public void Train(List <Person> people, int numberOfTrees, int skillSetSize)
{
double[][] inputs = _dataPointService.GenerateDataPointsFromPeople(people, skillSetSize);
int[] expectedResults = _dataPointService.GenerateExpectedResultFromPeople(people);
// Create the forest learning algorithm
var teacher = new RandomForestLearning()
{
NumberOfTrees = numberOfTrees, // use 10 trees in the forest
};
// Finally, learn a random forest from data
_randomForest = teacher.Learn(inputs, expectedResults);
// We can estimate class labels using
trainingPredictions = _randomForest.Decide(inputs);
// And the classification error (0.0006) can be computed as
double error = new ZeroOneLoss(expectedResults).Loss(_randomForest.Decide(inputs));
File.WriteAllLines(
@"C:\Users\Niall\Documents\Visual Studio 2015\Projects\LinkedInSearchUi\LinkedIn Dataset\XML\random_forest_predictions.txt" // <<== Put the file name here
, trainingPredictions.Select(d => d.ToString()).ToArray());
}
public void sample_ratio_less_than_1()
{
// https://github.com/accord-net/framework/issues/576
string localPath = Path.Combine(NUnit.Framework.TestContext.CurrentContext.TestDirectory, "gh576");
Accord.Math.Random.Generator.Seed = 1;
var nursery = new DataSets.Nursery(localPath);
int[][] inputs = nursery.Instances;
int[] outputs = nursery.ClassLabels;
var teacher = new RandomForestLearning(nursery.VariableNames)
{
NumberOfTrees = 1,
SampleRatio = 0.5
};
teacher.ParallelOptions.MaxDegreeOfParallelism = 1;
var forest = teacher.Learn(inputs, outputs);
forest.ParallelOptions.MaxDegreeOfParallelism = 1;
int[] predicted = forest.Decide(inputs);
double error = new ZeroOneLoss(outputs).Loss(forest.Decide(inputs));
Assert.AreEqual(0.0023148148148148147d, error, 1e-10);
}
public double CheckAccuracy(int trees, double ratio)
{
var variables = new DecisionVariable[Data.FeatureCount];
for (int i = 0; i < Data.FeatureCount; i++)
{
variables[i] = new DecisionVariable(i.ToString(), DecisionVariableKind.Continuous);
}
var options = new ParallelOptions();
options.MaxDegreeOfParallelism = 4;
double accuracy = 0;
for (int k = 0; k < Folds; k++)
{
RandomForestLearning teacher = new RandomForestLearning(variables);
//teacher.ParallelOptions = options;
teacher.SampleRatio = ratio;
teacher.NumberOfTrees = trees;
teacher.
var model = teacher.Learn(TrainInput[k], TrainOutput[k]);
int correct = 0;
for (int i = 0; i < Data.InstancesPerFold; i++)
{
var label = model.Decide(TestInput[k][i]);
if (label == TestOutput[k][i])
{
correct++;
}
}
accuracy += (double)correct / Data.InstancesPerFold;
}
return(accuracy);
}
public void test_serialization()
{
// Fix random seed for reproducibility
Accord.Math.Random.Generator.Seed = 1;
string[][] text = Resources.iris_data.Split(new[] { "\r\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);
var teacher = new RandomForestLearning()
{
NumberOfTrees = 10, // use 10 trees in the forest
};
var forest1 = teacher.Learn(inputs, outputs);
byte[] bytes = forest1.Save();
var forest2 = Serializer.Load <RandomForest>(bytes);
forest1.ParallelOptions.MaxDegreeOfParallelism = forest2.ParallelOptions.MaxDegreeOfParallelism = 1;
Assert.IsTrue(forest1.Decide(inputs).IsEqual(forest2.Decide(inputs)));
Assert.IsTrue(forest1.Transform(inputs).IsEqual(forest2.Transform(inputs)));
}
public void Run()
{
// iris datasetini yüklüyoruz
var iris = new Accord.DataSets.Iris();
// iris inputları ve outputlarını tanımlıyoruz
double[][] inputs = iris.Instances;
int[] outputs = iris.ClassLabels;
var teacher = new RandomForestLearning()
{
NumberOfTrees = 10, // 10 trees in the forest
};
// forest variable'ı oluşturup train ediyoruz
var forest = teacher.Learn(inputs, outputs);
// kendi inputlarımızla test ediyoruz
int[] predicated = forest.Decide(inputs);
// error hesaplama. outputs expected, predicated ise tahmin edilen
double error = new ZeroOneLoss(outputs).Loss(predicated);
// error 0 çıkacak
System.Console.WriteLine(error);
}
public RF(int treeCount = 10)
{
Accord.Math.Random.Generator.Seed = 1;
