GetSummaryDataView() implementation for Pca and Linear Predictors#185

New issue

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

Sign up for GitHub

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

Already on GitHub? Sign in to your account

Merged
TomFinley merged 19 commits into from
Jun 8, 2018
Merged

GetSummaryDataView() implementation for Pca and Linear Predictors #185

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
19 commits
Select commit Hold shift + click to select a range
ec890d6
GetSummaryDataView() implementation for Pca and Linear Predictors
ganik May 18, 2018
9394cdd
typo
ganik May 18, 2018
b508e68
Implement ICanGetSummaryAsIRow instead of ICanGetSummaryAsIDataView o…
ganik May 25, 2018
e072546
Merge branch 'master' of https://github.com/ganik/machinelearning
ganik May 25, 2018
ec8200a
Add vector column for top rank eigenvectors
ganik May 27, 2018
cf37f62
remove unnecessary code
ganik May 27, 2018
9943586
remove space
ganik May 27, 2018
45cd5f2
fix build
ganik May 28, 2018
083645f
no need for slot names
ganik May 29, 2018
58d0f31
Merge pull request #1 from dotnet/master
ganik May 30, 2018
c5c0173
Enable back PCA anomaly tests
ganik May 30, 2018
695abc5
fix PCA Anomaly tests baseline
ganik May 30, 2018
eea9c69
fix unit tests for Release
ganik May 30, 2018
637b325
Add PCA azure test data
ganik May 30, 2018
bdec903
Added entrypoint summpary test for LinearPredictor
ganik May 30, 2018
b942537
added PCA summary test
ganik May 30, 2018
678633c
use using() { } on IDisposable
ganik May 31, 2018
3031a4c
remove slot names
ganik Jun 4, 2018
b0c2e49
remove not needed datasets
ganik Jun 5, 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
21 changes: 21 additions & 0 deletions src/Microsoft.ML.PCA/PcaTrainer.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -310,6 +310,7 @@ public static CommonOutputs.AnomalyDetectionOutput TrainPcaAnomaly(IHostEnvironm
// REVIEW: move the predictor to a different file and fold EigenUtils.cs to this file.
public sealed class PcaPredictor : PredictorBase<Float>,
IValueMapper,
ICanGetSummaryAsIDataView,
ICanSaveInTextFormat, ICanSaveModel, ICanSaveSummary
{
public const string LoaderSignature = "pcaAnomExec";
Expand DownExpand Up@@ -471,6 +472,26 @@ public void SaveAsText(TextWriter writer, RoleMappedSchema schema)
}
}

public IDataView GetSummaryDataView(RoleMappedSchema schema)

@yaeldekelyaeldekelMay 29, 2018

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

GetSummaryDataView [](start = 25, length = 18)

Could you add a unit test for this?

@ganikganikMay 30, 2018

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

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

will do

@ganikganikMay 30, 2018

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

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

added

{
var bldr = new ArrayDataViewBuilder(Host);

var cols = new VBuffer<Float>[_rank + 1];
var names = new string[_rank + 1];
for (var i = 0; i < _rank; ++i)
{
names[i] = "EigenVector" + i;
cols[i] = _eigenVectors[i];
}
names[_rank] = "MeanVector";
cols[_rank] = _mean;

bldr.AddColumn("VectorName", names);
bldr.AddColumn("VectorData", NumberType.R4, cols);

return bldr.GetDataView();
}

public ColumnType InputType
{
get { return _inputType; }
Expand Down
76 changes: 28 additions & 48 deletions src/Microsoft.ML.StandardLearners/Standard/LinearPredictor.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -44,6 +44,7 @@ public abstract class LinearPredictor : PredictorBase<Float>,
ICanSaveInTextFormat,
ICanSaveInSourceCode,
ICanSaveModel,
ICanGetSummaryAsIRow,
ICanSaveSummary,
IPredictorWithFeatureWeights<Float>,
IWhatTheFeatureValueMapper,
Expand DownExpand Up@@ -343,6 +344,30 @@ public void SaveAsCode(TextWriter writer, RoleMappedSchema schema)

public abstract void SaveSummary(TextWriter writer, RoleMappedSchema schema);

public virtual IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
{
var cols = new List<IColumn>();

var names = default(VBuffer<DvText>);
MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
new VectorType(TextType.Instance, Weight.Length), ref names);
var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
var colType = new VectorType(NumberType.R4, Weight.Length);

// Add the bias and the weight columns.
var bias = Bias;
cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
var weights = Weight;
cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
return RowColumnUtils.GetRow(null, cols.ToArray());
}

public virtual IRow GetStatsIRowOrNull(RoleMappedSchema schema)
{
return null;
}

public abstract void SaveAsIni(TextWriter writer, RoleMappedSchema schema, ICalibrator calibrator = null);

public virtual void GetFeatureWeights(ref VBuffer<Float> weights)
Expand All@@ -366,8 +391,7 @@ public ValueMapper<TSrc, VBuffer<Float>> GetWhatTheFeatureMapper<TSrc, TDstContr

public sealed partial class LinearBinaryPredictor : LinearPredictor,
ICanGetSummaryInKeyValuePairs,
IParameterMixer<Float>,
ICanGetSummaryAsIRow
IParameterMixer<Float>
{
public const string LoaderSignature = "Linear2CExec";
public const string RegistrationName = "LinearBinaryPredictor";
Expand DownExpand Up@@ -503,26 +527,7 @@ public IList<KeyValuePair<string, object>> GetSummaryInKeyValuePairs(RoleMappedS
return results;
}

public IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
{
var cols = new List<IColumn>();

var names = default(VBuffer<DvText>);
MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
new VectorType(TextType.Instance, Weight.Length), ref names);
var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
var colType = new VectorType(NumberType.R4, Weight.Length);

// Add the bias and the weight columns.
var bias = Bias;
cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
var weights = Weight;
cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
return RowColumnUtils.GetRow(null, cols.ToArray());
}

public IRow GetStatsIRowOrNull(RoleMappedSchema schema)
public override IRow GetStatsIRowOrNull(RoleMappedSchema schema)
{
if (_stats == null)
return null;
Expand DownExpand Up@@ -582,8 +587,7 @@ public override void SaveAsIni(TextWriter writer, RoleMappedSchema schema, ICali

public sealed class LinearRegressionPredictor : RegressionPredictor,
IParameterMixer<Float>,
ICanGetSummaryInKeyValuePairs,
ICanGetSummaryAsIRow
ICanGetSummaryInKeyValuePairs
{
public const string LoaderSignature = "LinearRegressionExec";
public const string RegistrationName = "LinearRegressionPredictor";
Expand DownExpand Up@@ -663,30 +667,6 @@ public IList<KeyValuePair<string, object>> GetSummaryInKeyValuePairs(RoleMappedS

return results;
}

public IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
{
var cols = new List<IColumn>();

var names = default(VBuffer<DvText>);
MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
new VectorType(TextType.Instance, Weight.Length), ref names);
var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
var colType = new VectorType(NumberType.R4, Weight.Length);

// Add the bias and the weight columns.
var bias = Bias;
cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
var weights = Weight;
cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
return RowColumnUtils.GetRow(null, cols.ToArray());
}

public IRow GetStatsIRowOrNull(RoleMappedSchema schema)
{
return null;
}
}

public sealed class PoissonRegressionPredictor : RegressionPredictor, IParameterMixer<Float>
Expand Down
8 changes: 8 additions & 0 deletions test/BaselineOutput/Common/EntryPoints/lr-weights.txt
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col=Bias:R4:0
#@ col=Weights:R4:1-9
#@ }
Bias thickness uniform_size uniform_shape adhesion epit_size bare_nuclei bland_chromatin normal_nucleoli mitoses
-6.186806 2.65800762 1.68089855 1.944068 1.42514718 0.8536965 2.9325006 1.74816787 1.58165014 0.595681
10 changes: 10 additions & 0 deletions test/BaselineOutput/Common/EntryPoints/mc-lr-stats.txt
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,10 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col={name={Count of training examples} type=I8 src=0}
#@ col={name={Residual Deviance} type=R4 src=1}
#@ col={name={Null Deviance} type=R4 src=2}
#@ col=AIC:R4:3
#@ }
Count of training examples Residual Deviance Null Deviance AIC
683 119.098892 884.3502 159.098892
10 changes: 10 additions & 0 deletions test/BaselineOutput/Common/EntryPoints/mc-lr-weights.txt
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,10 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col=Bias:R4:0
#@ col=Weights:R4:1-9
#@ col=ClassNames:TX:10
#@ }
Bias thickness uniform_size uniform_shape adhesion epit_size bare_nuclei bland_chromatin normal_nucleoli mitoses ClassNames
3.36404228 -1.579712 -0.8266232 -1.051891 -0.79305464 -0.386733949 -1.59106934 -1.01550019 -0.8356989 -0.332574666 Class_0
-3.36404562 1.57971311 0.826623559 1.051891 0.7930542 0.386735022 1.59107041 1.015499 0.8356983 0.332574 Class_1
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
GetSummaryDataView() implementation for Pca and Linear Predictors#185

New issue

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

 Sign up for GitHub

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

Already on GitHub?
Sign in
to your account

 Merged

TomFinley
merged 19 commits into

from

Jun 8, 2018
 Merged


GetSummaryDataView() implementation for Pca and Linear Predictors
#185
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


