private static void XorLearn()
{
double[][] inputs =
{
new double[] { 0, 0 },
new double[] { 1, 0 },
new double[] { 0, 1 },
new double[] { 1, 1 }
};
int[] outputs =
{
0, 1, 1, 0
};
var smo = new SequentialMinimalOptimization <Gaussian>()
{
Complexity = 100
};
var svm = smo.Learn(inputs, outputs);
bool[] prediction = svm.Decide(inputs);
double error = new AccuracyLoss(outputs).Loss(prediction);
Console.WriteLine("Error: " + error);
ScatterplotBox.Show("Training data", inputs, outputs);
ScatterplotBox.Show("SVM results", inputs, prediction.ToZeroOne());
}
public double Predict(double[][] observations, int[] labels)
{
int[] predicted = machine.Decide(observations);
double error = new AccuracyLoss(labels).Loss(predicted);
return(1 - error);
}
public void Accuracy_Loss_2()
{
var sut = new AccuracyLoss();
var targets = Matrix <float> .Build.Dense(3, 2, new float[] { 1, 0, 1, 0, 1, 0 });
var predictions = Matrix <float> .Build.Dense(3, 2, new float[] { 0.9f, 0.8f, 0.3f, 0.1f, 0.2f, 0.7f });
var actual = sut.Loss(targets, predictions);
Assert.AreEqual(0.6666, actual, 0.001);
}
public static void Excute()
{
double[][] inputs =
{
/* 1.*/ new double[] { 0, 0 },
/* 2.*/ new double[] { 1, 0 },
/* 3.*/ new double[] { 0, 1 },
/* 4.*/ new double[] { 1, 1 },
};
double[][] inputs2 =
{
/* 1.*/ new double[] { 0, 0 },
/* 2.*/ new double[] { 1, 0 },
/* 3.*/ new double[] { 1, 1 },
/* 4.*/ new double[] { 1, 1 },
};
int[] outputs =
{
/* 1. 0 xor 0 = 0: */ 0,
/* 2. 1 xor 0 = 1: */ 1,
/* 3. 0 xor 1 = 1: */ 1,
/* 4. 1 xor 1 = 0: */ 0,
};
// Create the learning algorithm with the chosen kernel
var smo = new SequentialMinimalOptimization <Gaussian>()
{
Complexity = 100 // Create a hard-margin SVM
};
// Use the algorithm to learn the svm
var svm = smo.Learn(inputs, outputs);
// Compute the machine's answers for the given inputs
bool[] prediction = svm.Decide(inputs2);
// Compute the classification error between the expected
// values and the values actually predicted by the machine:
double error = new AccuracyLoss(outputs).Loss(prediction);
Console.WriteLine("Error: " + error);
// Show results on screen
ScatterplotBox.Show("Training data", inputs, outputs);
ScatterplotBox.Show("SVM results", inputs, prediction.ToZeroOne());
Console.ReadKey();
}
public double Learn(double[][] observations, int[] labels)
{
var teacher = new MulticlassSupportVectorLearning <Gaussian>()
{
Learner = (param) => new SequentialMinimalOptimization <Gaussian>()
{
UseKernelEstimation = true,
}
};
machine = teacher.Learn(observations, labels);
int[] predicted = machine.Decide(observations);
double error = new AccuracyLoss(labels).Loss(predicted);
return(1 - error);
}
public double Learn(double[][] observations, int[] labels)
{
int max = observations[0].Length;
DecisionVariable[] a = new DecisionVariable[max];
for (int i = 0; i < max; i++)
{
a[i] = DecisionVariable.Continuous(i.ToString());
}
C45Learning teacher = new C45Learning(a);
// Use the learning algorithm to induce the tree
machine = teacher.Learn(observations, labels);
// Classify the samples using the model
int[] predicted = machine.Decide(observations);
double error = new AccuracyLoss(labels).Loss(predicted);
return(1 - error);
}
public double Learn(double[][] observations, int[] labels)
{
var teacher = new NaiveBayesLearning <CauchyDistribution>();
//teacher.Options.InnerOption = new NormalOptions()
//{
// Regularization = 1e-5
//};
