public void new_method_create_tree()
{
string[][] text = Resources.iris_data.Split(new[] { '\n' }, StringSplitOptions.RemoveEmptyEntries).Apply(x => x.Split(','));
double[][] inputs = text.GetColumns(0, 1, 2, 3).To<double[][]>();
string[] labels = text.GetColumn(4);
var codebook = new Codification("Output", labels);
int[] outputs = codebook.Translate("Output", labels);
// And we can use the C4.5 for learning:
var teacher = new C45Learning();
// And finally induce the tree:
var tree = teacher.Learn(inputs, outputs);
// To get the estimated class labels, we can use
int[] predicted = tree.Decide(inputs);
// And the classification error can be computed as
double error = new ZeroOneLoss(outputs) // 0.0266
{
Mean = true
}.Loss(tree.Decide(inputs));
// Moreover, we may decide to convert our tree to a set of rules:
DecisionSet rules = tree.ToRules();
// And using the codebook, we can inspect the tree reasoning:
string ruleText = rules.ToString(codebook, "Output",
System.Globalization.CultureInfo.InvariantCulture);
// The output is:
string expected = @"Iris-setosa =: (2 <= 2.45)
Iris-versicolor =: (2 > 2.45) && (3 <= 1.75) && (0 <= 7.05) && (1 <= 2.85)
Iris-versicolor =: (2 > 2.45) && (3 <= 1.75) && (0 <= 7.05) && (1 > 2.85)
Iris-versicolor =: (2 > 2.45) && (3 > 1.75) && (0 <= 5.95) && (1 > 3.05)
Iris-virginica =: (2 > 2.45) && (3 <= 1.75) && (0 > 7.05)
Iris-virginica =: (2 > 2.45) && (3 > 1.75) && (0 > 5.95)
Iris-virginica =: (2 > 2.45) && (3 > 1.75) && (0 <= 5.95) && (1 <= 3.05)
";
Assert.AreEqual(0.026666666666666668, error, 1e-10);
double newError = ComputeError(rules, inputs, outputs);
Assert.AreEqual(0.026666666666666668, newError, 1e-10);
Assert.AreEqual(expected, ruleText);
}
private double run(double[][] inputs, int[] output)
{
int rows = inputs.Length;
int cols = inputs[0].Length;
int classes = output.DistinctCount();
int colsPerTree;
if (CoverageRatio == 0)
{
colsPerTree = (int)(System.Math.Sqrt(cols));
}
else
{
colsPerTree = (int)(cols * CoverageRatio);
}
var trees = forest.Trees;
int[] idx = Classes.Random(output, classes, trees.Length);
Parallel.For(0, trees.Length, i =>
{
var x = inputs.Get(idx);
var y = output.Get(idx);
var c45 = new C45Learning(forest.Trees[i])
{
MaxVariables = colsPerTree,
Join = 100
};
c45.Learn(x, y);
});
return 0;
}
public void IrisDatasetTest()
{
#region doc_iris
// In this example, we will process the famous Fisher's Iris dataset in
// which the task is to classify weather the features of an Iris flower
// belongs to an Iris setosa, an Iris versicolor, or an Iris virginica:
//
// - https://en.wikipedia.org/wiki/Iris_flower_data_set
//
// First, let's load the dataset into an array of text that we can process
string[][] text = Resources.iris_data.Split(new[] { '\n' }, StringSplitOptions.RemoveEmptyEntries).Apply(x => x.Split(','));
// The first four columns contain the flower features
double[][] inputs = text.GetColumns(0, 1, 2, 3).To<double[][]>();
// The last column contains the expected flower type
string[] labels = text.GetColumn(4);
// Since the labels are represented as text, the first step is to convert
// those text labels into integer class labels, so we can process them
// more easily. For this, we will create a codebook to encode class labels:
//
var codebook = new Codification("Output", labels);
// With the codebook, we can convert the labels:
int[] outputs = codebook.Translate("Output", labels);
// Let's declare the names of our input variables:
DecisionVariable[] features =
{
new DecisionVariable("sepal length", DecisionVariableKind.Continuous),
new DecisionVariable("sepal width", DecisionVariableKind.Continuous),