19 commits


Select commit
Hold shift + click to select a range
ec890d6

GetSummaryDataView() implementation for Pca and Linear Predictors


ganik May 18, 2018
9394cdd

typo


ganik May 18, 2018
b508e68

Implement ICanGetSummaryAsIRow instead of ICanGetSummaryAsIDataView o…


ganik May 25, 2018
e072546

Merge branch 'master' of https://github.com/ganik/machinelearning


ganik May 25, 2018
ec8200a

Add vector column for top rank eigenvectors


ganik May 27, 2018
cf37f62

remove unnecessary code


ganik May 27, 2018
9943586

remove space


ganik May 27, 2018
45cd5f2

fix build


ganik May 28, 2018
083645f

no need for slot names


ganik May 29, 2018
58d0f31

Merge pull request #1 from dotnet/master


ganik May 30, 2018
c5c0173

Enable back PCA anomaly tests


ganik May 30, 2018
695abc5

fix PCA Anomaly tests baseline


ganik May 30, 2018
eea9c69

fix unit tests for Release


ganik May 30, 2018
637b325

Add PCA azure test data


ganik May 30, 2018
bdec903

Added entrypoint summpary test for LinearPredictor


ganik May 30, 2018
b942537

added PCA summary test


ganik May 30, 2018
678633c

use using() { } on IDisposable


ganik May 31, 2018
3031a4c

remove slot names


ganik Jun 4, 2018
b0c2e49

remove not needed datasets


ganik Jun 5, 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


21 changes: 21 additions & 0 deletions
src/Microsoft.ML.PCA/PcaTrainer.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -310,6 +310,7 @@ public static CommonOutputs.AnomalyDetectionOutput TrainPcaAnomaly(IHostEnvironm
 // REVIEW: move the predictor to a different file and fold EigenUtils.cs to this file.
 public sealed class PcaPredictor : PredictorBase<Float>,
 IValueMapper,
 ICanGetSummaryAsIDataView,
 ICanSaveInTextFormat, ICanSaveModel, ICanSaveSummary
 {
 public const string LoaderSignature = "pcaAnomExec";
Expand DownExpand Up@@ -471,6 +472,26 @@ public void SaveAsText(TextWriter writer, RoleMappedSchema schema)
 }
 }

 public IDataView GetSummaryDataView(RoleMappedSchema schema)
@yaeldekelyaeldekelMay 29, 2018

Copy link


Copy Markdown

Choose a reason for hiding this comment

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

GetSummaryDataView [](start = 25, length = 18)
Could you add a unit test for this?
@ganikganikMay 30, 2018

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

will do
@ganikganikMay 30, 2018

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

added
 {
 var bldr = new ArrayDataViewBuilder(Host);

 var cols = new VBuffer<Float>[_rank + 1];
 var names = new string[_rank + 1];
 for (var i = 0; i < _rank; ++i)
 {
 names[i] = "EigenVector" + i;
 cols[i] = _eigenVectors[i];
 }
 names[_rank] = "MeanVector";
 cols[_rank] = _mean;

 bldr.AddColumn("VectorName", names);
 bldr.AddColumn("VectorData", NumberType.R4, cols);

 return bldr.GetDataView();
 }

 public ColumnType InputType
 {
 get { return _inputType; }
Expand Down

76 changes: 28 additions & 48 deletions
src/Microsoft.ML.StandardLearners/Standard/LinearPredictor.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -44,6 +44,7 @@ public abstract class LinearPredictor : PredictorBase<Float>,
 ICanSaveInTextFormat,
 ICanSaveInSourceCode,
 ICanSaveModel,
 ICanGetSummaryAsIRow,
 ICanSaveSummary,
 IPredictorWithFeatureWeights<Float>,
 IWhatTheFeatureValueMapper,
Expand DownExpand Up@@ -343,6 +344,30 @@ public void SaveAsCode(TextWriter writer, RoleMappedSchema schema)

 public abstract void SaveSummary(TextWriter writer, RoleMappedSchema schema);

 public virtual IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
 {
 var cols = new List<IColumn>();

 var names = default(VBuffer<DvText>);
 MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
 var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
 new VectorType(TextType.Instance, Weight.Length), ref names);
 var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
 var colType = new VectorType(NumberType.R4, Weight.Length);

 // Add the bias and the weight columns.
 var bias = Bias;
 cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
 var weights = Weight;
 cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
 return RowColumnUtils.GetRow(null, cols.ToArray());
 }

 public virtual IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 {
 return null;
 }

 public abstract void SaveAsIni(TextWriter writer, RoleMappedSchema schema, ICalibrator calibrator = null);

 public virtual void GetFeatureWeights(ref VBuffer<Float> weights)
Expand All@@ -366,8 +391,7 @@ public ValueMapper<TSrc, VBuffer<Float>> GetWhatTheFeatureMapper<TSrc, TDstContr

 public sealed partial class LinearBinaryPredictor : LinearPredictor,
 ICanGetSummaryInKeyValuePairs,
 IParameterMixer<Float>,
 ICanGetSummaryAsIRow
 IParameterMixer<Float>
 {
 public const string LoaderSignature = "Linear2CExec";
 public const string RegistrationName = "LinearBinaryPredictor";
Expand DownExpand Up@@ -503,26 +527,7 @@ public IList<KeyValuePair<string, object>> GetSummaryInKeyValuePairs(RoleMappedS
 return results;
 }

 public IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
 {
 var cols = new List<IColumn>();

 var names = default(VBuffer<DvText>);
 MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
 var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
 new VectorType(TextType.Instance, Weight.Length), ref names);
 var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
 var colType = new VectorType(NumberType.R4, Weight.Length);

 // Add the bias and the weight columns.
 var bias = Bias;
 cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
 var weights = Weight;
 cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
 return RowColumnUtils.GetRow(null, cols.ToArray());
 }

 public IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 public override IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 {
 if (_stats == null)
 return null;
Expand DownExpand Up@@ -582,8 +587,7 @@ public override void SaveAsIni(TextWriter writer, RoleMappedSchema schema, ICali

 public sealed class LinearRegressionPredictor : RegressionPredictor,
 IParameterMixer<Float>,
 ICanGetSummaryInKeyValuePairs,
 ICanGetSummaryAsIRow
 ICanGetSummaryInKeyValuePairs
 {
 public const string LoaderSignature = "LinearRegressionExec";
 public const string RegistrationName = "LinearRegressionPredictor";
Expand DownExpand Up@@ -663,30 +667,6 @@ public IList<KeyValuePair<string, object>> GetSummaryInKeyValuePairs(RoleMappedS

 return results;
 }

 public IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
 {
 var cols = new List<IColumn>();

 var names = default(VBuffer<DvText>);
 MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
 var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
 new VectorType(TextType.Instance, Weight.Length), ref names);
 var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
 var colType = new VectorType(NumberType.R4, Weight.Length);

 // Add the bias and the weight columns.
 var bias = Bias;
 cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
 var weights = Weight;
 cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
 return RowColumnUtils.GetRow(null, cols.ToArray());
 }

 public IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 {
 return null;
 }
 }

 public sealed class PoissonRegressionPredictor : RegressionPredictor, IParameterMixer<Float>
Expand Down

8 changes: 8 additions & 0 deletions
test/BaselineOutput/Common/EntryPoints/lr-weights.txt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col=Bias:R4:0
#@ col=Weights:R4:1-9
#@ }
Bias	thickness	uniform_size	uniform_shape	adhesion	epit_size	bare_nuclei	bland_chromatin	normal_nucleoli	mitoses
-6.186806	2.65800762	1.68089855	1.944068	1.42514718	0.8536965	2.9325006	1.74816787	1.58165014	0.595681

10 changes: 10 additions & 0 deletions
test/BaselineOutput/Common/EntryPoints/mc-lr-stats.txt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,10 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col={name={Count of training examples} type=I8 src=0}
#@ col={name={Residual Deviance} type=R4 src=1}
#@ col={name={Null Deviance} type=R4 src=2}
#@ col=AIC:R4:3
#@ }
Count of training examples	Residual Deviance	Null Deviance	AIC
683	119.098892	884.3502	159.098892

10 changes: 10 additions & 0 deletions
test/BaselineOutput/Common/EntryPoints/mc-lr-weights.txt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,10 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col=Bias:R4:0
#@ col=Weights:R4:1-9
#@ col=ClassNames:TX:10
#@ }
Bias	thickness	uniform_size	uniform_shape	adhesion	epit_size	bare_nuclei	bland_chromatin	normal_nucleoli	mitoses	ClassNames
3.36404228	-1.579712	-0.8266232	-1.051891	-0.79305464	-0.386733949	-1.59106934	-1.01550019	-0.8356989	-0.332574666	Class_0
-3.36404562	1.57971311	0.826623559	1.051891	0.7930542	0.386735022	1.59107041	1.015499	0.8356983	0.332574	Class_1
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
GetSummaryDataView() implementation for Pca and Linear Predictors#185

New issue

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

 Sign up for GitHub

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

Already on GitHub?
Sign in
to your account

 Merged

TomFinley
merged 19 commits into

from

Jun 8, 2018
 Merged


GetSummaryDataView() implementation for Pca and Linear Predictors
#185
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


