Added tests for new API where components(Loaders/Transforms/Learners) are directly instantiated.#468

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
zeahmed merged 2 commits into from
Jul 2, 2018
Merged

Added tests for new API where components(Loaders/Transforms/Learners) are directly instantiated. #468

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d8d4c2e
Added tests for new API where components(Loaders/Transforms/Learners)…
zeahmed Jul 2, 2018
0bfe5c3
Moved new tests to separate folder.
zeahmed Jul 2, 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
210 changes: 210 additions & 0 deletions test/Microsoft.ML.Tests/ScenariosWithDirectInstantiation/IrisPlantClassificationTests.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,210 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

using Microsoft.ML.Models;
using Microsoft.ML.Runtime;
using Microsoft.ML.Runtime.Api;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.Learners;
using Microsoft.ML.Runtime.Model;
using System;
using System.IO;
using Xunit;

namespace Microsoft.ML.Scenarios
{
public partial class ScenariosTests
{
[Fact]
public void TrainAndPredictIrisModelUsingDirectInstantiationTest()
{
string dataPath = GetDataPath("iris.txt");
string testDataPath = dataPath;

using (var env = new TlcEnvironment(seed: 1, conc: 1))
{
// Pipeline
var loader = new TextLoader(env,
new TextLoader.Arguments()
{
HasHeader = false,
Column = new[] {
new TextLoader.Column()
{
Name = "Label",
Source = new [] { new TextLoader.Range() { Min = 0, Max = 0} },
Type = DataKind.R4
},
new TextLoader.Column()
{
Name = "SepalLength",
Source = new [] { new TextLoader.Range() { Min = 1, Max = 1} },
Type = DataKind.R4
},
new TextLoader.Column()
{
Name = "SepalWidth",
Source = new [] { new TextLoader.Range() { Min = 2, Max = 2} },
Type = DataKind.R4
},
new TextLoader.Column()
{
Name = "PetalLength",
Source = new [] { new TextLoader.Range() { Min = 3, Max = 3} },
Type = DataKind.R4
},
new TextLoader.Column()
{
Name = "PetalWidth",
Source = new [] { new TextLoader.Range() { Min = 4, Max = 4} },
Type = DataKind.R4
}
}
}, new MultiFileSource(dataPath));

IDataTransform trans = new ConcatTransform(env, loader, "Features",
"SepalLength", "SepalWidth", "PetalLength", "PetalWidth");

// Normalizer is not automatically added though the trainer has 'NormalizeFeatures' On/Auto
trans = NormalizeTransform.CreateMinMaxNormalizer(env, trans, "Features");

// Train
var trainer = new SdcaMultiClassTrainer(env, new SdcaMultiClassTrainer.Arguments());

// Explicity adding CacheDataView since caching is not working though trainer has 'Caching' On/Auto
var cached = new CacheDataView(env, trans, prefetch: null);
var trainRoles = TrainUtils.CreateExamples(cached, label: "Label", feature: "Features");
trainer.Train(trainRoles);

// Get scorer and evaluate the predictions from test data
var pred = trainer.CreatePredictor();
IDataScorerTransform testDataScorer = GetScorer(env, trans, pred, testDataPath);
var metrics = Evaluate(env, testDataScorer);
CompareMatrics(metrics);

// Create prediction engine and test predictions
var model = env.CreatePredictionEngine<IrisData, IrisPrediction>(testDataScorer);
ComparePredictions(model);

// Get feature importance i.e. weight vector
var summary = ((MulticlassLogisticRegressionPredictor)pred).GetSummaryInKeyValuePairs(trainRoles.Schema);
Assert.Equal(7.757867, Convert.ToDouble(summary[0].Value), 5);
}
}

private void ComparePredictions(PredictionEngine<IrisData, IrisPrediction> model)
{
IrisPrediction prediction = model.Predict(new IrisData()
{
SepalLength = 3.3f,
SepalWidth = 1.6f,
PetalLength = 0.2f,
PetalWidth = 5.1f,
});

Assert.Equal(1, prediction.PredictedLabels[0], 2);
Assert.Equal(0, prediction.PredictedLabels[1], 2);
Assert.Equal(0, prediction.PredictedLabels[2], 2);

prediction = model.Predict(new IrisData()
{
SepalLength = 3.1f,
SepalWidth = 5.5f,
PetalLength = 2.2f,
PetalWidth = 6.4f,
});

Assert.Equal(0, prediction.PredictedLabels[0], 2);
Assert.Equal(0, prediction.PredictedLabels[1], 2);
Assert.Equal(1, prediction.PredictedLabels[2], 2);

prediction = model.Predict(new IrisData()
{
SepalLength = 3.1f,
SepalWidth = 2.5f,
PetalLength = 1.2f,
PetalWidth = 4.4f,
});

Assert.Equal(.2, prediction.PredictedLabels[0], 1);
Assert.Equal(.8, prediction.PredictedLabels[1], 1);
Assert.Equal(0, prediction.PredictedLabels[2], 2);
}

private void CompareMatrics(ClassificationMetrics metrics)
{
Assert.Equal(.98, metrics.AccuracyMacro);
Assert.Equal(.98, metrics.AccuracyMicro, 2);
Assert.Equal(.06, metrics.LogLoss, 2);
Assert.InRange(metrics.LogLossReduction, 94, 96);
Assert.Equal(1, metrics.TopKAccuracy);

Assert.Equal(3, metrics.PerClassLogLoss.Length);
Assert.Equal(0, metrics.PerClassLogLoss[0], 1);
Assert.Equal(.1, metrics.PerClassLogLoss[1], 1);
Assert.Equal(.1, metrics.PerClassLogLoss[2], 1);

ConfusionMatrix matrix = metrics.ConfusionMatrix;
Assert.Equal(3, matrix.Order);
Assert.Equal(3, matrix.ClassNames.Count);
Assert.Equal("0", matrix.ClassNames[0]);
Assert.Equal("1", matrix.ClassNames[1]);
Assert.Equal("2", matrix.ClassNames[2]);

Assert.Equal(50, matrix[0, 0]);
Assert.Equal(50, matrix["0", "0"]);
Assert.Equal(0, matrix[0, 1]);
Assert.Equal(0, matrix["0", "1"]);
Assert.Equal(0, matrix[0, 2]);
Assert.Equal(0, matrix["0", "2"]);

Assert.Equal(0, matrix[1, 0]);
Assert.Equal(0, matrix["1", "0"]);
Assert.Equal(48, matrix[1, 1]);
Assert.Equal(48, matrix["1", "1"]);
Assert.Equal(2, matrix[1, 2]);
Assert.Equal(2, matrix["1", "2"]);

Assert.Equal(0, matrix[2, 0]);
Assert.Equal(0, matrix["2", "0"]);
Assert.Equal(1, matrix[2, 1]);
Assert.Equal(1, matrix["2", "1"]);
Assert.Equal(49, matrix[2, 2]);
Assert.Equal(49, matrix["2", "2"]);
}

private ClassificationMetrics Evaluate(IHostEnvironment env, IDataView scoredData)
{
var dataEval = TrainUtils.CreateExamplesOpt(scoredData, label: "Label", feature: "Features");

// Evaluate.
// It does not work. It throws error "Failed to find 'Score' column" when Evaluate is called
//var evaluator = new MultiClassClassifierEvaluator(env, new MultiClassClassifierEvaluator.Arguments() { OutputTopKAcc = 3 });

var evaluator = new MultiClassMamlEvaluator(env, new MultiClassMamlEvaluator.Arguments() { OutputTopKAcc = 3 });
var metricsDic = evaluator.Evaluate(dataEval);

return ClassificationMetrics.FromMetrics(env, metricsDic["OverallMetrics"], metricsDic["ConfusionMatrix"])[0];
}

private IDataScorerTransform GetScorer(IHostEnvironment env, IDataView transforms, IPredictor pred, string testDataPath = null)
{
using (var ch = env.Start("Saving model"))
using (var memoryStream = new MemoryStream())
{
var trainRoles = TrainUtils.CreateExamples(transforms, label: "Label", feature: "Features");

// Model cannot be saved with CacheDataView
TrainUtils.SaveModel(env, ch, memoryStream, pred, trainRoles);
memoryStream.Position = 0;
using (var rep = RepositoryReader.Open(memoryStream, ch))
{
IDataLoader testPipe = ModelFileUtils.LoadLoader(env, rep, new MultiFileSource(testDataPath), true);
RoleMappedData testRoles = TrainUtils.CreateExamples(testPipe, label: "Label", feature: "Features");
return ScoreUtils.GetScorer(pred, testRoles, env, testRoles.Schema);
}
}
}
}
}
118 changes: 118 additions & 0 deletions test/Microsoft.ML.Tests/ScenariosWithDirectInstantiation/SentimentPredictionTests.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,118 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

using Microsoft.ML.Models;
using Microsoft.ML.Runtime;
using Microsoft.ML.Runtime.Api;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.FastTree;
using Microsoft.ML.Runtime.Internal.Calibration;
using Microsoft.ML.Runtime.Model;
using Microsoft.ML.Trainers;
using Microsoft.ML.Transforms;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using Xunit;

namespace Microsoft.ML.Scenarios
{
public partial class ScenariosTests
{
[Fact]
public void TrainAndPredictSentimentModelWithDirectionInstantiationTest()
{
var dataPath = GetDataPath(SentimentDataPath);
var testDataPath = GetDataPath(SentimentTestPath);

using (var env = new TlcEnvironment(seed: 1, conc: 1))
{
// Pipeline
var loader = new TextLoader(env,
new TextLoader.Arguments()
{
Separator = "tab",
HasHeader = true,
Column = new[]
{
new TextLoader.Column()
{
Name = "Label",
Source = new [] { new TextLoader.Range() { Min=0, Max=0} },
Type = DataKind.Num
},

new TextLoader.Column()
{
Name = "SentimentText",
Source = new [] { new TextLoader.Range() { Min=1, Max=1} },
Type = DataKind.Text
}
}
}, new MultiFileSource(dataPath));

var trans = TextTransform.Create(env, new TextTransform.Arguments()
{
Column = new TextTransform.Column
{
Name = "Features",
Source = new[] { "SentimentText" }
},
KeepDiacritics = false,
KeepPunctuations = false,
TextCase = Runtime.TextAnalytics.TextNormalizerTransform.CaseNormalizationMode.Lower,
OutputTokens = true,
StopWordsRemover = new Runtime.TextAnalytics.PredefinedStopWordsRemoverFactory(),
VectorNormalizer = TextTransform.TextNormKind.L2,
CharFeatureExtractor = new NgramExtractorTransform.NgramExtractorArguments() { NgramLength = 3, AllLengths = false },
WordFeatureExtractor = new NgramExtractorTransform.NgramExtractorArguments() { NgramLength = 2, AllLengths = true },
},
loader);

// Train
var trainer = new FastTreeBinaryClassificationTrainer(env, new FastTreeBinaryClassificationTrainer.Arguments()
{
NumLeaves = 5,
NumTrees = 5,
MinDocumentsInLeafs = 2
});

var trainRoles = TrainUtils.CreateExamples(trans, label: "Label", feature: "Features");
trainer.Train(trainRoles);

// Get scorer and evaluate the predictions from test data
var pred = trainer.CreatePredictor();
IDataScorerTransform testDataScorer = GetScorer(env, trans, pred, testDataPath);
var metrics = EvaluateBinary(env, testDataScorer);
ValidateBinaryMetrics(metrics);

// Create prediction engine and test predictions
var model = env.CreateBatchPredictionEngine<SentimentData, SentimentPrediction>(testDataScorer);
var sentiments = GetTestData();
var predictions = model.Predict(sentiments, false);
Assert.Equal(2, predictions.Count());
Assert.True(predictions.ElementAt(0).Sentiment.IsFalse);
Assert.True(predictions.ElementAt(1).Sentiment.IsTrue);

// Get feature importance based on feature gain during training
var summary = ((FeatureWeightsCalibratedPredictor)pred).GetSummaryInKeyValuePairs(trainRoles.Schema);
Assert.Equal(1.0, (double)summary[0].Value, 1);
}
}

private BinaryClassificationMetrics EvaluateBinary(IHostEnvironment env, IDataView scoredData)
{
var dataEval = TrainUtils.CreateExamplesOpt(scoredData, label: "Label", feature: "Features");

// Evaluate.
// It does not work. It throws error "Failed to find 'Score' column" when Evaluate is called
//var evaluator = new BinaryClassifierEvaluator(env, new BinaryClassifierEvaluator.Arguments());

var evaluator = new BinaryClassifierMamlEvaluator(env, new BinaryClassifierMamlEvaluator.Arguments());
var metricsDic = evaluator.Evaluate(dataEval);

return BinaryClassificationMetrics.FromMetrics(env, metricsDic["OverallMetrics"], metricsDic["ConfusionMatrix"])[0];
}
}
}
, '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
Added tests for new API where components(Loaders/Transforms/Learners) are directly instantiated.#468

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

zeahmed
merged 2 commits into

from

Jul 2, 2018
 Merged


Added tests for new API where components(Loaders/Transforms/Learners) are directly instantiated.
#468
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
d8d4c2e

