public void CheckTrain()
{
//model data
double[] incomes = { 63, 16, 28, 55, 22, 20 };
double[] ages = { 38, 23, 40, 27, 18, 40 };
bool[] willBuy = { true, false, true, true, false, false };
//test data
double[] incomesTest = { 58, 18, 22 };
double[] agesTest = { 36, 24, 37 };
bool[] yTest = { true, false, false };
//train and infer
var machine = new BayesPointMachine();
var model = machine.Train(incomes, ages, willBuy);
var result = machine.Test(incomesTest, agesTest, model);
var resultInBool = result.Select(bernoulli => bernoulli.GetProbTrue() > 0.5 ? true : false).ToList();
//check accuracy
var accuracy = 0;
for (var i = 0; i < resultInBool.Count(); i++)
{
accuracy += resultInBool[i] == yTest[i] ? 1:0;
}
Assert.Equal(100, accuracy * 100 / resultInBool.Count);
}
public void CheckTrain()
{
//model data
double[] incomes = { 63, 16, 28, 55, 22, 20 };
double[] ages = { 38, 23, 40, 27, 18, 40 };
bool[] willBuy = { true, false, true, true, false, false };
//test data
double[] incomesTest = { 58, 18, 22 };
double[] agesTest = { 36, 24, 37 };
bool[] yTest = { true, false, false };
//train and infer
var machine = new BayesPointMachine();
var model = machine.Train(incomes, ages, willBuy);
var result= machine.Test(incomesTest, agesTest, model);
var resultInBool = result.Select(bernoulli => bernoulli.GetProbTrue() > 0.5 ? true : false).ToList();
//check accuracy
var accuracy = 0;
for (var i = 0; i < resultInBool.Count(); i++)
{
accuracy += resultInBool[i] == yTest[i] ? 1:0;
}
Assert.Equal(100, accuracy*100/resultInBool.Count);
}
/// <summary>
/// Load data from CSV.
/// </summary>
/// <param name="csvFilePath">CSV file path.</param>
/// <param name="hasHeader">CSV has headers.</param>
public virtual void LoadDataFromCsv(string csvFilePath, bool hasHeader = false)
{
if (initialized == false)
{
throw new Exception("ML Model has not been initialized yet.");
}
lock (mlModelCompilation)
{
hasHeaders = hasHeader;
IEnumerable <string> csvLines = File.ReadAllLines(csvFilePath);
if (hasHeader)
{
csvLines = csvLines.Skip(1);
}
foreach (string line in csvLines)
{
IList <double> dict =
new List <double>();
string[] vals = line.Replace(" ", "").Split(",");
for (int i = 0; i < vals.Length - 1; i++)
{
dict.Add(Convert.ToDouble(vals[i]));
}
Validity.Add(Convert.ToBoolean(vals[vals.Length - 1]));
Data.Add(dict.ToArray());
}
// Create random variable w with VectorGuassian (of size 3)
// Features => (Gold | Nickel | Copper) Concentration, IsGoodMaterial?
w = Variable.Random(new VectorGaussian(Vector.Zero(FeatureCount), PositiveDefiniteMatrix.Identity(FeatureCount))).Named("w");
// Create Observable variable based on valid_ui;
y = Variable.Observed(Validity.ToArray());
BayesPointMachine.Run(this, y, w);
}
}
/// <summary>
/// Make a prediction.
/// </summary>
/// <typeparam name="TModel">Model type.</typeparam>
/// <param name="features">Feature values.</param>
/// <returns>Probability matrix is valid.</returns>
public virtual double Predict <TModel>(IList <double> features) where TModel : new()
{
if (initialized == false)
{
throw new Exception("ML Model has not been initialized yet.");
}
if (Data == null || Data.Count == 0)
{
throw new Exception("Dataset has 0 instances.");
}
if (features == null)
{
throw new ArgumentNullException("data");
}
lock (mlModelCompilation)
{
object model =
new TModel();
((BaseMLModel)model).Data =
new List <double[]>()
{
features.ToArray()
};
VectorGaussian wPosterior =
engine.Infer <VectorGaussian>(w);
VariableArray <bool> ytest =
Variable.Array <bool>(new Range(1));
BayesPointMachine.Run(this, ytest, Variable.Random(wPosterior).Named("w"));
return((engine.Infer(ytest) as IEnumerable <Bernoulli>)
.First()
.GetProbTrue());
}
}