19 commits


Select commit
Hold shift + click to select a range
ec890d6

GetSummaryDataView() implementation for Pca and Linear Predictors


ganik May 18, 2018
9394cdd

typo


ganik May 18, 2018
b508e68

Implement ICanGetSummaryAsIRow instead of ICanGetSummaryAsIDataView o…


ganik May 25, 2018
e072546

Merge branch 'master' of https://github.com/ganik/machinelearning


ganik May 25, 2018
ec8200a

Add vector column for top rank eigenvectors


ganik May 27, 2018
cf37f62

remove unnecessary code


ganik May 27, 2018
9943586

remove space


ganik May 27, 2018
45cd5f2

fix build


ganik May 28, 2018
083645f

no need for slot names


ganik May 29, 2018
58d0f31

Merge pull request #1 from dotnet/master


ganik May 30, 2018
c5c0173

Enable back PCA anomaly tests


ganik May 30, 2018
695abc5

fix PCA Anomaly tests baseline


ganik May 30, 2018
eea9c69

fix unit tests for Release


ganik May 30, 2018
637b325

Add PCA azure test data


ganik May 30, 2018
bdec903

Added entrypoint summpary test for LinearPredictor


ganik May 30, 2018
b942537

added PCA summary test


ganik May 30, 2018
678633c

use using() { } on IDisposable


ganik May 31, 2018
3031a4c

remove slot names


ganik Jun 4, 2018
b0c2e49

remove not needed datasets


ganik Jun 5, 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


21 changes: 21 additions & 0 deletions
src/Microsoft.ML.PCA/PcaTrainer.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -310,6 +310,7 @@ public static CommonOutputs.AnomalyDetectionOutput TrainPcaAnomaly(IHostEnvironm
 // REVIEW: move the predictor to a different file and fold EigenUtils.cs to this file.
 public sealed class PcaPredictor : PredictorBase<Float>,
 IValueMapper,
 ICanGetSummaryAsIDataView,
 ICanSaveInTextFormat, ICanSaveModel, ICanSaveSummary
 {
 public const string LoaderSignature = "pcaAnomExec";
Expand DownExpand Up@@ -471,6 +472,26 @@ public void SaveAsText(TextWriter writer, RoleMappedSchema schema)
 }
 }

 public IDataView GetSummaryDataView(RoleMappedSchema schema)
@yaeldekelyaeldekelMay 29, 2018

Copy link


Copy Markdown

Choose a reason for hiding this comment

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

GetSummaryDataView [](start = 25, length = 18)
Could you add a unit test for this?
@ganikganikMay 30, 2018

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

will do
@ganikganikMay 30, 2018

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

added
 {
 var bldr = new ArrayDataViewBuilder(Host);

 var cols = new VBuffer<Float>[_rank + 1];
 var names = new string[_rank + 1];
 for (var i = 0; i < _rank; ++i)
 {
 names[i] = "EigenVector" + i;
 cols[i] = _eigenVectors[i];
 }
 names[_rank] = "MeanVector";
 cols[_rank] = _mean;

 bldr.AddColumn("VectorName", names);
 bldr.AddColumn("VectorData", NumberType.R4, cols);

 return bldr.GetDataView();
 }

 public ColumnType InputType
 {
 get { return _inputType; }
Expand Down

76 changes: 28 additions & 48 deletions
src/Microsoft.ML.StandardLearners/Standard/LinearPredictor.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -44,6 +44,7 @@ public abstract class LinearPredictor : PredictorBase<Float>,
 ICanSaveInTextFormat,
 ICanSaveInSourceCode,
 ICanSaveModel,
 ICanGetSummaryAsIRow,
 ICanSaveSummary,
 IPredictorWithFeatureWeights<Float>,
 IWhatTheFeatureValueMapper,
Expand DownExpand Up@@ -343,6 +344,30 @@ public void SaveAsCode(TextWriter writer, RoleMappedSchema schema)

 public abstract void SaveSummary(TextWriter writer, RoleMappedSchema schema);

 public virtual IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
 {
 var cols = new List<IColumn>();

 var names = default(VBuffer<DvText>);
 MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
 var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
 new VectorType(TextType.Instance, Weight.Length), ref names);
 var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
 var colType = new VectorType(NumberType.R4, Weight.Length);

 // Add the bias and the weight columns.
 var bias = Bias;
 cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
 var weights = Weight;
 cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
 return RowColumnUtils.GetRow(null, cols.ToArray());
 }

 public virtual IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 {
 return null;
 }

 public abstract void SaveAsIni(TextWriter writer, RoleMappedSchema schema, ICalibrator calibrator = null);

 public virtual void GetFeatureWeights(ref VBuffer<Float> weights)
Expand All@@ -366,8 +391,7 @@ public ValueMapper<TSrc, VBuffer<Float>> GetWhatTheFeatureMapper<TSrc, TDstContr

 public sealed partial class LinearBinaryPredictor : LinearPredictor,
 ICanGetSummaryInKeyValuePairs,
 IParameterMixer<Float>,
 ICanGetSummaryAsIRow
 IParameterMixer<Float>
 {
 public const string LoaderSignature = "Linear2CExec";
 public const string RegistrationName = "LinearBinaryPredictor";
Expand DownExpand Up@@ -503,26 +527,7 @@ public IList<KeyValuePair<string, object>> GetSummaryInKeyValuePairs(RoleMappedS
 return results;
 }

 public IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
 {
 var cols = new List<IColumn>();

 var names = default(VBuffer<DvText>);
 MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
 var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
 new VectorType(TextType.Instance, Weight.Length), ref names);
 var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
 var colType = new VectorType(NumberType.R4, Weight.Length);

 // Add the bias and the weight columns.
 var bias = Bias;
 cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
 var weights = Weight;
 cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
 return RowColumnUtils.GetRow(null, cols.ToArray());
 }

 public IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 public override IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 {
 if (_stats == null)
 return null;
Expand DownExpand Up@@ -582,8 +587,7 @@ public override void SaveAsIni(TextWriter writer, RoleMappedSchema schema, ICali

 public sealed class LinearRegressionPredictor : RegressionPredictor,
 IParameterMixer<Float>,
 ICanGetSummaryInKeyValuePairs,
 ICanGetSummaryAsIRow
 ICanGetSummaryInKeyValuePairs
 {
 public const string LoaderSignature = "LinearRegressionExec";
 public const string RegistrationName = "LinearRegressionPredictor";
Expand DownExpand Up@@ -663,30 +667,6 @@ public IList<KeyValuePair<string, object>> GetSummaryInKeyValuePairs(RoleMappedS

 return results;
 }

 public IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
 {
 var cols = new List<IColumn>();

 var names = default(VBuffer<DvText>);
 MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
 var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
 new VectorType(TextType.Instance, Weight.Length), ref names);
 var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
 var colType = new VectorType(NumberType.R4, Weight.Length);

 // Add the bias and the weight columns.
 var bias = Bias;
 cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
 var weights = Weight;
 cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
 return RowColumnUtils.GetRow(null, cols.ToArray());
 }

 public IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 {
 return null;
 }
 }

 public sealed class PoissonRegressionPredictor : RegressionPredictor, IParameterMixer<Float>
Expand Down

8 changes: 8 additions & 0 deletions
test/BaselineOutput/Common/EntryPoints/lr-weights.txt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col=Bias:R4:0
#@ col=Weights:R4:1-9
#@ }
Bias	thickness	uniform_size	uniform_shape	adhesion	epit_size	bare_nuclei	bland_chromatin	normal_nucleoli	mitoses
-6.186806	2.65800762	1.68089855	1.944068	1.42514718	0.8536965	2.9325006	1.74816787	1.58165014	0.595681

10 changes: 10 additions & 0 deletions
test/BaselineOutput/Common/EntryPoints/mc-lr-stats.txt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,10 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col={name={Count of training examples} type=I8 src=0}
#@ col={name={Residual Deviance} type=R4 src=1}
#@ col={name={Null Deviance} type=R4 src=2}
#@ col=AIC:R4:3
#@ }
Count of training examples	Residual Deviance	Null Deviance	AIC
683	119.098892	884.3502	159.098892

10 changes: 10 additions & 0 deletions
test/BaselineOutput/Common/EntryPoints/mc-lr-weights.txt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,10 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col=Bias:R4:0
#@ col=Weights:R4:1-9
#@ col=ClassNames:TX:10
#@ }
Bias	thickness	uniform_size	uniform_shape	adhesion	epit_size	bare_nuclei	bland_chromatin	normal_nucleoli	mitoses	ClassNames
3.36404228	-1.579712	-0.8266232	-1.051891	-0.79305464	-0.386733949	-1.59106934	-1.01550019	-0.8356989	-0.332574666	Class_0
-3.36404562	1.57971311	0.826623559	1.051891	0.7930542	0.386735022	1.59107041	1.015499	0.8356983	0.332574	Class_1
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
GetSummaryDataView() implementation for Pca and Linear Predictors#185

New issue

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

 Sign up for GitHub

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

Already on GitHub?
Sign in
to your account

 Merged

TomFinley
merged 19 commits into

from

Jun 8, 2018
 Merged


GetSummaryDataView() implementation for Pca and Linear Predictors
#185
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