Added tests for new API where components(Loaders/Transforms/Learners)…


zeahmed Jul 2, 2018
0bfe5c3

Moved new tests to separate folder.


zeahmed Jul 2, 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


210 changes: 210 additions & 0 deletions
test/Microsoft.ML.Tests/ScenariosWithDirectInstantiation/IrisPlantClassificationTests.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,210 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

using Microsoft.ML.Models;
using Microsoft.ML.Runtime;
using Microsoft.ML.Runtime.Api;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.Learners;
using Microsoft.ML.Runtime.Model;
using System;
using System.IO;
using Xunit;

namespace Microsoft.ML.Scenarios
{
 public partial class ScenariosTests
 {
 [Fact]
 public void TrainAndPredictIrisModelUsingDirectInstantiationTest()
 {
 string dataPath = GetDataPath("iris.txt");
 string testDataPath = dataPath;

 using (var env = new TlcEnvironment(seed: 1, conc: 1))
 {
 // Pipeline
 var loader = new TextLoader(env,
 new TextLoader.Arguments()
 {
 HasHeader = false,
 Column = new[] {
 new TextLoader.Column()
 {
 Name = "Label",
 Source = new [] { new TextLoader.Range() { Min = 0, Max = 0} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "SepalLength",
 Source = new [] { new TextLoader.Range() { Min = 1, Max = 1} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "SepalWidth",
 Source = new [] { new TextLoader.Range() { Min = 2, Max = 2} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "PetalLength",
 Source = new [] { new TextLoader.Range() { Min = 3, Max = 3} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "PetalWidth",
 Source = new [] { new TextLoader.Range() { Min = 4, Max = 4} },
 Type = DataKind.R4
 }
 }
 }, new MultiFileSource(dataPath));

 IDataTransform trans = new ConcatTransform(env, loader, "Features",
 "SepalLength", "SepalWidth", "PetalLength", "PetalWidth");

 // Normalizer is not automatically added though the trainer has 'NormalizeFeatures' On/Auto
 trans = NormalizeTransform.CreateMinMaxNormalizer(env, trans, "Features");

 // Train
 var trainer = new SdcaMultiClassTrainer(env, new SdcaMultiClassTrainer.Arguments());

 // Explicity adding CacheDataView since caching is not working though trainer has 'Caching' On/Auto
 var cached = new CacheDataView(env, trans, prefetch: null);
 var trainRoles = TrainUtils.CreateExamples(cached, label: "Label", feature: "Features");
 trainer.Train(trainRoles);

 // Get scorer and evaluate the predictions from test data
 var pred = trainer.CreatePredictor();
 IDataScorerTransform testDataScorer = GetScorer(env, trans, pred, testDataPath);
 var metrics = Evaluate(env, testDataScorer);
 CompareMatrics(metrics);

 // Create prediction engine and test predictions
 var model = env.CreatePredictionEngine<IrisData, IrisPrediction>(testDataScorer);
 ComparePredictions(model);

 // Get feature importance i.e. weight vector
 var summary = ((MulticlassLogisticRegressionPredictor)pred).GetSummaryInKeyValuePairs(trainRoles.Schema);
 Assert.Equal(7.757867, Convert.ToDouble(summary[0].Value), 5);
 }
 }

 private void ComparePredictions(PredictionEngine<IrisData, IrisPrediction> model)
 {
 IrisPrediction prediction = model.Predict(new IrisData()
 {
 SepalLength = 3.3f,
 SepalWidth = 1.6f,
 PetalLength = 0.2f,
 PetalWidth = 5.1f,
 });

 Assert.Equal(1, prediction.PredictedLabels[0], 2);
 Assert.Equal(0, prediction.PredictedLabels[1], 2);
 Assert.Equal(0, prediction.PredictedLabels[2], 2);

 prediction = model.Predict(new IrisData()
 {
 SepalLength = 3.1f,
 SepalWidth = 5.5f,
 PetalLength = 2.2f,
 PetalWidth = 6.4f,
 });

 Assert.Equal(0, prediction.PredictedLabels[0], 2);
 Assert.Equal(0, prediction.PredictedLabels[1], 2);
 Assert.Equal(1, prediction.PredictedLabels[2], 2);

 prediction = model.Predict(new IrisData()
 {
 SepalLength = 3.1f,
 SepalWidth = 2.5f,
 PetalLength = 1.2f,
 PetalWidth = 4.4f,
 });

 Assert.Equal(.2, prediction.PredictedLabels[0], 1);
 Assert.Equal(.8, prediction.PredictedLabels[1], 1);
 Assert.Equal(0, prediction.PredictedLabels[2], 2);
 }

 private void CompareMatrics(ClassificationMetrics metrics)
 {
 Assert.Equal(.98, metrics.AccuracyMacro);
 Assert.Equal(.98, metrics.AccuracyMicro, 2);
 Assert.Equal(.06, metrics.LogLoss, 2);
 Assert.InRange(metrics.LogLossReduction, 94, 96);
 Assert.Equal(1, metrics.TopKAccuracy);

 Assert.Equal(3, metrics.PerClassLogLoss.Length);
 Assert.Equal(0, metrics.PerClassLogLoss[0], 1);
 Assert.Equal(.1, metrics.PerClassLogLoss[1], 1);
 Assert.Equal(.1, metrics.PerClassLogLoss[2], 1);

 ConfusionMatrix matrix = metrics.ConfusionMatrix;
 Assert.Equal(3, matrix.Order);
 Assert.Equal(3, matrix.ClassNames.Count);
 Assert.Equal("0", matrix.ClassNames[0]);
 Assert.Equal("1", matrix.ClassNames[1]);
 Assert.Equal("2", matrix.ClassNames[2]);

 Assert.Equal(50, matrix[0, 0]);
 Assert.Equal(50, matrix["0", "0"]);
 Assert.Equal(0, matrix[0, 1]);
 Assert.Equal(0, matrix["0", "1"]);
 Assert.Equal(0, matrix[0, 2]);
 Assert.Equal(0, matrix["0", "2"]);

 Assert.Equal(0, matrix[1, 0]);
 Assert.Equal(0, matrix["1", "0"]);
 Assert.Equal(48, matrix[1, 1]);
 Assert.Equal(48, matrix["1", "1"]);
 Assert.Equal(2, matrix[1, 2]);
 Assert.Equal(2, matrix["1", "2"]);

 Assert.Equal(0, matrix[2, 0]);
 Assert.Equal(0, matrix["2", "0"]);
 Assert.Equal(1, matrix[2, 1]);
 Assert.Equal(1, matrix["2", "1"]);
 Assert.Equal(49, matrix[2, 2]);
 Assert.Equal(49, matrix["2", "2"]);
 }

 private ClassificationMetrics Evaluate(IHostEnvironment env, IDataView scoredData)
 {
 var dataEval = TrainUtils.CreateExamplesOpt(scoredData, label: "Label", feature: "Features");

 // Evaluate.
 // It does not work. It throws error "Failed to find 'Score' column" when Evaluate is called
 //var evaluator = new MultiClassClassifierEvaluator(env, new MultiClassClassifierEvaluator.Arguments() { OutputTopKAcc = 3 });

 var evaluator = new MultiClassMamlEvaluator(env, new MultiClassMamlEvaluator.Arguments() { OutputTopKAcc = 3 });
 var metricsDic = evaluator.Evaluate(dataEval);

 return ClassificationMetrics.FromMetrics(env, metricsDic["OverallMetrics"], metricsDic["ConfusionMatrix"])[0];
 }

 private IDataScorerTransform GetScorer(IHostEnvironment env, IDataView transforms, IPredictor pred, string testDataPath = null)
 {
 using (var ch = env.Start("Saving model"))
 using (var memoryStream = new MemoryStream())
 {
 var trainRoles = TrainUtils.CreateExamples(transforms, label: "Label", feature: "Features");

 // Model cannot be saved with CacheDataView
 TrainUtils.SaveModel(env, ch, memoryStream, pred, trainRoles);
 memoryStream.Position = 0;
 using (var rep = RepositoryReader.Open(memoryStream, ch))
 {
 IDataLoader testPipe = ModelFileUtils.LoadLoader(env, rep, new MultiFileSource(testDataPath), true);
 RoleMappedData testRoles = TrainUtils.CreateExamples(testPipe, label: "Label", feature: "Features");
 return ScoreUtils.GetScorer(pred, testRoles, env, testRoles.Schema);
 }
 }
 }
 }
}

118 changes: 118 additions & 0 deletions
test/Microsoft.ML.Tests/ScenariosWithDirectInstantiation/SentimentPredictionTests.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,118 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

using Microsoft.ML.Models;
using Microsoft.ML.Runtime;
using Microsoft.ML.Runtime.Api;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.FastTree;
using Microsoft.ML.Runtime.Internal.Calibration;
using Microsoft.ML.Runtime.Model;
using Microsoft.ML.Trainers;
using Microsoft.ML.Transforms;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using Xunit;

namespace Microsoft.ML.Scenarios
{
 public partial class ScenariosTests
 {
 [Fact]
 public void TrainAndPredictSentimentModelWithDirectionInstantiationTest()
 {
 var dataPath = GetDataPath(SentimentDataPath);
 var testDataPath = GetDataPath(SentimentTestPath);

 using (var env = new TlcEnvironment(seed: 1, conc: 1))
 {
 // Pipeline
 var loader = new TextLoader(env,
 new TextLoader.Arguments()
 {
 Separator = "tab",
 HasHeader = true,
 Column = new[]
 {
 new TextLoader.Column()
 {
 Name = "Label",
 Source = new [] { new TextLoader.Range() { Min=0, Max=0} },
 Type = DataKind.Num
 },

 new TextLoader.Column()
 {
 Name = "SentimentText",
 Source = new [] { new TextLoader.Range() { Min=1, Max=1} },
 Type = DataKind.Text
 }
 }
 }, new MultiFileSource(dataPath));

 var trans = TextTransform.Create(env, new TextTransform.Arguments()
 {
 Column = new TextTransform.Column
 {
 Name = "Features",
 Source = new[] { "SentimentText" }
 },
 KeepDiacritics = false,
 KeepPunctuations = false,
 TextCase = Runtime.TextAnalytics.TextNormalizerTransform.CaseNormalizationMode.Lower,
 OutputTokens = true,
 StopWordsRemover = new Runtime.TextAnalytics.PredefinedStopWordsRemoverFactory(),
 VectorNormalizer = TextTransform.TextNormKind.L2,
 CharFeatureExtractor = new NgramExtractorTransform.NgramExtractorArguments() { NgramLength = 3, AllLengths = false },
 WordFeatureExtractor = new NgramExtractorTransform.NgramExtractorArguments() { NgramLength = 2, AllLengths = true },
 },
 loader);

 // Train
 var trainer = new FastTreeBinaryClassificationTrainer(env, new FastTreeBinaryClassificationTrainer.Arguments()
 {
 NumLeaves = 5,
 NumTrees = 5,
 MinDocumentsInLeafs = 2
 });

 var trainRoles = TrainUtils.CreateExamples(trans, label: "Label", feature: "Features");
 trainer.Train(trainRoles);

 // Get scorer and evaluate the predictions from test data
 var pred = trainer.CreatePredictor();
 IDataScorerTransform testDataScorer = GetScorer(env, trans, pred, testDataPath);
 var metrics = EvaluateBinary(env, testDataScorer);
 ValidateBinaryMetrics(metrics);

 // Create prediction engine and test predictions
 var model = env.CreateBatchPredictionEngine<SentimentData, SentimentPrediction>(testDataScorer);
 var sentiments = GetTestData();
 var predictions = model.Predict(sentiments, false);
 Assert.Equal(2, predictions.Count());
 Assert.True(predictions.ElementAt(0).Sentiment.IsFalse);
 Assert.True(predictions.ElementAt(1).Sentiment.IsTrue);

 // Get feature importance based on feature gain during training
 var summary = ((FeatureWeightsCalibratedPredictor)pred).GetSummaryInKeyValuePairs(trainRoles.Schema);
 Assert.Equal(1.0, (double)summary[0].Value, 1);
 }
 }

 private BinaryClassificationMetrics EvaluateBinary(IHostEnvironment env, IDataView scoredData)
 {
 var dataEval = TrainUtils.CreateExamplesOpt(scoredData, label: "Label", feature: "Features");

 // Evaluate.
 // It does not work. It throws error "Failed to find 'Score' column" when Evaluate is called
 //var evaluator = new BinaryClassifierEvaluator(env, new BinaryClassifierEvaluator.Arguments());

 var evaluator = new BinaryClassifierMamlEvaluator(env, new BinaryClassifierMamlEvaluator.Arguments());
 var metricsDic = evaluator.Evaluate(dataEval);

 return BinaryClassificationMetrics.FromMetrics(env, metricsDic["OverallMetrics"], metricsDic["ConfusionMatrix"])[0];
 }
 }
}

, '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
Added tests for new API where components(Loaders/Transforms/Learners) are directly instantiated.#468

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

zeahmed
merged 2 commits into

from

Jul 2, 2018
 Merged


Added tests for new API where components(Loaders/Transforms/Learners) are directly instantiated.
#468
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
d8d4c2e

