argument3);
 }
 }
}

21 changes: 11 additions & 10 deletions
src/Microsoft.ML.Data/Commands/CrossValidationCommand.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -28,8 +28,8 @@ public sealed class Arguments : DataCommand.ArgumentsBase
 [Argument(ArgumentType.Multiple, HelpText = "Trainer to use", ShortName = "tr")]
 public SubComponent<ITrainer, SignatureTrainer> Trainer = new SubComponent<ITrainer, SignatureTrainer>("AveragedPerceptron");

 [Argument(ArgumentType.Multiple, HelpText = "Scorer to use", NullName = "<Auto>", SortOrder = 101)]
 public SubComponent<IDataScorerTransform, SignatureDataScorer> Scorer;
 [Argument(ArgumentType.Multiple, HelpText = "Scorer to use", NullName = "<Auto>", SortOrder = 101, SignatureType = typeof(SignatureDataScorer))]
@Zruty0Zruty0Aug 9, 2018•

edited

Loading

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

SignatureDataScorer [](start = 134, length = 19)
I wonder if the information contained in SignatureType is identical to the information contained in typeof(Scorer) ?

As in, aren't these the type parameters you want to invoke with? #Closed
@eerhardteerhardtAug 14, 2018•

edited by Zruty0

Loading

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The parameter information definitely overlaps, but this isn't duplicate information.
For example, if there are two signature delegates:
publicdelegatevoidSignatureSweeper();publicdelegatevoidSignatureTrainer();
We can't discern which one we are trying to load from the component catalog solely on signature (both these signature delegates don't take any more parameters other than the Environment). #Closed
@Zruty0Zruty0Aug 15, 2018

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Oh, I see. So the signature is needed for subselecting a list.
In reply to: 210097300 [](ancestors = 210097300)
@eerhardteerhardtAug 15, 2018

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The signature is needed in order to find the component in the ComponentCatalog. We can have multiple components with the same name, but are different based on their "signature type". So the components are keyed off both a name and a signature type:
machinelearning/src/Microsoft.ML.Core/ComponentModel/ComponentCatalog.cs

Lines 35 to 41
in
e77f24e
/// <summary>
/// Used for dictionary lookup based on signature and name.
/// </summary>
internalstructKey:IEquatable<Key>
{
publicreadonlystringName;
publicreadonlyTypeSignature;
machinelearning/src/Microsoft.ML.Core/ComponentModel/ComponentCatalog.cs

Line 787
in
e77f24e
privatestaticLoadableClassInfoFindClassCore(LoadableClassInfo.Keykey)
 public IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> Scorer;

 [Argument(ArgumentType.Multiple, HelpText = "Evaluator to use", ShortName = "eval", NullName = "<Auto>", SortOrder = 102)]
 public SubComponent<IMamlEvaluator, SignatureMamlEvaluator> Evaluator;
Expand DownExpand Up@@ -76,8 +76,8 @@ public sealed class Arguments : DataCommand.ArgumentsBase
 [Argument(ArgumentType.AtMostOnce, IsInputFileName = true, HelpText = "The validation data file", ShortName = "valid")]
 public string ValidationFile;

 [Argument(ArgumentType.Multiple, HelpText = "Output calibrator", ShortName = "cali", NullName = "<None>")]
 public SubComponent<ICalibratorTrainer, SignatureCalibrator> Calibrator = new SubComponent<ICalibratorTrainer, SignatureCalibrator>("PlattCalibration");
 [Argument(ArgumentType.Multiple, HelpText = "Output calibrator", ShortName = "cali", NullName = "<None>", SignatureType = typeof(SignatureCalibrator))]
 public IComponentFactory<ICalibratorTrainer> Calibrator = new PlattCalibratorTrainerFactory();

 [Argument(ArgumentType.LastOccurenceWins, HelpText = "Number of instances to train the calibrator", ShortName = "numcali")]
 public int MaxCalibrationExamples = 1000000000;
Expand DownExpand Up@@ -383,9 +383,9 @@ public FoldResult(Dictionary<string, IDataView> metrics, ISchema scoreSchema, Ro
 private readonly string _splitColumn;
 private readonly int _numFolds;
 private readonly SubComponent<ITrainer, SignatureTrainer> _trainer;
 private readonly SubComponent<IDataScorerTransform, SignatureDataScorer> _scorer;
 private readonly IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> _scorer;
 private readonly SubComponent<IMamlEvaluator, SignatureMamlEvaluator> _evaluator;
 private readonly SubComponent<ICalibratorTrainer, SignatureCalibrator> _calibrator;
 private readonly IComponentFactory<ICalibratorTrainer> _calibrator;
 private readonly int _maxCalibrationExamples;
 private readonly bool _useThreads;
 private readonly bool? _cacheData;
Expand DownExpand Up@@ -423,7 +423,7 @@ public FoldHelper(
 Arguments args,
 Func<IHostEnvironment, IChannel, IDataView, ITrainer, RoleMappedData> createExamples,
 Func<IHostEnvironment, IChannel, IDataView, RoleMappedData, IDataView, RoleMappedData> applyTransformsToTestData,
SubComponent<IDataScorerTransform, SignatureDataScorer> scorer,
IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> scorer,
 SubComponent<IMamlEvaluator, SignatureMamlEvaluator> evaluator,
 Func<IDataView> getValidationDataView = null,
 Func<IHostEnvironment, IChannel, IDataView, RoleMappedData, IDataView, RoleMappedData> applyTransformsToValidationData = null,
Expand DownExpand Up@@ -559,11 +559,12 @@ private FoldResult RunFold(int fold)