19 commits


Select commit
Hold shift + click to select a range
ec890d6

GetSummaryDataView() implementation for Pca and Linear Predictors


ganik May 18, 2018
9394cdd

typo


ganik May 18, 2018
b508e68

Implement ICanGetSummaryAsIRow instead of ICanGetSummaryAsIDataView o…


ganik May 25, 2018
e072546

Merge branch 'master' of https://github.com/ganik/machinelearning


ganik May 25, 2018
ec8200a

Add vector column for top rank eigenvectors


ganik May 27, 2018
cf37f62

remove unnecessary code


ganik May 27, 2018
9943586

remove space


ganik May 27, 2018
45cd5f2

fix build


ganik May 28, 2018
083645f

no need for slot names


ganik May 29, 2018
58d0f31

Merge pull request #1 from dotnet/master


ganik May 30, 2018
c5c0173

Enable back PCA anomaly tests


ganik May 30, 2018
695abc5

fix PCA Anomaly tests baseline


ganik May 30, 2018
eea9c69

fix unit tests for Release


ganik May 30, 2018
637b325

Add PCA azure test data


ganik May 30, 2018
bdec903

Added entrypoint summpary test for LinearPredictor


ganik May 30, 2018
b942537

added PCA summary test


ganik May 30, 2018
678633c

use using() { } on IDisposable


ganik May 31, 2018
3031a4c

remove slot names


ganik Jun 4, 2018
b0c2e49

remove not needed datasets


ganik Jun 5, 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


21 changes: 21 additions & 0 deletions
src/Microsoft.ML.PCA/PcaTrainer.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -310,6 +310,7 @@ public static CommonOutputs.AnomalyDetectionOutput TrainPcaAnomaly(IHostEnvironm
 // REVIEW: move the predictor to a different file and fold EigenUtils.cs to this file.
 public sealed class PcaPredictor : PredictorBase<Float>,
 IValueMapper,
 ICanGetSummaryAsIDataView,
 ICanSaveInTextFormat, ICanSaveModel, ICanSaveSummary
 {
 public const string LoaderSignature = "pcaAnomExec";
Expand DownExpand Up@@ -471,6 +472,26 @@ public void SaveAsText(TextWriter writer, RoleMappedSchema schema)
 }
 }

 public IDataView GetSummaryDataView(RoleMappedSchema schema)
@yaeldekelyaeldekelMay 29, 2018

Copy link


Copy Markdown

Choose a reason for hiding this comment

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

GetSummaryDataView [](start = 25, length = 18)
Could you add a unit test for this?
@ganikganikMay 30, 2018

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

will do
@ganikganikMay 30, 2018

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

added
 {
 var bldr = new ArrayDataViewBuilder(Host);

 var cols = new VBuffer<Float>[_rank + 1];
 var names = new string[_rank + 1];
 for (var i = 0; i < _rank; ++i)
 {
 names[i] = "EigenVector" + i;
 cols[i] = _eigenVectors[i];
 }
 names[_rank] = "MeanVector";
 cols[_rank] = _mean;

 bldr.AddColumn("VectorName", names);
 bldr.AddColumn("VectorData", NumberType.R4, cols);

 return bldr.GetDataView();
 }

 public ColumnType InputType
 {
 get { return _inputType; }
Expand Down

76 changes: 28 additions & 48 deletions
src/Microsoft.ML.StandardLearners/Standard/LinearPredictor.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -44,6 +44,7 @@ public abstract class LinearPredictor : PredictorBase<Float>,
 ICanSaveInTextFormat,
 ICanSaveInSourceCode,
 ICanSaveModel,
 ICanGetSummaryAsIRow,
 ICanSaveSummary,
 IPredictorWithFeatureWeights<Float>,
 IWhatTheFeatureValueMapper,
Expand DownExpand Up@@ -343,6 +344,30 @@ public void SaveAsCode(TextWriter writer, RoleMappedSchema schema)

 public abstract void SaveSummary(TextWriter writer, RoleMappedSchema schema);

 public virtual IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
 {
 var cols = new List<IColumn>();

 var names = default(VBuffer<DvText>);
 MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
 var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
 new VectorType(TextType.Instance, Weight.Length), ref names);
 var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
 var colType = new VectorType(NumberType.R4, Weight.Length);

 // Add the bias and the weight columns.
 var bias = Bias;
 cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
 var weights = Weight;
 cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
 return RowColumnUtils.GetRow(null, cols.ToArray());
 }

 public virtual IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 {
 return null;
 }

 public abstract void SaveAsIni(TextWriter writer, RoleMappedSchema schema, ICalibrator calibrator = null);

 public virtual void GetFeatureWeights(ref VBuffer<Float> weights)
Expand All@@ -366,8 +391,7 @@ public ValueMapper<TSrc, VBuffer<Float>> GetWhatTheFeatureMapper<TSrc, TDstContr

 public sealed partial class LinearBinaryPredictor : LinearPredictor,
 ICanGetSummaryInKeyValuePairs,
 IParameterMixer<Float>,
 ICanGetSummaryAsIRow
 IParameterMixer<Float>
 {
 public const string LoaderSignature = "Linear2CExec";
 public const string RegistrationName = "LinearBinaryPredictor";
Expand DownExpand Up@@ -503,26 +527,7 @@ public IList<KeyValuePair<string, object>> GetSummaryInKeyValuePairs(RoleMappedS
 return results;
 }

 public IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
 {
 var cols = new List<IColumn>();

 var names = default(VBuffer<DvText>);
 MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
 var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
 new VectorType(TextType.Instance, Weight.Length), ref names);
 var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
 var colType = new VectorType(NumberType.R4, Weight.Length);

 // Add the bias and the weight columns.
 var bias = Bias;
 cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
 var weights = Weight;
 cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
 return RowColumnUtils.GetRow(null, cols.ToArray());
 }

 public IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 public override IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 {
 if (_stats == null)
 return null;
Expand DownExpand Up@@ -582,8 +587,7 @@ public override void SaveAsIni(TextWriter writer, RoleMappedSchema schema, ICali

 public sealed class LinearRegressionPredictor : RegressionPredictor,
 IParameterMixer<Float>,
 ICanGetSummaryInKeyValuePairs,
 ICanGetSummaryAsIRow
 ICanGetSummaryInKeyValuePairs
 {
 public const string LoaderSignature = "LinearRegressionExec";
 public const string RegistrationName = "LinearRegressionPredictor";
Expand DownExpand Up@@ -663,30 +667,6 @@ public IList<KeyValuePair<string, object>> GetSummaryInKeyValuePairs(RoleMappedS

 return results;
 }

 public IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
 {
 var cols = new List<IColumn>();

 var names = default(VBuffer<DvText>);
 MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
 var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
 new VectorType(TextType.Instance, Weight.Length), ref names);
 var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
 var colType = new VectorType(NumberType.R4, Weight.Length);

 // Add the bias and the weight columns.
 var bias = Bias;
 cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
 var weights = Weight;
 cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
 return RowColumnUtils.GetRow(null, cols.ToArray());
 }

 public IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 {
 return null;
 }
 }

 public sealed class PoissonRegressionPredictor : RegressionPredictor, IParameterMixer<Float>
Expand Down

8 changes: 8 additions & 0 deletions
test/BaselineOutput/Common/EntryPoints/lr-weights.txt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col=Bias:R4:0
#@ col=Weights:R4:1-9
#@ }
Bias	thickness	uniform_size	uniform_shape	adhesion	epit_size	bare_nuclei	bland_chromatin	normal_nucleoli	mitoses
-6.186806	2.65800762	1.68089855	1.944068	1.42514718	0.8536965	2.9325006	1.74816787	1.58165014	0.595681

10 changes: 10 additions & 0 deletions
test/BaselineOutput/Common/EntryPoints/mc-lr-stats.txt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,10 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col={name={Count of training examples} type=I8 src=0}
#@ col={name={Residual Deviance} type=R4 src=1}
#@ col={name={Null Deviance} type=R4 src=2}
#@ col=AIC:R4:3
#@ }
Count of training examples	Residual Deviance	Null Deviance	AIC
683	119.098892	884.3502	159.098892

10 changes: 10 additions & 0 deletions
test/BaselineOutput/Common/EntryPoints/mc-lr-weights.txt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,10 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col=Bias:R4:0
#@ col=Weights:R4:1-9
#@ col=ClassNames:TX:10
#@ }
Bias	thickness	uniform_size	uniform_shape	adhesion	epit_size	bare_nuclei	bland_chromatin	normal_nucleoli	mitoses	ClassNames
3.36404228	-1.579712	-0.8266232	-1.051891	-0.79305464	-0.386733949	-1.59106934	-1.01550019	-0.8356989	-0.332574666	Class_0
-3.36404562	1.57971311	0.826623559	1.051891	0.7930542	0.386735022	1.59107041	1.015499	0.8356983	0.332574	Class_1
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
GetSummaryDataView() implementation for Pca and Linear Predictors#185

New issue

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

 Sign up for GitHub

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

Already on GitHub?
Sign in
to your account

 Merged

TomFinley
merged 19 commits into

from

Jun 8, 2018
 Merged


GetSummaryDataView() implementation for Pca and Linear Predictors
#185
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