Added tests for new API where components(Loaders/Transforms/Learners)…


zeahmed Jul 2, 2018
0bfe5c3

Moved new tests to separate folder.


zeahmed Jul 2, 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


210 changes: 210 additions & 0 deletions
test/Microsoft.ML.Tests/ScenariosWithDirectInstantiation/IrisPlantClassificationTests.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,210 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

using Microsoft.ML.Models;
using Microsoft.ML.Runtime;
using Microsoft.ML.Runtime.Api;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.Learners;
using Microsoft.ML.Runtime.Model;
using System;
using System.IO;
using Xunit;

namespace Microsoft.ML.Scenarios
{
 public partial class ScenariosTests
 {
 [Fact]
 public void TrainAndPredictIrisModelUsingDirectInstantiationTest()
 {
 string dataPath = GetDataPath("iris.txt");
 string testDataPath = dataPath;

 using (var env = new TlcEnvironment(seed: 1, conc: 1))
 {
 // Pipeline
 var loader = new TextLoader(env,
 new TextLoader.Arguments()
 {
 HasHeader = false,
 Column = new[] {
 new TextLoader.Column()
 {
 Name = "Label",
 Source = new [] { new TextLoader.Range() { Min = 0, Max = 0} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "SepalLength",
 Source = new [] { new TextLoader.Range() { Min = 1, Max = 1} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "SepalWidth",
 Source = new [] { new TextLoader.Range() { Min = 2, Max = 2} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "PetalLength",
 Source = new [] { new TextLoader.Range() { Min = 3, Max = 3} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "PetalWidth",
 Source = new [] { new TextLoader.Range() { Min = 4, Max = 4} },
 Type = DataKind.R4
 }
 }
 }, new MultiFileSource(dataPath));

 IDataTransform trans = new ConcatTransform(env, loader, "Features",
 "SepalLength", "SepalWidth", "PetalLength", "PetalWidth");

 // Normalizer is not automatically added though the trainer has 'NormalizeFeatures' On/Auto
 trans = NormalizeTransform.CreateMinMaxNormalizer(env, trans, "Features");

 // Train
 var trainer = new SdcaMultiClassTrainer(env, new SdcaMultiClassTrainer.Arguments());

 // Explicity adding CacheDataView since caching is not working though trainer has 'Caching' On/Auto
 var cached = new CacheDataView(env, trans, prefetch: null);
 var trainRoles = TrainUtils.CreateExamples(cached, label: "Label", feature: "Features");
 trainer.Train(trainRoles);

 // Get scorer and evaluate the predictions from test data
 var pred = trainer.CreatePredictor();
 IDataScorerTransform testDataScorer = GetScorer(env, trans, pred, testDataPath);
 var metrics = Evaluate(env, testDataScorer);
 CompareMatrics(metrics);

 // Create prediction engine and test predictions
 var model = env.CreatePredictionEngine<IrisData, IrisPrediction>(testDataScorer);
 ComparePredictions(model);

 // Get feature importance i.e. weight vector
 var summary = ((MulticlassLogisticRegressionPredictor)pred).GetSummaryInKeyValuePairs(trainRoles.Schema);
 Assert.Equal(7.757867, Convert.ToDouble(summary[0].Value), 5);
 }
 }

 private void ComparePredictions(PredictionEngine<IrisData, IrisPrediction> model)
 {
 IrisPrediction prediction = model.Predict(new IrisData()
 {
 SepalLength = 3.3f,
 SepalWidth = 1.6f,
 PetalLength = 0.2f,
 PetalWidth = 5.1f,
 });

 Assert.Equal(1, prediction.PredictedLabels[0], 2);
 Assert.Equal(0, prediction.PredictedLabels[1], 2);
 Assert.Equal(0, prediction.PredictedLabels[2], 2);

 prediction = model.Predict(new IrisData()
 {
 SepalLength = 3.1f,
 SepalWidth = 5.5f,
 PetalLength = 2.2f,
 PetalWidth = 6.4f,
 });

 Assert.Equal(0, prediction.PredictedLabels[0], 2);
 Assert.Equal(0, prediction.PredictedLabels[1], 2);
 Assert.Equal(1, prediction.PredictedLabels[2], 2);

 prediction = model.Predict(new IrisData()
 {
 SepalLength = 3.1f,
 SepalWidth = 2.5f,
 PetalLength = 1.2f,
 PetalWidth = 4.4f,
 });

 Assert.Equal(.2, prediction.PredictedLabels[0], 1);
 Assert.Equal(.8, prediction.PredictedLabels[1], 1);
 Assert.Equal(0, prediction.PredictedLabels[2], 2);
 }

 private void CompareMatrics(ClassificationMetrics metrics)
 {
 Assert.Equal(.98, metrics.AccuracyMacro);
 Assert.Equal(.98, metrics.AccuracyMicro, 2);
 Assert.Equal(.06, metrics.LogLoss, 2);
 Assert.InRange(metrics.LogLossReduction, 94, 96);
 Assert.Equal(1, metrics.TopKAccuracy);

 Assert.Equal(3, metrics.PerClassLogLoss.Length);
 Assert.Equal(0, metrics.PerClassLogLoss[0], 1);
 Assert.Equal(.1, metrics.PerClassLogLoss[1], 1);
 Assert.Equal(.1, metrics.PerClassLogLoss[2], 1);

 ConfusionMatrix matrix = metrics.ConfusionMatrix;
 Assert.Equal(3, matrix.Order);
 Assert.Equal(3, matrix.ClassNames.Count);
 Assert.Equal("0", matrix.ClassNames[0]);
 Assert.Equal("1", matrix.ClassNames[1]);
 Assert.Equal("2", matrix.ClassNames[2]);

 Assert.Equal(50, matrix[0, 0]);
 Assert.Equal(50, matrix["0", "0"]);
 Assert.Equal(0, matrix[0, 1]);
 Assert.Equal(0, matrix["0", "1"]);
 Assert.Equal(0, matrix[0, 2]);
 Assert.Equal(0, matrix["0", "2"]);

 Assert.Equal(0, matrix[1, 0]);
 Assert.Equal(0, matrix["1", "0"]);
 Assert.Equal(48, matrix[1, 1]);
 Assert.Equal(48, matrix["1", "1"]);
 Assert.Equal(2, matrix[1, 2]);
 Assert.Equal(2, matrix["1", "2"]);

 Assert.Equal(0, matrix[2, 0]);
 Assert.Equal(0, matrix["2", "0"]);
 Assert.Equal(1, matrix[2, 1]);
 Assert.Equal(1, matrix["2", "1"]);
 Assert.Equal(49, matrix[2, 2]);
 Assert.Equal(49, matrix["2", "2"]);
 }

 private ClassificationMetrics Evaluate(IHostEnvironment env, IDataView scoredData)
 {
 var dataEval = TrainUtils.CreateExamplesOpt(scoredData, label: "Label", feature: "Features");

 // Evaluate.
 // It does not work. It throws error "Failed to find 'Score' column" when Evaluate is called
 //var evaluator = new MultiClassClassifierEvaluator(env, new MultiClassClassifierEvaluator.Arguments() { OutputTopKAcc = 3 });

 var evaluator = new MultiClassMamlEvaluator(env, new MultiClassMamlEvaluator.Arguments() { OutputTopKAcc = 3 });
 var metricsDic = evaluator.Evaluate(dataEval);

 return ClassificationMetrics.FromMetrics(env, metricsDic["OverallMetrics"], metricsDic["ConfusionMatrix"])[0];
 }

 private IDataScorerTransform GetScorer(IHostEnvironment env, IDataView transforms, IPredictor pred, string testDataPath = null)
 {
 using (var ch = env.Start("Saving model"))
 using (var memoryStream = new MemoryStream())
 {
 var trainRoles = TrainUtils.CreateExamples(transforms, label: "Label", feature: "Features");

 // Model cannot be saved with CacheDataView
 TrainUtils.SaveModel(env, ch, memoryStream, pred, trainRoles);
 memoryStream.Position = 0;
 using (var rep = RepositoryReader.Open(memoryStream, ch))
 {
 IDataLoader testPipe = ModelFileUtils.LoadLoader(env, rep, new MultiFileSource(testDataPath), true);
 RoleMappedData testRoles = TrainUtils.CreateExamples(testPipe, label: "Label", feature: "Features");
 return ScoreUtils.GetScorer(pred, testRoles, env, testRoles.Schema);
 }
 }
 }
 }
}

118 changes: 118 additions & 0 deletions
test/Microsoft.ML.Tests/ScenariosWithDirectInstantiation/SentimentPredictionTests.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,118 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

using Microsoft.ML.Models;
using Microsoft.ML.Runtime;
using Microsoft.ML.Runtime.Api;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.FastTree;
using Microsoft.ML.Runtime.Internal.Calibration;
using Microsoft.ML.Runtime.Model;
using Microsoft.ML.Trainers;
using Microsoft.ML.Transforms;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using Xunit;

namespace Microsoft.ML.Scenarios
{
 public partial class ScenariosTests
 {
 [Fact]
 public void TrainAndPredictSentimentModelWithDirectionInstantiationTest()
 {
 var dataPath = GetDataPath(SentimentDataPath);
 var testDataPath = GetDataPath(SentimentTestPath);

 using (var env = new TlcEnvironment(seed: 1, conc: 1))
 {
 // Pipeline
 var loader = new TextLoader(env,
 new TextLoader.Arguments()
 {
 Separator = "tab",
 HasHeader = true,
 Column = new[]
 {
 new TextLoader.Column()
 {
 Name = "Label",
 Source = new [] { new TextLoader.Range() { Min=0, Max=0} },
 Type = DataKind.Num
 },

 new TextLoader.Column()
 {
 Name = "SentimentText",
 Source = new [] { new TextLoader.Range() { Min=1, Max=1} },
 Type = DataKind.Text
 }
 }
 }, new MultiFileSource(dataPath));

 var trans = TextTransform.Create(env, new TextTransform.Arguments()
 {
 Column = new TextTransform.Column
 {
 Name = "Features",
 Source = new[] { "SentimentText" }
 },
 KeepDiacritics = false,
 KeepPunctuations = false,
 TextCase = Runtime.TextAnalytics.TextNormalizerTransform.CaseNormalizationMode.Lower,
 OutputTokens = true,
 StopWordsRemover = new Runtime.TextAnalytics.PredefinedStopWordsRemoverFactory(),
 VectorNormalizer = TextTransform.TextNormKind.L2,
 CharFeatureExtractor = new NgramExtractorTransform.NgramExtractorArguments() { NgramLength = 3, AllLengths = false },
 WordFeatureExtractor = new NgramExtractorTransform.NgramExtractorArguments() { NgramLength = 2, AllLengths = true },
 },
 loader);

 // Train
 var trainer = new FastTreeBinaryClassificationTrainer(env, new FastTreeBinaryClassificationTrainer.Arguments()
 {
 NumLeaves = 5,
 NumTrees = 5,
 MinDocumentsInLeafs = 2
 });

 var trainRoles = TrainUtils.CreateExamples(trans, label: "Label", feature: "Features");
 trainer.Train(trainRoles);

 // Get scorer and evaluate the predictions from test data
 var pred = trainer.CreatePredictor();
 IDataScorerTransform testDataScorer = GetScorer(env, trans, pred, testDataPath);
 var metrics = EvaluateBinary(env, testDataScorer);
 ValidateBinaryMetrics(metrics);

 // Create prediction engine and test predictions
 var model = env.CreateBatchPredictionEngine<SentimentData, SentimentPrediction>(testDataScorer);
 var sentiments = GetTestData();
 var predictions = model.Predict(sentiments, false);
 Assert.Equal(2, predictions.Count());
 Assert.True(predictions.ElementAt(0).Sentiment.IsFalse);
 Assert.True(predictions.ElementAt(1).Sentiment.IsTrue);

 // Get feature importance based on feature gain during training
 var summary = ((FeatureWeightsCalibratedPredictor)pred).GetSummaryInKeyValuePairs(trainRoles.Schema);
 Assert.Equal(1.0, (double)summary[0].Value, 1);
 }
 }

 private BinaryClassificationMetrics EvaluateBinary(IHostEnvironment env, IDataView scoredData)
 {
 var dataEval = TrainUtils.CreateExamplesOpt(scoredData, label: "Label", feature: "Features");

 // Evaluate.
 // It does not work. It throws error "Failed to find 'Score' column" when Evaluate is called
 //var evaluator = new BinaryClassifierEvaluator(env, new BinaryClassifierEvaluator.Arguments());

 var evaluator = new BinaryClassifierMamlEvaluator(env, new BinaryClassifierMamlEvaluator.Arguments());
 var metricsDic = evaluator.Evaluate(dataEval);

 return BinaryClassificationMetrics.FromMetrics(env, metricsDic["OverallMetrics"], metricsDic["ConfusionMatrix"])[0];
 }
 }
}

, '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
Added tests for new API where components(Loaders/Transforms/Learners) are directly instantiated.#468

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

zeahmed
merged 2 commits into

from

Jul 2, 2018
 Merged


Added tests for new API where components(Loaders/Transforms/Learners) are directly instantiated.
#468
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
d8d4c2e