new DecisionVariable("petal length", DecisionVariableKind.Continuous),
new DecisionVariable("petal width", DecisionVariableKind.Continuous),
};
// Now, we can finally create our tree for the 3 classes:
var tree = new DecisionTree(inputs: features, classes: 3);
// And we can use the C4.5 for learning:
var teacher = new C45Learning(tree);
// And finally induce the tree:
teacher.Learn(inputs, outputs);
// To get the estimated class labels, we can use
int[] predicted = tree.Decide(inputs);
// And the classification error can be computed as
double error = new ZeroOneLoss(outputs) // 0.0266
{
Mean = true
}.Loss(tree.Decide(inputs));
// Moreover, we may decide to convert our tree to a set of rules:
DecisionSet rules = tree.ToRules();
// And using the codebook, we can inspect the tree reasoning:
string ruleText = rules.ToString(codebook, "Output",
System.Globalization.CultureInfo.InvariantCulture);
// The output is:
string expected = @"Iris-setosa =: (petal length <= 2.45)
Iris-versicolor =: (petal length > 2.45) && (petal width <= 1.75) && (sepal length <= 7.05) && (sepal width <= 2.85)
Iris-versicolor =: (petal length > 2.45) && (petal width <= 1.75) && (sepal length <= 7.05) && (sepal width > 2.85)
Iris-versicolor =: (petal length > 2.45) && (petal width > 1.75) && (sepal length <= 5.95) && (sepal width > 3.05)
Iris-virginica =: (petal length > 2.45) && (petal width <= 1.75) && (sepal length > 7.05)
Iris-virginica =: (petal length > 2.45) && (petal width > 1.75) && (sepal length > 5.95)
Iris-virginica =: (petal length > 2.45) && (petal width > 1.75) && (sepal length <= 5.95) && (sepal width <= 3.05)
";
#endregion
Assert.AreEqual(0.026666666666666668, error, 1e-10);
Assert.AreEqual(4, tree.NumberOfInputs);
Assert.AreEqual(3, tree.NumberOfOutputs);
double newError = ComputeError(rules, inputs, outputs);
Assert.AreEqual(0.026666666666666668, newError, 1e-10);
Assert.AreEqual(expected, ruleText);
}
/// <summary>
/// Creates and learns a Decision Tree to recognize the
/// previously loaded dataset using the current settings.
/// </summary>
///
private void btnCreate_Click(object sender, EventArgs e)
{
if (dgvLearningSource.DataSource == null)
{
MessageBox.Show("Please load some data first.");
return;
}
// Finishes and save any pending changes to the given data
dgvLearningSource.EndEdit();
// Creates a matrix from the entire source data table
double[,] table = (dgvLearningSource.DataSource as DataTable).ToMatrix(out columnNames);
// Get only the input vector values (first two columns)
double[][] inputs = table.GetColumns(0, 1).ToArray();
// Get only the output labels (last column)
int[] outputs = table.GetColumn(2).ToInt32();
// Specify the input variables
DecisionVariable[] variables =
{
new DecisionVariable("x", DecisionVariableKind.Continuous),
new DecisionVariable("y", DecisionVariableKind.Continuous),
};
// Create the C4.5 learning algorithm
var c45 = new C45Learning(variables);
// Learn the decision tree using C4.5
tree = c45.Learn(inputs, outputs);
// Show the learned tree in the view
decisionTreeView1.TreeSource = tree;
// Get the ranges for each variable (X and Y)
DoubleRange[] ranges = table.GetRange(0);
// Generate a Cartesian coordinate system
double[][] map = Matrix.Cartesian(
Vector.Interval(ranges[0], 0.05),
Vector.Interval(ranges[1], 0.05));
// Classify each point in the Cartesian coordinate system
double[] result = map.Apply(tree.Compute).ToDouble();
double[,] surface = map.ToMatrix().InsertColumn(result);
CreateScatterplot(zedGraphControl2, surface);
lbStatus.Text = "Learning finished! Click the other tabs to explore results!";
}