19 commits


Select commit
Hold shift + click to select a range
ec890d6

GetSummaryDataView() implementation for Pca and Linear Predictors


ganik May 18, 2018
9394cdd

typo


ganik May 18, 2018
b508e68

Implement ICanGetSummaryAsIRow instead of ICanGetSummaryAsIDataView o…


ganik May 25, 2018
e072546

Merge branch 'master' of https://github.com/ganik/machinelearning


ganik May 25, 2018
ec8200a

Add vector column for top rank eigenvectors


ganik May 27, 2018
cf37f62

remove unnecessary code


ganik May 27, 2018
9943586

remove space


ganik May 27, 2018
45cd5f2

fix build


ganik May 28, 2018
083645f

no need for slot names


ganik May 29, 2018
58d0f31

Merge pull request #1 from dotnet/master


ganik May 30, 2018
c5c0173

Enable back PCA anomaly tests


ganik May 30, 2018
695abc5

fix PCA Anomaly tests baseline


ganik May 30, 2018
eea9c69

fix unit tests for Release


ganik May 30, 2018
637b325

Add PCA azure test data


ganik May 30, 2018
bdec903

Added entrypoint summpary test for LinearPredictor


ganik May 30, 2018
b942537

added PCA summary test


ganik May 30, 2018
678633c

use using() { } on IDisposable


ganik May 31, 2018
3031a4c

remove slot names


ganik Jun 4, 2018
b0c2e49

remove not needed datasets


ganik Jun 5, 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


21 changes: 21 additions & 0 deletions
src/Microsoft.ML.PCA/PcaTrainer.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -310,6 +310,7 @@ public static CommonOutputs.AnomalyDetectionOutput TrainPcaAnomaly(IHostEnvironm
 // REVIEW: move the predictor to a different file and fold EigenUtils.cs to this file.
 public sealed class PcaPredictor : PredictorBase<Float>,
 IValueMapper,
 ICanGetSummaryAsIDataView,
 ICanSaveInTextFormat, ICanSaveModel, ICanSaveSummary
 {
 public const string LoaderSignature = "pcaAnomExec";
Expand DownExpand Up@@ -471,6 +472,26 @@ public void SaveAsText(TextWriter writer, RoleMappedSchema schema)
 }
 }

 public IDataView GetSummaryDataView(RoleMappedSchema schema)
@yaeldekelyaeldekelMay 29, 2018

Copy link


Copy Markdown

Choose a reason for hiding this comment

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

GetSummaryDataView [](start = 25, length = 18)
Could you add a unit test for this?
@ganikganikMay 30, 2018

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

will do
@ganikganikMay 30, 2018

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

added
 {
 var bldr = new ArrayDataViewBuilder(Host);

 var cols = new VBuffer<Float>[_rank + 1];
 var names = new string[_rank + 1];
 for (var i = 0; i < _rank; ++i)
 {
 names[i] = "EigenVector" + i;
 cols[i] = _eigenVectors[i];
 }
 names[_rank] = "MeanVector";
 cols[_rank] = _mean;

 bldr.AddColumn("VectorName", names);
 bldr.AddColumn("VectorData", NumberType.R4, cols);

 return bldr.GetDataView();
 }

 public ColumnType InputType
 {
 get { return _inputType; }
Expand Down

76 changes: 28 additions & 48 deletions
src/Microsoft.ML.StandardLearners/Standard/LinearPredictor.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -44,6 +44,7 @@ public abstract class LinearPredictor : PredictorBase<Float>,
 ICanSaveInTextFormat,
 ICanSaveInSourceCode,
 ICanSaveModel,
 ICanGetSummaryAsIRow,
 ICanSaveSummary,
 IPredictorWithFeatureWeights<Float>,
 IWhatTheFeatureValueMapper,
Expand DownExpand Up@@ -343,6 +344,30 @@ public void SaveAsCode(TextWriter writer, RoleMappedSchema schema)

 public abstract void SaveSummary(TextWriter writer, RoleMappedSchema schema);

 public virtual IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
 {
 var cols = new List<IColumn>();

 var names = default(VBuffer<DvText>);
 MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
 var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
 new VectorType(TextType.Instance, Weight.Length), ref names);
 var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
 var colType = new VectorType(NumberType.R4, Weight.Length);

 // Add the bias and the weight columns.
 var bias = Bias;
 cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
 var weights = Weight;
 cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
 return RowColumnUtils.GetRow(null, cols.ToArray());
 }

 public virtual IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 {
 return null;
 }

 public abstract void SaveAsIni(TextWriter writer, RoleMappedSchema schema, ICalibrator calibrator = null);

 public virtual void GetFeatureWeights(ref VBuffer<Float> weights)
Expand All@@ -366,8 +391,7 @@ public ValueMapper<TSrc, VBuffer<Float>> GetWhatTheFeatureMapper<TSrc, TDstContr

 public sealed partial class LinearBinaryPredictor : LinearPredictor,
 ICanGetSummaryInKeyValuePairs,
 IParameterMixer<Float>,
 ICanGetSummaryAsIRow
 IParameterMixer<Float>
 {
 public const string LoaderSignature = "Linear2CExec";
 public const string RegistrationName = "LinearBinaryPredictor";
Expand DownExpand Up@@ -503,26 +527,7 @@ public IList<KeyValuePair<string, object>> GetSummaryInKeyValuePairs(RoleMappedS
 return results;
 }

 public IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
 {
 var cols = new List<IColumn>();

 var names = default(VBuffer<DvText>);
 MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
 var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
 new VectorType(TextType.Instance, Weight.Length), ref names);
 var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
 var colType = new VectorType(NumberType.R4, Weight.Length);

 // Add the bias and the weight columns.
 var bias = Bias;
 cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
 var weights = Weight;
 cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
 return RowColumnUtils.GetRow(null, cols.ToArray());
 }

 public IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 public override IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 {
 if (_stats == null)
 return null;
Expand DownExpand Up@@ -582,8 +587,7 @@ public override void SaveAsIni(TextWriter writer, RoleMappedSchema schema, ICali

 public sealed class LinearRegressionPredictor : RegressionPredictor,
 IParameterMixer<Float>,
 ICanGetSummaryInKeyValuePairs,
 ICanGetSummaryAsIRow
 ICanGetSummaryInKeyValuePairs
 {
 public const string LoaderSignature = "LinearRegressionExec";
 public const string RegistrationName = "LinearRegressionPredictor";
Expand DownExpand Up@@ -663,30 +667,6 @@ public IList<KeyValuePair<string, object>> GetSummaryInKeyValuePairs(RoleMappedS

 return results;
 }

 public IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
 {
 var cols = new List<IColumn>();

 var names = default(VBuffer<DvText>);
 MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
 var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
 new VectorType(TextType.Instance, Weight.Length), ref names);
 var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
 var colType = new VectorType(NumberType.R4, Weight.Length);

 // Add the bias and the weight columns.
 var bias = Bias;
 cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
 var weights = Weight;
 cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
 return RowColumnUtils.GetRow(null, cols.ToArray());
 }

 public IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 {
 return null;
 }
 }

 public sealed class PoissonRegressionPredictor : RegressionPredictor, IParameterMixer<Float>
Expand Down

8 changes: 8 additions & 0 deletions
test/BaselineOutput/Common/EntryPoints/lr-weights.txt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col=Bias:R4:0
#@ col=Weights:R4:1-9
#@ }
Bias	thickness	uniform_size	uniform_shape	adhesion	epit_size	bare_nuclei	bland_chromatin	normal_nucleoli	mitoses
-6.186806	2.65800762	1.68089855	1.944068	1.42514718	0.8536965	2.9325006	1.74816787	1.58165014	0.595681

10 changes: 10 additions & 0 deletions
test/BaselineOutput/Common/EntryPoints/mc-lr-stats.txt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,10 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col={name={Count of training examples} type=I8 src=0}
#@ col={name={Residual Deviance} type=R4 src=1}
#@ col={name={Null Deviance} type=R4 src=2}
#@ col=AIC:R4:3
#@ }
Count of training examples	Residual Deviance	Null Deviance	AIC
683	119.098892	884.3502	159.098892

10 changes: 10 additions & 0 deletions
test/BaselineOutput/Common/EntryPoints/mc-lr-weights.txt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,10 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col=Bias:R4:0
#@ col=Weights:R4:1-9
#@ col=ClassNames:TX:10
#@ }
Bias	thickness	uniform_size	uniform_shape	adhesion	epit_size	bare_nuclei	bland_chromatin	normal_nucleoli	mitoses	ClassNames
3.36404228	-1.579712	-0.8266232	-1.051891	-0.79305464	-0.386733949	-1.59106934	-1.01550019	-0.8356989	-0.332574666	Class_0
-3.36404562	1.57971311	0.826623559	1.051891	0.7930542	0.386735022	1.59107041	1.015499	0.8356983	0.332574	Class_1
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
GetSummaryDataView() implementation for Pca and Linear Predictors#185

New issue

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

 Sign up for GitHub

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

Already on GitHub?
Sign in
to your account

 Merged

TomFinley
merged 19 commits into

from

Jun 8, 2018
 Merged


GetSummaryDataView() implementation for Pca and Linear Predictors
#185
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