Added tests for new API where components(Loaders/Transforms/Learners)…


zeahmed Jul 2, 2018
0bfe5c3

Moved new tests to separate folder.


zeahmed Jul 2, 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


210 changes: 210 additions & 0 deletions
test/Microsoft.ML.Tests/ScenariosWithDirectInstantiation/IrisPlantClassificationTests.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,210 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

using Microsoft.ML.Models;
using Microsoft.ML.Runtime;
using Microsoft.ML.Runtime.Api;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.Learners;
using Microsoft.ML.Runtime.Model;
using System;
using System.IO;
using Xunit;

namespace Microsoft.ML.Scenarios
{
 public partial class ScenariosTests
 {
 [Fact]
 public void TrainAndPredictIrisModelUsingDirectInstantiationTest()
 {
 string dataPath = GetDataPath("iris.txt");
 string testDataPath = dataPath;

 using (var env = new TlcEnvironment(seed: 1, conc: 1))
 {
 // Pipeline
 var loader = new TextLoader(env,
 new TextLoader.Arguments()
 {
 HasHeader = false,
 Column = new[] {
 new TextLoader.Column()
 {
 Name = "Label",
 Source = new [] { new TextLoader.Range() { Min = 0, Max = 0} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "SepalLength",
 Source = new [] { new TextLoader.Range() { Min = 1, Max = 1} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "SepalWidth",
 Source = new [] { new TextLoader.Range() { Min = 2, Max = 2} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "PetalLength",
 Source = new [] { new TextLoader.Range() { Min = 3, Max = 3} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "PetalWidth",
 Source = new [] { new TextLoader.Range() { Min = 4, Max = 4} },
 Type = DataKind.R4
 }
 }
 }, new MultiFileSource(dataPath));

 IDataTransform trans = new ConcatTransform(env, loader, "Features",
 "SepalLength", "SepalWidth", "PetalLength", "PetalWidth");

 // Normalizer is not automatically added though the trainer has 'NormalizeFeatures' On/Auto
 trans = NormalizeTransform.CreateMinMaxNormalizer(env, trans, "Features");

 // Train
 var trainer = new SdcaMultiClassTrainer(env, new SdcaMultiClassTrainer.Arguments());

 // Explicity adding CacheDataView since caching is not working though trainer has 'Caching' On/Auto
 var cached = new CacheDataView(env, trans, prefetch: null);
 var trainRoles = TrainUtils.CreateExamples(cached, label: "Label", feature: "Features");
 trainer.Train(trainRoles);

 // Get scorer and evaluate the predictions from test data
 var pred = trainer.CreatePredictor();
 IDataScorerTransform testDataScorer = GetScorer(env, trans, pred, testDataPath);
 var metrics = Evaluate(env, testDataScorer);
 CompareMatrics(metrics);

 // Create prediction engine and test predictions
 var model = env.CreatePredictionEngine<IrisData, IrisPrediction>(testDataScorer);
 ComparePredictions(model);

 // Get feature importance i.e. weight vector
 var summary = ((MulticlassLogisticRegressionPredictor)pred).GetSummaryInKeyValuePairs(trainRoles.Schema);
 Assert.Equal(7.757867, Convert.ToDouble(summary[0].Value), 5);
 }
 }

 private void ComparePredictions(PredictionEngine<IrisData, IrisPrediction> model)
 {
 IrisPrediction prediction = model.Predict(new IrisData()
 {
 SepalLength = 3.3f,
 SepalWidth = 1.6f,
 PetalLength = 0.2f,
 PetalWidth = 5.1f,
 });

 Assert.Equal(1, prediction.PredictedLabels[0], 2);
 Assert.Equal(0, prediction.PredictedLabels[1], 2);
 Assert.Equal(0, prediction.PredictedLabels[2], 2);

 prediction = model.Predict(new IrisData()
 {
 SepalLength = 3.1f,
 SepalWidth = 5.5f,
 PetalLength = 2.2f,
 PetalWidth = 6.4f,
 });

 Assert.Equal(0, prediction.PredictedLabels[0], 2);
 Assert.Equal(0, prediction.PredictedLabels[1], 2);
 Assert.Equal(1, prediction.PredictedLabels[2], 2);

 prediction = model.Predict(new IrisData()
 {
 SepalLength = 3.1f,
 SepalWidth = 2.5f,
 PetalLength = 1.2f,
 PetalWidth = 4.4f,
 });

 Assert.Equal(.2, prediction.PredictedLabels[0], 1);
 Assert.Equal(.8, prediction.PredictedLabels[1], 1);
 Assert.Equal(0, prediction.PredictedLabels[2], 2);
 }

 private void CompareMatrics(ClassificationMetrics metrics)
 {
 Assert.Equal(.98, metrics.AccuracyMacro);
 Assert.Equal(.98, metrics.AccuracyMicro, 2);
 Assert.Equal(.06, metrics.LogLoss, 2);
 Assert.InRange(metrics.LogLossReduction, 94, 96);
 Assert.Equal(1, metrics.TopKAccuracy);

 Assert.Equal(3, metrics.PerClassLogLoss.Length);
 Assert.Equal(0, metrics.PerClassLogLoss[0], 1);
 Assert.Equal(.1, metrics.PerClassLogLoss[1], 1);
 Assert.Equal(.1, metrics.PerClassLogLoss[2], 1);

 ConfusionMatrix matrix = metrics.ConfusionMatrix;
 Assert.Equal(3, matrix.Order);
 Assert.Equal(3, matrix.ClassNames.Count);
 Assert.Equal("0", matrix.ClassNames[0]);
 Assert.Equal("1", matrix.ClassNames[1]);
 Assert.Equal("2", matrix.ClassNames[2]);

 Assert.Equal(50, matrix[0, 0]);
 Assert.Equal(50, matrix["0", "0"]);
 Assert.Equal(0, matrix[0, 1]);
 Assert.Equal(0, matrix["0", "1"]);
 Assert.Equal(0, matrix[0, 2]);
 Assert.Equal(0, matrix["0", "2"]);

 Assert.Equal(0, matrix[1, 0]);
 Assert.Equal(0, matrix["1", "0"]);
 Assert.Equal(48, matrix[1, 1]);
 Assert.Equal(48, matrix["1", "1"]);
 Assert.Equal(2, matrix[1, 2]);
 Assert.Equal(2, matrix["1", "2"]);

 Assert.Equal(0, matrix[2, 0]);
 Assert.Equal(0, matrix["2", "0"]);
 Assert.Equal(1, matrix[2, 1]);
 Assert.Equal(1, matrix["2", "1"]);
 Assert.Equal(49, matrix[2, 2]);
 Assert.Equal(49, matrix["2", "2"]);
 }

 private ClassificationMetrics Evaluate(IHostEnvironment env, IDataView scoredData)
 {
 var dataEval = TrainUtils.CreateExamplesOpt(scoredData, label: "Label", feature: "Features");

 // Evaluate.
 // It does not work. It throws error "Failed to find 'Score' column" when Evaluate is called
 //var evaluator = new MultiClassClassifierEvaluator(env, new MultiClassClassifierEvaluator.Arguments() { OutputTopKAcc = 3 });

 var evaluator = new MultiClassMamlEvaluator(env, new MultiClassMamlEvaluator.Arguments() { OutputTopKAcc = 3 });
 var metricsDic = evaluator.Evaluate(dataEval);

 return ClassificationMetrics.FromMetrics(env, metricsDic["OverallMetrics"], metricsDic["ConfusionMatrix"])[0];
 }

 private IDataScorerTransform GetScorer(IHostEnvironment env, IDataView transforms, IPredictor pred, string testDataPath = null)
 {
 using (var ch = env.Start("Saving model"))
 using (var memoryStream = new MemoryStream())
 {
 var trainRoles = TrainUtils.CreateExamples(transforms, label: "Label", feature: "Features");

 // Model cannot be saved with CacheDataView
 TrainUtils.SaveModel(env, ch, memoryStream, pred, trainRoles);
 memoryStream.Position = 0;
 using (var rep = RepositoryReader.Open(memoryStream, ch))
 {
 IDataLoader testPipe = ModelFileUtils.LoadLoader(env, rep, new MultiFileSource(testDataPath), true);
 RoleMappedData testRoles = TrainUtils.CreateExamples(testPipe, label: "Label", feature: "Features");
 return ScoreUtils.GetScorer(pred, testRoles, env, testRoles.Schema);
 }
 }
 }
 }
}

118 changes: 118 additions & 0 deletions
test/Microsoft.ML.Tests/ScenariosWithDirectInstantiation/SentimentPredictionTests.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,118 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

using Microsoft.ML.Models;
using Microsoft.ML.Runtime;
using Microsoft.ML.Runtime.Api;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.FastTree;
using Microsoft.ML.Runtime.Internal.Calibration;
using Microsoft.ML.Runtime.Model;
using Microsoft.ML.Trainers;
using Microsoft.ML.Transforms;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using Xunit;

namespace Microsoft.ML.Scenarios
{
 public partial class ScenariosTests
 {
 [Fact]
 public void TrainAndPredictSentimentModelWithDirectionInstantiationTest()
 {
 var dataPath = GetDataPath(SentimentDataPath);
 var testDataPath = GetDataPath(SentimentTestPath);

 using (var env = new TlcEnvironment(seed: 1, conc: 1))
 {
 // Pipeline
 var loader = new TextLoader(env,
 new TextLoader.Arguments()
 {
 Separator = "tab",
 HasHeader = true,
 Column = new[]
 {
 new TextLoader.Column()
 {
 Name = "Label",
 Source = new [] { new TextLoader.Range() { Min=0, Max=0} },
 Type = DataKind.Num
 },

 new TextLoader.Column()
 {
 Name = "SentimentText",
 Source = new [] { new TextLoader.Range() { Min=1, Max=1} },
 Type = DataKind.Text
 }
 }
 }, new MultiFileSource(dataPath));

 var trans = TextTransform.Create(env, new TextTransform.Arguments()
 {
 Column = new TextTransform.Column
 {
 Name = "Features",
 Source = new[] { "SentimentText" }
 },
 KeepDiacritics = false,
 KeepPunctuations = false,
 TextCase = Runtime.TextAnalytics.TextNormalizerTransform.CaseNormalizationMode.Lower,
 OutputTokens = true,
 StopWordsRemover = new Runtime.TextAnalytics.PredefinedStopWordsRemoverFactory(),
 VectorNormalizer = TextTransform.TextNormKind.L2,
 CharFeatureExtractor = new NgramExtractorTransform.NgramExtractorArguments() { NgramLength = 3, AllLengths = false },
 WordFeatureExtractor = new NgramExtractorTransform.NgramExtractorArguments() { NgramLength = 2, AllLengths = true },
 },
 loader);

 // Train
 var trainer = new FastTreeBinaryClassificationTrainer(env, new FastTreeBinaryClassificationTrainer.Arguments()
 {
 NumLeaves = 5,
 NumTrees = 5,
 MinDocumentsInLeafs = 2
 });

 var trainRoles = TrainUtils.CreateExamples(trans, label: "Label", feature: "Features");
 trainer.Train(trainRoles);

 // Get scorer and evaluate the predictions from test data
 var pred = trainer.CreatePredictor();
 IDataScorerTransform testDataScorer = GetScorer(env, trans, pred, testDataPath);
 var metrics = EvaluateBinary(env, testDataScorer);
 ValidateBinaryMetrics(metrics);

 // Create prediction engine and test predictions
 var model = env.CreateBatchPredictionEngine<SentimentData, SentimentPrediction>(testDataScorer);
 var sentiments = GetTestData();
 var predictions = model.Predict(sentiments, false);
 Assert.Equal(2, predictions.Count());
 Assert.True(predictions.ElementAt(0).Sentiment.IsFalse);
 Assert.True(predictions.ElementAt(1).Sentiment.IsTrue);

 // Get feature importance based on feature gain during training
 var summary = ((FeatureWeightsCalibratedPredictor)pred).GetSummaryInKeyValuePairs(trainRoles.Schema);
 Assert.Equal(1.0, (double)summary[0].Value, 1);
 }
 }

 private BinaryClassificationMetrics EvaluateBinary(IHostEnvironment env, IDataView scoredData)
 {
 var dataEval = TrainUtils.CreateExamplesOpt(scoredData, label: "Label", feature: "Features");

 // Evaluate.
 // It does not work. It throws error "Failed to find 'Score' column" when Evaluate is called
 //var evaluator = new BinaryClassifierEvaluator(env, new BinaryClassifierEvaluator.Arguments());

 var evaluator = new BinaryClassifierMamlEvaluator(env, new BinaryClassifierMamlEvaluator.Arguments());
 var metricsDic = evaluator.Evaluate(dataEval);

 return BinaryClassificationMetrics.FromMetrics(env, metricsDic["OverallMetrics"], metricsDic["ConfusionMatrix"])[0];
 }
 }
}

, '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
Added tests for new API where components(Loaders/Transforms/Learners) are directly instantiated.#468

