Binary classification samples update#3311

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
artidoro merged 5 commits into from
Apr 16, 2019
Merged

Binary classification samples update #3311

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
c2aa76e
binary classification samples
artidoro Apr 11, 2019
03afa1b
linear svm
artidoro Apr 12, 2019
4d52f12
review comments
artidoro Apr 15, 2019
6898477
Recover LIBMF
artidoro Apr 15, 2019
11ffadd
adding note about AUC for prior
artidoro Apr 16, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
114 changes: 90 additions & 24 deletions .../samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptron.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -1,44 +1,110 @@
using Microsoft.ML;
using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;

namespace Samples.Dynamic.Trainers.BinaryClassification
{
public static class AveragedPerceptron
{
// In this examples we will use the adult income dataset. The goal is to predict
// if a person's income is above $50K or not, based on demographic information about that person.
// For more details about this dataset, please see https://archive.ics.uci.edu/ml/datasets/adult.
public static void Example()
{
// Create a new context for ML.NET operations. It can be used for exception tracking and logging,
// as a catalog of available operations and as the source of randomness.
// Setting the seed to a fixed number in this example to make outputs deterministic.
var mlContext = new MLContext(seed: 0);

// Download and featurize the dataset.
var data = Microsoft.ML.SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
// Create a list of training data points.
var dataPoints = GenerateRandomDataPoints(1000);

// Leave out 10% of data for testing.
var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
// Convert the list of data points to an IDataView object, which is consumable by ML.NET API.
var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

// Create data training pipeline.
var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron(numberOfIterations: 10);
// Define the trainer.
var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron();

// Fit this pipeline to the training data.
var model = pipeline.Fit(trainTestData.TrainSet);
// Train the model.
var model = pipeline.Fit(trainingData);

// Evaluate how the model is doing on the test data.
var dataWithPredictions = model.Transform(trainTestData.TestSet);
var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(dataWithPredictions);
Microsoft.ML.SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
// Create testing data. Use different random seed to make it different from training data.
var testData = mlContext.Data.LoadFromEnumerable(GenerateRandomDataPoints(500, seed:123));

// Run the model on test data set.
var transformedTestData = model.Transform(testData);

// Convert IDataView object to a list.
var predictions = mlContext.Data.CreateEnumerable<Prediction>(transformedTestData, reuseRowObject: false).ToList();

// Print 5 predictions.
foreach (var p in predictions.Take(5))
Console.WriteLine($"Label: {p.Label}, Prediction: {p.PredictedLabel}");

// Expected output:
// Label: True, Prediction: True
// Label: False, Prediction: False
// Label: True, Prediction: True
// Label: True, Prediction: False
// Label: False, Prediction: False

// Evaluate the overall metrics.
var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(transformedTestData);
PrintMetrics(metrics);

// Expected output:
// Accuracy: 0.86
// AUC: 0.91
// F1 Score: 0.68
// Negative Precision: 0.90
// Negative Recall: 0.91
// Positive Precision: 0.70
// Positive Recall: 0.66
// Accuracy: 0.72
// AUC: 0.79
// F1 Score: 0.68
// Negative Precision: 0.71
// Negative Recall: 0.80
// Positive Precision: 0.74
// Positive Recall: 0.63
}

private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed=0)
{
var random = new Random(seed);
float randomFloat() => (float)random.NextDouble();
for (int i = 0; i < count; i++)
{
var label = randomFloat() > 0.5f;
yield return new DataPoint
{
Label = label,
// Create random features that are correlated with the label.
// For data points with false label, the feature values are slightly increased by adding a constant.
Features = Enumerable.Repeat(label, 50).Select(x => x ? randomFloat() : randomFloat() + 0.1f).ToArray()
};
}
}

// Example with label and 50 feature values. A data set is a collection of such examples.
private class DataPoint
{
public bool Label { get; set; }
[VectorType(50)]
public float[] Features { get; set; }
}

// Class used to capture predictions.
private class Prediction
{
// Original label.
public bool Label { get; set; }
// Predicted label from the trainer.
public bool PredictedLabel { get; set; }
}

// Pretty-print BinaryClassificationMetrics objects.
private static void PrintMetrics(BinaryClassificationMetrics metrics)
{
Console.WriteLine($"Accuracy: {metrics.Accuracy:F2}");
Console.WriteLine($"AUC: {metrics.AreaUnderRocCurve:F2}");
Console.WriteLine($"F1 Score: {metrics.F1Score:F2}");
Console.WriteLine($"Negative Precision: {metrics.NegativePrecision:F2}");
Console.WriteLine($"Negative Recall: {metrics.NegativeRecall:F2}");
Console.WriteLine($"Positive Precision: {metrics.PositivePrecision:F2}");
Console.WriteLine($"Positive Recall: {metrics.PositiveRecall:F2}");
}
}
}
}
29 changes: 29 additions & 0 deletions .../samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptron.tt
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,29 @@
<#@ include file="BinaryClassification.ttinclude"#>
<#+
string ClassName = "AveragedPerceptron";
string Trainer = "AveragedPerceptron";
string TrainerOptions = null;
bool IsCalibrated = false;
bool CacheData = false;

string LabelThreshold = "0.5f";
string DataSepValue = "0.1f";
string OptionsInclude = "";
string Comments= "";

string ExpectedOutputPerInstance = @"// Expected output:
// Label: True, Prediction: True
// Label: False, Prediction: False
// Label: True, Prediction: True
// Label: True, Prediction: False
// Label: False, Prediction: False";

string ExpectedOutput = @"// Expected output:
// Accuracy: 0.72
// AUC: 0.79
// F1 Score: 0.68
// Negative Precision: 0.71
// Negative Recall: 0.80
// Positive Precision: 0.74
// Positive Recall: 0.63";
#>
116 changes: 91 additions & 25 deletions ...crosoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptronWithOptions.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -1,28 +1,29 @@
using Microsoft.ML;
using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Trainers;

namespace Samples.Dynamic.Trainers.BinaryClassification
{
public static class AveragedPerceptronWithOptions
{
// In this examples we will use the adult income dataset. The goal is to predict
// if a person's income is above $50K or not, based on demographic information about that person.
// For more details about this dataset, please see https://archive.ics.uci.edu/ml/datasets/adult.
public static void Example()
{
// Create a new context for ML.NET operations. It can be used for exception tracking and logging,
// as a catalog of available operations and as the source of randomness.
// Setting the seed to a fixed number in this example to make outputs deterministic.
var mlContext = new MLContext(seed: 0);

// Download and featurize the dataset.
var data = Microsoft.ML.SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
// Create a list of training data points.
var dataPoints = GenerateRandomDataPoints(1000);

// Leave out 10% of data for testing.
var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
// Convert the list of data points to an IDataView object, which is consumable by ML.NET API.
var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

// Define the trainer options.
var options = new AveragedPerceptronTrainer.Options()
// Define trainer options.
var options = new AveragedPerceptronTrainer.Options
{
LossFunction = new SmoothedHingeLoss(),
LearningRate = 0.1f,
Expand All@@ -31,25 +32,90 @@ public static void Example()
NumberOfIterations = 10
};

// Create data training pipeline.
// Define the trainer.
var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron(options);

// Fit this pipeline to the training data.
var model = pipeline.Fit(trainTestData.TrainSet);
// Train the model.
var model = pipeline.Fit(trainingData);

// Evaluate how the model is doing on the test data.
var dataWithPredictions = model.Transform(trainTestData.TestSet);
var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(dataWithPredictions);
Microsoft.ML.SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
// Create testing data. Use different random seed to make it different from training data.
var testData = mlContext.Data.LoadFromEnumerable(GenerateRandomDataPoints(500, seed:123));

// Run the model on test data set.
var transformedTestData = model.Transform(testData);

// Convert IDataView object to a list.
var predictions = mlContext.Data.CreateEnumerable<Prediction>(transformedTestData, reuseRowObject: false).ToList();

// Print 5 predictions.
foreach (var p in predictions.Take(5))
Console.WriteLine($"Label: {p.Label}, Prediction: {p.PredictedLabel}");

// Expected output:
// Accuracy: 0.86
// AUC: 0.90
// F1 Score: 0.66
// Negative Precision: 0.89
// Negative Recall: 0.93
// Positive Precision: 0.72
// Positive Recall: 0.61
// Label: True, Prediction: True
// Label: False, Prediction: False
// Label: True, Prediction: True
// Label: True, Prediction: True
// Label: False, Prediction: False

// Evaluate the overall metrics.
var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(transformedTestData);
PrintMetrics(metrics);

// Expected output:
// Accuracy: 0.89
// AUC: 0.96
// F1 Score: 0.88
// Negative Precision: 0.87
// Negative Recall: 0.92
// Positive Precision: 0.91
// Positive Recall: 0.85
}

private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed=0)
{
var random = new Random(seed);
float randomFloat() => (float)random.NextDouble();
for (int i = 0; i < count; i++)
{
var label = randomFloat() > 0.5f;
yield return new DataPoint
{
Label = label,
// Create random features that are correlated with the label.
// For data points with false label, the feature values are slightly increased by adding a constant.
Features = Enumerable.Repeat(label, 50).Select(x => x ? randomFloat() : randomFloat() + 0.1f).ToArray()
};
}
}

// Example with label and 50 feature values. A data set is a collection of such examples.
private class DataPoint
{
public bool Label { get; set; }
[VectorType(50)]
public float[] Features { get; set; }
}

// Class used to capture predictions.
private class Prediction
{
// Original label.
public bool Label { get; set; }
// Predicted label from the trainer.
public bool PredictedLabel { get; set; }
}

// Pretty-print BinaryClassificationMetrics objects.
private static void PrintMetrics(BinaryClassificationMetrics metrics)
{
Console.WriteLine($"Accuracy: {metrics.Accuracy:F2}");
Console.WriteLine($"AUC: {metrics.AreaUnderRocCurve:F2}");
Console.WriteLine($"F1 Score: {metrics.F1Score:F2}");
Console.WriteLine($"Negative Precision: {metrics.NegativePrecision:F2}");
Console.WriteLine($"Negative Recall: {metrics.NegativeRecall:F2}");
Console.WriteLine($"Positive Precision: {metrics.PositivePrecision:F2}");
Console.WriteLine($"Positive Recall: {metrics.PositiveRecall:F2}");
}
}
}
}
37 changes: 37 additions & 0 deletions ...crosoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptronWithOptions.tt
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
<#@ include file="BinaryClassification.ttinclude"#>
<#+
string ClassName="AveragedPerceptronWithOptions";
string Trainer = "AveragedPerceptron";
bool IsCalibrated = false;

string LabelThreshold = "0.5f";
string DataSepValue = "0.1f";
string OptionsInclude = "using Microsoft.ML.Trainers;";
string Comments= "";
bool CacheData = false;

string TrainerOptions = @"AveragedPerceptronTrainer.Options
{
LossFunction = new SmoothedHingeLoss(),
LearningRate = 0.1f,
LazyUpdate = false,
RecencyGain = 0.1f,
NumberOfIterations = 10
}";

string ExpectedOutputPerInstance= @"// Expected output:
// Label: True, Prediction: True
// Label: False, Prediction: False
// Label: True, Prediction: True
// Label: True, Prediction: True
// Label: False, Prediction: False";

string ExpectedOutput = @"// Expected output:
// Accuracy: 0.89
// AUC: 0.96
// F1 Score: 0.88
// Negative Precision: 0.87
// Negative Recall: 0.92
// Positive Precision: 0.91
// Positive Recall: 0.85";
#>
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all 
 blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks");
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
Binary classification samples update#3311

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

artidoro
merged 5 commits into

from

Apr 16, 2019
 Merged


Binary classification samples update
#3311
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


