static void Main(string[] args)
{
// Classifier setup
var distance = new ManhattanDistance();
var classifier = new BasicClassifier(distance);
// Training
string dataPath = @"../data/trainingsample.csv";
Console.WriteLine($"Reading training data from {dataPath}");
Observation[] trainingSet = DataReader.ReadObservations(dataPath);
classifier.Train(trainingSet);
// Validation
string validationPath = @"../data/validationsample.csv";
Console.WriteLine($"Reading validation data from {validationPath}");
Observation[] validationSet = DataReader.ReadObservations(validationPath);
Console.WriteLine("Validating the classifier...");
var correct = Evaluator.Correct(validationSet, classifier);
Console.WriteLine("Classification score: {0:P2}", correct);
Console.ReadLine();
}
public void should_predict_nearest_label(List <DataPoint> dataPoints, List <int> pixels)
{
classifier.Train(dataPoints);
distance.Between(dataPoints[0].Pixels, pixels).Returns(3);
distance.Between(dataPoints[1].Pixels, pixels).Returns(1);
distance.Between(dataPoints[2].Pixels, pixels).Returns(8);
var result = classifier.Predict(pixels);
result.Should().Be(dataPoints[1].Label);
}
public void Test_model_Evaluator_scoring()
{
// arrange
var distance = new ManhattanDistance();
var classifier = new BasicClassifier(distance);
string trainingPath = Path.Combine(TestContext.DeploymentDirectory, "digits", "trainingsample.csv");
var trainingData = DataReader.ReadObservations(trainingPath);
classifier.Train(trainingData);
// act
var result = Evaluator.Score(trainingData[0], classifier);
// assert
Assert.AreEqual(result, 1.0);
}
public void Test_Base_Classifier_training()
{
//arrange
var distance = new ManhattanDistance();
var classifier = new BasicClassifier(distance);
string trainingPath = Path.Combine(TestContext.DeploymentDirectory, "digits", "trainingsample.csv");
var trainingData = DataReader.ReadObservations(trainingPath);
classifier.Train(trainingData);
//act
string labelResult = classifier.Predict(trainingData[0].Pixels);
//assert
Assert.IsFalse(string.IsNullOrEmpty(labelResult));
}
private static BasicClassifier GetTrainingClassifier()
{
var baseDirectory = @"C:\Users\pavel\Documents\Visual Studio 2017\Projects\DigitRecognizer\DigitRecognizer\";
var distance = new EuclidianDistance();
var classifier = new BasicClassifier(distance);
var trainingPath = $@"{baseDirectory}train.csv";
var training
= DataReader.ReadObservations(trainingPath);
classifier.Train(training);
return(classifier);
}
static void Main(string[] args)
{
var distance = new ManhattanDistance();
var classifier = new BasicClassifier(distance);
var trainingPath = "./data/train_truncated.csv";
var training = DataReader.ReadObservations(trainingPath);
classifier.Train(training);
var validationPath = "./data/validate_truncated.csv";
var validation = DataReader.ReadObservations(validationPath);
var correct = Evaluator.Correct(validation, classifier);
Console.WriteLine("Correctly classified {0:P2}", correct);
}
static void Main(string[] args)
{
var distance = new ManhattanDistance();
var classifier = new BasicClassifier(distance);
var trainingPath = @"C:\Users\ifeanyi\Documents\visual studio 2013\Projects\MLImageDigitizer\MLImageDigitizer\Data\trainingdata.csv";
var training = DataReader.ReadObservations(trainingPath);
classifier.Train(training);
var validationPath = @"C:\Users\ifeanyi\Documents\visual studio 2013\Projects\MLImageDigitizer\MLImageDigitizer\Data\validationdata.csv";
var validation = DataReader.ReadObservations(validationPath);
var correct = Evaluator.Correct(validation, classifier);
Console.WriteLine("Correctly classified: {0:P2}", correct);
Console.ReadLine();
}
static void Main(string[] args)
{
var classifier = new BasicClassifier();
var trainingPath = String.Format("{0}\\trainingsample.csv",System.IO.Directory.GetCurrentDirectory());
var validationPath = String.Format("{0}\\validationsample.csv", System.IO.Directory.GetCurrentDirectory());
Console.WriteLine("Training Data...");
var training = DigitDataReader.ReadObservations(trainingPath);
classifier.Train(training);
var validation = DigitDataReader.ReadObservations(validationPath);
var correctAverage = Evaluator.Correct(validation, classifier);
Console.WriteLine("Correctly classified: {0:P2}", correctAverage);
Console.WriteLine("Press Enter to exit...");
Console.ReadLine();
}
static void Main(string[] args)
{
var distance = new ManhattanDistance();
var classifier = new BasicClassifier(distance);
var dataPath = @"/Users/espen/git/ML-book-experiments/DigitsRecognizer/data/";
var trainingPath = dataPath + "trainingsample.csv";
var trainingSet = DataReader.ReadObservations(trainingPath);
classifier.Train(trainingSet);
var validationPath = dataPath + "validationsample.csv";
var validationSet = DataReader.ReadObservations(validationPath);
var correct = Evaluator.Correct(validationSet, classifier);
Console.WriteLine($"Correctly classified: {correct:P2}");
Console.WriteLine("Press enter to exit.");
Console.ReadLine();
}
static void Main(string[] args)
{
var distance = new ManhattanDistance();
var classifier = new BasicClassifier(distance);
//@:写路径字符串可以让字符串不需要转义，否则需要写两个\\
//读取训练集
var trainingPath = @"D:\SojS\machine-learning\machine-learning-projects-for-dot-net-developers\chapter-1\DigitsRecognizer\Data\trainingsample.csv";
var training = DataReader.ReadObservations(trainingPath);
//训练基本分类器
classifier.Train(training);
//读取验证集
var validationPath = @"D:\SojS\machine-learning\machine-learning-projects-for-dot-net-developers\chapter-1\DigitsRecognizer\Data\validationsample.csv";
var validation = DataReader.ReadObservations(validationPath);
//验证分类器
var correct = Evaluator.Correct(validation, classifier);
Console.WriteLine("{0:P2}", correct);
Console.ReadLine();
}