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

zeahmed
merged 2 commits into

from

Jul 2, 2018
 Merged


Added tests for new API where components(Loaders/Transforms/Learners) are directly instantiated.
#468
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
d8d4c2e

Added tests for new API where components(Loaders/Transforms/Learners)…


zeahmed Jul 2, 2018
0bfe5c3

Moved new tests to separate folder.


zeahmed Jul 2, 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


210 changes: 210 additions & 0 deletions
test/Microsoft.ML.Tests/ScenariosWithDirectInstantiation/IrisPlantClassificationTests.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,210 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

using Microsoft.ML.Models;
using Microsoft.ML.Runtime;
using Microsoft.ML.Runtime.Api;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.Learners;
using Microsoft.ML.Runtime.Model;
using System;
using System.IO;
using Xunit;

namespace Microsoft.ML.Scenarios
{
 public partial class ScenariosTests
 {
 [Fact]
 public void TrainAndPredictIrisModelUsingDirectInstantiationTest()
 {
 string dataPath = GetDataPath("iris.txt");
 string testDataPath = dataPath;

 using (var env = new TlcEnvironment(seed: 1, conc: 1))
 {
 // Pipeline
 var loader = new TextLoader(env,
 new TextLoader.Arguments()
 {
 HasHeader = false,
 Column = new[] {
 new TextLoader.Column()
 {
 Name = "Label",
 Source = new [] { new TextLoader.Range() { Min = 0, Max = 0} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "SepalLength",
 Source = new [] { new TextLoader.Range() { Min = 1, Max = 1} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "SepalWidth",
 Source = new [] { new TextLoader.Range() { Min = 2, Max = 2} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "PetalLength",
 Source = new [] { new TextLoader.Range() { Min = 3, Max = 3} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "PetalWidth",
 Source = new [] { new TextLoader.Range() { Min = 4, Max = 4} },
 Type = DataKind.R4
 }
 }
 }, new MultiFileSource(dataPath));

 IDataTransform trans = new ConcatTransform(env, loader, "Features",
 "SepalLength", "SepalWidth", "PetalLength", "PetalWidth");

 // Normalizer is not automatically added though the trainer has 'NormalizeFeatures' On/Auto
 trans = NormalizeTransform.CreateMinMaxNormalizer(env, trans, "Features");

 // Train
 var trainer = new SdcaMultiClassTrainer(env, new SdcaMultiClassTrainer.Arguments());

 // Explicity adding CacheDataView since caching is not working though trainer has 'Caching' On/Auto
 var cached = new CacheDataView(env, trans, prefetch: null);
 var trainRoles = TrainUtils.CreateExamples(cached, label: "Label", feature: "Features");
 trainer.Train(trainRoles);

 // Get scorer and evaluate the predictions from test data
 var pred = trainer.CreatePredictor();
 IDataScorerTransform testDataScorer = GetScorer(env, trans, pred, testDataPath);
 var metrics = Evaluate(env, testDataScorer);
 CompareMatrics(metrics);

 // Create prediction engine and test predictions
 var model = env.CreatePredictionEngine<IrisData, IrisPrediction>(testDataScorer);
 ComparePredictions(model);

 // Get feature importance i.e. weight vector
 var summary = ((MulticlassLogisticRegressionPredictor)pred).GetSummaryInKeyValuePairs(trainRoles.Schema);
 Assert.Equal(7.757867, Convert.ToDouble(summary[0].Value), 5);
 }
 }

 private void ComparePredictions(PredictionEngine<IrisData, IrisPrediction> model)
 {
 IrisPrediction prediction = model.Predict(new IrisData()
 {
 SepalLength = 3.3f,
 SepalWidth = 1.6f,
 PetalLength = 0.2f,
 PetalWidth = 5.1f,
 });

 Assert.Equal(1, prediction.PredictedLabels[0], 2);
 Assert.Equal(0, prediction.PredictedLabels[1], 2);
 Assert.Equal(0, prediction.PredictedLabels[2], 2);

 prediction = model.Predict(new IrisData()
 {
 SepalLength = 3.1f,
 SepalWidth = 5.5f,
 PetalLength = 2.2f,
 PetalWidth = 6.4f,
 });

 Assert.Equal(0, prediction.PredictedLabels[0], 2);
 Assert.Equal(0, prediction.PredictedLabels[1], 2);
 Assert.Equal(1, prediction.PredictedLabels[2], 2);

 prediction = model.Predict(new IrisData()
 {
 SepalLength = 3.1f,
 SepalWidth = 2.5f,
 PetalLength = 1.2f,
 PetalWidth = 4.4f,
 });

 Assert.Equal(.2, prediction.PredictedLabels[0], 1);
 Assert.Equal(.8, prediction.PredictedLabels[1], 1);
 Assert.Equal(0, prediction.PredictedLabels[2], 2);
 }

 private void CompareMatrics(ClassificationMetrics metrics)
 {
 Assert.Equal(.98, metrics.AccuracyMacro);
 Assert.Equal(.98, metrics.AccuracyMicro, 2);
 Assert.Equal(.06, metrics.LogLoss, 2);
 Assert.InRange(metrics.LogLossReduction, 94, 96);
 Assert.Equal(1, metrics.TopKAccuracy);

 Assert.Equal(3, metrics.PerClassLogLoss.Length);
 Assert.Equal(0, metrics.PerClassLogLoss[0], 1);
 Assert.Equal(.1, metrics.PerClassLogLoss[1], 1);
 Assert.Equal(.1, metrics.PerClassLogLoss[2], 1);

 ConfusionMatrix matrix = metrics.ConfusionMatrix;
 Assert.Equal(3, matrix.Order);
 Assert.Equal(3, matrix.ClassNames.Count);
 Assert.Equal("0", matrix.ClassNames[0]);
 Assert.Equal("1", matrix.ClassNames[1]);
 Assert.Equal("2", matrix.ClassNames[2]);

 Assert.Equal(50, matrix[0, 0]);
 Assert.Equal(50, matrix["0", "0"]);
 Assert.Equal(0, matrix[0, 1]);
 Assert.Equal(0, matrix["0", "1"]);
 Assert.Equal(0, matrix[0, 2]);
 Assert.Equal(0, matrix["0", "2"]);

 Assert.Equal(0, matrix[1, 0]);
 Assert.Equal(0, matrix["1", "0"]);
 Assert.Equal(48, matrix[1, 1]);
 Assert.Equal(48, matrix["1", "1"]);
 Assert.Equal(2, matrix[1, 2]);
 Assert.Equal(2, matrix["1", "2"]);

 Assert.Equal(0, matrix[2, 0]);
 Assert.Equal(0, matrix["2", "0"]);
 Assert.Equal(1, matrix[2, 1]);
 Assert.Equal(1, matrix["2", "1"]);
 Assert.Equal(49, matrix[2, 2]);
 Assert.Equal(49, matrix["2", "2"]);
 }

 private ClassificationMetrics Evaluate(IHostEnvironment env, IDataView scoredData)
 {
 var dataEval = TrainUtils.CreateExamplesOpt(scoredData, label: "Label", feature: "Features");

 // Evaluate.
 // It does not work. It throws error "Failed to find 'Score' column" when Evaluate is called
 //var evaluator = new MultiClassClassifierEvaluator(env, new MultiClassClassifierEvaluator.Arguments() { OutputTopKAcc = 3 });

 var evaluator = new MultiClassMamlEvaluator(env, new MultiClassMamlEvaluator.Arguments() { OutputTopKAcc = 3 });
 var metricsDic = evaluator.Evaluate(dataEval);

 return ClassificationMetrics.FromMetrics(env, metricsDic["OverallMetrics"], metricsDic["ConfusionMatrix"])[0];
 }

 private IDataScorerTransform GetScorer(IHostEnvironment env, IDataView transforms, IPredictor pred, string testDataPath = null)
 {
 using (var ch = env.Start("Saving model"))
 using (var memoryStream = new MemoryStream())
 {
 var trainRoles = TrainUtils.CreateExamples(transforms, label: "Label", feature: "Features");

 // Model cannot be saved with CacheDataView
 TrainUtils.SaveModel(env, ch, memoryStream, pred, trainRoles);
 memoryStream.Position = 0;
 using (var rep = RepositoryReader.Open(memoryStream, ch))
 {
 IDataLoader testPipe = ModelFileUtils.LoadLoader(env, rep, new MultiFileSource(testDataPath), true);
 RoleMappedData testRoles = TrainUtils.CreateExamples(testPipe, label: "Label", feature: "Features");
 return ScoreUtils.GetScorer(pred, testRoles, env, testRoles.Schema);
 }
 }
 }
 }
}

118 changes: 118 additions & 0 deletions
test/Microsoft.ML.Tests/ScenariosWithDirectInstantiation/SentimentPredictionTests.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,118 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

using Microsoft.ML.Models;
using Microsoft.ML.Runtime;
using Microsoft.ML.Runtime.Api;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.FastTree;
using Microsoft.ML.Runtime.Internal.Calibration;
using Microsoft.ML.Runtime.Model;
using Microsoft.ML.Trainers;
using Microsoft.ML.Transforms;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using Xunit;

namespace Microsoft.ML.Scenarios
{
 public partial class ScenariosTests
 {
 [Fact]
 public void TrainAndPredictSentimentModelWithDirectionInstantiationTest()
 {
 var dataPath = GetDataPath(SentimentDataPath);
 var testDataPath = GetDataPath(SentimentTestPath);

 using (var env = new TlcEnvironment(seed: 1, conc: 1))
 {
 // Pipeline
 var loader = new TextLoader(env,
 new TextLoader.Arguments()
 {
 Separator = "tab",
 HasHeader = true,
 Column = new[]
 {
 new TextLoader.Column()
 {
 Name = "Label",
 Source = new [] { new TextLoader.Range() { Min=0, Max=0} },
 Type = DataKind.Num
 },

 new TextLoader.Column()
 {
 Name = "SentimentText",
 Source = new [] { new TextLoader.Range() { Min=1, Max=1} },
 Type = DataKind.Text
 }
 }
 }, new MultiFileSource(dataPath));

 var trans = TextTransform.Create(env, new TextTransform.Arguments()
 {
 Column = new TextTransform.Column
 {
 Name = "Features",
 Source = new[] { "SentimentText" }
 },
 KeepDiacritics = false,
 KeepPunctuations = false,
 TextCase = Runtime.TextAnalytics.TextNormalizerTransform.CaseNormalizationMode.Lower,
 OutputTokens = true,
 StopWordsRemover = new Runtime.TextAnalytics.PredefinedStopWordsRemoverFactory(),
 VectorNormalizer = TextTransform.TextNormKind.L2,
 CharFeatureExtractor = new NgramExtractorTransform.NgramExtractorArguments() { NgramLength = 3, AllLengths = false },
 WordFeatureExtractor = new NgramExtractorTransform.NgramExtractorArguments() { NgramLength = 2, AllLengths = true },
 },
 loader);

 // Train
 var trainer = new FastTreeBinaryClassificationTrainer(env, new FastTreeBinaryClassificationTrainer.Arguments()
 {
 NumLeaves = 5,
 NumTrees = 5,
 MinDocumentsInLeafs = 2
 });

 var trainRoles = TrainUtils.CreateExamples(trans, label: "Label", feature: "Features");
 trainer.Train(trainRoles);

 // Get scorer and evaluate the predictions from test data
 var pred = trainer.CreatePredictor();
 IDataScorerTransform testDataScorer = GetScorer(env, trans, pred, testDataPath);
 var metrics = EvaluateBinary(env, testDataScorer);
 ValidateBinaryMetrics(metrics);

 // Create prediction engine and test predictions
 var model = env.CreateBatchPredictionEngine<SentimentData, SentimentPrediction>(testDataScorer);
 var sentiments = GetTestData();
 var predictions = model.Predict(sentiments, false);
 Assert.Equal(2, predictions.Count());
 Assert.True(predictions.ElementAt(0).Sentiment.IsFalse);
 Assert.True(predictions.ElementAt(1).Sentiment.IsTrue);

 // Get feature importance based on feature gain during training
 var summary = ((FeatureWeightsCalibratedPredictor)pred).GetSummaryInKeyValuePairs(trainRoles.Schema);
 Assert.Equal(1.0, (double)summary[0].Value, 1);
 }
 }

 private BinaryClassificationMetrics EvaluateBinary(IHostEnvironment env, IDataView scoredData)
 {
 var dataEval = TrainUtils.CreateExamplesOpt(scoredData, label: "Label", feature: "Features");

 // Evaluate.
 // It does not work. It throws error "Failed to find 'Score' column" when Evaluate is called
 //var evaluator = new BinaryClassifierEvaluator(env, new BinaryClassifierEvaluator.Arguments());

 var evaluator = new BinaryClassifierMamlEvaluator(env, new BinaryClassifierMamlEvaluator.Arguments());
 var metricsDic = evaluator.Evaluate(dataEval);

 return BinaryClassificationMetrics.FromMetrics(env, metricsDic["OverallMetrics"], metricsDic["ConfusionMatrix"])[0];
 }
 }
}

, '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
Added tests for new API where components(Loaders/Transforms/Learners) are directly instantiated.#468