// Use the learning algorithm to learn
machine = teacher.Learn(observations, labels);
// Classify the samples using the model
int[] predicted = machine.Decide(observations);
double error = new AccuracyLoss(labels).Loss(predicted);
return(1 - error);
}
static void Main(string[] args)
{
double[][] inputs =
{
/* 1. */ new double[] { 0, 0 },
/* 2. */ new double[] { 1, 0 },
/* 3. */ new double[] { 0, 1 },
/* 4. */ new double[] { 1, 1 }
};
int[] outputs =
{
/* 1. 0 xor 0 = 0: */ 1,
/* 2. 1 xor 0 = 1: */ 0,
/* 3. 0 xor 1 = 1: */ 0,
/* 4. 1 xor 1 = 0: */ 0,
};
var smo = new SequentialMinimalOptimization <Gaussian>()
{
Complexity = 100
};
var svm = smo.Learn(inputs, outputs);
bool[] prediction = svm.Decide(inputs);
double error = new AccuracyLoss(outputs).Loss(prediction);
Console.WriteLine("Error: " + error);
ScatterplotBox.Show("Training data", inputs, outputs);
ScatterplotBox.Show("SVM results", inputs, prediction.ToZeroOne());
Console.ReadKey();
}
private static void multinomial(double[][] inputs, int[] outputs)
{
var lbnr = new LowerBoundNewtonRaphson()
{
MaxIterations = 100,
Tolerance = 1e-6
};
// Learn a multinomial logistic regression using the teacher:
MultinomialLogisticRegression mlr = lbnr.Learn(inputs, outputs);
// We can compute the model answers
int[] answers = mlr.Decide(inputs);
// And also the probability of each of the answers
double[][] probabilities = mlr.Probabilities(inputs);
// Now we can check how good our model is at predicting
double error = new AccuracyLoss(outputs).Loss(answers);
// We can also verify the classes with highest
// probability are the ones being decided for:
int[] argmax = probabilities.ArgMax(dimension: 1); // should be same as 'answers'
}
[MTAThread]//用于宣告这个程序的线程模型为多线程单元，如果说单线程则是STAThread
public void linnerSVM(DataSet dataSet)
{
{
int i = 0;
string[] output = new string[dataSet.Tables[0].Rows.Count];//434行的数组
int[] outputInt = new int[dataSet.Tables[0].Rows.Count];
foreach (DataRow mDr in dataSet.Tables[0].Rows)
{
output[i++] = mDr[dataSet.Tables[0].Columns.Count - 1].ToString();
if (output[i - 1] == "差气层")
{
outputInt[i - 1] = 0;
}
else if (output[i - 1] == "气层")
{
outputInt[i - 1] = 1;
}
else if (output[i - 1] == "干层")
{
outputInt[i - 1] = -1;
}
else if (output[i - 1] == "水层")
{
outputInt[i - 1] = -1;
}
Console.WriteLine("{0},{1},{2}", output[i - 1], outputInt[i - 1], i - 1);//验证点
}
double[][] inputs = new double[dataSet.Tables[0].Rows.Count][];
Console.WriteLine(dataSet.Tables[0].Rows.Count);
for (int j = 0; j < dataSet.Tables[0].Rows.Count; j++)
{
inputs[j] = new double[11]; //dataSet.Tables[0].Columns.Count-7
for (int k = 6; k < dataSet.Tables[0].Columns.Count - 1; k++) //k=6 是从第7列作为维度,-2是最后一列不算
{
Console.WriteLine(dataSet.Tables[0].Rows[j][k].ToString());
inputs[j][k - 6] = Convert.ToDouble(dataSet.Tables[0].Rows[j][k].ToString());
Console.WriteLine("{0},{1}", j, k - 6);//验证点
}
}
//var ksvm = new SupportVectorMachine(new Gaussian(), 2);
//var ksvm = new SupportVectorMachine(11);
//创建采用我们所给予的输入与输出的学习算法
var smm = new SequentialMinimalOptimization <Gaussian>()
{
Complexity = 100
};
var svm = smm.Learn(inputs, outputInt);
bool[] prediction = svm.Decide(inputs);
double error = new AccuracyLoss(outputInt).Loss(prediction);
Console.WriteLine("error:" + error);
// Show results on screen
Console.WriteLine(prediction.ToZeroOne());
//ScatterplotBox.Show("SVM results", inputs, prediction.ToZeroOne());
//svm.Decide();测试
Console.ReadKey();
}
}