_teacher = new RandomForestLearning()
{
NumberOfTrees = treeCount
};
}
//private static double[] NormalizeData(double[] data, int min, int max)
//{
// var sorted = data.OrderBy(d => d);
// double dataMax = sorted.First();
// double dataMin = sorted.Last();
// double[] ret = new double[data.Length];
// double avgIn = (double)((min + max) / 2.0);
// double avgOut = ((dataMax + dataMin) / 2.0);
// for (int i = 0; i < data.Length; i++)
// {
// ret[i] = (double) Math.Round(avgOut * (data[i] + avgIn) / 2);
// }
// return ret;
//}
// train classifier and enter trades based on predictions
private void Classifier()
{
Generator.Seed = 1;
// input columns
double[][] inputs = z; // result;
// normalize the inputs array
//for (int i = 0; i < 5; i++)
//{
// z[i] = NormalizeData(z[i], 0, 1);
//}
// output column
int[] outputs = Label;
// set the learning algorithm
var teacher = new RandomForestLearning()
{
NumberOfTrees = 1000,
//SampleRatio = 1.0,
//Join = 2,
//CoverageRatio = 0.5,
};
// train the model
var model = teacher.Learn(inputs, outputs);
// set array to be predicted
double[] inputs2 = x[0];
// compute the machine's answer for the array to be classified
int answers = model.Decide(inputs2);
// enter long if predicted value is 1
if (answers == 1)
{
EnterLong();
}
// enter short if predicted value is 0
if (answers == 0)
{
EnterShort();
}
//Calculate the confusion matrix
ConfusionMatrix cm = ConfusionMatrix.Estimate(model, inputs, outputs);
false_neg = cm.FalseNegatives;
false_pos = cm.FalsePositives;
// Print false positive and false negative
Print(false_neg + ", " + false_pos);
}
private static double[] RandomForest(List <Wine> testingSet, List <Wine> trainingSet)
{
var teacher = new RandomForestLearning()
{
NumberOfTrees = 4
};
var forest = teacher.Learn(trainingSet.Select(x => x.GetParams()).ToArray(), trainingSet.Select(x => x.Quality).ToArray());
var result = forest.Decide(testingSet.Select(x => x.GetParams()).ToArray());
return(result.Select(x => (double)x).ToArray());
}
public void buildModel()
{
var attributes = DecisionVariable.FromData(inputs);
// Now, let's create the forest learning algorithm
var teacher = new RandomForestLearning(attributes)
{
NumberOfTrees = 1,
SampleRatio = 1.0
};
// Finally, learn a random forest from data
this.forest = teacher.Learn(inputs, outputs);
}
public void test_learn()
{
#region doc_iris
// Fix random seed for reproducibility
Accord.Math.Random.Generator.Seed = 1;
// 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[] { "\r\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);
// Create the forest learning algorithm
var teacher = new RandomForestLearning()
{
NumberOfTrees = 10, // use 10 trees in the forest
};
// Finally, learn a random forest from data
var forest = teacher.Learn(inputs, outputs);
// We can estimate class labels using
int[] predicted = forest.Decide(inputs);
// And the classification error (0.0006) can be computed as
double error = new ZeroOneLoss(outputs).Loss(forest.Decide(inputs));
#endregion
Assert.IsTrue(error < 0.015);
}
private int predict(double[][] trainingInputs, int[] trainingOutputs, double[][] inputToPredict)
{
var teacher = new RandomForestLearning()
{
NumberOfTrees = forestNumberOfTrees,
Join = forestJoin
};
var forest = teacher.Learn(trainingInputs, trainingOutputs);
int[] predicted = forest.Decide(inputToPredict);
return(predicted[0]);
}
private static RandomForest CreateRandomForestModel(
DecisionVariable[] decisionVariables,
GridSearchParameterCollection bestParameters,
double[][] trainingInputs,
int[] trainingOutputs)
{
var teacher = new RandomForestLearning(decisionVariables)
{
NumberOfTrees = (int)bestParameters["trees"].Value,
SampleRatio = bestParameters["sampleRatio"].Value,
Join = (int)bestParameters["join"].Value
};
// Create a training algorithm and learn the training data
var rfcModel = teacher.Learn(trainingInputs, trainingOutputs);
return(rfcModel);
}
/// <summary>
/// Classify our data using random forest classifer and save the model.