5 commits


Select commit
Hold shift + click to select a range
c2aa76e

binary classification samples


artidoro Apr 11, 2019
03afa1b

linear svm


artidoro Apr 12, 2019
4d52f12

review comments


artidoro Apr 15, 2019
6898477

Recover LIBMF


artidoro Apr 15, 2019
11ffadd

adding note about AUC for prior


artidoro Apr 16, 2019

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


114 changes: 90 additions & 24 deletions
.../samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptron.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,44 +1,110 @@
using Microsoft.ML;
using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;

namespace Samples.Dynamic.Trainers.BinaryClassification
{
 public static class AveragedPerceptron
 {
 // In this examples we will use the adult income dataset. The goal is to predict
 // if a person's income is above $50K or not, based on demographic information about that person.
 // For more details about this dataset, please see https://archive.ics.uci.edu/ml/datasets/adult.
 public static void Example()
 {
 // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
 // as a catalog of available operations and as the source of randomness.
 // Setting the seed to a fixed number in this example to make outputs deterministic.
 var mlContext = new MLContext(seed: 0);

 // Download and featurize the dataset.
 var data = Microsoft.ML.SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 // Create a list of training data points.
 var dataPoints = GenerateRandomDataPoints(1000);

 // Leave out 10% of data for testing.
 var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 // Convert the list of data points to an IDataView object, which is consumable by ML.NET API.
 var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

 // Create data training pipeline.
 var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron(numberOfIterations: 10);
 // Define the trainer.
 var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron();

 // Fit this pipeline to the training data.
 var model = pipeline.Fit(trainTestData.TrainSet);
 // Train the model.
 var model = pipeline.Fit(trainingData);

 // Evaluate how the model is doing on the test data.
 var dataWithPredictions = model.Transform(trainTestData.TestSet);
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(dataWithPredictions);
 Microsoft.ML.SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
 // Create testing data. Use different random seed to make it different from training data.
 var testData = mlContext.Data.LoadFromEnumerable(GenerateRandomDataPoints(500, seed:123));

 // Run the model on test data set.
 var transformedTestData = model.Transform(testData);

 // Convert IDataView object to a list.
 var predictions = mlContext.Data.CreateEnumerable<Prediction>(transformedTestData, reuseRowObject: false).ToList();

 // Print 5 predictions.
 foreach (var p in predictions.Take(5))
 Console.WriteLine($"Label: {p.Label}, Prediction: {p.PredictedLabel}");

 // Expected output:
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: False
 // Label: False, Prediction: False

 // Evaluate the overall metrics.
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(transformedTestData);
 PrintMetrics(metrics);

 // Expected output:
 // Accuracy: 0.86
 // AUC: 0.91
 // F1 Score: 0.68
 // Negative Precision: 0.90
 // Negative Recall: 0.91
 // Positive Precision: 0.70
 // Positive Recall: 0.66
 // Accuracy: 0.72
 // AUC: 0.79
 // F1 Score: 0.68
 // Negative Precision: 0.71
 // Negative Recall: 0.80
 // Positive Precision: 0.74
 // Positive Recall: 0.63
 }

 private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed=0)
 {
 var random = new Random(seed);
 float randomFloat() => (float)random.NextDouble();
 for (int i = 0; i < count; i++)
 {
 var label = randomFloat() > 0.5f;
 yield return new DataPoint
 {
 Label = label,
 // Create random features that are correlated with the label.
 // For data points with false label, the feature values are slightly increased by adding a constant.
 Features = Enumerable.Repeat(label, 50).Select(x => x ? randomFloat() : randomFloat() + 0.1f).ToArray()
 };
 }
 }

 // Example with label and 50 feature values. A data set is a collection of such examples.
 private class DataPoint
 {
 public bool Label { get; set; }
 [VectorType(50)]
 public float[] Features { get; set; }
 }

 // Class used to capture predictions.
 private class Prediction
 {
 // Original label.
 public bool Label { get; set; }
 // Predicted label from the trainer.
 public bool PredictedLabel { get; set; }
 }

 // Pretty-print BinaryClassificationMetrics objects.
 private static void PrintMetrics(BinaryClassificationMetrics metrics)
 {
 Console.WriteLine($"Accuracy: {metrics.Accuracy:F2}");
 Console.WriteLine($"AUC: {metrics.AreaUnderRocCurve:F2}");
 Console.WriteLine($"F1 Score: {metrics.F1Score:F2}");
 Console.WriteLine($"Negative Precision: {metrics.NegativePrecision:F2}");
 Console.WriteLine($"Negative Recall: {metrics.NegativeRecall:F2}");
 Console.WriteLine($"Positive Precision: {metrics.PositivePrecision:F2}");
 Console.WriteLine($"Positive Recall: {metrics.PositiveRecall:F2}");
 }
 }
}
}

29 changes: 29 additions & 0 deletions
.../samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptron.tt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,29 @@
<#@ include file="BinaryClassification.ttinclude"#>
<#+
string ClassName = "AveragedPerceptron";
string Trainer = "AveragedPerceptron";
string TrainerOptions = null;
bool IsCalibrated = false;
bool CacheData = false;

string LabelThreshold = "0.5f";
string DataSepValue = "0.1f";
string OptionsInclude = "";
string Comments= "";

string ExpectedOutputPerInstance = @"// Expected output:
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: False
 // Label: False, Prediction: False";

string ExpectedOutput = @"// Expected output:
 // Accuracy: 0.72
 // AUC: 0.79
 // F1 Score: 0.68
 // Negative Precision: 0.71
 // Negative Recall: 0.80
 // Positive Precision: 0.74
 // Positive Recall: 0.63";
#>

116 changes: 91 additions & 25 deletions
...crosoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptronWithOptions.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,28 +1,29 @@
using Microsoft.ML;
using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Trainers;

namespace Samples.Dynamic.Trainers.BinaryClassification
{
 public static class AveragedPerceptronWithOptions
 {
 // In this examples we will use the adult income dataset. The goal is to predict
 // if a person's income is above $50K or not, based on demographic information about that person.
 // For more details about this dataset, please see https://archive.ics.uci.edu/ml/datasets/adult.
 public static void Example()
 {
 // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
 // as a catalog of available operations and as the source of randomness.
 // Setting the seed to a fixed number in this example to make outputs deterministic.
 var mlContext = new MLContext(seed: 0);

 // Download and featurize the dataset.
 var data = Microsoft.ML.SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 // Create a list of training data points.
 var dataPoints = GenerateRandomDataPoints(1000);

 // Leave out 10% of data for testing.
 var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 // Convert the list of data points to an IDataView object, which is consumable by ML.NET API.
 var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

 // Define the trainer options.
 var options = new AveragedPerceptronTrainer.Options()
 // Define trainer options.
 var options = new AveragedPerceptronTrainer.Options
 {
 LossFunction = new SmoothedHingeLoss(),
 LearningRate = 0.1f,
Expand All@@ -31,25 +32,90 @@ public static void Example()
 NumberOfIterations = 10
 };

 // Create data training pipeline.
 // Define the trainer.
 var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron(options);

 // Fit this pipeline to the training data.
 var model = pipeline.Fit(trainTestData.TrainSet);
 // Train the model.
 var model = pipeline.Fit(trainingData);

 // Evaluate how the model is doing on the test data.
 var dataWithPredictions = model.Transform(trainTestData.TestSet);
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(dataWithPredictions);
 Microsoft.ML.SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
 // Create testing data. Use different random seed to make it different from training data.
 var testData = mlContext.Data.LoadFromEnumerable(GenerateRandomDataPoints(500, seed:123));

 // Run the model on test data set.
 var transformedTestData = model.Transform(testData);

 // Convert IDataView object to a list.
 var predictions = mlContext.Data.CreateEnumerable<Prediction>(transformedTestData, reuseRowObject: false).ToList();

 // Print 5 predictions.
 foreach (var p in predictions.Take(5))
 Console.WriteLine($"Label: {p.Label}, Prediction: {p.PredictedLabel}");

 // Expected output:
 // Accuracy: 0.86
 // AUC: 0.90
 // F1 Score: 0.66
 // Negative Precision: 0.89
 // Negative Recall: 0.93
 // Positive Precision: 0.72
 // Positive Recall: 0.61
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: True
 // Label: False, Prediction: False

 // Evaluate the overall metrics.
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(transformedTestData);
 PrintMetrics(metrics);

 // Expected output:
 // Accuracy: 0.89
 // AUC: 0.96
 // F1 Score: 0.88
 // Negative Precision: 0.87
 // Negative Recall: 0.92
 // Positive Precision: 0.91
 // Positive Recall: 0.85
 }

 private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed=0)
 {
 var random = new Random(seed);
 float randomFloat() => (float)random.NextDouble();
 for (int i = 0; i < count; i++)
 {
 var label = randomFloat() > 0.5f;
 yield return new DataPoint
 {
 Label = label,
 // Create random features that are correlated with the label.
 // For data points with false label, the feature values are slightly increased by adding a constant.
 Features = Enumerable.Repeat(label, 50).Select(x => x ? randomFloat() : randomFloat() + 0.1f).ToArray()
 };
 }
 }

 // Example with label and 50 feature values. A data set is a collection of such examples.
 private class DataPoint
 {
 public bool Label { get; set; }
 [VectorType(50)]
 public float[] Features { get; set; }
 }

 // Class used to capture predictions.
 private class Prediction
 {
 // Original label.
 public bool Label { get; set; }
 // Predicted label from the trainer.
 public bool PredictedLabel { get; set; }
 }

 // Pretty-print BinaryClassificationMetrics objects.
 private static void PrintMetrics(BinaryClassificationMetrics metrics)
 {
 Console.WriteLine($"Accuracy: {metrics.Accuracy:F2}");
 Console.WriteLine($"AUC: {metrics.AreaUnderRocCurve:F2}");
 Console.WriteLine($"F1 Score: {metrics.F1Score:F2}");
 Console.WriteLine($"Negative Precision: {metrics.NegativePrecision:F2}");
 Console.WriteLine($"Negative Recall: {metrics.NegativeRecall:F2}");
 Console.WriteLine($"Positive Precision: {metrics.PositivePrecision:F2}");
 Console.WriteLine($"Positive Recall: {metrics.PositiveRecall:F2}");
 }
 }
}
}

37 changes: 37 additions & 0 deletions
...crosoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptronWithOptions.tt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
<#@ include file="BinaryClassification.ttinclude"#>
<#+
string ClassName="AveragedPerceptronWithOptions";
string Trainer = "AveragedPerceptron";
bool IsCalibrated = false;

string LabelThreshold = "0.5f";
string DataSepValue = "0.1f";
string OptionsInclude = "using Microsoft.ML.Trainers;";
string Comments= "";
bool CacheData = false;

string TrainerOptions = @"AveragedPerceptronTrainer.Options
 {
 LossFunction = new SmoothedHingeLoss(),
 LearningRate = 0.1f,
 LazyUpdate = false,
 RecencyGain = 0.1f,
 NumberOfIterations = 10
 }";

string ExpectedOutputPerInstance= @"// Expected output:
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: True
 // Label: False, Prediction: False";

string ExpectedOutput = @"// Expected output:
 // Accuracy: 0.89
 // AUC: 0.96
 // F1 Score: 0.88
 // Negative Precision: 0.87
 // Negative Recall: 0.92
 // Positive Precision: 0.91
 // Positive Recall: 0.85";
#>
Loading

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

Skip to content
Binary classification samples update#3311

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

artidoro
merged 5 commits into

from

Apr 16, 2019
 Merged


Binary classification samples update
#3311
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