19 commits


Select commit
Hold shift + click to select a range
ec890d6

GetSummaryDataView() implementation for Pca and Linear Predictors


ganik May 18, 2018
9394cdd

typo


ganik May 18, 2018
b508e68

Implement ICanGetSummaryAsIRow instead of ICanGetSummaryAsIDataView o…


ganik May 25, 2018
e072546

Merge branch 'master' of https://github.com/ganik/machinelearning


ganik May 25, 2018
ec8200a

Add vector column for top rank eigenvectors


ganik May 27, 2018
cf37f62

remove unnecessary code


ganik May 27, 2018
9943586

remove space


ganik May 27, 2018
45cd5f2

fix build


ganik May 28, 2018
083645f

no need for slot names


ganik May 29, 2018
58d0f31

Merge pull request #1 from dotnet/master


ganik May 30, 2018
c5c0173

Enable back PCA anomaly tests


ganik May 30, 2018
695abc5

fix PCA Anomaly tests baseline


ganik May 30, 2018
eea9c69

fix unit tests for Release


ganik May 30, 2018
637b325

Add PCA azure test data


ganik May 30, 2018
bdec903

Added entrypoint summpary test for LinearPredictor


ganik May 30, 2018
b942537

added PCA summary test


ganik May 30, 2018
678633c

use using() { } on IDisposable


ganik May 31, 2018
3031a4c

remove slot names


ganik Jun 4, 2018
b0c2e49

remove not needed datasets


ganik Jun 5, 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


21 changes: 21 additions & 0 deletions
src/Microsoft.ML.PCA/PcaTrainer.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -310,6 +310,7 @@ public static CommonOutputs.AnomalyDetectionOutput TrainPcaAnomaly(IHostEnvironm
 // REVIEW: move the predictor to a different file and fold EigenUtils.cs to this file.
 public sealed class PcaPredictor : PredictorBase<Float>,
 IValueMapper,
 ICanGetSummaryAsIDataView,
 ICanSaveInTextFormat, ICanSaveModel, ICanSaveSummary
 {
 public const string LoaderSignature = "pcaAnomExec";
Expand DownExpand Up@@ -471,6 +472,26 @@ public void SaveAsText(TextWriter writer, RoleMappedSchema schema)
 }
 }

 public IDataView GetSummaryDataView(RoleMappedSchema schema)
@yaeldekelyaeldekelMay 29, 2018

Copy link


Copy Markdown

Choose a reason for hiding this comment

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

GetSummaryDataView [](start = 25, length = 18)
Could you add a unit test for this?
@ganikganikMay 30, 2018

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

will do
@ganikganikMay 30, 2018

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

added
 {
 var bldr = new ArrayDataViewBuilder(Host);

 var cols = new VBuffer<Float>[_rank + 1];
 var names = new string[_rank + 1];
 for (var i = 0; i < _rank; ++i)
 {
 names[i] = "EigenVector" + i;
 cols[i] = _eigenVectors[i];
 }
 names[_rank] = "MeanVector";
 cols[_rank] = _mean;

 bldr.AddColumn("VectorName", names);
 bldr.AddColumn("VectorData", NumberType.R4, cols);

 return bldr.GetDataView();
 }

 public ColumnType InputType
 {
 get { return _inputType; }
Expand Down

76 changes: 28 additions & 48 deletions
src/Microsoft.ML.StandardLearners/Standard/LinearPredictor.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -44,6 +44,7 @@ public abstract class LinearPredictor : PredictorBase<Float>,
 ICanSaveInTextFormat,
 ICanSaveInSourceCode,
 ICanSaveModel,
 ICanGetSummaryAsIRow,
 ICanSaveSummary,
 IPredictorWithFeatureWeights<Float>,
 IWhatTheFeatureValueMapper,
Expand DownExpand Up@@ -343,6 +344,30 @@ public void SaveAsCode(TextWriter writer, RoleMappedSchema schema)

 public abstract void SaveSummary(TextWriter writer, RoleMappedSchema schema);

 public virtual IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
 {
 var cols = new List<IColumn>();

 var names = default(VBuffer<DvText>);
 MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
 var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
 new VectorType(TextType.Instance, Weight.Length), ref names);
 var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
 var colType = new VectorType(NumberType.R4, Weight.Length);

 // Add the bias and the weight columns.
 var bias = Bias;
 cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
 var weights = Weight;
 cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
 return RowColumnUtils.GetRow(null, cols.ToArray());
 }

 public virtual IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 {
 return null;
 }

 public abstract void SaveAsIni(TextWriter writer, RoleMappedSchema schema, ICalibrator calibrator = null);

 public virtual void GetFeatureWeights(ref VBuffer<Float> weights)
Expand All@@ -366,8 +391,7 @@ public ValueMapper<TSrc, VBuffer<Float>> GetWhatTheFeatureMapper<TSrc, TDstContr

 public sealed partial class LinearBinaryPredictor : LinearPredictor,
 ICanGetSummaryInKeyValuePairs,
 IParameterMixer<Float>,
 ICanGetSummaryAsIRow
 IParameterMixer<Float>
 {
 public const string LoaderSignature = "Linear2CExec";
 public const string RegistrationName = "LinearBinaryPredictor";
Expand DownExpand Up@@ -503,26 +527,7 @@ public IList<KeyValuePair<string, object>> GetSummaryInKeyValuePairs(RoleMappedS
 return results;
 }

 public IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
 {
 var cols = new List<IColumn>();

 var names = default(VBuffer<DvText>);
 MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
 var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
 new VectorType(TextType.Instance, Weight.Length), ref names);
 var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
 var colType = new VectorType(NumberType.R4, Weight.Length);

 // Add the bias and the weight columns.
 var bias = Bias;
 cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
 var weights = Weight;
 cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
 return RowColumnUtils.GetRow(null, cols.ToArray());
 }

 public IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 public override IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 {
 if (_stats == null)
 return null;
Expand DownExpand Up@@ -582,8 +587,7 @@ public override void SaveAsIni(TextWriter writer, RoleMappedSchema schema, ICali

 public sealed class LinearRegressionPredictor : RegressionPredictor,
 IParameterMixer<Float>,
 ICanGetSummaryInKeyValuePairs,
 ICanGetSummaryAsIRow
 ICanGetSummaryInKeyValuePairs
 {
 public const string LoaderSignature = "LinearRegressionExec";
 public const string RegistrationName = "LinearRegressionPredictor";
Expand DownExpand Up@@ -663,30 +667,6 @@ public IList<KeyValuePair<string, object>> GetSummaryInKeyValuePairs(RoleMappedS

 return results;
 }

 public IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
 {
 var cols = new List<IColumn>();

 var names = default(VBuffer<DvText>);
 MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
 var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
 new VectorType(TextType.Instance, Weight.Length), ref names);
 var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
 var colType = new VectorType(NumberType.R4, Weight.Length);

 // Add the bias and the weight columns.
 var bias = Bias;
 cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
 var weights = Weight;
 cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
 return RowColumnUtils.GetRow(null, cols.ToArray());
 }

 public IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 {
 return null;
 }
 }

 public sealed class PoissonRegressionPredictor : RegressionPredictor, IParameterMixer<Float>
Expand Down

8 changes: 8 additions & 0 deletions
test/BaselineOutput/Common/EntryPoints/lr-weights.txt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col=Bias:R4:0
#@ col=Weights:R4:1-9
#@ }
Bias	thickness	uniform_size	uniform_shape	adhesion	epit_size	bare_nuclei	bland_chromatin	normal_nucleoli	mitoses
-6.186806	2.65800762	1.68089855	1.944068	1.42514718	0.8536965	2.9325006	1.74816787	1.58165014	0.595681

10 changes: 10 additions & 0 deletions
test/BaselineOutput/Common/EntryPoints/mc-lr-stats.txt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,10 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col={name={Count of training examples} type=I8 src=0}
#@ col={name={Residual Deviance} type=R4 src=1}
#@ col={name={Null Deviance} type=R4 src=2}
#@ col=AIC:R4:3
#@ }
Count of training examples	Residual Deviance	Null Deviance	AIC
683	119.098892	884.3502	159.098892

10 changes: 10 additions & 0 deletions
test/BaselineOutput/Common/EntryPoints/mc-lr-weights.txt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,10 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col=Bias:R4:0
#@ col=Weights:R4:1-9
#@ col=ClassNames:TX:10
#@ }
Bias	thickness	uniform_size	uniform_shape	adhesion	epit_size	bare_nuclei	bland_chromatin	normal_nucleoli	mitoses	ClassNames
3.36404228	-1.579712	-0.8266232	-1.051891	-0.79305464	-0.386733949	-1.59106934	-1.01550019	-0.8356989	-0.332574666	Class_0
-3.36404562	1.57971311	0.826623559	1.051891	0.7930542	0.386735022	1.59107041	1.015499	0.8356983	0.332574	Class_1
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
GetSummaryDataView() implementation for Pca and Linear Predictors#185

New issue

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

 Sign up for GitHub

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

Already on GitHub?
Sign in
to your account

 Merged

TomFinley
merged 19 commits into

from

Jun 8, 2018
 Merged


GetSummaryDataView() implementation for Pca and Linear Predictors
#185
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