/// </summary>
/// <param name="train_data">Frame objects that we will use to train classifers.</param>
/// <param name="test_data">Frame objects that we will use to test classifers.</param>
/// <param name="train_label">Labels of the train data.</param>
/// <param name="test_label">Labels of the test data.</param>
/// <param name="Classifier_Path">Path where we want to save the classifer on the disk.</param>
/// <param name="Classifier_Name">Name of the classifer we wnat to save.</param>
/// <param name="NumOfTrees">Number of trees used in Random forest classifer</param>
/// <returns></returns>
public void RandomForestLearning(double[][] train_data, double[][] test_data, int[] train_label, int[] test_label, String Classifier_Path, String Classifier_Name, int NumOfTrees = 20)
{
var teacher = new RandomForestLearning()
{
NumberOfTrees = NumOfTrees,
};
var forest = teacher.Learn(train_data, train_label);
int[] predicted = forest.Decide(test_data);
double error = new ZeroOneLoss(test_label).Loss(predicted);
Console.WriteLine(error);
forest.Save(Path.Combine(Classifier_Path, Classifier_Name));
}
public void Uczenie(string[] naglowki, string[][] dane)
{
Codification kody = new Codification(naglowki, dane);
int[][] symbole = kody.Transform(dane);
int[][] daneWejsciowe = symbole.Get(null, 0, -1);
KolumnaWynikow = symbole.GetColumn(-1);
RandomForestLearning nauczyciel = new RandomForestLearning()
{
SampleRatio = IloscDanychModelu
};
RandomForest las = nauczyciel.Learn(daneWejsciowe, KolumnaWynikow);
Rezultaty = las.Decide(daneWejsciowe);
}
public void constructor_test()
{
CultureInfo.DefaultThreadCurrentCulture = CultureInfo.InvariantCulture;
var times = ReadCSV(Properties.Resources.times);
var features = ReadCSV(Properties.Resources.features);
var didSolve = times.Select(list => list.Select(d => d < 5000).ToList()).ToList();
var foldCount = 10;
for (int i = 0; i < foldCount; i++)
{
var elementsPerFold = didSolve.Count / foldCount;
var y_test = didSolve.Skip(i * elementsPerFold).Take(elementsPerFold);
var y_train = didSolve.Except(y_test).ToList();
var x_test = features.Skip(i * elementsPerFold).Take(elementsPerFold);
var x_train = features.Except(x_test);
var allSolverPredictions = new List <bool[]>();
for (int j = 0; j < y_train.First().Count; j++)
{
var y_train_current_solver = y_train.Select(list => list.Skip(j).First()).Select(b => b ? 1 : 0);
var randomForestLearning = new RandomForestLearning()
{
Trees = 10
};
var currentSolverPredictions = new List <bool>();
var randomForest = randomForestLearning.Learn(x_train.Select(list => list.ToArray()).ToArray(),
y_train_current_solver.ToArray());
foreach (var test_instance in x_test)
{
var compute = randomForest.Compute(test_instance.ToArray());
currentSolverPredictions.Add(compute != 0);
}
allSolverPredictions.Add(currentSolverPredictions.ToArray());
}
Assert.AreEqual(allSolverPredictions.Count, 29);
foreach (var p in allSolverPredictions)
{
Assert.AreEqual(p.Length, 424);
}
}
}
static RandomForest RandomForestClassification(List <int[]> trainingData, List <int[]> testingData, out double precision)
{
int testingCount = testingData.Count / 10;
int trainingCount = testingData.Count - testingCount;
double errorAverage = 0;
int indexTestingStart = testingData.Count - testingCount;
int indexTestingEnd = testingData.Count;
double prec = 0;
Console.WriteLine("Random Forest Classification");
RandomForest bestforest = null;
for (int i = 0; i < iterations; i++)
{
var watch = System.Diagnostics.Stopwatch.StartNew();
Console.WriteLine("Testing from: {0} to {1}", indexTestingStart, indexTestingEnd);
int[][] inputData, testinputData;
int[] outputData, testoutputData;
PrepareInputOutput(out inputData, out outputData, out testinputData, out testoutputData, trainingData, testingData, indexTestingStart, indexTestingEnd);
var RanForest = new RandomForestLearning()
{
NumberOfTrees = 100,
};
var forest = RanForest.Learn(inputData, outputData);
Console.WriteLine("Medis sukurtas - ismokta");
double er = new ZeroOneLoss(testoutputData).Loss(forest.Decide(testinputData));
Console.WriteLine("Apmokymo tikslumas: {0}", 1 - er);
if (1 - er > prec)
{
prec = 1 - er;
bestforest = forest;
}
watch.Stop();
var elapsedMs = watch.ElapsedMilliseconds;
Console.WriteLine("Iteracija baigta per: {0}ms", elapsedMs);
indexTestingEnd = indexTestingStart;
indexTestingStart -= testingCount;
errorAverage += er;
Console.WriteLine("------------------------------------------------------------------------------");
}
precision = 1 - (errorAverage / iterations);
return(bestforest);
}
/// <summary>
/// Trains the classifier and computes the training error if option provided.