5 commits


Select commit
Hold shift + click to select a range
c2aa76e

binary classification samples


artidoro Apr 11, 2019
03afa1b

linear svm


artidoro Apr 12, 2019
4d52f12

review comments


artidoro Apr 15, 2019
6898477

Recover LIBMF


artidoro Apr 15, 2019
11ffadd

adding note about AUC for prior


artidoro Apr 16, 2019

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


114 changes: 90 additions & 24 deletions
.../samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptron.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,44 +1,110 @@
using Microsoft.ML;
using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;

namespace Samples.Dynamic.Trainers.BinaryClassification
{
 public static class AveragedPerceptron
 {
 // In this examples we will use the adult income dataset. The goal is to predict
 // if a person's income is above $50K or not, based on demographic information about that person.
 // For more details about this dataset, please see https://archive.ics.uci.edu/ml/datasets/adult.
 public static void Example()
 {
 // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
 // as a catalog of available operations and as the source of randomness.
 // Setting the seed to a fixed number in this example to make outputs deterministic.
 var mlContext = new MLContext(seed: 0);

 // Download and featurize the dataset.
 var data = Microsoft.ML.SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 // Create a list of training data points.
 var dataPoints = GenerateRandomDataPoints(1000);

 // Leave out 10% of data for testing.
 var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 // Convert the list of data points to an IDataView object, which is consumable by ML.NET API.
 var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

 // Create data training pipeline.
 var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron(numberOfIterations: 10);
 // Define the trainer.
 var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron();

 // Fit this pipeline to the training data.
 var model = pipeline.Fit(trainTestData.TrainSet);
 // Train the model.
 var model = pipeline.Fit(trainingData);

 // Evaluate how the model is doing on the test data.
 var dataWithPredictions = model.Transform(trainTestData.TestSet);
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(dataWithPredictions);
 Microsoft.ML.SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
 // Create testing data. Use different random seed to make it different from training data.
 var testData = mlContext.Data.LoadFromEnumerable(GenerateRandomDataPoints(500, seed:123));

 // Run the model on test data set.
 var transformedTestData = model.Transform(testData);

 // Convert IDataView object to a list.
 var predictions = mlContext.Data.CreateEnumerable<Prediction>(transformedTestData, reuseRowObject: false).ToList();

 // Print 5 predictions.
 foreach (var p in predictions.Take(5))
 Console.WriteLine($"Label: {p.Label}, Prediction: {p.PredictedLabel}");

 // Expected output:
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: False
 // Label: False, Prediction: False

 // Evaluate the overall metrics.
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(transformedTestData);
 PrintMetrics(metrics);

 // Expected output:
 // Accuracy: 0.86
 // AUC: 0.91
 // F1 Score: 0.68
 // Negative Precision: 0.90
 // Negative Recall: 0.91
 // Positive Precision: 0.70
 // Positive Recall: 0.66
 // Accuracy: 0.72
 // AUC: 0.79
 // F1 Score: 0.68
 // Negative Precision: 0.71
 // Negative Recall: 0.80
 // Positive Precision: 0.74
 // Positive Recall: 0.63
 }

 private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed=0)
 {
 var random = new Random(seed);
 float randomFloat() => (float)random.NextDouble();
 for (int i = 0; i < count; i++)
 {
 var label = randomFloat() > 0.5f;
 yield return new DataPoint
 {
 Label = label,
 // Create random features that are correlated with the label.
 // For data points with false label, the feature values are slightly increased by adding a constant.
 Features = Enumerable.Repeat(label, 50).Select(x => x ? randomFloat() : randomFloat() + 0.1f).ToArray()
 };
 }
 }

 // Example with label and 50 feature values. A data set is a collection of such examples.
 private class DataPoint
 {
 public bool Label { get; set; }
 [VectorType(50)]
 public float[] Features { get; set; }
 }

 // Class used to capture predictions.
 private class Prediction
 {
 // Original label.
 public bool Label { get; set; }
 // Predicted label from the trainer.
 public bool PredictedLabel { get; set; }
 }

 // Pretty-print BinaryClassificationMetrics objects.
 private static void PrintMetrics(BinaryClassificationMetrics metrics)
 {
 Console.WriteLine($"Accuracy: {metrics.Accuracy:F2}");
 Console.WriteLine($"AUC: {metrics.AreaUnderRocCurve:F2}");
 Console.WriteLine($"F1 Score: {metrics.F1Score:F2}");
 Console.WriteLine($"Negative Precision: {metrics.NegativePrecision:F2}");
 Console.WriteLine($"Negative Recall: {metrics.NegativeRecall:F2}");
 Console.WriteLine($"Positive Precision: {metrics.PositivePrecision:F2}");
 Console.WriteLine($"Positive Recall: {metrics.PositiveRecall:F2}");
 }
 }
}
}

29 changes: 29 additions & 0 deletions
.../samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptron.tt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,29 @@
<#@ include file="BinaryClassification.ttinclude"#>
<#+
string ClassName = "AveragedPerceptron";
string Trainer = "AveragedPerceptron";
string TrainerOptions = null;
bool IsCalibrated = false;
bool CacheData = false;

string LabelThreshold = "0.5f";
string DataSepValue = "0.1f";
string OptionsInclude = "";
string Comments= "";

string ExpectedOutputPerInstance = @"// Expected output:
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: False
 // Label: False, Prediction: False";

string ExpectedOutput = @"// Expected output:
 // Accuracy: 0.72
 // AUC: 0.79
 // F1 Score: 0.68
 // Negative Precision: 0.71
 // Negative Recall: 0.80
 // Positive Precision: 0.74
 // Positive Recall: 0.63";
#>

116 changes: 91 additions & 25 deletions
...crosoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptronWithOptions.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,28 +1,29 @@
using Microsoft.ML;
using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Trainers;

namespace Samples.Dynamic.Trainers.BinaryClassification
{
 public static class AveragedPerceptronWithOptions
 {
 // In this examples we will use the adult income dataset. The goal is to predict
 // if a person's income is above $50K or not, based on demographic information about that person.
 // For more details about this dataset, please see https://archive.ics.uci.edu/ml/datasets/adult.
 public static void Example()
 {
 // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
 // as a catalog of available operations and as the source of randomness.
 // Setting the seed to a fixed number in this example to make outputs deterministic.
 var mlContext = new MLContext(seed: 0);

 // Download and featurize the dataset.
 var data = Microsoft.ML.SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 // Create a list of training data points.
 var dataPoints = GenerateRandomDataPoints(1000);

 // Leave out 10% of data for testing.
 var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 // Convert the list of data points to an IDataView object, which is consumable by ML.NET API.
 var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

 // Define the trainer options.
 var options = new AveragedPerceptronTrainer.Options()
 // Define trainer options.
 var options = new AveragedPerceptronTrainer.Options
 {
 LossFunction = new SmoothedHingeLoss(),
 LearningRate = 0.1f,
Expand All@@ -31,25 +32,90 @@ public static void Example()
 NumberOfIterations = 10
 };

 // Create data training pipeline.
 // Define the trainer.
 var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron(options);

 // Fit this pipeline to the training data.
 var model = pipeline.Fit(trainTestData.TrainSet);
 // Train the model.
 var model = pipeline.Fit(trainingData);

 // Evaluate how the model is doing on the test data.
 var dataWithPredictions = model.Transform(trainTestData.TestSet);
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(dataWithPredictions);
 Microsoft.ML.SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
 // Create testing data. Use different random seed to make it different from training data.
 var testData = mlContext.Data.LoadFromEnumerable(GenerateRandomDataPoints(500, seed:123));

 // Run the model on test data set.
 var transformedTestData = model.Transform(testData);

 // Convert IDataView object to a list.
 var predictions = mlContext.Data.CreateEnumerable<Prediction>(transformedTestData, reuseRowObject: false).ToList();

 // Print 5 predictions.
 foreach (var p in predictions.Take(5))
 Console.WriteLine($"Label: {p.Label}, Prediction: {p.PredictedLabel}");

 // Expected output:
 // Accuracy: 0.86
 // AUC: 0.90
 // F1 Score: 0.66
 // Negative Precision: 0.89
 // Negative Recall: 0.93
 // Positive Precision: 0.72
 // Positive Recall: 0.61
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: True
 // Label: False, Prediction: False

 // Evaluate the overall metrics.
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(transformedTestData);
 PrintMetrics(metrics);

 // Expected output:
 // Accuracy: 0.89
 // AUC: 0.96
 // F1 Score: 0.88
 // Negative Precision: 0.87
 // Negative Recall: 0.92
 // Positive Precision: 0.91
 // Positive Recall: 0.85
 }

 private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed=0)
 {
 var random = new Random(seed);
 float randomFloat() => (float)random.NextDouble();
 for (int i = 0; i < count; i++)
 {
 var label = randomFloat() > 0.5f;
 yield return new DataPoint
 {
 Label = label,
 // Create random features that are correlated with the label.
 // For data points with false label, the feature values are slightly increased by adding a constant.
 Features = Enumerable.Repeat(label, 50).Select(x => x ? randomFloat() : randomFloat() + 0.1f).ToArray()
 };
 }
 }

 // Example with label and 50 feature values. A data set is a collection of such examples.
 private class DataPoint
 {
 public bool Label { get; set; }
 [VectorType(50)]
 public float[] Features { get; set; }
 }

 // Class used to capture predictions.
 private class Prediction
 {
 // Original label.
 public bool Label { get; set; }
 // Predicted label from the trainer.
 public bool PredictedLabel { get; set; }
 }

 // Pretty-print BinaryClassificationMetrics objects.
 private static void PrintMetrics(BinaryClassificationMetrics metrics)
 {
 Console.WriteLine($"Accuracy: {metrics.Accuracy:F2}");
 Console.WriteLine($"AUC: {metrics.AreaUnderRocCurve:F2}");
 Console.WriteLine($"F1 Score: {metrics.F1Score:F2}");
 Console.WriteLine($"Negative Precision: {metrics.NegativePrecision:F2}");
 Console.WriteLine($"Negative Recall: {metrics.NegativeRecall:F2}");
 Console.WriteLine($"Positive Precision: {metrics.PositivePrecision:F2}");
 Console.WriteLine($"Positive Recall: {metrics.PositiveRecall:F2}");
 }
 }
}
}

37 changes: 37 additions & 0 deletions
...crosoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptronWithOptions.tt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
<#@ include file="BinaryClassification.ttinclude"#>
<#+
string ClassName="AveragedPerceptronWithOptions";
string Trainer = "AveragedPerceptron";
bool IsCalibrated = false;

string LabelThreshold = "0.5f";
string DataSepValue = "0.1f";
string OptionsInclude = "using Microsoft.ML.Trainers;";
string Comments= "";
bool CacheData = false;

string TrainerOptions = @"AveragedPerceptronTrainer.Options
 {
 LossFunction = new SmoothedHingeLoss(),
 LearningRate = 0.1f,
 LazyUpdate = false,
 RecencyGain = 0.1f,
 NumberOfIterations = 10
 }";

string ExpectedOutputPerInstance= @"// Expected output:
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: True
 // Label: False, Prediction: False";

string ExpectedOutput = @"// Expected output:
 // Accuracy: 0.89
 // AUC: 0.96
 // F1 Score: 0.88
 // Negative Precision: 0.87
 // Negative Recall: 0.92
 // Positive Precision: 0.91
 // Positive Recall: 0.85";
#>
Loading

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

Skip to content
Binary classification samples update#3311

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

artidoro
merged 5 commits into

from

Apr 16, 2019
 Merged


Binary classification samples update
#3311
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