19 commits


Select commit
Hold shift + click to select a range
ec890d6

GetSummaryDataView() implementation for Pca and Linear Predictors


ganik May 18, 2018
9394cdd

typo


ganik May 18, 2018
b508e68

Implement ICanGetSummaryAsIRow instead of ICanGetSummaryAsIDataView o…


ganik May 25, 2018
e072546

Merge branch 'master' of https://github.com/ganik/machinelearning


ganik May 25, 2018
ec8200a

Add vector column for top rank eigenvectors


ganik May 27, 2018
cf37f62

remove unnecessary code


ganik May 27, 2018
9943586

remove space


ganik May 27, 2018
45cd5f2

fix build


ganik May 28, 2018
083645f

no need for slot names


ganik May 29, 2018
58d0f31

Merge pull request #1 from dotnet/master


ganik May 30, 2018
c5c0173

Enable back PCA anomaly tests


ganik May 30, 2018
695abc5

fix PCA Anomaly tests baseline


ganik May 30, 2018
eea9c69

fix unit tests for Release


ganik May 30, 2018
637b325

Add PCA azure test data


ganik May 30, 2018
bdec903

Added entrypoint summpary test for LinearPredictor


ganik May 30, 2018
b942537

added PCA summary test


ganik May 30, 2018
678633c

use using() { } on IDisposable


ganik May 31, 2018
3031a4c

remove slot names


ganik Jun 4, 2018
b0c2e49

remove not needed datasets


ganik Jun 5, 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


21 changes: 21 additions & 0 deletions
src/Microsoft.ML.PCA/PcaTrainer.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -310,6 +310,7 @@ public static CommonOutputs.AnomalyDetectionOutput TrainPcaAnomaly(IHostEnvironm
 // REVIEW: move the predictor to a different file and fold EigenUtils.cs to this file.
 public sealed class PcaPredictor : PredictorBase<Float>,
 IValueMapper,
 ICanGetSummaryAsIDataView,
 ICanSaveInTextFormat, ICanSaveModel, ICanSaveSummary
 {
 public const string LoaderSignature = "pcaAnomExec";
Expand DownExpand Up@@ -471,6 +472,26 @@ public void SaveAsText(TextWriter writer, RoleMappedSchema schema)
 }
 }

 public IDataView GetSummaryDataView(RoleMappedSchema schema)
@yaeldekelyaeldekelMay 29, 2018

Copy link


Copy Markdown

Choose a reason for hiding this comment

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

GetSummaryDataView [](start = 25, length = 18)
Could you add a unit test for this?
@ganikganikMay 30, 2018

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

will do
@ganikganikMay 30, 2018

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

added
 {
 var bldr = new ArrayDataViewBuilder(Host);

 var cols = new VBuffer<Float>[_rank + 1];
 var names = new string[_rank + 1];
 for (var i = 0; i < _rank; ++i)
 {
 names[i] = "EigenVector" + i;
 cols[i] = _eigenVectors[i];
 }
 names[_rank] = "MeanVector";
 cols[_rank] = _mean;

 bldr.AddColumn("VectorName", names);
 bldr.AddColumn("VectorData", NumberType.R4, cols);

 return bldr.GetDataView();
 }

 public ColumnType InputType
 {
 get { return _inputType; }
Expand Down

76 changes: 28 additions & 48 deletions
src/Microsoft.ML.StandardLearners/Standard/LinearPredictor.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -44,6 +44,7 @@ public abstract class LinearPredictor : PredictorBase<Float>,
 ICanSaveInTextFormat,
 ICanSaveInSourceCode,
 ICanSaveModel,
 ICanGetSummaryAsIRow,
 ICanSaveSummary,
 IPredictorWithFeatureWeights<Float>,
 IWhatTheFeatureValueMapper,
Expand DownExpand Up@@ -343,6 +344,30 @@ public void SaveAsCode(TextWriter writer, RoleMappedSchema schema)

 public abstract void SaveSummary(TextWriter writer, RoleMappedSchema schema);

 public virtual IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
 {
 var cols = new List<IColumn>();

 var names = default(VBuffer<DvText>);
 MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
 var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
 new VectorType(TextType.Instance, Weight.Length), ref names);
 var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
 var colType = new VectorType(NumberType.R4, Weight.Length);

 // Add the bias and the weight columns.
 var bias = Bias;
 cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
 var weights = Weight;
 cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
 return RowColumnUtils.GetRow(null, cols.ToArray());
 }

 public virtual IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 {
 return null;
 }

 public abstract void SaveAsIni(TextWriter writer, RoleMappedSchema schema, ICalibrator calibrator = null);

 public virtual void GetFeatureWeights(ref VBuffer<Float> weights)
Expand All@@ -366,8 +391,7 @@ public ValueMapper<TSrc, VBuffer<Float>> GetWhatTheFeatureMapper<TSrc, TDstContr

 public sealed partial class LinearBinaryPredictor : LinearPredictor,
 ICanGetSummaryInKeyValuePairs,
 IParameterMixer<Float>,
 ICanGetSummaryAsIRow
 IParameterMixer<Float>
 {
 public const string LoaderSignature = "Linear2CExec";
 public const string RegistrationName = "LinearBinaryPredictor";
Expand DownExpand Up@@ -503,26 +527,7 @@ public IList<KeyValuePair<string, object>> GetSummaryInKeyValuePairs(RoleMappedS
 return results;
 }

 public IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
 {
 var cols = new List<IColumn>();

 var names = default(VBuffer<DvText>);
 MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
 var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
 new VectorType(TextType.Instance, Weight.Length), ref names);
 var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
 var colType = new VectorType(NumberType.R4, Weight.Length);

 // Add the bias and the weight columns.
 var bias = Bias;
 cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
 var weights = Weight;
 cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
 return RowColumnUtils.GetRow(null, cols.ToArray());
 }

 public IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 public override IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 {
 if (_stats == null)
 return null;
Expand DownExpand Up@@ -582,8 +587,7 @@ public override void SaveAsIni(TextWriter writer, RoleMappedSchema schema, ICali

 public sealed class LinearRegressionPredictor : RegressionPredictor,
 IParameterMixer<Float>,
 ICanGetSummaryInKeyValuePairs,
 ICanGetSummaryAsIRow
 ICanGetSummaryInKeyValuePairs
 {
 public const string LoaderSignature = "LinearRegressionExec";
 public const string RegistrationName = "LinearRegressionPredictor";
Expand DownExpand Up@@ -663,30 +667,6 @@ public IList<KeyValuePair<string, object>> GetSummaryInKeyValuePairs(RoleMappedS

 return results;
 }

 public IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
 {
 var cols = new List<IColumn>();

 var names = default(VBuffer<DvText>);
 MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
 var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
 new VectorType(TextType.Instance, Weight.Length), ref names);
 var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
 var colType = new VectorType(NumberType.R4, Weight.Length);

 // Add the bias and the weight columns.
 var bias = Bias;
 cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
 var weights = Weight;
 cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
 return RowColumnUtils.GetRow(null, cols.ToArray());
 }

 public IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 {
 return null;
 }
 }

 public sealed class PoissonRegressionPredictor : RegressionPredictor, IParameterMixer<Float>
Expand Down

8 changes: 8 additions & 0 deletions
test/BaselineOutput/Common/EntryPoints/lr-weights.txt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col=Bias:R4:0
#@ col=Weights:R4:1-9
#@ }
Bias	thickness	uniform_size	uniform_shape	adhesion	epit_size	bare_nuclei	bland_chromatin	normal_nucleoli	mitoses
-6.186806	2.65800762	1.68089855	1.944068	1.42514718	0.8536965	2.9325006	1.74816787	1.58165014	0.595681

10 changes: 10 additions & 0 deletions
test/BaselineOutput/Common/EntryPoints/mc-lr-stats.txt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,10 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col={name={Count of training examples} type=I8 src=0}
#@ col={name={Residual Deviance} type=R4 src=1}
#@ col={name={Null Deviance} type=R4 src=2}
#@ col=AIC:R4:3
#@ }
Count of training examples	Residual Deviance	Null Deviance	AIC
683	119.098892	884.3502	159.098892

10 changes: 10 additions & 0 deletions
test/BaselineOutput/Common/EntryPoints/mc-lr-weights.txt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,10 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col=Bias:R4:0
#@ col=Weights:R4:1-9
#@ col=ClassNames:TX:10
#@ }
Bias	thickness	uniform_size	uniform_shape	adhesion	epit_size	bare_nuclei	bland_chromatin	normal_nucleoli	mitoses	ClassNames
3.36404228	-1.579712	-0.8266232	-1.051891	-0.79305464	-0.386733949	-1.59106934	-1.01550019	-0.8356989	-0.332574666	Class_0
-3.36404562	1.57971311	0.826623559	1.051891	0.7930542	0.386735022	1.59107041	1.015499	0.8356983	0.332574	Class_1
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
GetSummaryDataView() implementation for Pca and Linear Predictors#185

New issue

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

 Sign up for GitHub

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

Already on GitHub?
Sign in
to your account

 Merged

TomFinley
merged 19 commits into

from

Jun 8, 2018
 Merged


GetSummaryDataView() implementation for Pca and Linear Predictors
#185
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