 // Score.
 ch.Trace("Scoring and evaluating");
 var bindable = ScoreUtils.GetSchemaBindableMapper(host, predictor, _scorer);
 ch.Assert(_scorer == null || _scorer is ICommandLineComponentFactory, "CrossValidationCommand should only be used from the command line.");
 var bindable = ScoreUtils.GetSchemaBindableMapper(host, predictor, scorerFactorySettings: _scorer as ICommandLineComponentFactory);
 ch.AssertValue(bindable);
 var mapper = bindable.Bind(host, testData.Schema);
 var scorerComp = _scorer.IsGood() ? _scorer : ScoreUtils.GetScorerComponent(mapper);
 IDataScorerTransform scorePipe = scorerComp.CreateInstance(host, testData.Data, mapper, trainData.Schema);
 var scorerComp = _scorer ?? ScoreUtils.GetScorerComponent(mapper);
 IDataScorerTransform scorePipe = scorerComp.CreateComponent(host, testData.Data, mapper, trainData.Schema);

 // Save per-fold model.
 string modelFileName = ConstructPerFoldName(_outputModelFile, fold);
Expand Down
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
 Move Scorers and Calibrators to use IComponentFactory.#671

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

eerhardt
merged 6 commits into

from

Aug 16, 2018
 Merged


Move Scorers and Calibrators to use IComponentFactory.
#671
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


6 commits


Select commit
Hold shift + click to select a range
c1bb9f4

Move Scorers and Calibrators to use IComponentFactory.


eerhardt Aug 6, 2018
92f5b7a

fix test issue


eerhardt Aug 9, 2018
446c72c

Remove last SubComponent usage from ScoreCommand.


eerhardt Aug 9, 2018
c0f1c3b

Keep the Create method's signature so DI can find it.


eerhardt Aug 9, 2018
f32af76

Respond to PR feedback.


eerhardt Aug 14, 2018
3688862

Change CmdParser ComponentFactoryFactory to not throw an exception du…


eerhardt Aug 14, 2018

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


13 changes: 11 additions & 2 deletions
src/Microsoft.ML.Api/ComponentCreation.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -6,6 +6,7 @@
using System.IO;
using Microsoft.ML.Runtime.CommandLine;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.EntryPoints;
using Microsoft.ML.Runtime.Model;

namespace Microsoft.ML.Runtime.Api
Expand DownExpand Up@@ -304,12 +305,20 @@ public static IDataScorerTransform CreateScorer(this IHostEnvironment env, strin
 env.CheckValue(predictor, nameof(predictor));
 env.CheckValueOrNull(trainSchema);

var subComponent = SubComponent.Parse<IDataScorerTransform, SignatureDataScorer>(settings);
 var bindable = ScoreUtils.GetSchemaBindableMapper(env, predictor.Pred, subComponent);
ICommandLineComponentFactory scorerFactorySettings = ParseScorerSettings(settings);
 var bindable = ScoreUtils.GetSchemaBindableMapper(env, predictor.Pred, scorerFactorySettings: scorerFactorySettings);
 var mapper = bindable.Bind(env, data.Schema);
 return CreateCore<IDataScorerTransform, SignatureDataScorer>(env, settings, data.Data, mapper, trainSchema);
 }

 private static ICommandLineComponentFactory ParseScorerSettings(string settings)
 {
 return CmdParser.CreateComponentFactory(
 typeof(IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform>),
 typeof(SignatureDataScorer),
 settings);
 }

 /// <summary>
 /// Creates a default data scorer appropriate to the predictor's prediction kind.
 /// </summary>
Expand Down

361 changes: 240 additions & 121 deletions
src/Microsoft.ML.Core/CommandLine/CmdParser.cs

View file


Open in desktop


Large diffs are not rendered by default.