/// </summary>
/// <param name="trainingData">The training data that will be used to train classifier.</param>
/// <param name="trainingLabels">The training labels related to provided training data.</param>
/// <param name="calculateError">The boolean check to tell if the training error should be calculated.</param>
public override void Train(List <double[]> trainingData, List <int> trainingLabels, bool calculateError = true)
{
LearningAlgorithm = new RandomForestLearning();
if (NumTrees > 0)
{
LearningAlgorithm.NumberOfTrees = NumTrees;
}
if (SamplePropotion > 0)
{
LearningAlgorithm.SampleRatio = SamplePropotion;
}
Model = LearningAlgorithm.Learn(trainingData.ToArray(), trainingLabels.ToArray());
if (calculateError == true)
{
TrainingError = new ZeroOneLoss(trainingLabels.ToArray()).Loss(Model.Decide(trainingData.ToArray()));
}
}
private static void randomForest(double[][] inputs, int[] outputs)
{
var teacher = new RandomForestLearning()
{
NumberOfTrees = 100, // Use 100 decision trees to cover this problem
};
// Use the learning algorithm to induce the tree
RandomForest rf = teacher.Learn(inputs, outputs);
// Classify the samples using the RF
int[] predicted = rf.Decide(inputs);
// Create a confusion matrix to check the quality of the predictions:
var cm = new ConfusionMatrix(predicted: predicted, expected: outputs);
// Check the accuracy measure:
double accuracy = cm.Accuracy; // (should be 1.0 or 100%)
}
public Classifier(List <Person> data, int size)
{
var testSet = data.Take(size).ToList();
var learnSet = data.Skip(size).ToList();
double[][] inputs = learnSet.Select(x => new double[6] {
x.Parch, x.Pclass, x.SibSp, x.Sex, x.Fare, x.Embarked
}).ToArray();
int[] outputs = learnSet.Select(x => x.Survived).ToArray();
DecisionVariable[] variables =
{
new DecisionVariable("Parch", DecisionVariableKind.Discrete),
new DecisionVariable("Pclass", DecisionVariableKind.Discrete),
new DecisionVariable("SibSp", DecisionVariableKind.Discrete),
new DecisionVariable("Sex", DecisionVariableKind.Discrete),
new DecisionVariable("Fare", DecisionVariableKind.Continuous),
new DecisionVariable("Embarked", DecisionVariableKind.Discrete)
};
var teacher = new RandomForestLearning()
{
NumberOfTrees = 10,
};
var tree = teacher.Learn(inputs, outputs);
var result = tree.Decide(testSet.Select(x => new double[6] {
x.Parch, x.Pclass, x.SibSp, x.Sex, x.Fare, x.Embarked
}).ToArray());
var good = 0f;
for (int i = 0; i < result.Count(); ++i)
{
if (result[i] == (testSet[i].Survived))
{
good++;
}
}
Console.WriteLine($"Good: {good/ size * 100}%");
}
/// <summary>
/// <inheritdoc />
/// </summary>
public override void Train()
{
var inputs = data.GetSelectedInput(features);
var outputs = data.GetExpectedClassificationOutput();
var DecisionVariables = new List <DecisionVariable>();
for (int i = 0; i < inputs[0].Length; i++)
{
DecisionVariables.Add(DecisionVariable.Continuous(i.ToString(), new DoubleRange(0.0, 1.0)));
}
var teacher = new RandomForestLearning(DecisionVariables.ToArray())
{
NumberOfTrees = 20
};
forest = teacher.Learn(inputs, outputs);
Save();
}
public override void Train(List <double[]> trainingData, List <double> trainingLabels, bool calculateError = true)
{
LearningAlgorithm = new RandomForestLearning();
if (NumTrees > 0)
{
LearningAlgorithm.NumberOfTrees = NumTrees;
}
if (SamplePropotion > 0)
{
LearningAlgorithm.SampleRatio = SamplePropotion;
}
int[][] TrainingData = TypeCasters.DoubleMultiArrayToInt(trainingData).ToArray();
int[] TrainingLabels = TypeCasters.DoubleArrayToInt(trainingLabels).ToArray();
Model = LearningAlgorithm.Learn(TrainingData, TrainingLabels);