5 commits


Select commit
Hold shift + click to select a range
c2aa76e

binary classification samples


artidoro Apr 11, 2019
03afa1b

linear svm


artidoro Apr 12, 2019
4d52f12

review comments


artidoro Apr 15, 2019
6898477

Recover LIBMF


artidoro Apr 15, 2019
11ffadd

adding note about AUC for prior


artidoro Apr 16, 2019

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


114 changes: 90 additions & 24 deletions
.../samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptron.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,44 +1,110 @@
using Microsoft.ML;
using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;

namespace Samples.Dynamic.Trainers.BinaryClassification
{
 public static class AveragedPerceptron
 {
 // In this examples we will use the adult income dataset. The goal is to predict
 // if a person's income is above $50K or not, based on demographic information about that person.
 // For more details about this dataset, please see https://archive.ics.uci.edu/ml/datasets/adult.
 public static void Example()
 {
 // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
 // as a catalog of available operations and as the source of randomness.
 // Setting the seed to a fixed number in this example to make outputs deterministic.
 var mlContext = new MLContext(seed: 0);

 // Download and featurize the dataset.
 var data = Microsoft.ML.SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 // Create a list of training data points.
 var dataPoints = GenerateRandomDataPoints(1000);

 // Leave out 10% of data for testing.
 var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 // Convert the list of data points to an IDataView object, which is consumable by ML.NET API.
 var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

 // Create data training pipeline.
 var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron(numberOfIterations: 10);
 // Define the trainer.
 var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron();

 // Fit this pipeline to the training data.
 var model = pipeline.Fit(trainTestData.TrainSet);
 // Train the model.
 var model = pipeline.Fit(trainingData);

 // Evaluate how the model is doing on the test data.
 var dataWithPredictions = model.Transform(trainTestData.TestSet);
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(dataWithPredictions);
 Microsoft.ML.SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
 // Create testing data. Use different random seed to make it different from training data.
 var testData = mlContext.Data.LoadFromEnumerable(GenerateRandomDataPoints(500, seed:123));

 // Run the model on test data set.
 var transformedTestData = model.Transform(testData);

 // Convert IDataView object to a list.
 var predictions = mlContext.Data.CreateEnumerable<Prediction>(transformedTestData, reuseRowObject: false).ToList();

 // Print 5 predictions.
 foreach (var p in predictions.Take(5))
 Console.WriteLine($"Label: {p.Label}, Prediction: {p.PredictedLabel}");

 // Expected output:
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: False
 // Label: False, Prediction: False

 // Evaluate the overall metrics.
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(transformedTestData);
 PrintMetrics(metrics);

 // Expected output:
 // Accuracy: 0.86
 // AUC: 0.91
 // F1 Score: 0.68
 // Negative Precision: 0.90
 // Negative Recall: 0.91
 // Positive Precision: 0.70
 // Positive Recall: 0.66
 // Accuracy: 0.72
 // AUC: 0.79
 // F1 Score: 0.68
 // Negative Precision: 0.71
 // Negative Recall: 0.80
 // Positive Precision: 0.74
 // Positive Recall: 0.63
 }

 private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed=0)
 {
 var random = new Random(seed);
 float randomFloat() => (float)random.NextDouble();
 for (int i = 0; i < count; i++)
 {
 var label = randomFloat() > 0.5f;
 yield return new DataPoint
 {
 Label = label,
 // Create random features that are correlated with the label.
 // For data points with false label, the feature values are slightly increased by adding a constant.
 Features = Enumerable.Repeat(label, 50).Select(x => x ? randomFloat() : randomFloat() + 0.1f).ToArray()
 };
 }
 }

 // Example with label and 50 feature values. A data set is a collection of such examples.
 private class DataPoint
 {
 public bool Label { get; set; }
 [VectorType(50)]
 public float[] Features { get; set; }
 }

 // Class used to capture predictions.
 private class Prediction
 {
 // Original label.
 public bool Label { get; set; }
 // Predicted label from the trainer.
 public bool PredictedLabel { get; set; }
 }

 // Pretty-print BinaryClassificationMetrics objects.
 private static void PrintMetrics(BinaryClassificationMetrics metrics)
 {
 Console.WriteLine($"Accuracy: {metrics.Accuracy:F2}");
 Console.WriteLine($"AUC: {metrics.AreaUnderRocCurve:F2}");
 Console.WriteLine($"F1 Score: {metrics.F1Score:F2}");
 Console.WriteLine($"Negative Precision: {metrics.NegativePrecision:F2}");
 Console.WriteLine($"Negative Recall: {metrics.NegativeRecall:F2}");
 Console.WriteLine($"Positive Precision: {metrics.PositivePrecision:F2}");
 Console.WriteLine($"Positive Recall: {metrics.PositiveRecall:F2}");
 }
 }
}
}

29 changes: 29 additions & 0 deletions
.../samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptron.tt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,29 @@
<#@ include file="BinaryClassification.ttinclude"#>
<#+
string ClassName = "AveragedPerceptron";
string Trainer = "AveragedPerceptron";
string TrainerOptions = null;
bool IsCalibrated = false;
bool CacheData = false;

string LabelThreshold = "0.5f";
string DataSepValue = "0.1f";
string OptionsInclude = "";
string Comments= "";

string ExpectedOutputPerInstance = @"// Expected output:
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: False
 // Label: False, Prediction: False";

string ExpectedOutput = @"// Expected output:
 // Accuracy: 0.72
 // AUC: 0.79
 // F1 Score: 0.68
 // Negative Precision: 0.71
 // Negative Recall: 0.80
 // Positive Precision: 0.74
 // Positive Recall: 0.63";
#>

116 changes: 91 additions & 25 deletions
...crosoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptronWithOptions.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,28 +1,29 @@
using Microsoft.ML;
using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Trainers;

namespace Samples.Dynamic.Trainers.BinaryClassification
{
 public static class AveragedPerceptronWithOptions
 {
 // In this examples we will use the adult income dataset. The goal is to predict
 // if a person's income is above $50K or not, based on demographic information about that person.
 // For more details about this dataset, please see https://archive.ics.uci.edu/ml/datasets/adult.
 public static void Example()
 {
 // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
 // as a catalog of available operations and as the source of randomness.
 // Setting the seed to a fixed number in this example to make outputs deterministic.
 var mlContext = new MLContext(seed: 0);

 // Download and featurize the dataset.
 var data = Microsoft.ML.SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 // Create a list of training data points.
 var dataPoints = GenerateRandomDataPoints(1000);

 // Leave out 10% of data for testing.
 var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 // Convert the list of data points to an IDataView object, which is consumable by ML.NET API.
 var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

 // Define the trainer options.
 var options = new AveragedPerceptronTrainer.Options()
 // Define trainer options.
 var options = new AveragedPerceptronTrainer.Options
 {
 LossFunction = new SmoothedHingeLoss(),
 LearningRate = 0.1f,
Expand All@@ -31,25 +32,90 @@ public static void Example()
 NumberOfIterations = 10
 };

 // Create data training pipeline.
 // Define the trainer.
 var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron(options);

 // Fit this pipeline to the training data.
 var model = pipeline.Fit(trainTestData.TrainSet);
 // Train the model.
 var model = pipeline.Fit(trainingData);

 // Evaluate how the model is doing on the test data.
 var dataWithPredictions = model.Transform(trainTestData.TestSet);
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(dataWithPredictions);
 Microsoft.ML.SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
 // Create testing data. Use different random seed to make it different from training data.
 var testData = mlContext.Data.LoadFromEnumerable(GenerateRandomDataPoints(500, seed:123));

 // Run the model on test data set.
 var transformedTestData = model.Transform(testData);

 // Convert IDataView object to a list.
 var predictions = mlContext.Data.CreateEnumerable<Prediction>(transformedTestData, reuseRowObject: false).ToList();

 // Print 5 predictions.
 foreach (var p in predictions.Take(5))
 Console.WriteLine($"Label: {p.Label}, Prediction: {p.PredictedLabel}");

 // Expected output:
 // Accuracy: 0.86
 // AUC: 0.90
 // F1 Score: 0.66
 // Negative Precision: 0.89
 // Negative Recall: 0.93
 // Positive Precision: 0.72
 // Positive Recall: 0.61
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: True
 // Label: False, Prediction: False

 // Evaluate the overall metrics.
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(transformedTestData);
 PrintMetrics(metrics);

 // Expected output:
 // Accuracy: 0.89
 // AUC: 0.96
 // F1 Score: 0.88
 // Negative Precision: 0.87
 // Negative Recall: 0.92
 // Positive Precision: 0.91
 // Positive Recall: 0.85
 }

 private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed=0)
 {
 var random = new Random(seed);
 float randomFloat() => (float)random.NextDouble();
 for (int i = 0; i < count; i++)
 {
 var label = randomFloat() > 0.5f;
 yield return new DataPoint
 {
 Label = label,
 // Create random features that are correlated with the label.
 // For data points with false label, the feature values are slightly increased by adding a constant.
 Features = Enumerable.Repeat(label, 50).Select(x => x ? randomFloat() : randomFloat() + 0.1f).ToArray()
 };
 }
 }

 // Example with label and 50 feature values. A data set is a collection of such examples.
 private class DataPoint
 {
 public bool Label { get; set; }
 [VectorType(50)]
 public float[] Features { get; set; }
 }

 // Class used to capture predictions.
 private class Prediction
 {
 // Original label.
 public bool Label { get; set; }
 // Predicted label from the trainer.
 public bool PredictedLabel { get; set; }
 }

 // Pretty-print BinaryClassificationMetrics objects.
 private static void PrintMetrics(BinaryClassificationMetrics metrics)
 {
 Console.WriteLine($"Accuracy: {metrics.Accuracy:F2}");
 Console.WriteLine($"AUC: {metrics.AreaUnderRocCurve:F2}");
 Console.WriteLine($"F1 Score: {metrics.F1Score:F2}");
 Console.WriteLine($"Negative Precision: {metrics.NegativePrecision:F2}");
 Console.WriteLine($"Negative Recall: {metrics.NegativeRecall:F2}");
 Console.WriteLine($"Positive Precision: {metrics.PositivePrecision:F2}");
 Console.WriteLine($"Positive Recall: {metrics.PositiveRecall:F2}");
 }
 }
}
}

37 changes: 37 additions & 0 deletions
...crosoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptronWithOptions.tt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
<#@ include file="BinaryClassification.ttinclude"#>
<#+
string ClassName="AveragedPerceptronWithOptions";
string Trainer = "AveragedPerceptron";
bool IsCalibrated = false;

string LabelThreshold = "0.5f";
string DataSepValue = "0.1f";
string OptionsInclude = "using Microsoft.ML.Trainers;";
string Comments= "";
bool CacheData = false;

string TrainerOptions = @"AveragedPerceptronTrainer.Options
 {
 LossFunction = new SmoothedHingeLoss(),
 LearningRate = 0.1f,
 LazyUpdate = false,
 RecencyGain = 0.1f,
 NumberOfIterations = 10
 }";

string ExpectedOutputPerInstance= @"// Expected output:
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: True
 // Label: False, Prediction: False";

string ExpectedOutput = @"// Expected output:
 // Accuracy: 0.89
 // AUC: 0.96
 // F1 Score: 0.88
 // Negative Precision: 0.87
 // Negative Recall: 0.92
 // Positive Precision: 0.91
 // Positive Recall: 0.85";
#>
Loading

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

Skip to content
Binary classification samples update#3311

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

artidoro
merged 5 commits into

from

Apr 16, 2019
 Merged


Binary classification samples update
#3311
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