28 changes: 28 additions & 0 deletions
src/Microsoft.ML.Core/EntryPoints/ComponentFactory.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -64,4 +64,32 @@ public interface IComponentFactory<in TArg1, in TArg2, out TComponent> : ICompon
 {
 TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2);
 }

 /// <summary>
 /// An interface for creating a component when we take three extra parameters (and an <see cref="IHostEnvironment"/>).
 /// </summary>
 public interface IComponentFactory<in TArg1, in TArg2, in TArg3, out TComponent> : IComponentFactory
 {
 TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2, TArg3 argument3);
 }

 /// <summary>
 /// A class for creating a component when we take three extra parameters
 /// (and an <see cref="IHostEnvironment"/>) that simply wraps a delegate which
 /// creates the component.
 /// </summary>
 public class SimpleComponentFactory<TArg1, TArg2, TArg3, TComponent> : IComponentFactory<TArg1, TArg2, TArg3, TComponent>
@TomFinleyTomFinleyAug 16, 2018

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

SimpleComponentFactory [](start = 17, length = 22)
Thanks @eerhardt. As we discussed in #681 perhaps we can hide these implementations of the interface, but we'll do that after we merge this I suppose.
@eerhardteerhardtAug 16, 2018

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, I will take care of all the SimpleComponentFactory classes being hidden in #681.
 {
 private Func<IHostEnvironment, TArg1, TArg2, TArg3, TComponent> _factory;

 public SimpleComponentFactory(Func<IHostEnvironment, TArg1, TArg2, TArg3, TComponent> factory)
 {
 _factory = factory;
 }

 public TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2, TArg3 argument3)
 {
 return _factory(env, argument1, argument2, argument3);
 }
 }
}

21 changes: 11 additions & 10 deletions
src/Microsoft.ML.Data/Commands/CrossValidationCommand.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -28,8 +28,8 @@ public sealed class Arguments : DataCommand.ArgumentsBase
 [Argument(ArgumentType.Multiple, HelpText = "Trainer to use", ShortName = "tr")]
 public SubComponent<ITrainer, SignatureTrainer> Trainer = new SubComponent<ITrainer, SignatureTrainer>("AveragedPerceptron");

 [Argument(ArgumentType.Multiple, HelpText = "Scorer to use", NullName = "<Auto>", SortOrder = 101)]
 public SubComponent<IDataScorerTransform, SignatureDataScorer> Scorer;
 [Argument(ArgumentType.Multiple, HelpText = "Scorer to use", NullName = "<Auto>", SortOrder = 101, SignatureType = typeof(SignatureDataScorer))]
@Zruty0Zruty0Aug 9, 2018•

edited

Loading

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

SignatureDataScorer [](start = 134, length = 19)
I wonder if the information contained in SignatureType is identical to the information contained in typeof(Scorer) ?

As in, aren't these the type parameters you want to invoke with? #Closed
@eerhardteerhardtAug 14, 2018•

edited by Zruty0

Loading

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The parameter information definitely overlaps, but this isn't duplicate information.
For example, if there are two signature delegates:
publicdelegatevoidSignatureSweeper();publicdelegatevoidSignatureTrainer();
We can't discern which one we are trying to load from the component catalog solely on signature (both these signature delegates don't take any more parameters other than the Environment). #Closed
@Zruty0Zruty0Aug 15, 2018

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Oh, I see. So the signature is needed for subselecting a list.
In reply to: 210097300 [](ancestors = 210097300)
@eerhardteerhardtAug 15, 2018

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The signature is needed in order to find the component in the ComponentCatalog. We can have multiple components with the same name, but are different based on their "signature type". So the components are keyed off both a name and a signature type:
machinelearning/src/Microsoft.ML.Core/ComponentModel/ComponentCatalog.cs

Lines 35 to 41
in
e77f24e
/// <summary>
/// Used for dictionary lookup based on signature and name.
/// </summary>
internalstructKey:IEquatable<Key>
{
publicreadonlystringName;
publicreadonlyTypeSignature;
machinelearning/src/Microsoft.ML.Core/ComponentModel/ComponentCatalog.cs

Line 787
in
e77f24e
privatestaticLoadableClassInfoFindClassCore(LoadableClassInfo.Keykey)
 public IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> Scorer;

 [Argument(ArgumentType.Multiple, HelpText = "Evaluator to use", ShortName = "eval", NullName = "<Auto>", SortOrder = 102)]
 public SubComponent<IMamlEvaluator, SignatureMamlEvaluator> Evaluator;
Expand DownExpand Up@@ -76,8 +76,8 @@ public sealed class Arguments : DataCommand.ArgumentsBase
 [Argument(ArgumentType.AtMostOnce, IsInputFileName = true, HelpText = "The validation data file", ShortName = "valid")]
 public string ValidationFile;

 [Argument(ArgumentType.Multiple, HelpText = "Output calibrator", ShortName = "cali", NullName = "<None>")]
 public SubComponent<ICalibratorTrainer, SignatureCalibrator> Calibrator = new SubComponent<ICalibratorTrainer, SignatureCalibrator>("PlattCalibration");
 [Argument(ArgumentType.Multiple, HelpText = "Output calibrator", ShortName = "cali", NullName = "<None>", SignatureType = typeof(SignatureCalibrator))]
 public IComponentFactory<ICalibratorTrainer> Calibrator = new PlattCalibratorTrainerFactory();