19 commits


Select commit
Hold shift + click to select a range
ec890d6

GetSummaryDataView() implementation for Pca and Linear Predictors


ganik May 18, 2018
9394cdd

typo


ganik May 18, 2018
b508e68

Implement ICanGetSummaryAsIRow instead of ICanGetSummaryAsIDataView o…


ganik May 25, 2018
e072546

Merge branch 'master' of https://github.com/ganik/machinelearning


ganik May 25, 2018
ec8200a

Add vector column for top rank eigenvectors


ganik May 27, 2018
cf37f62

remove unnecessary code


ganik May 27, 2018
9943586

remove space


ganik May 27, 2018
45cd5f2

fix build


ganik May 28, 2018
083645f

no need for slot names


ganik May 29, 2018
58d0f31

Merge pull request #1 from dotnet/master


ganik May 30, 2018
c5c0173

Enable back PCA anomaly tests


ganik May 30, 2018
695abc5

fix PCA Anomaly tests baseline


ganik May 30, 2018
eea9c69

fix unit tests for Release


ganik May 30, 2018
637b325

Add PCA azure test data


ganik May 30, 2018
bdec903

Added entrypoint summpary test for LinearPredictor


ganik May 30, 2018
b942537

added PCA summary test


ganik May 30, 2018
678633c

use using() { } on IDisposable


ganik May 31, 2018
3031a4c

remove slot names


ganik Jun 4, 2018
b0c2e49

remove not needed datasets


ganik Jun 5, 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


21 changes: 21 additions & 0 deletions
src/Microsoft.ML.PCA/PcaTrainer.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -310,6 +310,7 @@ public static CommonOutputs.AnomalyDetectionOutput TrainPcaAnomaly(IHostEnvironm
 // REVIEW: move the predictor to a different file and fold EigenUtils.cs to this file.
 public sealed class PcaPredictor : PredictorBase<Float>,
 IValueMapper,
 ICanGetSummaryAsIDataView,
 ICanSaveInTextFormat, ICanSaveModel, ICanSaveSummary
 {
 public const string LoaderSignature = "pcaAnomExec";
Expand DownExpand Up@@ -471,6 +472,26 @@ public void SaveAsText(TextWriter writer, RoleMappedSchema schema)
 }
 }

 public IDataView GetSummaryDataView(RoleMappedSchema schema)
@yaeldekelyaeldekelMay 29, 2018

Copy link


Copy Markdown

Choose a reason for hiding this comment

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

GetSummaryDataView [](start = 25, length = 18)
Could you add a unit test for this?
@ganikganikMay 30, 2018

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

will do
@ganikganikMay 30, 2018

Copy link


Copy Markdown

ContributorAuthor
Choose a reason for hiding this comment

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

added
 {
 var bldr = new ArrayDataViewBuilder(Host);

 var cols = new VBuffer<Float>[_rank + 1];
 var names = new string[_rank + 1];
 for (var i = 0; i < _rank; ++i)
 {
 names[i] = "EigenVector" + i;
 cols[i] = _eigenVectors[i];
 }
 names[_rank] = "MeanVector";
 cols[_rank] = _mean;

 bldr.AddColumn("VectorName", names);
 bldr.AddColumn("VectorData", NumberType.R4, cols);

 return bldr.GetDataView();
 }

 public ColumnType InputType
 {
 get { return _inputType; }
Expand Down

76 changes: 28 additions & 48 deletions
src/Microsoft.ML.StandardLearners/Standard/LinearPredictor.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -44,6 +44,7 @@ public abstract class LinearPredictor : PredictorBase<Float>,
 ICanSaveInTextFormat,
 ICanSaveInSourceCode,
 ICanSaveModel,
 ICanGetSummaryAsIRow,
 ICanSaveSummary,
 IPredictorWithFeatureWeights<Float>,
 IWhatTheFeatureValueMapper,
Expand DownExpand Up@@ -343,6 +344,30 @@ public void SaveAsCode(TextWriter writer, RoleMappedSchema schema)

 public abstract void SaveSummary(TextWriter writer, RoleMappedSchema schema);

 public virtual IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
 {
 var cols = new List<IColumn>();

 var names = default(VBuffer<DvText>);
 MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
 var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
 new VectorType(TextType.Instance, Weight.Length), ref names);
 var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
 var colType = new VectorType(NumberType.R4, Weight.Length);

 // Add the bias and the weight columns.
 var bias = Bias;
 cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
 var weights = Weight;
 cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
 return RowColumnUtils.GetRow(null, cols.ToArray());
 }

 public virtual IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 {
 return null;
 }

 public abstract void SaveAsIni(TextWriter writer, RoleMappedSchema schema, ICalibrator calibrator = null);

 public virtual void GetFeatureWeights(ref VBuffer<Float> weights)
Expand All@@ -366,8 +391,7 @@ public ValueMapper<TSrc, VBuffer<Float>> GetWhatTheFeatureMapper<TSrc, TDstContr

 public sealed partial class LinearBinaryPredictor : LinearPredictor,
 ICanGetSummaryInKeyValuePairs,
 IParameterMixer<Float>,
 ICanGetSummaryAsIRow
 IParameterMixer<Float>
 {
 public const string LoaderSignature = "Linear2CExec";
 public const string RegistrationName = "LinearBinaryPredictor";
Expand DownExpand Up@@ -503,26 +527,7 @@ public IList<KeyValuePair<string, object>> GetSummaryInKeyValuePairs(RoleMappedS
 return results;
 }

 public IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
 {
 var cols = new List<IColumn>();

 var names = default(VBuffer<DvText>);
 MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
 var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
 new VectorType(TextType.Instance, Weight.Length), ref names);
 var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
 var colType = new VectorType(NumberType.R4, Weight.Length);

 // Add the bias and the weight columns.
 var bias = Bias;
 cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
 var weights = Weight;
 cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
 return RowColumnUtils.GetRow(null, cols.ToArray());
 }

 public IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 public override IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 {
 if (_stats == null)
 return null;
Expand DownExpand Up@@ -582,8 +587,7 @@ public override void SaveAsIni(TextWriter writer, RoleMappedSchema schema, ICali

 public sealed class LinearRegressionPredictor : RegressionPredictor,
 IParameterMixer<Float>,
 ICanGetSummaryInKeyValuePairs,
 ICanGetSummaryAsIRow
 ICanGetSummaryInKeyValuePairs
 {
 public const string LoaderSignature = "LinearRegressionExec";
 public const string RegistrationName = "LinearRegressionPredictor";
Expand DownExpand Up@@ -663,30 +667,6 @@ public IList<KeyValuePair<string, object>> GetSummaryInKeyValuePairs(RoleMappedS

 return results;
 }

 public IRow GetSummaryIRowOrNull(RoleMappedSchema schema)
 {
 var cols = new List<IColumn>();

 var names = default(VBuffer<DvText>);
 MetadataUtils.GetSlotNames(schema, RoleMappedSchema.ColumnRole.Feature, Weight.Length, ref names);
 var slotNamesCol = RowColumnUtils.GetColumn(MetadataUtils.Kinds.SlotNames,
 new VectorType(TextType.Instance, Weight.Length), ref names);
 var slotNamesRow = RowColumnUtils.GetRow(null, slotNamesCol);
 var colType = new VectorType(NumberType.R4, Weight.Length);

 // Add the bias and the weight columns.
 var bias = Bias;
 cols.Add(RowColumnUtils.GetColumn("Bias", NumberType.R4, ref bias));
 var weights = Weight;
 cols.Add(RowColumnUtils.GetColumn("Weights", colType, ref weights, slotNamesRow));
 return RowColumnUtils.GetRow(null, cols.ToArray());
 }

 public IRow GetStatsIRowOrNull(RoleMappedSchema schema)
 {
 return null;
 }
 }

 public sealed class PoissonRegressionPredictor : RegressionPredictor, IParameterMixer<Float>
Expand Down

8 changes: 8 additions & 0 deletions
test/BaselineOutput/Common/EntryPoints/lr-weights.txt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col=Bias:R4:0
#@ col=Weights:R4:1-9
#@ }
Bias	thickness	uniform_size	uniform_shape	adhesion	epit_size	bare_nuclei	bland_chromatin	normal_nucleoli	mitoses
-6.186806	2.65800762	1.68089855	1.944068	1.42514718	0.8536965	2.9325006	1.74816787	1.58165014	0.595681

10 changes: 10 additions & 0 deletions
test/BaselineOutput/Common/EntryPoints/mc-lr-stats.txt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,10 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col={name={Count of training examples} type=I8 src=0}
#@ col={name={Residual Deviance} type=R4 src=1}
#@ col={name={Null Deviance} type=R4 src=2}
#@ col=AIC:R4:3
#@ }
Count of training examples	Residual Deviance	Null Deviance	AIC
683	119.098892	884.3502	159.098892

10 changes: 10 additions & 0 deletions
test/BaselineOutput/Common/EntryPoints/mc-lr-weights.txt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,10 @@
#@ TextLoader{
#@ header+
#@ sep=tab
#@ col=Bias:R4:0
#@ col=Weights:R4:1-9
#@ col=ClassNames:TX:10
#@ }
Bias	thickness	uniform_size	uniform_shape	adhesion	epit_size	bare_nuclei	bland_chromatin	normal_nucleoli	mitoses	ClassNames
3.36404228	-1.579712	-0.8266232	-1.051891	-0.79305464	-0.386733949	-1.59106934	-1.01550019	-0.8356989	-0.332574666	Class_0
-3.36404562	1.57971311	0.826623559	1.051891	0.7930542	0.386735022	1.59107041	1.015499	0.8356983	0.332574	Class_1
Loading