public void LargeRunTest2()
{
Accord.Math.Random.Generator.Seed = 0;
int[,] random = Matrix.Random(1000, 10, 0.0, 10.0).ToInt32();
int[][] samples = random.ToJagged();
int[] outputs = new int[1000];
for (int i = 0; i < samples.Length; i++)
{
if (samples[i][0] > 5 || Tools.Random.NextDouble() > 0.85)
outputs[i] = 1;
}
DecisionVariable[] vars = new DecisionVariable[10];
for (int i = 0; i < vars.Length; i++)
vars[i] = new DecisionVariable("x" + i, 10);
DecisionTree tree = new DecisionTree(vars, 2);
var teacher = new ID3Learning(tree);
double error = teacher.Run(samples, outputs);
Assert.AreEqual(0, error);
var rules = DecisionSet.FromDecisionTree(tree);
Simplification simpl = new Simplification(rules)
{
Alpha = 0.05
};
error = simpl.ComputeError(samples.ToDouble(), outputs);
Assert.AreEqual(0, error);
double newError = simpl.Compute(samples.ToDouble(), outputs);
Assert.AreEqual(0.097, newError);
}
//
//You can use the following additional attributes as you write your tests:
//
//Use ClassInitialize to run code before running the first test in the class
//[ClassInitialize()]
//public static void MyClassInitialize(TestContext testContext)
//{
//}
//
//Use ClassCleanup to run code after all tests in a class have run
//[ClassCleanup()]
//public static void MyClassCleanup()
//{
//}
//
//Use TestInitialize to run code before running each test
//[TestInitialize()]
//public void MyTestInitialize()
//{
//}
//
//Use TestCleanup to run code after each test has run
//[TestCleanup()]
//public void MyTestCleanup()
//{
//}
//
#endregion
public static void CreateMitchellExample(out DecisionTree tree, out int[][] inputs, out int[] outputs)
{
DataTable data = new DataTable("Mitchell's Tennis Example");
data.Columns.Add("Day", "Outlook", "Temperature", "Humidity", "Wind", "PlayTennis");
data.Rows.Add("D1", "Sunny", "Hot", "High", "Weak", "No");
data.Rows.Add("D2", "Sunny", "Hot", "High", "Strong", "No");
data.Rows.Add("D3", "Overcast", "Hot", "High", "Weak", "Yes");
data.Rows.Add("D4", "Rain", "Mild", "High", "Weak", "Yes");
data.Rows.Add("D5", "Rain", "Cool", "Normal", "Weak", "Yes");
data.Rows.Add("D6", "Rain", "Cool", "Normal", "Strong", "No");
data.Rows.Add("D7", "Overcast", "Cool", "Normal", "Strong", "Yes");
data.Rows.Add("D8", "Sunny", "Mild", "High", "Weak", "No");
data.Rows.Add("D9", "Sunny", "Cool", "Normal", "Weak", "Yes");
data.Rows.Add("D10", "Rain", "Mild", "Normal", "Weak", "Yes");
data.Rows.Add("D11", "Sunny", "Mild", "Normal", "Strong", "Yes");
data.Rows.Add("D12", "Overcast", "Mild", "High", "Strong", "Yes");
data.Rows.Add("D13", "Overcast", "Hot", "Normal", "Weak", "Yes");
data.Rows.Add("D14", "Rain", "Mild", "High", "Strong", "No");
// Create a new codification codebook to
// convert strings into integer symbols
Codification codebook = new Codification(data);
DecisionVariable[] attributes =
{
new DecisionVariable("Outlook", codebook["Outlook"].Symbols), // 3 possible values (Sunny, overcast, rain)
new DecisionVariable("Temperature", codebook["Temperature"].Symbols), // 3 possible values (Hot, mild, cool)
new DecisionVariable("Humidity", codebook["Humidity"].Symbols), // 2 possible values (High, normal)