 [Argument(ArgumentType.LastOccurenceWins, HelpText = "Number of instances to train the calibrator", ShortName = "numcali")]
 public int MaxCalibrationExamples = 1000000000;
Expand DownExpand Up@@ -383,9 +383,9 @@ public FoldResult(Dictionary<string, IDataView> metrics, ISchema scoreSchema, Ro
 private readonly string _splitColumn;
 private readonly int _numFolds;
 private readonly SubComponent<ITrainer, SignatureTrainer> _trainer;
 private readonly SubComponent<IDataScorerTransform, SignatureDataScorer> _scorer;
 private readonly IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> _scorer;
 private readonly SubComponent<IMamlEvaluator, SignatureMamlEvaluator> _evaluator;
 private readonly SubComponent<ICalibratorTrainer, SignatureCalibrator> _calibrator;
 private readonly IComponentFactory<ICalibratorTrainer> _calibrator;
 private readonly int _maxCalibrationExamples;
 private readonly bool _useThreads;
 private readonly bool? _cacheData;
Expand DownExpand Up@@ -423,7 +423,7 @@ public FoldHelper(
 Arguments args,
 Func<IHostEnvironment, IChannel, IDataView, ITrainer, RoleMappedData> createExamples,
 Func<IHostEnvironment, IChannel, IDataView, RoleMappedData, IDataView, RoleMappedData> applyTransformsToTestData,
SubComponent<IDataScorerTransform, SignatureDataScorer> scorer,
IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> scorer,
 SubComponent<IMamlEvaluator, SignatureMamlEvaluator> evaluator,
 Func<IDataView> getValidationDataView = null,
 Func<IHostEnvironment, IChannel, IDataView, RoleMappedData, IDataView, RoleMappedData> applyTransformsToValidationData = null,
Expand DownExpand Up@@ -559,11 +559,12 @@ private FoldResult RunFold(int fold)

 // Score.
 ch.Trace("Scoring and evaluating");
 var bindable = ScoreUtils.GetSchemaBindableMapper(host, predictor, _scorer);
 ch.Assert(_scorer == null || _scorer is ICommandLineComponentFactory, "CrossValidationCommand should only be used from the command line.");
 var bindable = ScoreUtils.GetSchemaBindableMapper(host, predictor, scorerFactorySettings: _scorer as ICommandLineComponentFactory);
 ch.AssertValue(bindable);
 var mapper = bindable.Bind(host, testData.Schema);
 var scorerComp = _scorer.IsGood() ? _scorer : ScoreUtils.GetScorerComponent(mapper);
 IDataScorerTransform scorePipe = scorerComp.CreateInstance(host, testData.Data, mapper, trainData.Schema);
 var scorerComp = _scorer ?? ScoreUtils.GetScorerComponent(mapper);
 IDataScorerTransform scorePipe = scorerComp.CreateComponent(host, testData.Data, mapper, trainData.Schema);

 // Save per-fold model.
 string modelFileName = ConstructPerFoldName(_outputModelFile, fold);
Expand Down
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
 Move Scorers and Calibrators to use IComponentFactory.#671

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

eerhardt
merged 6 commits into

from

Aug 16, 2018
 Merged


Move Scorers and Calibrators to use IComponentFactory.
#671
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


6 commits


Select commit
Hold shift + click to select a range
c1bb9f4

Move Scorers and Calibrators to use IComponentFactory.


eerhardt Aug 6, 2018
92f5b7a

fix test issue


eerhardt Aug 9, 2018
446c72c

Remove last SubComponent usage from ScoreCommand.


eerhardt Aug 9, 2018
c0f1c3b

Keep the Create method's signature so DI can find it.


eerhardt Aug 9, 2018
f32af76

Respond to PR feedback.


eerhardt Aug 14, 2018
3688862

Change CmdParser ComponentFactoryFactory to not throw an exception du…


eerhardt Aug 14, 2018

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


13 changes: 11 additions & 2 deletions
src/Microsoft.ML.Api/ComponentCreation.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -6,6 +6,7 @@
using System.IO;
using Microsoft.ML.Runtime.CommandLine;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.EntryPoints;
using Microsoft.ML.Runtime.Model;

namespace Microsoft.ML.Runtime.Api
Expand DownExpand Up@@ -304,12 +305,20 @@ public static IDataScorerTransform CreateScorer(this IHostEnvironment env, strin
 env.CheckValue(predictor, nameof(predictor));
 env.CheckValueOrNull(trainSchema);

var subComponent = SubComponent.Parse<IDataScorerTransform, SignatureDataScorer>(settings);
 var bindable = ScoreUtils.GetSchemaBindableMapper(env, predictor.Pred, subComponent);
ICommandLineComponentFactory scorerFactorySettings = ParseScorerSettings(settings);
 var bindable = ScoreUtils.GetSchemaBindableMapper(env, predictor.Pred, scorerFactorySettings: scorerFactorySettings);
 var mapper = bindable.Bind(env, data.Schema);
 return CreateCore<IDataScorerTransform, SignatureDataScorer>(env, settings, data.Data, mapper, trainSchema);
 }

 private static ICommandLineComponentFactory ParseScorerSettings(string settings)
 {
 return CmdParser.CreateComponentFactory(
 typeof(IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform>),
 typeof(SignatureDataScorer),
 settings);
 }

 /// <summary>
 /// Creates a default data scorer appropriate to the predictor's prediction kind.
 /// </summary>
Expand Down

361 changes: 240 additions & 121 deletions
src/Microsoft.ML.Core/CommandLine/CmdParser.cs

View file


Open in desktop


Large diffs are not rendered by default.