5 commits


Select commit
Hold shift + click to select a range
c2aa76e

binary classification samples


artidoro Apr 11, 2019
03afa1b

linear svm


artidoro Apr 12, 2019
4d52f12

review comments


artidoro Apr 15, 2019
6898477

Recover LIBMF


artidoro Apr 15, 2019
11ffadd

adding note about AUC for prior


artidoro Apr 16, 2019

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


114 changes: 90 additions & 24 deletions
.../samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptron.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,44 +1,110 @@
using Microsoft.ML;
using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;

namespace Samples.Dynamic.Trainers.BinaryClassification
{
 public static class AveragedPerceptron
 {
 // In this examples we will use the adult income dataset. The goal is to predict
 // if a person's income is above $50K or not, based on demographic information about that person.
 // For more details about this dataset, please see https://archive.ics.uci.edu/ml/datasets/adult.
 public static void Example()
 {
 // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
 // as a catalog of available operations and as the source of randomness.
 // Setting the seed to a fixed number in this example to make outputs deterministic.
 var mlContext = new MLContext(seed: 0);

 // Download and featurize the dataset.
 var data = Microsoft.ML.SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 // Create a list of training data points.
 var dataPoints = GenerateRandomDataPoints(1000);

 // Leave out 10% of data for testing.
 var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 // Convert the list of data points to an IDataView object, which is consumable by ML.NET API.
 var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

 // Create data training pipeline.
 var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron(numberOfIterations: 10);
 // Define the trainer.
 var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron();

 // Fit this pipeline to the training data.
 var model = pipeline.Fit(trainTestData.TrainSet);
 // Train the model.
 var model = pipeline.Fit(trainingData);

 // Evaluate how the model is doing on the test data.
 var dataWithPredictions = model.Transform(trainTestData.TestSet);
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(dataWithPredictions);
 Microsoft.ML.SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
 // Create testing data. Use different random seed to make it different from training data.
 var testData = mlContext.Data.LoadFromEnumerable(GenerateRandomDataPoints(500, seed:123));

 // Run the model on test data set.
 var transformedTestData = model.Transform(testData);

 // Convert IDataView object to a list.
 var predictions = mlContext.Data.CreateEnumerable<Prediction>(transformedTestData, reuseRowObject: false).ToList();

 // Print 5 predictions.
 foreach (var p in predictions.Take(5))
 Console.WriteLine($"Label: {p.Label}, Prediction: {p.PredictedLabel}");

 // Expected output:
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: False
 // Label: False, Prediction: False

 // Evaluate the overall metrics.
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(transformedTestData);
 PrintMetrics(metrics);

 // Expected output:
 // Accuracy: 0.86
 // AUC: 0.91
 // F1 Score: 0.68
 // Negative Precision: 0.90
 // Negative Recall: 0.91
 // Positive Precision: 0.70
 // Positive Recall: 0.66
 // Accuracy: 0.72
 // AUC: 0.79
 // F1 Score: 0.68
 // Negative Precision: 0.71
 // Negative Recall: 0.80
 // Positive Precision: 0.74
 // Positive Recall: 0.63
 }

 private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed=0)
 {
 var random = new Random(seed);
 float randomFloat() => (float)random.NextDouble();
 for (int i = 0; i < count; i++)
 {
 var label = randomFloat() > 0.5f;
 yield return new DataPoint
 {
 Label = label,
 // Create random features that are correlated with the label.
 // For data points with false label, the feature values are slightly increased by adding a constant.
 Features = Enumerable.Repeat(label, 50).Select(x => x ? randomFloat() : randomFloat() + 0.1f).ToArray()
 };
 }
 }

 // Example with label and 50 feature values. A data set is a collection of such examples.
 private class DataPoint
 {
 public bool Label { get; set; }
 [VectorType(50)]
 public float[] Features { get; set; }
 }

 // Class used to capture predictions.
 private class Prediction
 {
 // Original label.
 public bool Label { get; set; }
 // Predicted label from the trainer.
 public bool PredictedLabel { get; set; }
 }

 // Pretty-print BinaryClassificationMetrics objects.
 private static void PrintMetrics(BinaryClassificationMetrics metrics)
 {
 Console.WriteLine($"Accuracy: {metrics.Accuracy:F2}");
 Console.WriteLine($"AUC: {metrics.AreaUnderRocCurve:F2}");
 Console.WriteLine($"F1 Score: {metrics.F1Score:F2}");
 Console.WriteLine($"Negative Precision: {metrics.NegativePrecision:F2}");
 Console.WriteLine($"Negative Recall: {metrics.NegativeRecall:F2}");
 Console.WriteLine($"Positive Precision: {metrics.PositivePrecision:F2}");
 Console.WriteLine($"Positive Recall: {metrics.PositiveRecall:F2}");
 }
 }
}
}

29 changes: 29 additions & 0 deletions
.../samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptron.tt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,29 @@
<#@ include file="BinaryClassification.ttinclude"#>
<#+
string ClassName = "AveragedPerceptron";
string Trainer = "AveragedPerceptron";
string TrainerOptions = null;
bool IsCalibrated = false;
bool CacheData = false;

string LabelThreshold = "0.5f";
string DataSepValue = "0.1f";
string OptionsInclude = "";
string Comments= "";

string ExpectedOutputPerInstance = @"// Expected output:
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: False
 // Label: False, Prediction: False";

string ExpectedOutput = @"// Expected output:
 // Accuracy: 0.72
 // AUC: 0.79
 // F1 Score: 0.68
 // Negative Precision: 0.71
 // Negative Recall: 0.80
 // Positive Precision: 0.74
 // Positive Recall: 0.63";
#>

116 changes: 91 additions & 25 deletions
...crosoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptronWithOptions.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,28 +1,29 @@
using Microsoft.ML;
using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Trainers;

namespace Samples.Dynamic.Trainers.BinaryClassification
{
 public static class AveragedPerceptronWithOptions
 {
 // In this examples we will use the adult income dataset. The goal is to predict
 // if a person's income is above $50K or not, based on demographic information about that person.
 // For more details about this dataset, please see https://archive.ics.uci.edu/ml/datasets/adult.
 public static void Example()
 {
 // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
 // as a catalog of available operations and as the source of randomness.
 // Setting the seed to a fixed number in this example to make outputs deterministic.
 var mlContext = new MLContext(seed: 0);

 // Download and featurize the dataset.
 var data = Microsoft.ML.SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 // Create a list of training data points.
 var dataPoints = GenerateRandomDataPoints(1000);

 // Leave out 10% of data for testing.
 var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 // Convert the list of data points to an IDataView object, which is consumable by ML.NET API.
 var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

 // Define the trainer options.
 var options = new AveragedPerceptronTrainer.Options()
 // Define trainer options.
 var options = new AveragedPerceptronTrainer.Options
 {
 LossFunction = new SmoothedHingeLoss(),
 LearningRate = 0.1f,
Expand All@@ -31,25 +32,90 @@ public static void Example()
 NumberOfIterations = 10
 };

 // Create data training pipeline.
 // Define the trainer.
 var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron(options);

 // Fit this pipeline to the training data.
 var model = pipeline.Fit(trainTestData.TrainSet);
 // Train the model.
 var model = pipeline.Fit(trainingData);

 // Evaluate how the model is doing on the test data.
 var dataWithPredictions = model.Transform(trainTestData.TestSet);
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(dataWithPredictions);
 Microsoft.ML.SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
 // Create testing data. Use different random seed to make it different from training data.
 var testData = mlContext.Data.LoadFromEnumerable(GenerateRandomDataPoints(500, seed:123));

 // Run the model on test data set.
 var transformedTestData = model.Transform(testData);

 // Convert IDataView object to a list.
 var predictions = mlContext.Data.CreateEnumerable<Prediction>(transformedTestData, reuseRowObject: false).ToList();

 // Print 5 predictions.
 foreach (var p in predictions.Take(5))
 Console.WriteLine($"Label: {p.Label}, Prediction: {p.PredictedLabel}");

 // Expected output:
 // Accuracy: 0.86
 // AUC: 0.90
 // F1 Score: 0.66
 // Negative Precision: 0.89
 // Negative Recall: 0.93
 // Positive Precision: 0.72
 // Positive Recall: 0.61
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: True
 // Label: False, Prediction: False

 // Evaluate the overall metrics.
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(transformedTestData);
 PrintMetrics(metrics);

 // Expected output:
 // Accuracy: 0.89
 // AUC: 0.96
 // F1 Score: 0.88
 // Negative Precision: 0.87
 // Negative Recall: 0.92
 // Positive Precision: 0.91
 // Positive Recall: 0.85
 }

 private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed=0)
 {
 var random = new Random(seed);
 float randomFloat() => (float)random.NextDouble();
 for (int i = 0; i < count; i++)
 {
 var label = randomFloat() > 0.5f;
 yield return new DataPoint
 {
 Label = label,
 // Create random features that are correlated with the label.
 // For data points with false label, the feature values are slightly increased by adding a constant.
 Features = Enumerable.Repeat(label, 50).Select(x => x ? randomFloat() : randomFloat() + 0.1f).ToArray()
 };
 }
 }

 // Example with label and 50 feature values. A data set is a collection of such examples.
 private class DataPoint
 {
 public bool Label { get; set; }
 [VectorType(50)]
 public float[] Features { get; set; }
 }

 // Class used to capture predictions.
 private class Prediction
 {
 // Original label.
 public bool Label { get; set; }
 // Predicted label from the trainer.
 public bool PredictedLabel { get; set; }
 }

 // Pretty-print BinaryClassificationMetrics objects.
 private static void PrintMetrics(BinaryClassificationMetrics metrics)
 {
 Console.WriteLine($"Accuracy: {metrics.Accuracy:F2}");
 Console.WriteLine($"AUC: {metrics.AreaUnderRocCurve:F2}");
 Console.WriteLine($"F1 Score: {metrics.F1Score:F2}");
 Console.WriteLine($"Negative Precision: {metrics.NegativePrecision:F2}");
 Console.WriteLine($"Negative Recall: {metrics.NegativeRecall:F2}");
 Console.WriteLine($"Positive Precision: {metrics.PositivePrecision:F2}");
 Console.WriteLine($"Positive Recall: {metrics.PositiveRecall:F2}");
 }
 }
}
}

37 changes: 37 additions & 0 deletions
...crosoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptronWithOptions.tt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
<#@ include file="BinaryClassification.ttinclude"#>
<#+
string ClassName="AveragedPerceptronWithOptions";
string Trainer = "AveragedPerceptron";
bool IsCalibrated = false;

string LabelThreshold = "0.5f";
string DataSepValue = "0.1f";
string OptionsInclude = "using Microsoft.ML.Trainers;";
string Comments= "";
bool CacheData = false;

string TrainerOptions = @"AveragedPerceptronTrainer.Options
 {
 LossFunction = new SmoothedHingeLoss(),
 LearningRate = 0.1f,
 LazyUpdate = false,
 RecencyGain = 0.1f,
 NumberOfIterations = 10
 }";

string ExpectedOutputPerInstance= @"// Expected output:
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: True
 // Label: False, Prediction: False";

string ExpectedOutput = @"// Expected output:
 // Accuracy: 0.89
 // AUC: 0.96
 // F1 Score: 0.88
 // Negative Precision: 0.87
 // Negative Recall: 0.92
 // Positive Precision: 0.91
 // Positive Recall: 0.85";
#>
Loading

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

Skip to content
Binary classification samples update#3311

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

artidoro
merged 5 commits into

from

Apr 16, 2019
 Merged


Binary classification samples update
#3311
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