new DecisionVariable("Wind", codebook["Wind"].Symbols) // 2 possible values (Weak, strong)
};
int classCount = codebook["PlayTennis"].Symbols; // 2 possible values (yes, no)
tree = new DecisionTree(attributes, classCount);
ID3Learning id3 = new ID3Learning(tree);
// Extract symbols from data and train the classifier
DataTable symbols = codebook.Apply(data);
inputs = symbols.ToArray<int>("Outlook", "Temperature", "Humidity", "Wind");
outputs = symbols.ToArray<int>("PlayTennis");
double error = id3.Run(inputs, outputs);
Assert.AreEqual(0, error);
foreach (DataRow row in data.Rows)
{
var x = codebook.Translate(row, "Outlook", "Temperature", "Humidity", "Wind");
int y = tree.Compute(x);
string actual = codebook.Translate("PlayTennis", y);
string expected = row["PlayTennis"] as string;
Assert.AreEqual(expected, actual);
}
{
string answer = codebook.Translate("PlayTennis",
tree.Compute(codebook.Translate("Sunny", "Hot", "High", "Strong")));
Assert.AreEqual("No", answer);
}
}
public void ConsistencyTest1()
{
int[,] random = Matrix.Random(1000, 10, 0, 10).ToInt32();
int[][] samples = random.ToArray();
int[] outputs = new int[1000];
for (int i = 0; i < samples.Length; i++)
{
if (samples[i][0] > 8)
outputs[i] = 1;
}
DecisionVariable[] vars = new DecisionVariable[10];
for (int i = 0; i < vars.Length; i++)
vars[i] = new DecisionVariable(i.ToString(), new IntRange(0,10));
DecisionTree tree = new DecisionTree(vars, 2);
ID3Learning teacher = new ID3Learning(tree);
double error = teacher.Run(samples, outputs);
Assert.AreEqual(0, error);
Assert.AreEqual(11, tree.Root.Branches.Count);
for (int i = 0; i < tree.Root.Branches.Count; i++)
Assert.IsTrue(tree.Root.Branches[i].IsLeaf);
}
public void IncompleteDiscreteVariableTest()
{
DecisionTree tree;
int[][] inputs;
int[] outputs;
DataTable data = new DataTable("Degenerated Tennis Example");
data.Columns.Add("Day", "Outlook", "Temperature", "Humidity", "Wind", "PlayTennis");
data.Rows.Add("D1", "Sunny", "Hot", "High", "Weak", "No");
data.Rows.Add("D2", "Sunny", "Hot", "High", "Strong", "No");
data.Rows.Add("D3", "Overcast", "Hot", "High", "Weak", "Yes");
data.Rows.Add("D4", "Rain", "Mild", "High", "Weak", "Yes");
data.Rows.Add("D5", "Rain", "Cool", "Normal", "Weak", "Yes");
data.Rows.Add("D6", "Rain", "Cool", "Normal", "Strong", "No");
data.Rows.Add("D7", "Overcast", "Cool", "Normal", "Strong", "Yes");
data.Rows.Add("D8", "Sunny", "Mild", "High", "Weak", "No");
data.Rows.Add("D9", "Sunny", "Cool", "Normal", "Weak", "Yes");
data.Rows.Add("D10", "Rain", "Mild", "Normal", "Weak", "Yes");
data.Rows.Add("D11", "Sunny", "Mild", "Normal", "Strong", "Yes");
data.Rows.Add("D12", "Overcast", "Mild", "High", "Strong", "Yes");
data.Rows.Add("D13", "Overcast", "Hot", "Normal", "Weak", "Yes");
data.Rows.Add("D14", "Rain", "Mild", "High", "Strong", "No");
// Create a new codification codebook to
// convert strings into integer symbols
Codification codebook = new Codification(data);
DecisionVariable[] attributes =
{
new DecisionVariable("Outlook", codebook["Outlook"].Symbols+200), // 203 possible values, 200 undefined
new DecisionVariable("Temperature", codebook["Temperature"].Symbols), // 3 possible values (Hot, mild, cool)