if (calculateError == true)
{
TrainingError = new ZeroOneLoss(TrainingLabels).Loss(Model.Decide(TrainingData));
}
}
public void test_learn()
{
#region doc_iris
// Fix random seed for reproducibility
Accord.Math.Random.Generator.Seed = 1;
// 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:
var iris = new DataSets.Iris();
double[][] inputs = iris.Instances; // flower features
int[] outputs = iris.ClassLabels; // flower categories
// Create the forest learning algorithm
var teacher = new RandomForestLearning()
{
NumberOfTrees = 10, // use 10 trees in the forest
};
// Finally, learn a random forest from data
var forest = teacher.Learn(inputs, outputs);
// We can estimate class labels using
int[] predicted = forest.Decide(inputs);
// And the classification error (0.0006) can be computed as
double error = new ZeroOneLoss(outputs).Loss(forest.Decide(inputs));
#endregion
Assert.AreEqual(10, forest.Trees.Length);
Assert.IsTrue(error < 0.015);
}
static void Main(string[] args)
{
// sample input
double[][] inputs =
{
new double[] { 0, 0 },
new double[] { 1, 0 },
new double[] { 0, 1 },
new double[] { 1, 1 },
};
// sample binary output
int[] outputs =
{
0,
1,
1,
0,
};
// sample binary output for Neural Network
double[][] nnOutputs =
{
new double[] { 1, 0 },
new double[] { 0, 1 },
new double[] { 0, 1 },
new double[] { 1, 0 },
};
// sample multinomial output
int[] multiOutputs =
{
0,
1,
1,
2,
};
// 1. Binary Logistic Regression
var learner = new IterativeReweightedLeastSquares <LogisticRegression>()
{
MaxIterations = 100
};
var model = learner.Learn(inputs, outputs);
var preds = model.Decide(inputs);
Console.WriteLine("\n\n*Binary Logistic Regression Predictions: {0}", String.Join(", ", preds));
// 2. Multinomial Logistic Regression
var learner2 = new MultinomialLogisticLearning <GradientDescent>()
{
MiniBatchSize = 4
};
var model2 = learner2.Learn(inputs, multiOutputs);
var preds2 = model2.Decide(inputs);
Console.WriteLine("\n\n*Multinomial Logistic Regression Predictions: {0}", String.Join(", ", preds2));
// 3. Binary Naive Bayes Classifier
var learner3 = new NaiveBayesLearning <NormalDistribution>();
var model3 = learner3.Learn(inputs, outputs);
var preds3 = model2.Decide(inputs);
Console.WriteLine("\n\n*Binary Naive Bayes Predictions: {0}", String.Join(", ", preds3));
// 4. RandomForest
var learner4 = new RandomForestLearning()
{
NumberOfTrees = 3,
CoverageRatio = 0.9,
SampleRatio = 0.9
};
var model4 = learner4.Learn(inputs, outputs);
var preds4 = model4.Decide(inputs);
Console.WriteLine("\n\n*Binary RandomForest Classifier Predictions: {0}", String.Join(", ", preds4));
// 5. SVM
var learner5 = new SequentialMinimalOptimization <Gaussian>();
var model5 = learner.Learn(inputs, outputs);
var preds5 = model5.Decide(inputs);
Console.WriteLine("\n\n*Binary SVM Predictions: {0}", String.Join(", ", preds5));
// 6. Neural Network
var network = new ActivationNetwork(
new BipolarSigmoidFunction(2),
2,
1,
2
);
var teacher = new LevenbergMarquardtLearning(network);
Console.WriteLine("\n-- Training Neural Network");
int numEpoch = 3;
double error = Double.PositiveInfinity;
for (int i = 0; i < numEpoch; i++)
{
error = teacher.RunEpoch(inputs, nnOutputs);
Console.WriteLine("* Epoch {0} - error: {1:0.0000}", i + 1, error);
}
double[][] nnPreds = inputs.Select(
x => network.Compute(x)
).ToArray();
int[] preds6 = nnPreds.Select(
x => x.ToList().IndexOf(x.Max())
).ToArray();
Console.WriteLine("\n\n*Binary Neural Network Predictions: {0}", String.Join(", ", preds6));
Console.WriteLine("\n\n\n\nDONE!!");
Console.ReadKey();