5 commits


Select commit
Hold shift + click to select a range
c2aa76e

binary classification samples


artidoro Apr 11, 2019
03afa1b

linear svm


artidoro Apr 12, 2019
4d52f12

review comments


artidoro Apr 15, 2019
6898477

Recover LIBMF


artidoro Apr 15, 2019
11ffadd

adding note about AUC for prior


artidoro Apr 16, 2019

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


114 changes: 90 additions & 24 deletions
.../samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptron.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,44 +1,110 @@
using Microsoft.ML;
using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;

namespace Samples.Dynamic.Trainers.BinaryClassification
{
 public static class AveragedPerceptron
 {
 // In this examples we will use the adult income dataset. The goal is to predict
 // if a person's income is above $50K or not, based on demographic information about that person.
 // For more details about this dataset, please see https://archive.ics.uci.edu/ml/datasets/adult.
 public static void Example()
 {
 // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
 // as a catalog of available operations and as the source of randomness.
 // Setting the seed to a fixed number in this example to make outputs deterministic.
 var mlContext = new MLContext(seed: 0);

 // Download and featurize the dataset.
 var data = Microsoft.ML.SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 // Create a list of training data points.
 var dataPoints = GenerateRandomDataPoints(1000);

 // Leave out 10% of data for testing.
 var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 // Convert the list of data points to an IDataView object, which is consumable by ML.NET API.
 var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

 // Create data training pipeline.
 var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron(numberOfIterations: 10);
 // Define the trainer.
 var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron();

 // Fit this pipeline to the training data.
 var model = pipeline.Fit(trainTestData.TrainSet);
 // Train the model.
 var model = pipeline.Fit(trainingData);

 // Evaluate how the model is doing on the test data.
 var dataWithPredictions = model.Transform(trainTestData.TestSet);
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(dataWithPredictions);
 Microsoft.ML.SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
 // Create testing data. Use different random seed to make it different from training data.
 var testData = mlContext.Data.LoadFromEnumerable(GenerateRandomDataPoints(500, seed:123));

 // Run the model on test data set.
 var transformedTestData = model.Transform(testData);

 // Convert IDataView object to a list.
 var predictions = mlContext.Data.CreateEnumerable<Prediction>(transformedTestData, reuseRowObject: false).ToList();

 // Print 5 predictions.
 foreach (var p in predictions.Take(5))
 Console.WriteLine($"Label: {p.Label}, Prediction: {p.PredictedLabel}");

 // Expected output:
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: False
 // Label: False, Prediction: False

 // Evaluate the overall metrics.
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(transformedTestData);
 PrintMetrics(metrics);

 // Expected output:
 // Accuracy: 0.86
 // AUC: 0.91
 // F1 Score: 0.68
 // Negative Precision: 0.90
 // Negative Recall: 0.91
 // Positive Precision: 0.70
 // Positive Recall: 0.66
 // Accuracy: 0.72
 // AUC: 0.79
 // F1 Score: 0.68
 // Negative Precision: 0.71
 // Negative Recall: 0.80
 // Positive Precision: 0.74
 // Positive Recall: 0.63
 }

 private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed=0)
 {
 var random = new Random(seed);
 float randomFloat() => (float)random.NextDouble();
 for (int i = 0; i < count; i++)
 {
 var label = randomFloat() > 0.5f;
 yield return new DataPoint
 {
 Label = label,
 // Create random features that are correlated with the label.
 // For data points with false label, the feature values are slightly increased by adding a constant.
 Features = Enumerable.Repeat(label, 50).Select(x => x ? randomFloat() : randomFloat() + 0.1f).ToArray()
 };
 }
 }

 // Example with label and 50 feature values. A data set is a collection of such examples.
 private class DataPoint
 {
 public bool Label { get; set; }
 [VectorType(50)]
 public float[] Features { get; set; }
 }

 // Class used to capture predictions.
 private class Prediction
 {
 // Original label.
 public bool Label { get; set; }
 // Predicted label from the trainer.
 public bool PredictedLabel { get; set; }
 }

 // Pretty-print BinaryClassificationMetrics objects.
 private static void PrintMetrics(BinaryClassificationMetrics metrics)
 {
 Console.WriteLine($"Accuracy: {metrics.Accuracy:F2}");
 Console.WriteLine($"AUC: {metrics.AreaUnderRocCurve:F2}");
 Console.WriteLine($"F1 Score: {metrics.F1Score:F2}");
 Console.WriteLine($"Negative Precision: {metrics.NegativePrecision:F2}");
 Console.WriteLine($"Negative Recall: {metrics.NegativeRecall:F2}");
 Console.WriteLine($"Positive Precision: {metrics.PositivePrecision:F2}");
 Console.WriteLine($"Positive Recall: {metrics.PositiveRecall:F2}");
 }
 }
}
}

29 changes: 29 additions & 0 deletions
.../samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptron.tt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,29 @@
<#@ include file="BinaryClassification.ttinclude"#>
<#+
string ClassName = "AveragedPerceptron";
string Trainer = "AveragedPerceptron";
string TrainerOptions = null;
bool IsCalibrated = false;
bool CacheData = false;

string LabelThreshold = "0.5f";
string DataSepValue = "0.1f";
string OptionsInclude = "";
string Comments= "";

string ExpectedOutputPerInstance = @"// Expected output:
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: False
 // Label: False, Prediction: False";

string ExpectedOutput = @"// Expected output:
 // Accuracy: 0.72
 // AUC: 0.79
 // F1 Score: 0.68
 // Negative Precision: 0.71
 // Negative Recall: 0.80
 // Positive Precision: 0.74
 // Positive Recall: 0.63";
#>

116 changes: 91 additions & 25 deletions
...crosoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptronWithOptions.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,28 +1,29 @@
using Microsoft.ML;
using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Trainers;

namespace Samples.Dynamic.Trainers.BinaryClassification
{
 public static class AveragedPerceptronWithOptions
 {
 // In this examples we will use the adult income dataset. The goal is to predict
 // if a person's income is above $50K or not, based on demographic information about that person.
 // For more details about this dataset, please see https://archive.ics.uci.edu/ml/datasets/adult.
 public static void Example()
 {
 // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
 // as a catalog of available operations and as the source of randomness.
 // Setting the seed to a fixed number in this example to make outputs deterministic.
 var mlContext = new MLContext(seed: 0);

 // Download and featurize the dataset.
 var data = Microsoft.ML.SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 // Create a list of training data points.
 var dataPoints = GenerateRandomDataPoints(1000);

 // Leave out 10% of data for testing.
 var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 // Convert the list of data points to an IDataView object, which is consumable by ML.NET API.
 var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

 // Define the trainer options.
 var options = new AveragedPerceptronTrainer.Options()
 // Define trainer options.
 var options = new AveragedPerceptronTrainer.Options
 {
 LossFunction = new SmoothedHingeLoss(),
 LearningRate = 0.1f,
Expand All@@ -31,25 +32,90 @@ public static void Example()
 NumberOfIterations = 10
 };

 // Create data training pipeline.
 // Define the trainer.
 var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron(options);

 // Fit this pipeline to the training data.
 var model = pipeline.Fit(trainTestData.TrainSet);
 // Train the model.
 var model = pipeline.Fit(trainingData);

 // Evaluate how the model is doing on the test data.
 var dataWithPredictions = model.Transform(trainTestData.TestSet);
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(dataWithPredictions);
 Microsoft.ML.SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
 // Create testing data. Use different random seed to make it different from training data.
 var testData = mlContext.Data.LoadFromEnumerable(GenerateRandomDataPoints(500, seed:123));

 // Run the model on test data set.
 var transformedTestData = model.Transform(testData);

 // Convert IDataView object to a list.
 var predictions = mlContext.Data.CreateEnumerable<Prediction>(transformedTestData, reuseRowObject: false).ToList();

 // Print 5 predictions.
 foreach (var p in predictions.Take(5))
 Console.WriteLine($"Label: {p.Label}, Prediction: {p.PredictedLabel}");

 // Expected output:
 // Accuracy: 0.86
 // AUC: 0.90
 // F1 Score: 0.66
 // Negative Precision: 0.89
 // Negative Recall: 0.93
 // Positive Precision: 0.72
 // Positive Recall: 0.61
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: True
 // Label: False, Prediction: False

 // Evaluate the overall metrics.
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(transformedTestData);
 PrintMetrics(metrics);

 // Expected output:
 // Accuracy: 0.89
 // AUC: 0.96
 // F1 Score: 0.88
 // Negative Precision: 0.87
 // Negative Recall: 0.92
 // Positive Precision: 0.91
 // Positive Recall: 0.85
 }

 private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed=0)
 {
 var random = new Random(seed);
 float randomFloat() => (float)random.NextDouble();
 for (int i = 0; i < count; i++)
 {
 var label = randomFloat() > 0.5f;
 yield return new DataPoint
 {
 Label = label,
 // Create random features that are correlated with the label.
 // For data points with false label, the feature values are slightly increased by adding a constant.
 Features = Enumerable.Repeat(label, 50).Select(x => x ? randomFloat() : randomFloat() + 0.1f).ToArray()
 };
 }
 }

 // Example with label and 50 feature values. A data set is a collection of such examples.
 private class DataPoint
 {
 public bool Label { get; set; }
 [VectorType(50)]
 public float[] Features { get; set; }
 }

 // Class used to capture predictions.
 private class Prediction
 {
 // Original label.
 public bool Label { get; set; }
 // Predicted label from the trainer.
 public bool PredictedLabel { get; set; }
 }

 // Pretty-print BinaryClassificationMetrics objects.
 private static void PrintMetrics(BinaryClassificationMetrics metrics)
 {
 Console.WriteLine($"Accuracy: {metrics.Accuracy:F2}");
 Console.WriteLine($"AUC: {metrics.AreaUnderRocCurve:F2}");
 Console.WriteLine($"F1 Score: {metrics.F1Score:F2}");
 Console.WriteLine($"Negative Precision: {metrics.NegativePrecision:F2}");
 Console.WriteLine($"Negative Recall: {metrics.NegativeRecall:F2}");
 Console.WriteLine($"Positive Precision: {metrics.PositivePrecision:F2}");
 Console.WriteLine($"Positive Recall: {metrics.PositiveRecall:F2}");
 }
 }
}
}

37 changes: 37 additions & 0 deletions
...crosoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptronWithOptions.tt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
<#@ include file="BinaryClassification.ttinclude"#>
<#+
string ClassName="AveragedPerceptronWithOptions";
string Trainer = "AveragedPerceptron";
bool IsCalibrated = false;

string LabelThreshold = "0.5f";
string DataSepValue = "0.1f";
string OptionsInclude = "using Microsoft.ML.Trainers;";
string Comments= "";
bool CacheData = false;

string TrainerOptions = @"AveragedPerceptronTrainer.Options
 {
 LossFunction = new SmoothedHingeLoss(),
 LearningRate = 0.1f,
 LazyUpdate = false,
 RecencyGain = 0.1f,
 NumberOfIterations = 10
 }";

string ExpectedOutputPerInstance= @"// Expected output:
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: True
 // Label: False, Prediction: False";

string ExpectedOutput = @"// Expected output:
 // Accuracy: 0.89
 // AUC: 0.96
 // F1 Score: 0.88
 // Negative Precision: 0.87
 // Negative Recall: 0.92
 // Positive Precision: 0.91
 // Positive Recall: 0.85";
#>
Loading

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

Skip to content
Binary classification samples update#3311

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

artidoro
merged 5 commits into

from

Apr 16, 2019
 Merged


Binary classification samples update
#3311
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