new DecisionVariable("Humidity", codebook["Humidity"].Symbols), // 2 possible values (High, normal)
new DecisionVariable("Wind", codebook["Wind"].Symbols) // 2 possible values (Weak, strong)
};
int classCount = codebook["PlayTennis"].Symbols; // 2 possible values (yes, no)
tree = new DecisionTree(attributes, classCount);
ID3Learning id3 = new ID3Learning(tree);
// Extract symbols from data and train the classifier
DataTable symbols = codebook.Apply(data);
inputs = symbols.ToArray<int>("Outlook", "Temperature", "Humidity", "Wind");
outputs = symbols.ToArray<int>("PlayTennis");
double error = id3.Run(inputs, outputs);
Assert.AreEqual(203, tree.Root.Branches.Count);
Assert.IsTrue(tree.Root.Branches[100].IsLeaf);
Assert.IsNull(tree.Root.Branches[100].Output);
for (int i = 0; i < inputs.Length; i++)
{
int y = tree.Compute(inputs[i]);
Assert.AreEqual(outputs[i], y);
}
}
public void ConstantDiscreteVariableTest()
{
DecisionTree tree;
int[][] inputs;
int[] outputs;
DataTable data = new DataTable("Degenerated Tennis Example");
data.Columns.Add("Day", "Outlook", "Temperature", "Humidity", "Wind", "PlayTennis");
data.Rows.Add("D1", "Sunny", "Hot", "High", "Weak", "No");
data.Rows.Add("D2", "Sunny", "Hot", "High", "Strong", "No");
data.Rows.Add("D3", "Overcast", "Hot", "High", "Weak", "Yes");
data.Rows.Add("D4", "Rain", "Hot", "High", "Weak", "Yes");
data.Rows.Add("D5", "Rain", "Hot", "Normal", "Weak", "Yes");
data.Rows.Add("D6", "Rain", "Hot", "Normal", "Strong", "No");
data.Rows.Add("D7", "Overcast", "Hot", "Normal", "Strong", "Yes");
data.Rows.Add("D8", "Sunny", "Hot", "High", "Weak", "No");
data.Rows.Add("D9", "Sunny", "Hot", "Normal", "Weak", "Yes");
data.Rows.Add("D10", "Rain", "Hot", "Normal", "Weak", "Yes");
data.Rows.Add("D11", "Sunny", "Hot", "Normal", "Strong", "Yes");
data.Rows.Add("D12", "Overcast", "Hot", "High", "Strong", "Yes");
data.Rows.Add("D13", "Overcast", "Hot", "Normal", "Weak", "Yes");
data.Rows.Add("D14", "Rain", "Hot", "High", "Strong", "No");
// Create a new codification codebook to
// convert strings into integer symbols
Codification codebook = new Codification(data);
DecisionVariable[] attributes =
{
new DecisionVariable("Outlook", codebook["Outlook"].Symbols), // 3 possible values (Sunny, overcast, rain)
new DecisionVariable("Temperature", codebook["Temperature"].Symbols), // 1 constant value (Hot)
new DecisionVariable("Humidity", codebook["Humidity"].Symbols), // 2 possible values (High, normal)
new DecisionVariable("Wind", codebook["Wind"].Symbols) // 2 possible values (Weak, strong)
};
int classCount = codebook["PlayTennis"].Symbols; // 2 possible values (yes, no)
bool thrown = false;
try
{
tree = new DecisionTree(attributes, classCount);
}
catch
{
thrown = true;
}
Assert.IsTrue(thrown);
attributes[1] = new DecisionVariable("Temperature", 2);
tree = new DecisionTree(attributes, classCount);
ID3Learning id3 = new ID3Learning(tree);
// Extract symbols from data and train the classifier
DataTable symbols = codebook.Apply(data);
inputs = symbols.ToArray<int>("Outlook", "Temperature", "Humidity", "Wind");
outputs = symbols.ToArray<int>("PlayTennis");