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

zeahmed
merged 2 commits into

from

Jul 2, 2018
 Merged


Added tests for new API where components(Loaders/Transforms/Learners) are directly instantiated.
#468
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
d8d4c2e

Added tests for new API where components(Loaders/Transforms/Learners)…


zeahmed Jul 2, 2018
0bfe5c3

Moved new tests to separate folder.


zeahmed Jul 2, 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


210 changes: 210 additions & 0 deletions
test/Microsoft.ML.Tests/ScenariosWithDirectInstantiation/IrisPlantClassificationTests.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,210 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

using Microsoft.ML.Models;
using Microsoft.ML.Runtime;
using Microsoft.ML.Runtime.Api;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.Learners;
using Microsoft.ML.Runtime.Model;
using System;
using System.IO;
using Xunit;

namespace Microsoft.ML.Scenarios
{
 public partial class ScenariosTests
 {
 [Fact]
 public void TrainAndPredictIrisModelUsingDirectInstantiationTest()
 {
 string dataPath = GetDataPath("iris.txt");
 string testDataPath = dataPath;

 using (var env = new TlcEnvironment(seed: 1, conc: 1))
 {
 // Pipeline
 var loader = new TextLoader(env,
 new TextLoader.Arguments()
 {
 HasHeader = false,
 Column = new[] {
 new TextLoader.Column()
 {
 Name = "Label",
 Source = new [] { new TextLoader.Range() { Min = 0, Max = 0} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "SepalLength",
 Source = new [] { new TextLoader.Range() { Min = 1, Max = 1} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "SepalWidth",
 Source = new [] { new TextLoader.Range() { Min = 2, Max = 2} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "PetalLength",
 Source = new [] { new TextLoader.Range() { Min = 3, Max = 3} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "PetalWidth",
 Source = new [] { new TextLoader.Range() { Min = 4, Max = 4} },
 Type = DataKind.R4
 }
 }
 }, new MultiFileSource(dataPath));

 IDataTransform trans = new ConcatTransform(env, loader, "Features",
 "SepalLength", "SepalWidth", "PetalLength", "PetalWidth");

 // Normalizer is not automatically added though the trainer has 'NormalizeFeatures' On/Auto
 trans = NormalizeTransform.CreateMinMaxNormalizer(env, trans, "Features");

 // Train
 var trainer = new SdcaMultiClassTrainer(env, new SdcaMultiClassTrainer.Arguments());

 // Explicity adding CacheDataView since caching is not working though trainer has 'Caching' On/Auto
 var cached = new CacheDataView(env, trans, prefetch: null);
 var trainRoles = TrainUtils.CreateExamples(cached, label: "Label", feature: "Features");
 trainer.Train(trainRoles);

 // Get scorer and evaluate the predictions from test data
 var pred = trainer.CreatePredictor();
 IDataScorerTransform testDataScorer = GetScorer(env, trans, pred, testDataPath);
 var metrics = Evaluate(env, testDataScorer);
 CompareMatrics(metrics);

 // Create prediction engine and test predictions
 var model = env.CreatePredictionEngine<IrisData, IrisPrediction>(testDataScorer);
 ComparePredictions(model);

 // Get feature importance i.e. weight vector
 var summary = ((MulticlassLogisticRegressionPredictor)pred).GetSummaryInKeyValuePairs(trainRoles.Schema);
 Assert.Equal(7.757867, Convert.ToDouble(summary[0].Value), 5);
 }
 }

 private void ComparePredictions(PredictionEngine<IrisData, IrisPrediction> model)
 {
 IrisPrediction prediction = model.Predict(new IrisData()
 {
 SepalLength = 3.3f,
 SepalWidth = 1.6f,
 PetalLength = 0.2f,
 PetalWidth = 5.1f,
 });

 Assert.Equal(1, prediction.PredictedLabels[0], 2);
 Assert.Equal(0, prediction.PredictedLabels[1], 2);
 Assert.Equal(0, prediction.PredictedLabels[2], 2);

 prediction = model.Predict(new IrisData()
 {
 SepalLength = 3.1f,
 SepalWidth = 5.5f,
 PetalLength = 2.2f,
 PetalWidth = 6.4f,
 });

 Assert.Equal(0, prediction.PredictedLabels[0], 2);
 Assert.Equal(0, prediction.PredictedLabels[1], 2);
 Assert.Equal(1, prediction.PredictedLabels[2], 2);

 prediction = model.Predict(new IrisData()
 {
 SepalLength = 3.1f,
 SepalWidth = 2.5f,
 PetalLength = 1.2f,
 PetalWidth = 4.4f,
 });

 Assert.Equal(.2, prediction.PredictedLabels[0], 1);
 Assert.Equal(.8, prediction.PredictedLabels[1], 1);
 Assert.Equal(0, prediction.PredictedLabels[2], 2);
 }

 private void CompareMatrics(ClassificationMetrics metrics)
 {
 Assert.Equal(.98, metrics.AccuracyMacro);
 Assert.Equal(.98, metrics.AccuracyMicro, 2);
 Assert.Equal(.06, metrics.LogLoss, 2);
 Assert.InRange(metrics.LogLossReduction, 94, 96);
 Assert.Equal(1, metrics.TopKAccuracy);

 Assert.Equal(3, metrics.PerClassLogLoss.Length);
 Assert.Equal(0, metrics.PerClassLogLoss[0], 1);
 Assert.Equal(.1, metrics.PerClassLogLoss[1], 1);
 Assert.Equal(.1, metrics.PerClassLogLoss[2], 1);

 ConfusionMatrix matrix = metrics.ConfusionMatrix;
 Assert.Equal(3, matrix.Order);
 Assert.Equal(3, matrix.ClassNames.Count);
 Assert.Equal("0", matrix.ClassNames[0]);
 Assert.Equal("1", matrix.ClassNames[1]);
 Assert.Equal("2", matrix.ClassNames[2]);

 Assert.Equal(50, matrix[0, 0]);
 Assert.Equal(50, matrix["0", "0"]);
 Assert.Equal(0, matrix[0, 1]);
 Assert.Equal(0, matrix["0", "1"]);
 Assert.Equal(0, matrix[0, 2]);
 Assert.Equal(0, matrix["0", "2"]);

 Assert.Equal(0, matrix[1, 0]);
 Assert.Equal(0, matrix["1", "0"]);
 Assert.Equal(48, matrix[1, 1]);
 Assert.Equal(48, matrix["1", "1"]);
 Assert.Equal(2, matrix[1, 2]);
 Assert.Equal(2, matrix["1", "2"]);

 Assert.Equal(0, matrix[2, 0]);
 Assert.Equal(0, matrix["2", "0"]);
 Assert.Equal(1, matrix[2, 1]);
 Assert.Equal(1, matrix["2", "1"]);
 Assert.Equal(49, matrix[2, 2]);
 Assert.Equal(49, matrix["2", "2"]);
 }

 private ClassificationMetrics Evaluate(IHostEnvironment env, IDataView scoredData)
 {
 var dataEval = TrainUtils.CreateExamplesOpt(scoredData, label: "Label", feature: "Features");

 // Evaluate.
 // It does not work. It throws error "Failed to find 'Score' column" when Evaluate is called
 //var evaluator = new MultiClassClassifierEvaluator(env, new MultiClassClassifierEvaluator.Arguments() { OutputTopKAcc = 3 });

 var evaluator = new MultiClassMamlEvaluator(env, new MultiClassMamlEvaluator.Arguments() { OutputTopKAcc = 3 });
 var metricsDic = evaluator.Evaluate(dataEval);

 return ClassificationMetrics.FromMetrics(env, metricsDic["OverallMetrics"], metricsDic["ConfusionMatrix"])[0];
 }

 private IDataScorerTransform GetScorer(IHostEnvironment env, IDataView transforms, IPredictor pred, string testDataPath = null)
 {
 using (var ch = env.Start("Saving model"))
 using (var memoryStream = new MemoryStream())
 {
 var trainRoles = TrainUtils.CreateExamples(transforms, label: "Label", feature: "Features");

 // Model cannot be saved with CacheDataView
 TrainUtils.SaveModel(env, ch, memoryStream, pred, trainRoles);
 memoryStream.Position = 0;
 using (var rep = RepositoryReader.Open(memoryStream, ch))
 {
 IDataLoader testPipe = ModelFileUtils.LoadLoader(env, rep, new MultiFileSource(testDataPath), true);
 RoleMappedData testRoles = TrainUtils.CreateExamples(testPipe, label: "Label", feature: "Features");
 return ScoreUtils.GetScorer(pred, testRoles, env, testRoles.Schema);
 }
 }
 }
 }
}

118 changes: 118 additions & 0 deletions
test/Microsoft.ML.Tests/ScenariosWithDirectInstantiation/SentimentPredictionTests.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,118 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

using Microsoft.ML.Models;
using Microsoft.ML.Runtime;
using Microsoft.ML.Runtime.Api;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.FastTree;
using Microsoft.ML.Runtime.Internal.Calibration;
using Microsoft.ML.Runtime.Model;
using Microsoft.ML.Trainers;
using Microsoft.ML.Transforms;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using Xunit;

namespace Microsoft.ML.Scenarios
{
 public partial class ScenariosTests
 {
 [Fact]
 public void TrainAndPredictSentimentModelWithDirectionInstantiationTest()
 {
 var dataPath = GetDataPath(SentimentDataPath);
 var testDataPath = GetDataPath(SentimentTestPath);

 using (var env = new TlcEnvironment(seed: 1, conc: 1))
 {
 // Pipeline
 var loader = new TextLoader(env,
 new TextLoader.Arguments()
 {
 Separator = "tab",
 HasHeader = true,
 Column = new[]
 {
 new TextLoader.Column()
 {
 Name = "Label",
 Source = new [] { new TextLoader.Range() { Min=0, Max=0} },
 Type = DataKind.Num
 },

 new TextLoader.Column()
 {
 Name = "SentimentText",
 Source = new [] { new TextLoader.Range() { Min=1, Max=1} },
 Type = DataKind.Text
 }
 }
 }, new MultiFileSource(dataPath));

 var trans = TextTransform.Create(env, new TextTransform.Arguments()
 {
 Column = new TextTransform.Column
 {
 Name = "Features",
 Source = new[] { "SentimentText" }
 },
 KeepDiacritics = false,
 KeepPunctuations = false,
 TextCase = Runtime.TextAnalytics.TextNormalizerTransform.CaseNormalizationMode.Lower,
 OutputTokens = true,
 StopWordsRemover = new Runtime.TextAnalytics.PredefinedStopWordsRemoverFactory(),
 VectorNormalizer = TextTransform.TextNormKind.L2,
 CharFeatureExtractor = new NgramExtractorTransform.NgramExtractorArguments() { NgramLength = 3, AllLengths = false },
 WordFeatureExtractor = new NgramExtractorTransform.NgramExtractorArguments() { NgramLength = 2, AllLengths = true },
 },
 loader);

 // Train
 var trainer = new FastTreeBinaryClassificationTrainer(env, new FastTreeBinaryClassificationTrainer.Arguments()
 {
 NumLeaves = 5,
 NumTrees = 5,
 MinDocumentsInLeafs = 2
 });

 var trainRoles = TrainUtils.CreateExamples(trans, label: "Label", feature: "Features");
 trainer.Train(trainRoles);

 // Get scorer and evaluate the predictions from test data
 var pred = trainer.CreatePredictor();
 IDataScorerTransform testDataScorer = GetScorer(env, trans, pred, testDataPath);
 var metrics = EvaluateBinary(env, testDataScorer);
 ValidateBinaryMetrics(metrics);

 // Create prediction engine and test predictions
 var model = env.CreateBatchPredictionEngine<SentimentData, SentimentPrediction>(testDataScorer);
 var sentiments = GetTestData();
 var predictions = model.Predict(sentiments, false);
 Assert.Equal(2, predictions.Count());
 Assert.True(predictions.ElementAt(0).Sentiment.IsFalse);
 Assert.True(predictions.ElementAt(1).Sentiment.IsTrue);

 // Get feature importance based on feature gain during training
 var summary = ((FeatureWeightsCalibratedPredictor)pred).GetSummaryInKeyValuePairs(trainRoles.Schema);
 Assert.Equal(1.0, (double)summary[0].Value, 1);
 }
 }

 private BinaryClassificationMetrics EvaluateBinary(IHostEnvironment env, IDataView scoredData)
 {
 var dataEval = TrainUtils.CreateExamplesOpt(scoredData, label: "Label", feature: "Features");

 // Evaluate.
 // It does not work. It throws error "Failed to find 'Score' column" when Evaluate is called
 //var evaluator = new BinaryClassifierEvaluator(env, new BinaryClassifierEvaluator.Arguments());

 var evaluator = new BinaryClassifierMamlEvaluator(env, new BinaryClassifierMamlEvaluator.Arguments());
 var metricsDic = evaluator.Evaluate(dataEval);

 return BinaryClassificationMetrics.FromMetrics(env, metricsDic["OverallMetrics"], metricsDic["ConfusionMatrix"])[0];
 }
 }
}

, '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
Added tests for new API where components(Loaders/Transforms/Learners) are directly instantiated.#468