28 changes: 28 additions & 0 deletions
src/Microsoft.ML.Core/EntryPoints/ComponentFactory.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -64,4 +64,32 @@ public interface IComponentFactory<in TArg1, in TArg2, out TComponent> : ICompon
 {
 TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2);
 }

 /// <summary>
 /// An interface for creating a component when we take three extra parameters (and an <see cref="IHostEnvironment"/>).
 /// </summary>
 public interface IComponentFactory<in TArg1, in TArg2, in TArg3, out TComponent> : IComponentFactory
 {
 TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2, TArg3 argument3);
 }

 /// <summary>
 /// A class for creating a component when we take three extra parameters
 /// (and an <see cref="IHostEnvironment"/>) that simply wraps a delegate which
 /// creates the component.
 /// </summary>
 public class SimpleComponentFactory<TArg1, TArg2, TArg3, TComponent> : IComponentFactory<TArg1, TArg2, TArg3, TComponent>
@TomFinleyTomFinleyAug 16, 2018

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

SimpleComponentFactory [](start = 17, length = 22)
Thanks @eerhardt. As we discussed in #681 perhaps we can hide these implementations of the interface, but we'll do that after we merge this I suppose.
@eerhardteerhardtAug 16, 2018

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, I will take care of all the SimpleComponentFactory classes being hidden in #681.
 {
 private Func<IHostEnvironment, TArg1, TArg2, TArg3, TComponent> _factory;

 public SimpleComponentFactory(Func<IHostEnvironment, TArg1, TArg2, TArg3, TComponent> factory)
 {
 _factory = factory;
 }

 public TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2, TArg3 argument3)
 {
 return _factory(env, argument1, argument2, argument3);
 }
 }
}

21 changes: 11 additions & 10 deletions
src/Microsoft.ML.Data/Commands/CrossValidationCommand.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -28,8 +28,8 @@ public sealed class Arguments : DataCommand.ArgumentsBase
 [Argument(ArgumentType.Multiple, HelpText = "Trainer to use", ShortName = "tr")]
 public SubComponent<ITrainer, SignatureTrainer> Trainer = new SubComponent<ITrainer, SignatureTrainer>("AveragedPerceptron");

 [Argument(ArgumentType.Multiple, HelpText = "Scorer to use", NullName = "<Auto>", SortOrder = 101)]
 public SubComponent<IDataScorerTransform, SignatureDataScorer> Scorer;
 [Argument(ArgumentType.Multiple, HelpText = "Scorer to use", NullName = "<Auto>", SortOrder = 101, SignatureType = typeof(SignatureDataScorer))]
@Zruty0Zruty0Aug 9, 2018•

edited

Loading

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

SignatureDataScorer [](start = 134, length = 19)
I wonder if the information contained in SignatureType is identical to the information contained in typeof(Scorer) ?

As in, aren't these the type parameters you want to invoke with? #Closed
@eerhardteerhardtAug 14, 2018•

edited by Zruty0

Loading

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The parameter information definitely overlaps, but this isn't duplicate information.
For example, if there are two signature delegates:
publicdelegatevoidSignatureSweeper();publicdelegatevoidSignatureTrainer();
We can't discern which one we are trying to load from the component catalog solely on signature (both these signature delegates don't take any more parameters other than the Environment). #Closed
@Zruty0Zruty0Aug 15, 2018

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Oh, I see. So the signature is needed for subselecting a list.
In reply to: 210097300 [](ancestors = 210097300)
@eerhardteerhardtAug 15, 2018

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The signature is needed in order to find the component in the ComponentCatalog. We can have multiple components with the same name, but are different based on their "signature type". So the components are keyed off both a name and a signature type:
machinelearning/src/Microsoft.ML.Core/ComponentModel/ComponentCatalog.cs

Lines 35 to 41
in
e77f24e
/// <summary>
/// Used for dictionary lookup based on signature and name.
/// </summary>
internalstructKey:IEquatable<Key>
{
publicreadonlystringName;
publicreadonlyTypeSignature;
machinelearning/src/Microsoft.ML.Core/ComponentModel/ComponentCatalog.cs

Line 787
in
e77f24e
privatestaticLoadableClassInfoFindClassCore(LoadableClassInfo.Keykey)
 public IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> Scorer;

 [Argument(ArgumentType.Multiple, HelpText = "Evaluator to use", ShortName = "eval", NullName = "<Auto>", SortOrder = 102)]
 public SubComponent<IMamlEvaluator, SignatureMamlEvaluator> Evaluator;
Expand DownExpand Up@@ -76,8 +76,8 @@ public sealed class Arguments : DataCommand.ArgumentsBase
 [Argument(ArgumentType.AtMostOnce, IsInputFileName = true, HelpText = "The validation data file", ShortName = "valid")]
 public string ValidationFile;