double error = id3.Run(inputs, outputs);
for (int i = 0; i < inputs.Length; i++)
{
int y = tree.Compute(inputs[i]);
Assert.AreEqual(outputs[i], y);
}
}
public void RunTest()
{
int[][] inputs =
{
new int[] { 0, 0 },
new int[] { 0, 1 },
new int[] { 1, 0 },
new int[] { 1, 1 },
};
int[] outputs = // xor
{
0,
1,
1,
0
};
DecisionVariable[] attributes =
{
new DecisionVariable("x", DecisionVariableKind.Discrete),
new DecisionVariable("y", DecisionVariableKind.Discrete),
};
DecisionTree tree = new DecisionTree(attributes, 2);
ID3Learning teacher = new ID3Learning(tree);
double error = teacher.Run(inputs, outputs);
Assert.AreEqual(0, error);
Assert.AreEqual(0, tree.Root.Branches.AttributeIndex); // x
Assert.AreEqual(2, tree.Root.Branches.Count);
Assert.IsNull(tree.Root.Value);
Assert.IsNull(tree.Root.Value);
Assert.AreEqual(0.0, tree.Root.Branches[0].Value); // x = [0]
Assert.AreEqual(1.0, tree.Root.Branches[1].Value); // x = [1]
Assert.AreEqual(tree.Root, tree.Root.Branches[0].Parent);
Assert.AreEqual(tree.Root, tree.Root.Branches[1].Parent);
Assert.AreEqual(2, tree.Root.Branches[0].Branches.Count);
Assert.AreEqual(2, tree.Root.Branches[1].Branches.Count);
Assert.IsTrue(tree.Root.Branches[0].Branches[0].IsLeaf);
Assert.IsTrue(tree.Root.Branches[0].Branches[1].IsLeaf);
Assert.IsTrue(tree.Root.Branches[1].Branches[0].IsLeaf);
Assert.IsTrue(tree.Root.Branches[1].Branches[1].IsLeaf);
Assert.AreEqual(0.0, tree.Root.Branches[0].Branches[0].Value); // y = [0]
Assert.AreEqual(1.0, tree.Root.Branches[0].Branches[1].Value); // y = [1]
Assert.AreEqual(0.0, tree.Root.Branches[1].Branches[0].Value); // y = [0]
Assert.AreEqual(1.0, tree.Root.Branches[1].Branches[1].Value); // y = [1]
Assert.AreEqual(0, tree.Root.Branches[0].Branches[0].Output); // 0 ^ 0 = 0
Assert.AreEqual(1, tree.Root.Branches[0].Branches[1].Output); // 0 ^ 1 = 1
Assert.AreEqual(1, tree.Root.Branches[1].Branches[0].Output); // 1 ^ 0 = 1
Assert.AreEqual(0, tree.Root.Branches[1].Branches[1].Output); // 1 ^ 1 = 0
}
public static void CreateXORExample(out DecisionTree tree, out int[][] inputs, out int[] outputs)
{
inputs = new int[][]
{
new int[] { 1, 0, 0, 1 },
new int[] { 0, 1, 0, 0 },
new int[] { 0, 0, 0, 0 },
new int[] { 1, 1, 0, 0 },
new int[] { 0, 1, 1, 1 },
new int[] { 0, 0, 1, 1 },
new int[] { 1, 0, 1, 1 }
};
outputs = new int[]
{
1, 1, 0, 0, 1, 0, 1
};
DecisionVariable[] attributes =
{
new DecisionVariable("a1", 2),
new DecisionVariable("a2", 2),
new DecisionVariable("a3", 2),
new DecisionVariable("a4", 2)
};
int classCount = 2;
tree = new DecisionTree(attributes, classCount);
ID3Learning id3 = new ID3Learning(tree);
double error = id3.Run(inputs, outputs);
}
public void LargeSampleTest_WithRepetition()
{
Accord.Math.Tools.SetupGenerator(0);
int[][] dataSamples = Matrix.Random(500, 3, 0, 10).ToInt32().ToArray();
int[] target = Matrix.Random(500, 1, 0, 2).ToInt32().GetColumn(0);
DecisionVariable[] features =
{
new DecisionVariable("Outlook", 10),
new DecisionVariable("Temperature", 10),
new DecisionVariable("Humidity", 10),
};
DecisionTree tree = new DecisionTree(features, 2);
ID3Learning id3Learning = new ID3Learning(tree)
{
Rejection = false,