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

zeahmed
merged 2 commits into

from

Jul 2, 2018
 Merged


Added tests for new API where components(Loaders/Transforms/Learners) are directly instantiated.
#468
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
d8d4c2e

Added tests for new API where components(Loaders/Transforms/Learners)…


zeahmed Jul 2, 2018
0bfe5c3

Moved new tests to separate folder.


zeahmed Jul 2, 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


210 changes: 210 additions & 0 deletions
test/Microsoft.ML.Tests/ScenariosWithDirectInstantiation/IrisPlantClassificationTests.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,210 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

using Microsoft.ML.Models;
using Microsoft.ML.Runtime;
using Microsoft.ML.Runtime.Api;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.Learners;
using Microsoft.ML.Runtime.Model;
using System;
using System.IO;
using Xunit;

namespace Microsoft.ML.Scenarios
{
 public partial class ScenariosTests
 {
 [Fact]
 public void TrainAndPredictIrisModelUsingDirectInstantiationTest()
 {
 string dataPath = GetDataPath("iris.txt");
 string testDataPath = dataPath;

 using (var env = new TlcEnvironment(seed: 1, conc: 1))
 {
 // Pipeline
 var loader = new TextLoader(env,
 new TextLoader.Arguments()
 {
 HasHeader = false,
 Column = new[] {
 new TextLoader.Column()
 {
 Name = "Label",
 Source = new [] { new TextLoader.Range() { Min = 0, Max = 0} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "SepalLength",
 Source = new [] { new TextLoader.Range() { Min = 1, Max = 1} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "SepalWidth",
 Source = new [] { new TextLoader.Range() { Min = 2, Max = 2} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "PetalLength",
 Source = new [] { new TextLoader.Range() { Min = 3, Max = 3} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "PetalWidth",
 Source = new [] { new TextLoader.Range() { Min = 4, Max = 4} },
 Type = DataKind.R4
 }
 }
 }, new MultiFileSource(dataPath));

 IDataTransform trans = new ConcatTransform(env, loader, "Features",
 "SepalLength", "SepalWidth", "PetalLength", "PetalWidth");

 // Normalizer is not automatically added though the trainer has 'NormalizeFeatures' On/Auto
 trans = NormalizeTransform.CreateMinMaxNormalizer(env, trans, "Features");

 // Train
 var trainer = new SdcaMultiClassTrainer(env, new SdcaMultiClassTrainer.Arguments());

 // Explicity adding CacheDataView since caching is not working though trainer has 'Caching' On/Auto
 var cached = new CacheDataView(env, trans, prefetch: null);
 var trainRoles = TrainUtils.CreateExamples(cached, label: "Label", feature: "Features");
 trainer.Train(trainRoles);

 // Get scorer and evaluate the predictions from test data
 var pred = trainer.CreatePredictor();
 IDataScorerTransform testDataScorer = GetScorer(env, trans, pred, testDataPath);
 var metrics = Evaluate(env, testDataScorer);
 CompareMatrics(metrics);

 // Create prediction engine and test predictions
 var model = env.CreatePredictionEngine<IrisData, IrisPrediction>(testDataScorer);
 ComparePredictions(model);

 // Get feature importance i.e. weight vector
 var summary = ((MulticlassLogisticRegressionPredictor)pred).GetSummaryInKeyValuePairs(trainRoles.Schema);
 Assert.Equal(7.757867, Convert.ToDouble(summary[0].Value), 5);
 }
 }

 private void ComparePredictions(PredictionEngine<IrisData, IrisPrediction> model)
 {
 IrisPrediction prediction = model.Predict(new IrisData()
 {
 SepalLength = 3.3f,
 SepalWidth = 1.6f,
 PetalLength = 0.2f,
 PetalWidth = 5.1f,
 });

 Assert.Equal(1, prediction.PredictedLabels[0], 2);
 Assert.Equal(0, prediction.PredictedLabels[1], 2);
 Assert.Equal(0, prediction.PredictedLabels[2], 2);

 prediction = model.Predict(new IrisData()
 {
 SepalLength = 3.1f,
 SepalWidth = 5.5f,
 PetalLength = 2.2f,
 PetalWidth = 6.4f,
 });

 Assert.Equal(0, prediction.PredictedLabels[0], 2);
 Assert.Equal(0, prediction.PredictedLabels[1], 2);
 Assert.Equal(1, prediction.PredictedLabels[2], 2);

 prediction = model.Predict(new IrisData()
 {
 SepalLength = 3.1f,
 SepalWidth = 2.5f,
 PetalLength = 1.2f,
 PetalWidth = 4.4f,
 });

 Assert.Equal(.2, prediction.PredictedLabels[0], 1);
 Assert.Equal(.8, prediction.PredictedLabels[1], 1);
 Assert.Equal(0, prediction.PredictedLabels[2], 2);
 }

 private void CompareMatrics(ClassificationMetrics metrics)
 {
 Assert.Equal(.98, metrics.AccuracyMacro);
 Assert.Equal(.98, metrics.AccuracyMicro, 2);
 Assert.Equal(.06, metrics.LogLoss, 2);
 Assert.InRange(metrics.LogLossReduction, 94, 96);
 Assert.Equal(1, metrics.TopKAccuracy);

 Assert.Equal(3, metrics.PerClassLogLoss.Length);
 Assert.Equal(0, metrics.PerClassLogLoss[0], 1);
 Assert.Equal(.1, metrics.PerClassLogLoss[1], 1);
 Assert.Equal(.1, metrics.PerClassLogLoss[2], 1);

 ConfusionMatrix matrix = metrics.ConfusionMatrix;
 Assert.Equal(3, matrix.Order);
 Assert.Equal(3, matrix.ClassNames.Count);
 Assert.Equal("0", matrix.ClassNames[0]);
 Assert.Equal("1", matrix.ClassNames[1]);
 Assert.Equal("2", matrix.ClassNames[2]);

 Assert.Equal(50, matrix[0, 0]);
 Assert.Equal(50, matrix["0", "0"]);
 Assert.Equal(0, matrix[0, 1]);
 Assert.Equal(0, matrix["0", "1"]);
 Assert.Equal(0, matrix[0, 2]);
 Assert.Equal(0, matrix["0", "2"]);

 Assert.Equal(0, matrix[1, 0]);
 Assert.Equal(0, matrix["1", "0"]);
 Assert.Equal(48, matrix[1, 1]);
 Assert.Equal(48, matrix["1", "1"]);
 Assert.Equal(2, matrix[1, 2]);
 Assert.Equal(2, matrix["1", "2"]);

 Assert.Equal(0, matrix[2, 0]);
 Assert.Equal(0, matrix["2", "0"]);
 Assert.Equal(1, matrix[2, 1]);
 Assert.Equal(1, matrix["2", "1"]);
 Assert.Equal(49, matrix[2, 2]);
 Assert.Equal(49, matrix["2", "2"]);
 }

 private ClassificationMetrics Evaluate(IHostEnvironment env, IDataView scoredData)
 {
 var dataEval = TrainUtils.CreateExamplesOpt(scoredData, label: "Label", feature: "Features");

 // Evaluate.
 // It does not work. It throws error "Failed to find 'Score' column" when Evaluate is called
 //var evaluator = new MultiClassClassifierEvaluator(env, new MultiClassClassifierEvaluator.Arguments() { OutputTopKAcc = 3 });

 var evaluator = new MultiClassMamlEvaluator(env, new MultiClassMamlEvaluator.Arguments() { OutputTopKAcc = 3 });
 var metricsDic = evaluator.Evaluate(dataEval);

 return ClassificationMetrics.FromMetrics(env, metricsDic["OverallMetrics"], metricsDic["ConfusionMatrix"])[0];
 }

 private IDataScorerTransform GetScorer(IHostEnvironment env, IDataView transforms, IPredictor pred, string testDataPath = null)
 {
 using (var ch = env.Start("Saving model"))
 using (var memoryStream = new MemoryStream())
 {
 var trainRoles = TrainUtils.CreateExamples(transforms, label: "Label", feature: "Features");

 // Model cannot be saved with CacheDataView
 TrainUtils.SaveModel(env, ch, memoryStream, pred, trainRoles);
 memoryStream.Position = 0;
 using (var rep = RepositoryReader.Open(memoryStream, ch))
 {
 IDataLoader testPipe = ModelFileUtils.LoadLoader(env, rep, new MultiFileSource(testDataPath), true);
 RoleMappedData testRoles = TrainUtils.CreateExamples(testPipe, label: "Label", feature: "Features");
 return ScoreUtils.GetScorer(pred, testRoles, env, testRoles.Schema);
 }
 }
 }
 }
}

118 changes: 118 additions & 0 deletions
test/Microsoft.ML.Tests/ScenariosWithDirectInstantiation/SentimentPredictionTests.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,118 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

using Microsoft.ML.Models;
using Microsoft.ML.Runtime;
using Microsoft.ML.Runtime.Api;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.FastTree;
using Microsoft.ML.Runtime.Internal.Calibration;
using Microsoft.ML.Runtime.Model;
using Microsoft.ML.Trainers;
using Microsoft.ML.Transforms;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using Xunit;

namespace Microsoft.ML.Scenarios
{
 public partial class ScenariosTests
 {
 [Fact]
 public void TrainAndPredictSentimentModelWithDirectionInstantiationTest()
 {
 var dataPath = GetDataPath(SentimentDataPath);
 var testDataPath = GetDataPath(SentimentTestPath);

 using (var env = new TlcEnvironment(seed: 1, conc: 1))
 {
 // Pipeline
 var loader = new TextLoader(env,
 new TextLoader.Arguments()
 {
 Separator = "tab",
 HasHeader = true,
 Column = new[]
 {
 new TextLoader.Column()
 {
 Name = "Label",
 Source = new [] { new TextLoader.Range() { Min=0, Max=0} },
 Type = DataKind.Num
 },

 new TextLoader.Column()
 {
 Name = "SentimentText",
 Source = new [] { new TextLoader.Range() { Min=1, Max=1} },
 Type = DataKind.Text
 }
 }
 }, new MultiFileSource(dataPath));

 var trans = TextTransform.Create(env, new TextTransform.Arguments()
 {
 Column = new TextTransform.Column
 {
 Name = "Features",
 Source = new[] { "SentimentText" }
 },
 KeepDiacritics = false,
 KeepPunctuations = false,
 TextCase = Runtime.TextAnalytics.TextNormalizerTransform.CaseNormalizationMode.Lower,
 OutputTokens = true,
 StopWordsRemover = new Runtime.TextAnalytics.PredefinedStopWordsRemoverFactory(),
 VectorNormalizer = TextTransform.TextNormKind.L2,
 CharFeatureExtractor = new NgramExtractorTransform.NgramExtractorArguments() { NgramLength = 3, AllLengths = false },
 WordFeatureExtractor = new NgramExtractorTransform.NgramExtractorArguments() { NgramLength = 2, AllLengths = true },
 },
 loader);

 // Train
 var trainer = new FastTreeBinaryClassificationTrainer(env, new FastTreeBinaryClassificationTrainer.Arguments()
 {
 NumLeaves = 5,
 NumTrees = 5,
 MinDocumentsInLeafs = 2
 });

 var trainRoles = TrainUtils.CreateExamples(trans, label: "Label", feature: "Features");
 trainer.Train(trainRoles);

 // Get scorer and evaluate the predictions from test data
 var pred = trainer.CreatePredictor();
 IDataScorerTransform testDataScorer = GetScorer(env, trans, pred, testDataPath);
 var metrics = EvaluateBinary(env, testDataScorer);
 ValidateBinaryMetrics(metrics);

 // Create prediction engine and test predictions
 var model = env.CreateBatchPredictionEngine<SentimentData, SentimentPrediction>(testDataScorer);
 var sentiments = GetTestData();
 var predictions = model.Predict(sentiments, false);
 Assert.Equal(2, predictions.Count());
 Assert.True(predictions.ElementAt(0).Sentiment.IsFalse);
 Assert.True(predictions.ElementAt(1).Sentiment.IsTrue);

 // Get feature importance based on feature gain during training
 var summary = ((FeatureWeightsCalibratedPredictor)pred).GetSummaryInKeyValuePairs(trainRoles.Schema);
 Assert.Equal(1.0, (double)summary[0].Value, 1);
 }
 }

 private BinaryClassificationMetrics EvaluateBinary(IHostEnvironment env, IDataView scoredData)
 {
 var dataEval = TrainUtils.CreateExamplesOpt(scoredData, label: "Label", feature: "Features");

 // Evaluate.
 // It does not work. It throws error "Failed to find 'Score' column" when Evaluate is called
 //var evaluator = new BinaryClassifierEvaluator(env, new BinaryClassifierEvaluator.Arguments());

 var evaluator = new BinaryClassifierMamlEvaluator(env, new BinaryClassifierMamlEvaluator.Arguments());
 var metricsDic = evaluator.Evaluate(dataEval);

 return BinaryClassificationMetrics.FromMetrics(env, metricsDic["OverallMetrics"], metricsDic["ConfusionMatrix"])[0];
 }
 }
}

, '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
Added tests for new API where components(Loaders/Transforms/Learners) are directly instantiated.#468