 [Argument(ArgumentType.Multiple, HelpText = "Output calibrator", ShortName = "cali", NullName = "<None>")]
 public SubComponent<ICalibratorTrainer, SignatureCalibrator> Calibrator = new SubComponent<ICalibratorTrainer, SignatureCalibrator>("PlattCalibration");
 [Argument(ArgumentType.Multiple, HelpText = "Output calibrator", ShortName = "cali", NullName = "<None>", SignatureType = typeof(SignatureCalibrator))]
 public IComponentFactory<ICalibratorTrainer> Calibrator = new PlattCalibratorTrainerFactory();

 [Argument(ArgumentType.LastOccurenceWins, HelpText = "Number of instances to train the calibrator", ShortName = "numcali")]
 public int MaxCalibrationExamples = 1000000000;
Expand DownExpand Up@@ -383,9 +383,9 @@ public FoldResult(Dictionary<string, IDataView> metrics, ISchema scoreSchema, Ro
 private readonly string _splitColumn;
 private readonly int _numFolds;
 private readonly SubComponent<ITrainer, SignatureTrainer> _trainer;
 private readonly SubComponent<IDataScorerTransform, SignatureDataScorer> _scorer;
 private readonly IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> _scorer;
 private readonly SubComponent<IMamlEvaluator, SignatureMamlEvaluator> _evaluator;
 private readonly SubComponent<ICalibratorTrainer, SignatureCalibrator> _calibrator;
 private readonly IComponentFactory<ICalibratorTrainer> _calibrator;
 private readonly int _maxCalibrationExamples;
 private readonly bool _useThreads;
 private readonly bool? _cacheData;
Expand DownExpand Up@@ -423,7 +423,7 @@ public FoldHelper(
 Arguments args,
 Func<IHostEnvironment, IChannel, IDataView, ITrainer, RoleMappedData> createExamples,
 Func<IHostEnvironment, IChannel, IDataView, RoleMappedData, IDataView, RoleMappedData> applyTransformsToTestData,
SubComponent<IDataScorerTransform, SignatureDataScorer> scorer,
IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> scorer,
 SubComponent<IMamlEvaluator, SignatureMamlEvaluator> evaluator,
 Func<IDataView> getValidationDataView = null,
 Func<IHostEnvironment, IChannel, IDataView, RoleMappedData, IDataView, RoleMappedData> applyTransformsToValidationData = null,
Expand DownExpand Up@@ -559,11 +559,12 @@ private FoldResult RunFold(int fold)

 // Score.
 ch.Trace("Scoring and evaluating");
 var bindable = ScoreUtils.GetSchemaBindableMapper(host, predictor, _scorer);
 ch.Assert(_scorer == null || _scorer is ICommandLineComponentFactory, "CrossValidationCommand should only be used from the command line.");
 var bindable = ScoreUtils.GetSchemaBindableMapper(host, predictor, scorerFactorySettings: _scorer as ICommandLineComponentFactory);
 ch.AssertValue(bindable);
 var mapper = bindable.Bind(host, testData.Schema);
 var scorerComp = _scorer.IsGood() ? _scorer : ScoreUtils.GetScorerComponent(mapper);
 IDataScorerTransform scorePipe = scorerComp.CreateInstance(host, testData.Data, mapper, trainData.Schema);
 var scorerComp = _scorer ?? ScoreUtils.GetScorerComponent(mapper);
 IDataScorerTransform scorePipe = scorerComp.CreateComponent(host, testData.Data, mapper, trainData.Schema);

 // Save per-fold model.
 string modelFileName = ConstructPerFoldName(_outputModelFile, fold);
Expand Down
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
 Move Scorers and Calibrators to use IComponentFactory.#671

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

eerhardt
merged 6 commits into

from

Aug 16, 2018
 Merged


Move Scorers and Calibrators to use IComponentFactory.
#671
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


6 commits


Select commit
Hold shift + click to select a range
c1bb9f4

Move Scorers and Calibrators to use IComponentFactory.


eerhardt Aug 6, 2018
92f5b7a

fix test issue


eerhardt Aug 9, 2018
446c72c

Remove last SubComponent usage from ScoreCommand.


eerhardt Aug 9, 2018
c0f1c3b

Keep the Create method's signature so DI can find it.


eerhardt Aug 9, 2018
f32af76

Respond to PR feedback.