5 commits


Select commit
Hold shift + click to select a range
c2aa76e

binary classification samples


artidoro Apr 11, 2019
03afa1b

linear svm


artidoro Apr 12, 2019
4d52f12

review comments


artidoro Apr 15, 2019
6898477

Recover LIBMF


artidoro Apr 15, 2019
11ffadd

adding note about AUC for prior


artidoro Apr 16, 2019

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


114 changes: 90 additions & 24 deletions
.../samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptron.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,44 +1,110 @@
using Microsoft.ML;
using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;

namespace Samples.Dynamic.Trainers.BinaryClassification
{
 public static class AveragedPerceptron
 {
 // In this examples we will use the adult income dataset. The goal is to predict
 // if a person's income is above $50K or not, based on demographic information about that person.
 // For more details about this dataset, please see https://archive.ics.uci.edu/ml/datasets/adult.
 public static void Example()
 {
 // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
 // as a catalog of available operations and as the source of randomness.
 // Setting the seed to a fixed number in this example to make outputs deterministic.
 var mlContext = new MLContext(seed: 0);

 // Download and featurize the dataset.
 var data = Microsoft.ML.SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 // Create a list of training data points.
 var dataPoints = GenerateRandomDataPoints(1000);

 // Leave out 10% of data for testing.
 var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 // Convert the list of data points to an IDataView object, which is consumable by ML.NET API.
 var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

 // Create data training pipeline.
 var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron(numberOfIterations: 10);
 // Define the trainer.
 var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron();

 // Fit this pipeline to the training data.
 var model = pipeline.Fit(trainTestData.TrainSet);
 // Train the model.
 var model = pipeline.Fit(trainingData);

 // Evaluate how the model is doing on the test data.
 var dataWithPredictions = model.Transform(trainTestData.TestSet);
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(dataWithPredictions);
 Microsoft.ML.SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
 // Create testing data. Use different random seed to make it different from training data.
 var testData = mlContext.Data.LoadFromEnumerable(GenerateRandomDataPoints(500, seed:123));

 // Run the model on test data set.
 var transformedTestData = model.Transform(testData);

 // Convert IDataView object to a list.
 var predictions = mlContext.Data.CreateEnumerable<Prediction>(transformedTestData, reuseRowObject: false).ToList();

 // Print 5 predictions.
 foreach (var p in predictions.Take(5))
 Console.WriteLine($"Label: {p.Label}, Prediction: {p.PredictedLabel}");

 // Expected output:
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: False
 // Label: False, Prediction: False

 // Evaluate the overall metrics.
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(transformedTestData);
 PrintMetrics(metrics);

 // Expected output:
 // Accuracy: 0.86
 // AUC: 0.91
 // F1 Score: 0.68
 // Negative Precision: 0.90
 // Negative Recall: 0.91
 // Positive Precision: 0.70
 // Positive Recall: 0.66
 // Accuracy: 0.72
 // AUC: 0.79
 // F1 Score: 0.68
 // Negative Precision: 0.71
 // Negative Recall: 0.80
 // Positive Precision: 0.74
 // Positive Recall: 0.63
 }

 private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed=0)
 {
 var random = new Random(seed);
 float randomFloat() => (float)random.NextDouble();
 for (int i = 0; i < count; i++)
 {
 var label = randomFloat() > 0.5f;
 yield return new DataPoint
 {
 Label = label,
 // Create random features that are correlated with the label.
 // For data points with false label, the feature values are slightly increased by adding a constant.
 Features = Enumerable.Repeat(label, 50).Select(x => x ? randomFloat() : randomFloat() + 0.1f).ToArray()
 };
 }
 }

 // Example with label and 50 feature values. A data set is a collection of such examples.
 private class DataPoint
 {
 public bool Label { get; set; }
 [VectorType(50)]
 public float[] Features { get; set; }
 }

 // Class used to capture predictions.
 private class Prediction
 {
 // Original label.
 public bool Label { get; set; }
 // Predicted label from the trainer.
 public bool PredictedLabel { get; set; }
 }

 // Pretty-print BinaryClassificationMetrics objects.
 private static void PrintMetrics(BinaryClassificationMetrics metrics)
 {
 Console.WriteLine($"Accuracy: {metrics.Accuracy:F2}");
 Console.WriteLine($"AUC: {metrics.AreaUnderRocCurve:F2}");
 Console.WriteLine($"F1 Score: {metrics.F1Score:F2}");
 Console.WriteLine($"Negative Precision: {metrics.NegativePrecision:F2}");
 Console.WriteLine($"Negative Recall: {metrics.NegativeRecall:F2}");
 Console.WriteLine($"Positive Precision: {metrics.PositivePrecision:F2}");
 Console.WriteLine($"Positive Recall: {metrics.PositiveRecall:F2}");
 }
 }
}
}

29 changes: 29 additions & 0 deletions
.../samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptron.tt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,29 @@
<#@ include file="BinaryClassification.ttinclude"#>
<#+
string ClassName = "AveragedPerceptron";
string Trainer = "AveragedPerceptron";
string TrainerOptions = null;
bool IsCalibrated = false;
bool CacheData = false;

string LabelThreshold = "0.5f";
string DataSepValue = "0.1f";
string OptionsInclude = "";
string Comments= "";

string ExpectedOutputPerInstance = @"// Expected output:
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: False
 // Label: False, Prediction: False";

string ExpectedOutput = @"// Expected output:
 // Accuracy: 0.72
 // AUC: 0.79
 // F1 Score: 0.68
 // Negative Precision: 0.71
 // Negative Recall: 0.80
 // Positive Precision: 0.74
 // Positive Recall: 0.63";
#>

116 changes: 91 additions & 25 deletions
...crosoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptronWithOptions.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,28 +1,29 @@
using Microsoft.ML;
using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Trainers;

namespace Samples.Dynamic.Trainers.BinaryClassification
{
 public static class AveragedPerceptronWithOptions
 {
 // In this examples we will use the adult income dataset. The goal is to predict
 // if a person's income is above $50K or not, based on demographic information about that person.
 // For more details about this dataset, please see https://archive.ics.uci.edu/ml/datasets/adult.
 public static void Example()
 {
 // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
 // as a catalog of available operations and as the source of randomness.
 // Setting the seed to a fixed number in this example to make outputs deterministic.
 var mlContext = new MLContext(seed: 0);

 // Download and featurize the dataset.
 var data = Microsoft.ML.SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 // Create a list of training data points.
 var dataPoints = GenerateRandomDataPoints(1000);

 // Leave out 10% of data for testing.
 var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 // Convert the list of data points to an IDataView object, which is consumable by ML.NET API.
 var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

 // Define the trainer options.
 var options = new AveragedPerceptronTrainer.Options()
 // Define trainer options.
 var options = new AveragedPerceptronTrainer.Options
 {
 LossFunction = new SmoothedHingeLoss(),
 LearningRate = 0.1f,
Expand All@@ -31,25 +32,90 @@ public static void Example()
 NumberOfIterations = 10
 };

 // Create data training pipeline.
 // Define the trainer.
 var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron(options);

 // Fit this pipeline to the training data.
 var model = pipeline.Fit(trainTestData.TrainSet);
 // Train the model.
 var model = pipeline.Fit(trainingData);

 // Evaluate how the model is doing on the test data.
 var dataWithPredictions = model.Transform(trainTestData.TestSet);
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(dataWithPredictions);
 Microsoft.ML.SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
 // Create testing data. Use different random seed to make it different from training data.
 var testData = mlContext.Data.LoadFromEnumerable(GenerateRandomDataPoints(500, seed:123));

 // Run the model on test data set.
 var transformedTestData = model.Transform(testData);

 // Convert IDataView object to a list.
 var predictions = mlContext.Data.CreateEnumerable<Prediction>(transformedTestData, reuseRowObject: false).ToList();

 // Print 5 predictions.
 foreach (var p in predictions.Take(5))
 Console.WriteLine($"Label: {p.Label}, Prediction: {p.PredictedLabel}");

 // Expected output:
 // Accuracy: 0.86
 // AUC: 0.90
 // F1 Score: 0.66
 // Negative Precision: 0.89
 // Negative Recall: 0.93
 // Positive Precision: 0.72
 // Positive Recall: 0.61
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: True
 // Label: False, Prediction: False

 // Evaluate the overall metrics.
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(transformedTestData);
 PrintMetrics(metrics);

 // Expected output:
 // Accuracy: 0.89
 // AUC: 0.96
 // F1 Score: 0.88
 // Negative Precision: 0.87
 // Negative Recall: 0.92
 // Positive Precision: 0.91
 // Positive Recall: 0.85
 }

 private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed=0)
 {
 var random = new Random(seed);
 float randomFloat() => (float)random.NextDouble();
 for (int i = 0; i < count; i++)
 {
 var label = randomFloat() > 0.5f;
 yield return new DataPoint
 {
 Label = label,
 // Create random features that are correlated with the label.
 // For data points with false label, the feature values are slightly increased by adding a constant.
 Features = Enumerable.Repeat(label, 50).Select(x => x ? randomFloat() : randomFloat() + 0.1f).ToArray()
 };
 }
 }

 // Example with label and 50 feature values. A data set is a collection of such examples.
 private class DataPoint
 {
 public bool Label { get; set; }
 [VectorType(50)]
 public float[] Features { get; set; }
 }

 // Class used to capture predictions.
 private class Prediction
 {
 // Original label.
 public bool Label { get; set; }
 // Predicted label from the trainer.
 public bool PredictedLabel { get; set; }
 }

 // Pretty-print BinaryClassificationMetrics objects.
 private static void PrintMetrics(BinaryClassificationMetrics metrics)
 {
 Console.WriteLine($"Accuracy: {metrics.Accuracy:F2}");
 Console.WriteLine($"AUC: {metrics.AreaUnderRocCurve:F2}");
 Console.WriteLine($"F1 Score: {metrics.F1Score:F2}");
 Console.WriteLine($"Negative Precision: {metrics.NegativePrecision:F2}");
 Console.WriteLine($"Negative Recall: {metrics.NegativeRecall:F2}");
 Console.WriteLine($"Positive Precision: {metrics.PositivePrecision:F2}");
 Console.WriteLine($"Positive Recall: {metrics.PositiveRecall:F2}");
 }
 }
}
}

37 changes: 37 additions & 0 deletions
...crosoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptronWithOptions.tt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
<#@ include file="BinaryClassification.ttinclude"#>
<#+
string ClassName="AveragedPerceptronWithOptions";
string Trainer = "AveragedPerceptron";
bool IsCalibrated = false;

string LabelThreshold = "0.5f";
string DataSepValue = "0.1f";
string OptionsInclude = "using Microsoft.ML.Trainers;";
string Comments= "";
bool CacheData = false;

string TrainerOptions = @"AveragedPerceptronTrainer.Options
 {
 LossFunction = new SmoothedHingeLoss(),
 LearningRate = 0.1f,
 LazyUpdate = false,
 RecencyGain = 0.1f,
 NumberOfIterations = 10
 }";

string ExpectedOutputPerInstance= @"// Expected output:
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: True
 // Label: False, Prediction: False";

string ExpectedOutput = @"// Expected output:
 // Accuracy: 0.89
 // AUC: 0.96
 // F1 Score: 0.88
 // Negative Precision: 0.87
 // Negative Recall: 0.92
 // Positive Precision: 0.91
 // Positive Recall: 0.85";
#>
Loading

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

Skip to content
Binary classification samples update#3311

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

artidoro
merged 5 commits into

from

Apr 16, 2019
 Merged


Binary classification samples update
#3311
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


5 commits


Select commit
Hold shift + click to select a range
c2aa76e

binary classification samples


artidoro Apr 11, 2019
03afa1b

linear svm


artidoro Apr 12, 2019
4d52f12

review comments


artidoro Apr 15, 2019
6898477

Recover LIBMF


artidoro Apr 15, 2019
11ffadd

adding note about AUC for prior


artidoro Apr 16, 2019

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


114 changes: 90 additions & 24 deletions
.../samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptron.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,44 +1,110 @@
using Microsoft.ML;
using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;

namespace Samples.Dynamic.Trainers.BinaryClassification
{
 public static class AveragedPerceptron
 {
 // In this examples we will use the adult income dataset. The goal is to predict
 // if a person's income is above $50K or not, based on demographic information about that person.
 // For more details about this dataset, please see https://archive.ics.uci.edu/ml/datasets/adult.
 public static void Example()
 {
 // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
 // as a catalog of available operations and as the source of randomness.
 // Setting the seed to a fixed number in this example to make outputs deterministic.
 var mlContext = new MLContext(seed: 0);