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

zeahmed
merged 2 commits into

from

Jul 2, 2018
 Merged


Added tests for new API where components(Loaders/Transforms/Learners) are directly instantiated.
#468
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
d8d4c2e

Added tests for new API where components(Loaders/Transforms/Learners)…


zeahmed Jul 2, 2018
0bfe5c3

Moved new tests to separate folder.


zeahmed Jul 2, 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


210 changes: 210 additions & 0 deletions
test/Microsoft.ML.Tests/ScenariosWithDirectInstantiation/IrisPlantClassificationTests.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,210 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

using Microsoft.ML.Models;
using Microsoft.ML.Runtime;
using Microsoft.ML.Runtime.Api;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.Learners;
using Microsoft.ML.Runtime.Model;
using System;
using System.IO;
using Xunit;

namespace Microsoft.ML.Scenarios
{
 public partial class ScenariosTests
 {
 [Fact]
 public void TrainAndPredictIrisModelUsingDirectInstantiationTest()
 {
 string dataPath = GetDataPath("iris.txt");
 string testDataPath = dataPath;

 using (var env = new TlcEnvironment(seed: 1, conc: 1))
 {
 // Pipeline
 var loader = new TextLoader(env,
 new TextLoader.Arguments()
 {
 HasHeader = false,
 Column = new[] {
 new TextLoader.Column()
 {
 Name = "Label",
 Source = new [] { new TextLoader.Range() { Min = 0, Max = 0} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "SepalLength",
 Source = new [] { new TextLoader.Range() { Min = 1, Max = 1} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "SepalWidth",
 Source = new [] { new TextLoader.Range() { Min = 2, Max = 2} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "PetalLength",
 Source = new [] { new TextLoader.Range() { Min = 3, Max = 3} },
 Type = DataKind.R4
 },
 new TextLoader.Column()
 {
 Name = "PetalWidth",
 Source = new [] { new TextLoader.Range() { Min = 4, Max = 4} },
 Type = DataKind.R4
 }
 }
 }, new MultiFileSource(dataPath));

 IDataTransform trans = new ConcatTransform(env, loader, "Features",
 "SepalLength", "SepalWidth", "PetalLength", "PetalWidth");

 // Normalizer is not automatically added though the trainer has 'NormalizeFeatures' On/Auto
 trans = NormalizeTransform.CreateMinMaxNormalizer(env, trans, "Features");

 // Train
 var trainer = new SdcaMultiClassTrainer(env, new SdcaMultiClassTrainer.Arguments());

 // Explicity adding CacheDataView since caching is not working though trainer has 'Caching' On/Auto
 var cached = new CacheDataView(env, trans, prefetch: null);
 var trainRoles = TrainUtils.CreateExamples(cached, label: "Label", feature: "Features");
 trainer.Train(trainRoles);

 // Get scorer and evaluate the predictions from test data
 var pred = trainer.CreatePredictor();
 IDataScorerTransform testDataScorer = GetScorer(env, trans, pred, testDataPath);
 var metrics = Evaluate(env, testDataScorer);
 CompareMatrics(metrics);

 // Create prediction engine and test predictions
 var model = env.CreatePredictionEngine<IrisData, IrisPrediction>(testDataScorer);
 ComparePredictions(model);

 // Get feature importance i.e. weight vector
 var summary = ((MulticlassLogisticRegressionPredictor)pred).GetSummaryInKeyValuePairs(trainRoles.Schema);
 Assert.Equal(7.757867, Convert.ToDouble(summary[0].Value), 5);
 }
 }

 private void ComparePredictions(PredictionEngine<IrisData, IrisPrediction> model)
 {
 IrisPrediction prediction = model.Predict(new IrisData()
 {
 SepalLength = 3.3f,
 SepalWidth = 1.6f,
 PetalLength = 0.2f,
 PetalWidth = 5.1f,
 });

 Assert.Equal(1, prediction.PredictedLabels[0], 2);
 Assert.Equal(0, prediction.PredictedLabels[1], 2);
 Assert.Equal(0, prediction.PredictedLabels[2], 2);

 prediction = model.Predict(new IrisData()
 {
 SepalLength = 3.1f,
 SepalWidth = 5.5f,
 PetalLength = 2.2f,
 PetalWidth = 6.4f,
 });

 Assert.Equal(0, prediction.PredictedLabels[0], 2);
 Assert.Equal(0, prediction.PredictedLabels[1], 2);
 Assert.Equal(1, prediction.PredictedLabels[2], 2);

 prediction = model.Predict(new IrisData()
 {
 SepalLength = 3.1f,
 SepalWidth = 2.5f,
 PetalLength = 1.2f,
 PetalWidth = 4.4f,
 });

 Assert.Equal(.2, prediction.PredictedLabels[0], 1);
 Assert.Equal(.8, prediction.PredictedLabels[1], 1);
 Assert.Equal(0, prediction.PredictedLabels[2], 2);
 }

 private void CompareMatrics(ClassificationMetrics metrics)
 {
 Assert.Equal(.98, metrics.AccuracyMacro);
 Assert.Equal(.98, metrics.AccuracyMicro, 2);
 Assert.Equal(.06, metrics.LogLoss, 2);
 Assert.InRange(metrics.LogLossReduction, 94, 96);
 Assert.Equal(1, metrics.TopKAccuracy);

 Assert.Equal(3, metrics.PerClassLogLoss.Length);
 Assert.Equal(0, metrics.PerClassLogLoss[0], 1);
 Assert.Equal(.1, metrics.PerClassLogLoss[1], 1);
 Assert.Equal(.1, metrics.PerClassLogLoss[2], 1);

 ConfusionMatrix matrix = metrics.ConfusionMatrix;
 Assert.Equal(3, matrix.Order);
 Assert.Equal(3, matrix.ClassNames.Count);
 Assert.Equal("0", matrix.ClassNames[0]);
 Assert.Equal("1", matrix.ClassNames[1]);
 Assert.Equal("2", matrix.ClassNames[2]);

 Assert.Equal(50, matrix[0, 0]);
 Assert.Equal(50, matrix["0", "0"]);
 Assert.Equal(0, matrix[0, 1]);
 Assert.Equal(0, matrix["0", "1"]);
 Assert.Equal(0, matrix[0, 2]);
 Assert.Equal(0, matrix["0", "2"]);

 Assert.Equal(0, matrix[1, 0]);
 Assert.Equal(0, matrix["1", "0"]);
 Assert.Equal(48, matrix[1, 1]);
 Assert.Equal(48, matrix["1", "1"]);
 Assert.Equal(2, matrix[1, 2]);
 Assert.Equal(2, matrix["1", "2"]);

 Assert.Equal(0, matrix[2, 0]);
 Assert.Equal(0, matrix["2", "0"]);
 Assert.Equal(1, matrix[2, 1]);
 Assert.Equal(1, matrix["2", "1"]);
 Assert.Equal(49, matrix[2, 2]);
 Assert.Equal(49, matrix["2", "2"]);
 }

 private ClassificationMetrics Evaluate(IHostEnvironment env, IDataView scoredData)
 {
 var dataEval = TrainUtils.CreateExamplesOpt(scoredData, label: "Label", feature: "Features");

 // Evaluate.
 // It does not work. It throws error "Failed to find 'Score' column" when Evaluate is called
 //var evaluator = new MultiClassClassifierEvaluator(env, new MultiClassClassifierEvaluator.Arguments() { OutputTopKAcc = 3 });

 var evaluator = new MultiClassMamlEvaluator(env, new MultiClassMamlEvaluator.Arguments() { OutputTopKAcc = 3 });
 var metricsDic = evaluator.Evaluate(dataEval);

 return ClassificationMetrics.FromMetrics(env, metricsDic["OverallMetrics"], metricsDic["ConfusionMatrix"])[0];
 }

 private IDataScorerTransform GetScorer(IHostEnvironment env, IDataView transforms, IPredictor pred, string testDataPath = null)
 {
 using (var ch = env.Start("Saving model"))
 using (var memoryStream = new MemoryStream())
 {
 var trainRoles = TrainUtils.CreateExamples(transforms, label: "Label", feature: "Features");

 // Model cannot be saved with CacheDataView
 TrainUtils.SaveModel(env, ch, memoryStream, pred, trainRoles);
 memoryStream.Position = 0;
 using (var rep = RepositoryReader.Open(memoryStream, ch))
 {
 IDataLoader testPipe = ModelFileUtils.LoadLoader(env, rep, new MultiFileSource(testDataPath), true);
 RoleMappedData testRoles = TrainUtils.CreateExamples(testPipe, label: "Label", feature: "Features");
 return ScoreUtils.GetScorer(pred, testRoles, env, testRoles.Schema);
 }
 }
 }
 }
}

118 changes: 118 additions & 0 deletions
test/Microsoft.ML.Tests/ScenariosWithDirectInstantiation/SentimentPredictionTests.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,118 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

using Microsoft.ML.Models;
using Microsoft.ML.Runtime;
using Microsoft.ML.Runtime.Api;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.FastTree;
using Microsoft.ML.Runtime.Internal.Calibration;
using Microsoft.ML.Runtime.Model;
using Microsoft.ML.Trainers;
using Microsoft.ML.Transforms;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using Xunit;

namespace Microsoft.ML.Scenarios
{
 public partial class ScenariosTests
 {
 [Fact]
 public void TrainAndPredictSentimentModelWithDirectionInstantiationTest()
 {
 var dataPath = GetDataPath(SentimentDataPath);
 var testDataPath = GetDataPath(SentimentTestPath);

 using (var env = new TlcEnvironment(seed: 1, conc: 1))
 {
 // Pipeline
 var loader = new TextLoader(env,
 new TextLoader.Arguments()
 {
 Separator = "tab",
 HasHeader = true,
 Column = new[]
 {
 new TextLoader.Column()
 {
 Name = "Label",
 Source = new [] { new TextLoader.Range() { Min=0, Max=0} },
 Type = DataKind.Num
 },

 new TextLoader.Column()
 {
 Name = "SentimentText",
 Source = new [] { new TextLoader.Range() { Min=1, Max=1} },
 Type = DataKind.Text
 }
 }
 }, new MultiFileSource(dataPath));

 var trans = TextTransform.Create(env, new TextTransform.Arguments()
 {
 Column = new TextTransform.Column
 {
 Name = "Features",
 Source = new[] { "SentimentText" }
 },
 KeepDiacritics = false,
 KeepPunctuations = false,
 TextCase = Runtime.TextAnalytics.TextNormalizerTransform.CaseNormalizationMode.Lower,
 OutputTokens = true,
 StopWordsRemover = new Runtime.TextAnalytics.PredefinedStopWordsRemoverFactory(),
 VectorNormalizer = TextTransform.TextNormKind.L2,
 CharFeatureExtractor = new NgramExtractorTransform.NgramExtractorArguments() { NgramLength = 3, AllLengths = false },
 WordFeatureExtractor = new NgramExtractorTransform.NgramExtractorArguments() { NgramLength = 2, AllLengths = true },
 },
 loader);

 // Train
 var trainer = new FastTreeBinaryClassificationTrainer(env, new FastTreeBinaryClassificationTrainer.Arguments()
 {
 NumLeaves = 5,
 NumTrees = 5,
 MinDocumentsInLeafs = 2
 });

 var trainRoles = TrainUtils.CreateExamples(trans, label: "Label", feature: "Features");
 trainer.Train(trainRoles);

 // Get scorer and evaluate the predictions from test data
 var pred = trainer.CreatePredictor();
 IDataScorerTransform testDataScorer = GetScorer(env, trans, pred, testDataPath);
 var metrics = EvaluateBinary(env, testDataScorer);
 ValidateBinaryMetrics(metrics);

 // Create prediction engine and test predictions
 var model = env.CreateBatchPredictionEngine<SentimentData, SentimentPrediction>(testDataScorer);
 var sentiments = GetTestData();
 var predictions = model.Predict(sentiments, false);
 Assert.Equal(2, predictions.Count());
 Assert.True(predictions.ElementAt(0).Sentiment.IsFalse);
 Assert.True(predictions.ElementAt(1).Sentiment.IsTrue);

 // Get feature importance based on feature gain during training
 var summary = ((FeatureWeightsCalibratedPredictor)pred).GetSummaryInKeyValuePairs(trainRoles.Schema);
 Assert.Equal(1.0, (double)summary[0].Value, 1);
 }
 }

 private BinaryClassificationMetrics EvaluateBinary(IHostEnvironment env, IDataView scoredData)
 {
 var dataEval = TrainUtils.CreateExamplesOpt(scoredData, label: "Label", feature: "Features");

 // Evaluate.
 // It does not work. It throws error "Failed to find 'Score' column" when Evaluate is called
 //var evaluator = new BinaryClassifierEvaluator(env, new BinaryClassifierEvaluator.Arguments());

 var evaluator = new BinaryClassifierMamlEvaluator(env, new BinaryClassifierMamlEvaluator.Arguments());
 var metricsDic = evaluator.Evaluate(dataEval);

 return BinaryClassificationMetrics.FromMetrics(env, metricsDic["OverallMetrics"], metricsDic["ConfusionMatrix"])[0];
 }
 }
}