Join = 2 // every variable can join two times
};
double error = id3Learning.Run(dataSamples, target);
int height = tree.GetHeight();
Assert.AreEqual(6, height);
foreach (var node in tree)
{
if (node.IsLeaf)
Assert.IsNotNull(node.Output);
}
Assert.IsTrue(error < 0.15);
}
public void LargeSampleTest1()
{
Accord.Math.Tools.SetupGenerator(0);
int[][] dataSamples = Matrix.Random(500, 3, 0, 10).ToInt32().ToArray();
int[] target = Matrix.Random(500, 1, 0, 2).ToInt32().GetColumn(0);
DecisionVariable[] features =
{
new DecisionVariable("Outlook", 10),
new DecisionVariable("Temperature", 10),
new DecisionVariable("Humidity", 10),
};
DecisionTree tree = new DecisionTree(features, 2);
ID3Learning id3Learning = new ID3Learning(tree);
double error = id3Learning.Run(dataSamples, target);
Assert.IsTrue(error < 0.2);
var code = tree.ToCode("MyTree");
Assert.IsNotNull(code);
Assert.IsTrue(code.Length > 0);
}
public void ArgumentCheck1()
{
int[][] samples =
{
new [] { 0, 2, 4 },
new [] { 1, 5, 2 },
null,
new [] { 1, 5, 6 },
};
int[] outputs =
{
1, 1, 0, 0
};
DecisionVariable[] vars = new DecisionVariable[3];
for (int i = 0; i < vars.Length; i++)
vars[i] = DecisionVariable.Discrete(i.ToString(), new IntRange(0, 10));
DecisionTree tree = new DecisionTree(vars, 2);
ID3Learning teacher = new ID3Learning(tree);
bool thrown = false;
try { double error = teacher.Run(samples, outputs); }
catch (ArgumentNullException) { thrown = true; }
Assert.IsTrue(thrown);
}
/// <summary>
/// Создание дерева
/// </summary>
/// <param name="sender"></param>
/// <param name="e"></param>
private void btnCreate_Click(object sender, EventArgs e)
{
try
{
if (dgvLearningSource.DataSource == null)
{
MessageBox.Show("Загрузите данные");
return;
}
if (Tree_property.Property_View == true)
{
Tree_property.ShowDialog();
}
// Завершаем операцию с DataGridView
dgvLearningSource.EndEdit();
#region Алгоритм С4.5
///
///Алгоритм С4.5
///
if (Tree_property.Alg == "C4.5")
{
// // создаем матрицу из data table
double[,] sourceMatrix = (dgvLearningSource.DataSource as DataTable).ToMatrix(out sourceColumns);
C45Learning c45;
// получаем входные значения
double[][] inputs = sourceMatrix.Submatrix(null, 0, Tree_property.Coun_In - 1).ToArray();
// получаем выходные значения
int[] outputs = sourceMatrix.GetColumn(Tree_property.Coun_Out - 1).ToInt32();
DecisionVariable[] attributes = new DecisionVariable[Tree_property.Coun_In];
for (int j = 0; j < Tree_property.Coun_In; j++)
{
attributes[j] = new DecisionVariable(dgvLearningSource.Columns[j].Name, DecisionAttributeKind.Continuous);
}
// создаем дерево решений
tree = new DecisionTree(attributes, 60);
c45 = new C45Learning(tree);
double error = c45.Run(inputs, outputs);
}
#endregion
#region Алгоритм ID3
///
///Алгоритм ID3
///
if (Tree_property.Alg == "ID3")
{
// создаем матрицу из дататыйбл
int[][] arr = (dgvLearningSource.DataSource as DataTable).ToIntArray(sourceColumns);
int[,] sourceMatrix = arr.ToMatrix();
//// получаем входные значения
int[][] inputs = sourceMatrix.Submatrix(null, 0, Tree_property.Coun_In - 1).ToArray();
//// получаем выходные значения
int[] outputs = sourceMatrix.GetColumn(Tree_property.Coun_In - 1);