eerhardt Aug 14, 2018
3688862

Change CmdParser ComponentFactoryFactory to not throw an exception du…


eerhardt Aug 14, 2018

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


13 changes: 11 additions & 2 deletions
src/Microsoft.ML.Api/ComponentCreation.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -6,6 +6,7 @@
using System.IO;
using Microsoft.ML.Runtime.CommandLine;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.EntryPoints;
using Microsoft.ML.Runtime.Model;

namespace Microsoft.ML.Runtime.Api
Expand DownExpand Up@@ -304,12 +305,20 @@ public static IDataScorerTransform CreateScorer(this IHostEnvironment env, strin
 env.CheckValue(predictor, nameof(predictor));
 env.CheckValueOrNull(trainSchema);

var subComponent = SubComponent.Parse<IDataScorerTransform, SignatureDataScorer>(settings);
 var bindable = ScoreUtils.GetSchemaBindableMapper(env, predictor.Pred, subComponent);
ICommandLineComponentFactory scorerFactorySettings = ParseScorerSettings(settings);
 var bindable = ScoreUtils.GetSchemaBindableMapper(env, predictor.Pred, scorerFactorySettings: scorerFactorySettings);
 var mapper = bindable.Bind(env, data.Schema);
 return CreateCore<IDataScorerTransform, SignatureDataScorer>(env, settings, data.Data, mapper, trainSchema);
 }

 private static ICommandLineComponentFactory ParseScorerSettings(string settings)
 {
 return CmdParser.CreateComponentFactory(
 typeof(IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform>),
 typeof(SignatureDataScorer),
 settings);
 }

 /// <summary>
 /// Creates a default data scorer appropriate to the predictor's prediction kind.
 /// </summary>
Expand Down

361 changes: 240 additions & 121 deletions
src/Microsoft.ML.Core/CommandLine/CmdParser.cs

View file


Open in desktop


Large diffs are not rendered by default.


28 changes: 28 additions & 0 deletions
src/Microsoft.ML.Core/EntryPoints/ComponentFactory.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -64,4 +64,32 @@ public interface IComponentFactory<in TArg1, in TArg2, out TComponent> : ICompon
 {
 TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2);
 }

 /// <summary>
 /// An interface for creating a component when we take three extra parameters (and an <see cref="IHostEnvironment"/>).
 /// </summary>
 public interface IComponentFactory<in TArg1, in TArg2, in TArg3, out TComponent> : IComponentFactory
 {
 TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2, TArg3 argument3);
 }

 /// <summary>
 /// A class for creating a component when we take three extra parameters
 /// (and an <see cref="IHostEnvironment"/>) that simply wraps a delegate which
 /// creates the component.
 /// </summary>
 public class SimpleComponentFactory<TArg1, TArg2, TArg3, TComponent> : IComponentFactory<TArg1, TArg2, TArg3, TComponent>
@TomFinleyTomFinleyAug 16, 2018

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

SimpleComponentFactory [](start = 17, length = 22)
Thanks @eerhardt. As we discussed in #681 perhaps we can hide these implementations of the interface, but we'll do that after we merge this I suppose.
@eerhardteerhardtAug 16, 2018

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, I will take care of all the SimpleComponentFactory classes being hidden in #681.
 {
 private Func<IHostEnvironment, TArg1, TArg2, TArg3, TComponent> _factory;

 public SimpleComponentFactory(Func<IHostEnvironment, TArg1, TArg2, TArg3, TComponent> factory)
 {
 _factory = factory;
 }

 public TComponent CreateComponent(IHostEnvironment env, TArg1 argument1, TArg2 argument2, TArg3 argument3)
 {
 return _factory(env, argument1, argument2, argument3);
 }
 }
}

21 changes: 11 additions & 10 deletions
src/Microsoft.ML.Data/Commands/CrossValidationCommand.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -28,8 +28,8 @@ public sealed class Arguments : DataCommand.ArgumentsBase
 [Argument(ArgumentType.Multiple, HelpText = "Trainer to use", ShortName = "tr")]
 public SubComponent<ITrainer, SignatureTrainer> Trainer = new SubComponent<ITrainer, SignatureTrainer>("AveragedPerceptron");

 [Argument(ArgumentType.Multiple, HelpText = "Scorer to use", NullName = "<Auto>", SortOrder = 101)]
 public SubComponent<IDataScorerTransform, SignatureDataScorer> Scorer;
 [Argument(ArgumentType.Multiple, HelpText = "Scorer to use", NullName = "<Auto>", SortOrder = 101, SignatureType = typeof(SignatureDataScorer))]
@Zruty0Zruty0Aug 9, 2018•

edited

Loading

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

SignatureDataScorer [](start = 134, length = 19)
I wonder if the information contained in SignatureType is identical to the information contained in typeof(Scorer) ?