}
public static void TrainClassifiers()
{
// -------------------------- Logistic Regression ----------------------------------
var MLRG = new MultinomialLogisticLearning <GradientDescent>();
Predictor.MultinomialLogisticRegression = MLRG.Learn(PredictorPointsTrain, FrequencyLabelsInt);
// -------------------------- Random Forest ----------------------------------
var teacher = new RandomForestLearning()
{
NumberOfTrees = NumTrees,
};
Predictor.RandomForest = teacher.Learn(PredictorPointsTrain, FrequencyLabelsInt);
// -------------------------- Minimum Mean Distance ----------------------------------
Predictor.MinimumMeanDistance = new MinimumMeanDistanceClassifier();
// Compute the analysis and create a classifier
Predictor.MinimumMeanDistance.Learn(PredictorPointsTrain, FrequencyLabelsInt);
// -------------------------- Support Vector Machine ----------------------------------
// Declare the parameters and ranges to be searched
/*GridSearchRange[] ranges =
* {
* new GridSearchRange("complexity", new double[] { 0.00000001, 5.20, 0.30, 0.50 } ),
* };*/
// Instantiate a new Grid Search algorithm for Kernel Support Vector Machines
/* var gridsearch = new GridSearch<SupportVectorMachine>(ranges);
*
* // Set the fitting function for the algorithm
* gridsearch.Fitting = delegate (GridSearchParameterCollection parameters, out double error)
* {
* // The parameters to be tried will be passed as a function parameter.
* double complexity = parameters["complexity"].Value;
*
* // Use the parameters to build the SVM model
* SupportVectorMachine ksvm = new SupportVectorMachine( 2);
*
*
* // Create a new learning algorithm for SVMs
* SequentialMinimalOptimization smo = new SequentialMinimalOptimization(ksvm, PredictorPointsTrain, FrequencyLabelsInt);
* smo.Complexity = complexity;
*
* // Measure the model performance to return as an out parameter
* error = smo.Run();
*
* return ksvm; // Return the current model
* };
*
*
* // Declare some out variables to pass to the grid search algorithm
* GridSearchParameterCollection bestParameters; double minError;
*
* // Compute the grid search to find the best Support Vector Machine
* Predictor.SVM = gridsearch.Compute(out bestParameters, out minError);*/
}
public void LargeRunTest()
{
string localPath = Path.Combine(NUnit.Framework.TestContext.CurrentContext.TestDirectory, "rf");
#region doc_nursery
// Fix random seed for reproducibility
Accord.Math.Random.Generator.Seed = 1;
// This example uses the Nursery Database available from the University of
// California Irvine repository of machine learning databases, available at
//
// http://archive.ics.uci.edu/ml/machine-learning-databases/nursery/nursery.names
//
// The description paragraph is listed as follows.
//
// Nursery Database was derived from a hierarchical decision model
// originally developed to rank applications for nursery schools. It
// was used during several years in 1980's when there was excessive
// enrollment to these schools in Ljubljana, Slovenia, and the
// rejected applications frequently needed an objective
// explanation. The final decision depended on three subproblems:
// occupation of parents and child's nursery, family structure and
// financial standing, and social and health picture of the family.
// The model was developed within expert system shell for decision
// making DEX (M. Bohanec, V. Rajkovic: Expert system for decision
// making. Sistemica 1(1), pp. 145-157, 1990.).
//
// Let's begin by loading the raw data. This string variable contains
// the contents of the nursery.data file as a single, continuous text.