DecisionVariable[] attributes = new DecisionVariable[Tree_property.Coun_In];
for (int j = 0; j < Tree_property.Coun_In; j++)
{
attributes[j] = new DecisionVariable(j.ToString(), DecisionAttributeKind.Continuous);
}
// создаем дерево решений
tree = new DecisionTree(attributes, 60);
ID3Learning id3learning = new ID3Learning(tree);
double error = id3learning.Run(inputs, outputs);
}
#endregion
asd.Dispose();
asd.Close();
Drawing dr = new Drawing();
dr.recursion(tree.Root, tree.Root.Branches, 0);
dr.Save_();
asd = new Tree_View();
asd.userControl11.Load_f(Application.StartupPath);
System.Linq.Expressions.Expression df = tree.ToExpression();
// выбираем tabe page для просмотра дерева
tabControl.SelectTab(tabOverview);
// отображаем построенной дереыыо решений
decisionTreeView1.TreeSource = tree;
try
{
File.Copy(@".\Resources\recursion.png", @".\Resources\recursion2.png", true);
}
catch
{
}
using (Stream s = File.OpenRead(@".\Resources\recursion2.png"))
{
pictureBox1.Image = Image.FromStream(s);
}
}
catch (Exception t)
{
MessageBox.Show(t.Message);
}
}
//
//You can use the following additional attributes as you write your tests:
//
//Use ClassInitialize to run code before running the first test in the class
//[ClassInitialize()]
//public static void MyClassInitialize(TestContext testContext)
//{
//}
//
//Use ClassCleanup to run code after all tests in a class have run
//[ClassCleanup()]
//public static void MyClassCleanup()
//{
//}
//
//Use TestInitialize to run code before running each test
//[TestInitialize()]
//public void MyTestInitialize()
//{
//}
//
//Use TestCleanup to run code after each test has run
//[TestCleanup()]
//public void MyTestCleanup()
//{
//}
//
#endregion
public static void CreateMitchellExample(out DecisionTree tree, out int[][] inputs, out int[] outputs)
{
DataTable data = new DataTable("Mitchell's Tennis Example");
data.Columns.Add("Day", "Outlook", "Temperature", "Humidity", "Wind", "PlayTennis");
data.Rows.Add("D1", "Sunny", "Hot", "High", "Weak", "No");
data.Rows.Add("D2", "Sunny", "Hot", "High", "Strong", "No");
data.Rows.Add("D3", "Overcast", "Hot", "High", "Weak", "Yes");
data.Rows.Add("D4", "Rain", "Mild", "High", "Weak", "Yes");
data.Rows.Add("D5", "Rain", "Cool", "Normal", "Weak", "Yes");
data.Rows.Add("D6", "Rain", "Cool", "Normal", "Strong", "No");
data.Rows.Add("D7", "Overcast", "Cool", "Normal", "Strong", "Yes");
data.Rows.Add("D8", "Sunny", "Mild", "High", "Weak", "No");
data.Rows.Add("D9", "Sunny", "Cool", "Normal", "Weak", "Yes");
data.Rows.Add("D10", "Rain", "Mild", "Normal", "Weak", "Yes");
data.Rows.Add("D11", "Sunny", "Mild", "Normal", "Strong", "Yes");
data.Rows.Add("D12", "Overcast", "Mild", "High", "Strong", "Yes");
data.Rows.Add("D13", "Overcast", "Hot", "Normal", "Weak", "Yes");
data.Rows.Add("D14", "Rain", "Mild", "High", "Strong", "No");
// Create a new codification codebook to
// convert strings into integer symbols
Codification codebook = new Codification(data);
DecisionVariable[] attributes =
{
new DecisionVariable("Outlook", codebook["Outlook"].Symbols), // 3 possible values (Sunny, overcast, rain)
new DecisionVariable("Temperature", codebook["Temperature"].Symbols), // 3 possible values (Hot, mild, cool)