 // Download and featurize the dataset.
 var data = Microsoft.ML.SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 // Create a list of training data points.
 var dataPoints = GenerateRandomDataPoints(1000);

 // Leave out 10% of data for testing.
 var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 // Convert the list of data points to an IDataView object, which is consumable by ML.NET API.
 var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

 // Create data training pipeline.
 var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron(numberOfIterations: 10);
 // Define the trainer.
 var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron();

 // Fit this pipeline to the training data.
 var model = pipeline.Fit(trainTestData.TrainSet);
 // Train the model.
 var model = pipeline.Fit(trainingData);

 // Evaluate how the model is doing on the test data.
 var dataWithPredictions = model.Transform(trainTestData.TestSet);
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(dataWithPredictions);
 Microsoft.ML.SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
 // Create testing data. Use different random seed to make it different from training data.
 var testData = mlContext.Data.LoadFromEnumerable(GenerateRandomDataPoints(500, seed:123));

 // Run the model on test data set.
 var transformedTestData = model.Transform(testData);

 // Convert IDataView object to a list.
 var predictions = mlContext.Data.CreateEnumerable<Prediction>(transformedTestData, reuseRowObject: false).ToList();

 // Print 5 predictions.
 foreach (var p in predictions.Take(5))
 Console.WriteLine($"Label: {p.Label}, Prediction: {p.PredictedLabel}");

 // Expected output:
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: False
 // Label: False, Prediction: False

 // Evaluate the overall metrics.
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(transformedTestData);
 PrintMetrics(metrics);

 // Expected output:
 // Accuracy: 0.86
 // AUC: 0.91
 // F1 Score: 0.68
 // Negative Precision: 0.90
 // Negative Recall: 0.91
 // Positive Precision: 0.70
 // Positive Recall: 0.66
 // Accuracy: 0.72
 // AUC: 0.79
 // F1 Score: 0.68
 // Negative Precision: 0.71
 // Negative Recall: 0.80
 // Positive Precision: 0.74
 // Positive Recall: 0.63
 }

 private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed=0)
 {
 var random = new Random(seed);
 float randomFloat() => (float)random.NextDouble();
 for (int i = 0; i < count; i++)
 {
 var label = randomFloat() > 0.5f;
 yield return new DataPoint
 {
 Label = label,
 // Create random features that are correlated with the label.
 // For data points with false label, the feature values are slightly increased by adding a constant.
 Features = Enumerable.Repeat(label, 50).Select(x => x ? randomFloat() : randomFloat() + 0.1f).ToArray()
 };
 }
 }

 // Example with label and 50 feature values. A data set is a collection of such examples.
 private class DataPoint
 {
 public bool Label { get; set; }
 [VectorType(50)]
 public float[] Features { get; set; }
 }

 // Class used to capture predictions.
 private class Prediction
 {
 // Original label.
 public bool Label { get; set; }
 // Predicted label from the trainer.
 public bool PredictedLabel { get; set; }
 }

 // Pretty-print BinaryClassificationMetrics objects.
 private static void PrintMetrics(BinaryClassificationMetrics metrics)
 {
 Console.WriteLine($"Accuracy: {metrics.Accuracy:F2}");
 Console.WriteLine($"AUC: {metrics.AreaUnderRocCurve:F2}");
 Console.WriteLine($"F1 Score: {metrics.F1Score:F2}");
 Console.WriteLine($"Negative Precision: {metrics.NegativePrecision:F2}");
 Console.WriteLine($"Negative Recall: {metrics.NegativeRecall:F2}");
 Console.WriteLine($"Positive Precision: {metrics.PositivePrecision:F2}");
 Console.WriteLine($"Positive Recall: {metrics.PositiveRecall:F2}");
 }
 }
}
}

29 changes: 29 additions & 0 deletions
.../samples/Microsoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptron.tt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,29 @@
<#@ include file="BinaryClassification.ttinclude"#>
<#+
string ClassName = "AveragedPerceptron";
string Trainer = "AveragedPerceptron";
string TrainerOptions = null;
bool IsCalibrated = false;
bool CacheData = false;

string LabelThreshold = "0.5f";
string DataSepValue = "0.1f";
string OptionsInclude = "";
string Comments= "";

string ExpectedOutputPerInstance = @"// Expected output:
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: False
 // Label: False, Prediction: False";

string ExpectedOutput = @"// Expected output:
 // Accuracy: 0.72
 // AUC: 0.79
 // F1 Score: 0.68
 // Negative Precision: 0.71
 // Negative Recall: 0.80
 // Positive Precision: 0.74
 // Positive Recall: 0.63";
#>

116 changes: 91 additions & 25 deletions
...crosoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptronWithOptions.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -1,28 +1,29 @@
using Microsoft.ML;
using System;
using System.Collections.Generic;
using System.Linq;
using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Trainers;

namespace Samples.Dynamic.Trainers.BinaryClassification
{
 public static class AveragedPerceptronWithOptions
 {
 // In this examples we will use the adult income dataset. The goal is to predict
 // if a person's income is above $50K or not, based on demographic information about that person.
 // For more details about this dataset, please see https://archive.ics.uci.edu/ml/datasets/adult.
 public static void Example()
 {
 // Create a new context for ML.NET operations. It can be used for exception tracking and logging, 
 // as a catalog of available operations and as the source of randomness.
 // Setting the seed to a fixed number in this example to make outputs deterministic.
 var mlContext = new MLContext(seed: 0);

 // Download and featurize the dataset.
 var data = Microsoft.ML.SamplesUtils.DatasetUtils.LoadFeaturizedAdultDataset(mlContext);
 // Create a list of training data points.
 var dataPoints = GenerateRandomDataPoints(1000);

 // Leave out 10% of data for testing.
 var trainTestData = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
 // Convert the list of data points to an IDataView object, which is consumable by ML.NET API.
 var trainingData = mlContext.Data.LoadFromEnumerable(dataPoints);

 // Define the trainer options.
 var options = new AveragedPerceptronTrainer.Options()
 // Define trainer options.
 var options = new AveragedPerceptronTrainer.Options
 {
 LossFunction = new SmoothedHingeLoss(),
 LearningRate = 0.1f,
Expand All@@ -31,25 +32,90 @@ public static void Example()
 NumberOfIterations = 10
 };

 // Create data training pipeline.
 // Define the trainer.
 var pipeline = mlContext.BinaryClassification.Trainers.AveragedPerceptron(options);

 // Fit this pipeline to the training data.
 var model = pipeline.Fit(trainTestData.TrainSet);
 // Train the model.
 var model = pipeline.Fit(trainingData);

 // Evaluate how the model is doing on the test data.
 var dataWithPredictions = model.Transform(trainTestData.TestSet);
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(dataWithPredictions);
 Microsoft.ML.SamplesUtils.ConsoleUtils.PrintMetrics(metrics);
 // Create testing data. Use different random seed to make it different from training data.
 var testData = mlContext.Data.LoadFromEnumerable(GenerateRandomDataPoints(500, seed:123));

 // Run the model on test data set.
 var transformedTestData = model.Transform(testData);

 // Convert IDataView object to a list.
 var predictions = mlContext.Data.CreateEnumerable<Prediction>(transformedTestData, reuseRowObject: false).ToList();

 // Print 5 predictions.
 foreach (var p in predictions.Take(5))
 Console.WriteLine($"Label: {p.Label}, Prediction: {p.PredictedLabel}");

 // Expected output:
 // Accuracy: 0.86
 // AUC: 0.90
 // F1 Score: 0.66
 // Negative Precision: 0.89
 // Negative Recall: 0.93
 // Positive Precision: 0.72
 // Positive Recall: 0.61
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: True
 // Label: False, Prediction: False

 // Evaluate the overall metrics.
 var metrics = mlContext.BinaryClassification.EvaluateNonCalibrated(transformedTestData);
 PrintMetrics(metrics);

 // Expected output:
 // Accuracy: 0.89
 // AUC: 0.96
 // F1 Score: 0.88
 // Negative Precision: 0.87
 // Negative Recall: 0.92
 // Positive Precision: 0.91
 // Positive Recall: 0.85
 }

 private static IEnumerable<DataPoint> GenerateRandomDataPoints(int count, int seed=0)
 {
 var random = new Random(seed);
 float randomFloat() => (float)random.NextDouble();
 for (int i = 0; i < count; i++)
 {
 var label = randomFloat() > 0.5f;
 yield return new DataPoint
 {
 Label = label,
 // Create random features that are correlated with the label.
 // For data points with false label, the feature values are slightly increased by adding a constant.
 Features = Enumerable.Repeat(label, 50).Select(x => x ? randomFloat() : randomFloat() + 0.1f).ToArray()
 };
 }
 }

 // Example with label and 50 feature values. A data set is a collection of such examples.
 private class DataPoint
 {
 public bool Label { get; set; }
 [VectorType(50)]
 public float[] Features { get; set; }
 }

 // Class used to capture predictions.
 private class Prediction
 {
 // Original label.
 public bool Label { get; set; }
 // Predicted label from the trainer.
 public bool PredictedLabel { get; set; }
 }

 // Pretty-print BinaryClassificationMetrics objects.
 private static void PrintMetrics(BinaryClassificationMetrics metrics)
 {
 Console.WriteLine($"Accuracy: {metrics.Accuracy:F2}");
 Console.WriteLine($"AUC: {metrics.AreaUnderRocCurve:F2}");
 Console.WriteLine($"F1 Score: {metrics.F1Score:F2}");
 Console.WriteLine($"Negative Precision: {metrics.NegativePrecision:F2}");
 Console.WriteLine($"Negative Recall: {metrics.NegativeRecall:F2}");
 Console.WriteLine($"Positive Precision: {metrics.PositivePrecision:F2}");
 Console.WriteLine($"Positive Recall: {metrics.PositiveRecall:F2}");
 }
 }
}
}

37 changes: 37 additions & 0 deletions
...crosoft.ML.Samples/Dynamic/Trainers/BinaryClassification/AveragedPerceptronWithOptions.tt

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
<#@ include file="BinaryClassification.ttinclude"#>
<#+
string ClassName="AveragedPerceptronWithOptions";
string Trainer = "AveragedPerceptron";
bool IsCalibrated = false;

string LabelThreshold = "0.5f";
string DataSepValue = "0.1f";
string OptionsInclude = "using Microsoft.ML.Trainers;";
string Comments= "";
bool CacheData = false;

string TrainerOptions = @"AveragedPerceptronTrainer.Options
 {
 LossFunction = new SmoothedHingeLoss(),
 LearningRate = 0.1f,
 LazyUpdate = false,
 RecencyGain = 0.1f,
 NumberOfIterations = 10
 }";

string ExpectedOutputPerInstance= @"// Expected output:
 // Label: True, Prediction: True
 // Label: False, Prediction: False
 // Label: True, Prediction: True
 // Label: True, Prediction: True
 // Label: False, Prediction: False";

string ExpectedOutput = @"// Expected output:
 // Accuracy: 0.89
 // AUC: 0.96
 // F1 Score: 0.88
 // Negative Precision: 0.87
 // Negative Recall: 0.92
 // Positive Precision: 0.91
 // Positive Recall: 0.85";
#>
Loading