//
var nursery = new DataSets.Nursery(path: localPath);
int[][] inputs = nursery.Instances;
int[] outputs = nursery.ClassLabels;
// Now, let's create the forest learning algorithm
var teacher = new RandomForestLearning(nursery.VariableNames)
{
NumberOfTrees = 1,
SampleRatio = 1.0
};
// Finally, learn a random forest from data
var forest = teacher.Learn(inputs, outputs);
// We can estimate class labels using
int[] predicted = forest.Decide(inputs);
// And the classification error (0) can be computed as
double error = new ZeroOneLoss(outputs).Loss(forest.Decide(inputs));
#endregion
Assert.AreEqual(0, error, 1e-10);
Assert.IsTrue(outputs.IsEqual(predicted));
Assert.AreEqual(0, error);
for (int i = 0; i < inputs.Length; i++)
{
int expected = outputs[i];
int actual = forest.Compute(inputs[i].ToDouble());
Assert.AreEqual(expected, actual);
}
}
public void LargeRunTest()
{
#region doc_nursery
// Fix random seed for reproducibility
Accord.Math.Random.Generator.Seed = 1;
// This example uses the Nursery Database available from the University of
// California Irvine repository of machine learning databases, available at
//
// http://archive.ics.uci.edu/ml/machine-learning-databases/nursery/nursery.names
//
// The description paragraph is listed as follows.
//
// Nursery Database was derived from a hierarchical decision model
// originally developed to rank applications for nursery schools. It
// was used during several years in 1980's when there was excessive
// enrollment to these schools in Ljubljana, Slovenia, and the
// rejected applications frequently needed an objective
// explanation. The final decision depended on three subproblems:
// occupation of parents and child's nursery, family structure and
// financial standing, and social and health picture of the family.
// The model was developed within expert system shell for decision
// making DEX (M. Bohanec, V. Rajkovic: Expert system for decision
// making. Sistemica 1(1), pp. 145-157, 1990.).
//
// Let's begin by loading the raw data. This string variable contains
// the contents of the nursery.data file as a single, continuous text.
//
string nurseryData = Resources.nursery;
// Those are the input columns available in the data
//
string[] inputColumns =
{
"parents", "has_nurs", "form", "children",
"housing", "finance", "social", "health"
};
// And this is the output, the last column of the data.
//
string outputColumn = "output";
// Let's populate a data table with this information.
//
DataTable table = new DataTable("Nursery");
table.Columns.Add(inputColumns);
table.Columns.Add(outputColumn);
string[] lines = nurseryData.Split(
new[] { "\r\n" }, StringSplitOptions.RemoveEmptyEntries);
foreach (var line in lines)
{
table.Rows.Add(line.Split(','));
}
// Now, we have to convert the textual, categorical data found
// in the table to a more manageable discrete representation.
//
// For this, we will create a codebook to translate text to
// discrete integer symbols:
//
Codification codebook = new Codification(table);
// And then convert all data into symbols
//
DataTable symbols = codebook.Apply(table);
double[][] inputs = symbols.ToArray(inputColumns);
int[] outputs = symbols.ToArray <int>(outputColumn);
// From now on, we can start creating the decision tree.
//
var attributes = DecisionVariable.FromCodebook(codebook, inputColumns);
// Now, let's create the forest learning algorithm
var teacher = new RandomForestLearning(attributes)
{
NumberOfTrees = 1,
SampleRatio = 1.0
};
// Finally, learn a random forest from data
var forest = teacher.Learn(inputs, outputs);
// We can estimate class labels using
int[] predicted = forest.Decide(inputs);
// And the classification error (0) can be computed as
double error = new ZeroOneLoss(outputs).Loss(forest.Decide(inputs));
#endregion
Assert.AreEqual(0, error, 1e-10);
Assert.IsTrue(outputs.IsEqual(predicted));
Assert.AreEqual(12960, lines.Length);
Assert.AreEqual("usual,proper,complete,1,convenient,convenient,nonprob,recommended,recommend", lines[0]);
Assert.AreEqual("great_pret,very_crit,foster,more,critical,inconv,problematic,not_recom,not_recom", lines[lines.Length - 1]);
Assert.AreEqual(0, error);
for (int i = 0; i < inputs.Length; i++)
{
int expected = outputs[i];
int actual = forest.Compute(inputs[i]);
Assert.AreEqual(expected, actual);
}
}
private List <Colaborador> metodoquedefineoscolaboradores(int pGerencia, int pClassificacao, int pDificuldade, int pPrioridade, int pTipoFalha)