new DecisionVariable("Humidity", codebook["Humidity"].Symbols), // 2 possible values (High, normal)
new DecisionVariable("Wind", codebook["Wind"].Symbols) // 2 possible values (Weak, strong)
};
int classCount = codebook["PlayTennis"].Symbols; // 2 possible values (yes, no)
tree = new DecisionTree(attributes, classCount);
ID3Learning id3 = new ID3Learning(tree);
// Extract symbols from data and train the classifier
DataTable symbols = codebook.Apply(data);
inputs = symbols.ToIntArray("Outlook", "Temperature", "Humidity", "Wind");
outputs = symbols.ToIntArray("PlayTennis").GetColumn(0);
id3.Run(inputs, outputs);
}
public string kararAgaci(DataTable tbl)
{
int classCount = 2;
Codification codebook = new Codification(tbl);
DecisionVariable[] attributes ={
new DecisionVariable("Clump Thickness",10),
new DecisionVariable("Uniformity of Cell Size",10),new DecisionVariable("Uniformity of Cell Shape",10),
new DecisionVariable("Marginal Adhesion",10),new DecisionVariable("Single Epithelial Cell Size",10),
new DecisionVariable("Bare Nuclei",10),new DecisionVariable("Bland Chromatin",10),
new DecisionVariable("Normal Nucleoli",10),new DecisionVariable("Mitoses",10),
};
DecisionTree tree = new DecisionTree(attributes, classCount);
ID3Learning id3learning = new ID3Learning(tree);
// Translate our training data into integer symbols using our codebook:
DataTable symbols = codebook.Apply(tbl);
int[][] inputs = symbols.ToIntArray("Clump Thickness", "Uniformity of Cell Size", "Uniformity of Cell Shape", "Marginal Adhesion", "Single Epithelial Cell Size", "Bare Nuclei", "Bland Chromatin", "Normal Nucleoli", "Mitoses");
int[] outputs = symbols.ToIntArray("Class").GetColumn(0);
// symbols.
id3learning.Run(inputs, outputs);
int[] query = codebook.Translate(inputlar[0], inputlar[1], inputlar[2], inputlar[3],
inputlar[4], inputlar[5], inputlar[6], inputlar[7], inputlar[8]);
int output = tree.Compute(query);
string answer = codebook.Translate("Class", output);
return answer;
}
public void Run(String filename)
{
ReadFile(filename);
// Create a new codification codebook to
// convert strings into integer symbols
Codification codebook = new Codification(data, inputColumns.ToArray());
// Translate our training data into integer symbols using our codebook:
DataTable symbols = codebook.Apply(data);
foreach (String s in inputColumns)
CreateDic(s, symbols);
CreateDic(outputColumn, symbols);
int[][] inputs = (from p in symbols.AsEnumerable()
select GetInputRow(p)
).Cast<int[]>().ToArray();
int[] outputs = (from p in symbols.AsEnumerable()
select GetIndex(outputColumn, p[outputColumn].ToString())).Cast<int>().ToArray();
// Gather information about decision variables
DecisionVariable[] attributes = GetDecisionVariables();
int classCount = GetCount(outputColumn); // 2 possible output values for playing tennis: yes or no
//Create the decision tree using the attributes and classes
DecisionTree tree = new DecisionTree(attributes, classCount);
// Create a new instance of the ID3 algorithm
ID3Learning id3learning = new ID3Learning(tree);
//C45Learning c45learning = new C45Learning(tree);
// Learn the training instances!
