static async Task Main(string[] args)
{
// Create a learning pipeline
var pipeline = new LearningPipeline();
// Load training data and add it to the pipeline
string dataPath = @".\data\titanic.training.csv";
var data = new TextLoader(dataPath).CreateFrom <TitanicData>(useHeader: true, separator: ',');
pipeline.Add(data);
// Transform any text feature to numeric values
pipeline.Add(new CategoricalOneHotVectorizer(
"Sex",
"Ticket",
"Fare",
"Cabin",
"Embarked"));
// Put all features into a vector
pipeline.Add(new ColumnConcatenator(
"Features",
"Pclass",
"Sex",
"Age",
"SibSp",
"Parch",
"Ticket",
"Fare",
"Cabin",
"Embarked"));
// Add a learning algorithm to the pipeline.
// This is a classification scenario (Did this passenger survive?)
pipeline.Add(new FastTreeBinaryClassifier()
{
NumLeaves = 5, NumTrees = 5, MinDocumentsInLeafs = 2
});
// Train your model based on the data set
Console.WriteLine($"Training Titanic.ML model...");
var model = pipeline.Train <TitanicData, TitanicPrediction>();
// Save the model to a file
var modelPath = @".\data\titanic.model";
await model.WriteAsync(modelPath);
// Use your model to make a prediction
var prediction = model.Predict(new TitanicData()
{
Pclass = 3f,
Name = "Braund, Mr. Owen Harris",
Sex = "male",
Age = 31,
SibSp = 0,
Parch = 0,
Ticket = "335097",
Fare = "7.75",
Cabin = "",
Embarked = "Q"
});
Console.WriteLine($"Did this passenger survive? {(prediction.Survived ? "Yes" : "No")}");
// Evaluate the model using the test data
Console.WriteLine($"Evaluating Titanic.ML model...");
dataPath = @".\data\titanic.csv";
data = new TextLoader(dataPath).CreateFrom <TitanicData>(useHeader: true, separator: ',');
var evaluator = new Microsoft.ML.Models.BinaryClassificationEvaluator();
var metrics = evaluator.Evaluate(model, data);
Console.WriteLine($"Accuracy: {metrics.Accuracy:P2}");
Console.WriteLine($"Auc: {metrics.Auc:P2}");
Console.WriteLine($"F1Score: {metrics.F1Score:P2}");
}
public void TestSimpleTrainExperiment()
{
var dataPath = GetDataPath(@"adult.tiny.with-schema.txt");
using (var env = new TlcEnvironment())
{
var experiment = env.CreateExperiment();
var importInput = new ML.Data.TextLoader(dataPath);
var importOutput = experiment.Add(importInput);
var catInput = new ML.Transforms.CategoricalOneHotVectorizer
{
Data = importOutput.Data
};
catInput.AddColumn("Categories");
var catOutput = experiment.Add(catInput);
var concatInput = new ML.Transforms.ColumnConcatenator
{
Data = catOutput.OutputData
};
concatInput.AddColumn("Features", "Categories", "NumericFeatures");
var concatOutput = experiment.Add(concatInput);
var sdcaInput = new ML.Trainers.StochasticDualCoordinateAscentBinaryClassifier
{
TrainingData = concatOutput.OutputData,
LossFunction = new HingeLossSDCAClassificationLossFunction()
{
Margin = 1.1f
},
NumThreads = 1,
Shuffle = false
};
var sdcaOutput = experiment.Add(sdcaInput);
var scoreInput = new ML.Transforms.DatasetScorer
{
Data = concatOutput.OutputData,
PredictorModel = sdcaOutput.PredictorModel
};
var scoreOutput = experiment.Add(scoreInput);
var evalInput = new ML.Models.BinaryClassificationEvaluator
{
Data = scoreOutput.ScoredData
};
var evalOutput = experiment.Add(evalInput);
experiment.Compile();
experiment.SetInput(importInput.InputFile, new SimpleFileHandle(env, dataPath, false, false));
experiment.Run();
var data = experiment.GetOutput(evalOutput.OverallMetrics);
var schema = data.Schema;
var b = schema.TryGetColumnIndex("AUC", out int aucCol);
Assert.True(b);
using (var cursor = data.GetRowCursor(col => col == aucCol))
{
var getter = cursor.GetGetter <double>(aucCol);
b = cursor.MoveNext();
Assert.True(b);
double auc = 0;
getter(ref auc);
Assert.Equal(0.93, auc, 2);
b = cursor.MoveNext();
Assert.False(b);
}
}
}