{
string filename = "C:/Users/Oscar/Downloads/solics-completo.csv";
CsvReader reader = new CsvReader(filename, hasHeaders: true);
DataTable table = reader.ToTable();
string[] inputNames = new[] { "Id", "Gerencia", "Cliente", "Sistema", "Modulo", "Classificacao", "TipoFalha", "Prioridade", "Dificuldade" };
string[] outputNames = new[] { "Colaborador" };
/*var codification1 = new Codification()
* {
* { "Id", CodificationVariable.Ordinal},
* { "Gerencia", CodificationVariable.Discrete },
* { "Cliente", CodificationVariable.Discrete },
* { "Sistema", CodificationVariable.Discrete },
* { "Modulo", CodificationVariable.Discrete },
* { "Classificacao", CodificationVariable.Discrete},
* { "TipoFalha", CodificationVariable.Discrete },
* { "Prioridade", CodificationVariable.Discrete },
* { "Dificuldade", CodificationVariable.Discrete },
* };
*
* var codification2 = new Codification()
* {
* DefaultMissingValueReplacement = Double.NaN
* };
*
* codification1.Learn(table);
* codification2.Learn(table);
*
*/
Codification codebook = new Codification(table);
//DataTable symbols = codification.Apply(table);
//int[] outputis = symbols.ToArray<int>("COLABORADOR");
// Now, transform symbols into a vector representation, growing the number of inputs:
//double[][] x = codification.Transform(table, inputNames, out inputNames).ToDouble();
int[][] x = codebook.Apply(table, "Id", "Gerencia", "Cliente", "Sistema", "Modulo", "Classificacao", "TipoFalha", "Prioridade", "Dificuldade").ToJagged(out inputNames).ToInt32();
//double[][] y = codification.Transform(table, outputNames, out outputNames).ToDouble();
//int[] y = codification.Apply(table, "COLABORADOR").ToJagged(out outputName);
string outputName; // can see below the new variable names that will be generated)
int[] outputs = codebook.Apply(table, "Colaborador").ToVector(out outputName).ToInt32();
/*
* // Create the multi-class learning algorithm for the machine
* var teacher = new MultilabelSupportVectorLearning<Gaussian>()
* {
* // Configure the learning algorithm to use SMO to train the
* // underlying SVMs in each of the binary class subproblems.
* Learner = (param) => new SequentialMinimalOptimization<Gaussian>()
* {
* // Estimate a suitable guess for the Gaussian kernel's parameters.
* // This estimate can serve as a starting point for a grid search.
* UseKernelEstimation = true
* }
* };
*
* // Learn a machine
* var machine = teacher.Learn(x, outputs);
*
* // Create the multi-class learning algorithm for the machine
* var calibration = new MultilabelSupportVectorLearning<Gaussian>()
* {
* Model = machine, // We will start with an existing machine
*
* // Configure the learning algorithm to use SMO to train the
* // underlying SVMs in each of the binary class subproblems.
* Learner = (param) => new ProbabilisticOutputCalibration<Gaussian>()
* {
* Model = param.Model // Start with an existing machine
* }
* };
*
*
* // Configure parallel execution options
* calibration.ParallelOptions.MaxDegreeOfParallelism = 1;
*
* // Learn a machine
* calibration.Learn(x, outputs);
*
* // Obtain class predictions for each sample
* bool[][] predicted = machine.Decide(x);
*
* // Get class scores for each sample
* double[][] scores = machine.Scores(x);
*
* // Get log-likelihoods (should be same as scores)
* double[][] logl = machine.LogLikelihoods(x);
*
* // Get probability for each sample
* double[][] prob = machine.Probabilities(x);
*
* // Compute classification error using mean accuracy (mAcc)
* double error = new HammingLoss(outputs).Loss(predicted);
* double loss = new CategoryCrossEntropyLoss(outputs).Loss(prob);*/
Accord.Math.Random.Generator.Seed = 1;
DecisionVariable[] Attributes = DecisionVariable.FromCodebook(codebook, inputNames);
// Now, let's create the forest learning algorithm
var teacher = new RandomForestLearning(Attributes)
{
NumberOfTrees = 1,
SampleRatio = 1.0
};
// Finally, learn a random forest from data
var forest = teacher.Learn(x, outputs);
// We can estimate class labels using
int[] predicted = forest.Decide(x);
// And the classification error (0) can be computed as
double error = new ZeroOneLoss(outputs).Loss(forest.Decide(x));
// Compute classification error using mean accuracy (mAcc)
double error2 = new HammingLoss(outputs).Loss(predicted);
List <Colaborador> lLista = new List <Colaborador>();
//lLista.AddRange(db.Colaborador.Where(x => x.Nome.StartsWith("J")).OrderBy(x => x.Nome));
return(lLista);
}