id3learning.Run(inputs, outputs);
//c45learning.Run(inputs2, outputs);
/*
string answer = codebook.Translate(outputColumn,
tree.Compute(codebook.Translate("Sunny", "Hot", "High", "Strong")));
Console.WriteLine("Calculate for: Sunny, Hot, High, Strong");
Console.WriteLine("Answer: " + answer);
*/
var expression = tree.ToExpression();
Console.WriteLine(tree.ToCode("ClassTest"));
DecisionSet rules = tree.ToRules();
Console.WriteLine(rules.ToString());
// Compiles the expression to IL
var func = expression.Compile();
}
public void Run()
{
DataTable data = new DataTable("Mitchell's Tennis Example");
data.Columns.Add("Day");
data.Columns.Add("Outlook");
data.Columns.Add("Temperature");
data.Columns.Add("Humidity");
data.Columns.Add("Wind");
data.Columns.Add("PlayTennis");
data.Rows.Add("D1", "Sunny", "Hot", "High", "Weak", "No");
data.Rows.Add("D2", "Sunny", "Hot", "High", "Strong", "No");
data.Rows.Add("D3", "Overcast", "Hot", "High", "Weak", "Yes");
data.Rows.Add("D4", "Rain", "Mild", "High", "Weak", "Yes");
data.Rows.Add("D5", "Rain", "Cool", "Normal", "Weak", "Yes");
data.Rows.Add("D6", "Rain", "Cool", "Normal", "Strong", "No");
data.Rows.Add("D7", "Overcast", "Cool", "Normal", "Strong", "Yes");
data.Rows.Add("D8", "Sunny", "Mild", "High", "Weak", "No");
data.Rows.Add("D9", "Sunny", "Cool", "Normal", "Weak", "Yes");
data.Rows.Add("D10", "Rain", "Mild", "Normal", "Weak", "Yes");
data.Rows.Add("D11", "Sunny", "Mild", "Normal", "Strong", "Yes");
data.Rows.Add("D12", "Overcast", "Mild", "High", "Strong", "Yes");
data.Rows.Add("D13", "Overcast", "Hot", "Normal", "Weak", "Yes");
data.Rows.Add("D14", "Rain", "Mild", "High", "Strong", "No");
// Create a new codification codebook to
// convert strings into integer symbols
Codification codebook = new Codification(data, "Outlook", "Temperature", "Humidity", "Wind", "PlayTennis");
// Translate our training data into integer symbols using our codebook:
DataTable symbols = codebook.Apply(data);
CreateDic("Outlook", symbols);
CreateDic("Temperature", symbols);
CreateDic("Humidity", symbols);
CreateDic("Wind", symbols);
CreateDic("PlayTennis", symbols);
int[][] inputs = (from p in symbols.AsEnumerable()
select new int[]
{
GetIndex("Outlook", p["Outlook"].ToString()),
GetIndex("Temperature", p["Temperature"].ToString()),
GetIndex("Humidity", p["Humidity"].ToString()),
GetIndex("Wind", p["Wind"].ToString())
}).Cast<int[]>().ToArray();
int[] outputs = (from p in symbols.AsEnumerable()
select GetIndex("PlayTennis", p["PlayTennis"].ToString())).Cast<int>().ToArray();
/*
// Gather information about decision variables
DecisionVariable[] attributes =
{
new DecisionVariable("Outlook", 3), // 3 possible values (Sunny, overcast, rain)
new DecisionVariable("Temperature", 3), // 3 possible values (Hot, mild, cool)
new DecisionVariable("Humidity", 2), // 2 possible values (High, normal)
new DecisionVariable("Wind", 2) // 2 possible values (Weak, strong)
};
*/
DecisionVariable[] attributes =
{
new DecisionVariable("Outlook", GetCount("Outlook")), // 3 possible values (Sunny, overcast, rain)
new DecisionVariable("Temperature", GetCount("Temperature")), // 3 possible values (Hot, mild, cool)
new DecisionVariable("Humidity", GetCount("Humidity")), // 2 possible values (High, normal)
new DecisionVariable("Wind", GetCount("Wind")) // 2 possible values (Weak, strong)
};
int classCount = GetCount("PlayTennis"); // 2 possible output values for playing tennis: yes or no
//Create the decision tree using the attributes and classes
DecisionTree tree = new DecisionTree(attributes, classCount);
// Create a new instance of the ID3 algorithm
ID3Learning id3learning = new ID3Learning(tree);
// Learn the training instances!
id3learning.Run(inputs, outputs);
string answer = codebook.Translate("PlayTennis",
tree.Compute(codebook.Translate("Sunny", "Hot", "High", "Strong")));
Console.WriteLine("Calculate for: Sunny, Hot, High, Strong");
Console.WriteLine("Answer: " + answer);
var expression = tree.ToExpression();
Console.WriteLine(tree.ToCode("ClassTest"));
DecisionSet s = tree.ToRules();
Console.WriteLine(s.ToString());
// Compiles the expression to IL
var func = expression.Compile();
}