As in, aren't these the type parameters you want to invoke with? #Closed
@eerhardteerhardtAug 14, 2018•

edited by Zruty0

Loading

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The parameter information definitely overlaps, but this isn't duplicate information.
For example, if there are two signature delegates:
publicdelegatevoidSignatureSweeper();publicdelegatevoidSignatureTrainer();
We can't discern which one we are trying to load from the component catalog solely on signature (both these signature delegates don't take any more parameters other than the Environment). #Closed
@Zruty0Zruty0Aug 15, 2018

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Oh, I see. So the signature is needed for subselecting a list.
In reply to: 210097300 [](ancestors = 210097300)
@eerhardteerhardtAug 15, 2018

Copy link


Copy Markdown

MemberAuthor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The signature is needed in order to find the component in the ComponentCatalog. We can have multiple components with the same name, but are different based on their "signature type". So the components are keyed off both a name and a signature type:
machinelearning/src/Microsoft.ML.Core/ComponentModel/ComponentCatalog.cs

Lines 35 to 41
in
e77f24e
/// <summary>
/// Used for dictionary lookup based on signature and name.
/// </summary>
internalstructKey:IEquatable<Key>
{
publicreadonlystringName;
publicreadonlyTypeSignature;
machinelearning/src/Microsoft.ML.Core/ComponentModel/ComponentCatalog.cs

Line 787
in
e77f24e
privatestaticLoadableClassInfoFindClassCore(LoadableClassInfo.Keykey)
 public IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> Scorer;

 [Argument(ArgumentType.Multiple, HelpText = "Evaluator to use", ShortName = "eval", NullName = "<Auto>", SortOrder = 102)]
 public SubComponent<IMamlEvaluator, SignatureMamlEvaluator> Evaluator;
Expand DownExpand Up@@ -76,8 +76,8 @@ public sealed class Arguments : DataCommand.ArgumentsBase
 [Argument(ArgumentType.AtMostOnce, IsInputFileName = true, HelpText = "The validation data file", ShortName = "valid")]
 public string ValidationFile;

 [Argument(ArgumentType.Multiple, HelpText = "Output calibrator", ShortName = "cali", NullName = "<None>")]
 public SubComponent<ICalibratorTrainer, SignatureCalibrator> Calibrator = new SubComponent<ICalibratorTrainer, SignatureCalibrator>("PlattCalibration");
 [Argument(ArgumentType.Multiple, HelpText = "Output calibrator", ShortName = "cali", NullName = "<None>", SignatureType = typeof(SignatureCalibrator))]
 public IComponentFactory<ICalibratorTrainer> Calibrator = new PlattCalibratorTrainerFactory();

 [Argument(ArgumentType.LastOccurenceWins, HelpText = "Number of instances to train the calibrator", ShortName = "numcali")]
 public int MaxCalibrationExamples = 1000000000;
Expand DownExpand Up@@ -383,9 +383,9 @@ public FoldResult(Dictionary<string, IDataView> metrics, ISchema scoreSchema, Ro
 private readonly string _splitColumn;
 private readonly int _numFolds;
 private readonly SubComponent<ITrainer, SignatureTrainer> _trainer;
 private readonly SubComponent<IDataScorerTransform, SignatureDataScorer> _scorer;
 private readonly IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> _scorer;
 private readonly SubComponent<IMamlEvaluator, SignatureMamlEvaluator> _evaluator;
 private readonly SubComponent<ICalibratorTrainer, SignatureCalibrator> _calibrator;
 private readonly IComponentFactory<ICalibratorTrainer> _calibrator;
 private readonly int _maxCalibrationExamples;
 private readonly bool _useThreads;
 private readonly bool? _cacheData;
Expand DownExpand Up@@ -423,7 +423,7 @@ public FoldHelper(
 Arguments args,
 Func<IHostEnvironment, IChannel, IDataView, ITrainer, RoleMappedData> createExamples,
 Func<IHostEnvironment, IChannel, IDataView, RoleMappedData, IDataView, RoleMappedData> applyTransformsToTestData,
SubComponent<IDataScorerTransform, SignatureDataScorer> scorer,
IComponentFactory<IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform> scorer,
 SubComponent<IMamlEvaluator, SignatureMamlEvaluator> evaluator,
 Func<IDataView> getValidationDataView = null,
 Func<IHostEnvironment, IChannel, IDataView, RoleMappedData, IDataView, RoleMappedData> applyTransformsToValidationData = null,
Expand DownExpand Up@@ -559,11 +559,12 @@ private FoldResult RunFold(int fold)

 // Score.
 ch.Trace("Scoring and evaluating");
 var bindable = ScoreUtils.GetSchemaBindableMapper(host, predictor, _scorer);
 ch.Assert(_scorer == null || _scorer is ICommandLineComponentFactory, "CrossValidationCommand should only be used from the command line.");
 var bindable = ScoreUtils.GetSchemaBindableMapper(host, predictor, scorerFactorySettings: _scorer as ICommandLineComponentFactory);
 ch.AssertValue(bindable);
 var mapper = bindable.Bind(host, testData.Schema);
 var scorerComp = _scorer.IsGood() ? _scorer : ScoreUtils.GetScorerComponent(mapper);
 IDataScorerTransform scorePipe = scorerComp.CreateInstance(host, testData.Data, mapper, trainData.Schema);
 var scorerComp = _scorer ?? ScoreUtils.GetScorerComponent(mapper);
 IDataScorerTransform scorePipe = scorerComp.CreateComponent(host, testData.Data, mapper, trainData.Schema);

 // Save per-fold model.
 string modelFileName = ConstructPerFoldName(_outputModelFile, fold);
Expand Down
Loading