/// <summary>The initialize.</summary>
/// <param name="configuration">The configuration.</param>
/// <param name="logManager">The log manager.</param>
/// <param name="cacheManager">The cache manager.</param>
/// <param name="preprocessingManager">The preprocessing manager.</param>
/// <param name="runStartTime">The run start time.</param>
/// <param name="timeMeasure">The time measure.</param>
private void Initialize(
WebGreaseConfiguration configuration,
LogManager logManager,
ICacheManager cacheManager,
PreprocessingManager preprocessingManager,
DateTimeOffset runStartTime,
ITimeMeasure timeMeasure)
{
if (configuration == null)
{
throw new ArgumentNullException("configuration");
}
if (configuration.Global.TreatWarningsAsErrors != null)
{
logManager.TreatWarningsAsErrors = configuration.Global.TreatWarningsAsErrors == true;
}
// Note: Configuration needs to be set before the other ones.
this.Configuration = configuration;
this.Configuration.Validate();
this.Measure = timeMeasure;
this.Log = logManager;
this.Cache = cacheManager;
this.Preprocessing = preprocessingManager;
this.SessionStartTime = runStartTime;
this.Cache.SetContext(this);
this.Preprocessing.SetContext(this);
}
public ISolver simpleSeparation(int percentTrain)
{
int sizeTrainDataset = Convert.ToInt32(InputData.Length * ((double)percentTrain / 100));
int sizeTestDataset = InputData.Length - sizeTrainDataset;
float[][] trainInputDataset = new float[sizeTrainDataset][];
float[][] testInputDataset = new float[InputData.Length - sizeTrainDataset][];
float[] trainOutputDataset = new float[sizeTrainDataset];
float[] testOutputDataset = new float[InputData.Length - sizeTrainDataset];
Array.Copy(InputData, trainInputDataset, sizeTrainDataset);
Array.Copy(InputData, sizeTrainDataset, testInputDataset, 0, sizeTestDataset);
Array.Copy(OutputData, trainOutputDataset, sizeTrainDataset);
Array.Copy(OutputData, sizeTrainDataset, testOutputDataset, 0, sizeTestDataset);
if (ISolver is INeuralNetwork)
{
LearningAlgoManager la = new LearningAlgoManager()
{
usedAlgo = LS.LearningAlgorithmName,
GeneticParams = LS.LAParameters
};
ClosingError = la.startLearn(ISolver, trainInputDataset, trainOutputDataset);
}
else if (ISolver is DecisionTree)
{
DecisionTreeLearning la = new DecisionTreeLearning();
ClosingError = la.startLearn(ISolver, trainInputDataset, trainOutputDataset);
}
PreprocessingManager preprocessing = new PreprocessingManager();
mistakeTrain = 0;
List <string> expectedOutputValues = trainOutputDataset.Select(x => Convert.ToString(x)).ToList();
List <string> obtainedOutputValues = new List <string>();
for (int i = 0; i < sizeTrainDataset; i++)
{
obtainedOutputValues.Add(Convert.ToString(ISolver.Solve(trainInputDataset[i])[0]));
}
List <bool> comparisonOfResult = preprocessing.compareExAndObValues(expectedOutputValues, obtainedOutputValues, SelectionID, ParameterID);
var counts = comparisonOfResult.GroupBy(x => x).ToDictionary(x => x.Key, x => x.Count());
mistakeTrain = (float)counts[false] / (float)sizeTrainDataset;
mistakeTest = 0;
expectedOutputValues = testOutputDataset.Select(x => Convert.ToString(x)).ToList();
obtainedOutputValues.Clear();
for (int i = 0; i < sizeTestDataset; i++)
{
obtainedOutputValues.Add(Convert.ToString(ISolver.Solve(testInputDataset[i])[0]));
}
comparisonOfResult = preprocessing.compareExAndObValues(expectedOutputValues, obtainedOutputValues, SelectionID, ParameterID);
counts = comparisonOfResult.GroupBy(x => x).ToDictionary(x => x.Key, x => x.Count());
mistakeTest = (float)counts[false] / (float)sizeTestDataset;
return(ISolver);
}
private ISolver crossValidation(int folds)
{
ISolver curSolver = ISolver.Copy();
List <float> listOfTestMistakes = new List <float>();
for (int k = 0; k < folds; k++)
{
float kMistakeTrain = 0;
float kMistakeTest = 0;
float[][] trainInputDataset = GetInputTrainData(InputData, folds, k);
float[][] testInputDataset = GetInputTestData(InputData, folds, k);
float[] trainOutputDataset = GetOutputTrainData(OutputData, folds, k);
float[] testOutputDataset = GetTestOutputData(OutputData, folds, k);
LearningAlgoManager la = new LearningAlgoManager()
{
usedAlgo = LS.LearningAlgorithmName,
GeneticParams = LS.LAParameters
};
PreprocessingManager preprocessing = new PreprocessingManager();
ClosingError = la.startLearn(ISolver, trainInputDataset, trainOutputDataset);
int sizeTrainDataset = trainInputDataset.Length;
List <string> expectedOutputValues = trainOutputDataset.Select(x => Convert.ToString(x)).ToList();
List <string> obtainedOutputValues = new List <string>();
for (int i = 0; i < sizeTrainDataset; i++)
{
obtainedOutputValues.Add(Convert.ToString(ISolver.Solve(trainInputDataset[i])[0]));
}
List <bool> comparisonOfResult = preprocessing.compareExAndObValues(expectedOutputValues, obtainedOutputValues, SelectionID, ParameterID);
var counts = comparisonOfResult.GroupBy(x => x).ToDictionary(x => x.Key, x => x.Count());
kMistakeTrain = (float)counts[false] / (float)sizeTrainDataset;
int sizeTestDataset = testOutputDataset.Length;
expectedOutputValues = testOutputDataset.Select(x => Convert.ToString(x)).ToList();
obtainedOutputValues.Clear();
for (int i = 0; i < sizeTestDataset; i++)
{
obtainedOutputValues.Add(Convert.ToString(ISolver.Solve(testInputDataset[i])[0]));
}
comparisonOfResult = preprocessing.compareExAndObValues(expectedOutputValues, obtainedOutputValues, SelectionID, ParameterID);
counts = comparisonOfResult.GroupBy(x => x).ToDictionary(x => x.Key, x => x.Count());
kMistakeTest = (float)counts[false] / (float)sizeTestDataset;
if (k != 0 && kMistakeTest < listOfTestMistakes.Min())
{
curSolver = ISolver.Copy();
mistakeTest = kMistakeTest;
mistakeTrain = kMistakeTrain;
}
listOfTestMistakes.Add(kMistakeTest);
}
ISolver = curSolver.Copy() as INeuralNetwork;
return(ISolver);
}
public void Solve()
{
SelectionID = SelectedLearning.SelectionID;
ParameterID = SelectedLearning.ParameterID;
ISolver isolver = this.SelectedLearning.LearnedSolver.Soul;
List <string> curOutputValues = new List <string>();
foreach (var item in SolvingList)
{
curOutputValues.Add(Convert.ToString(isolver.Solve(item.X.Select(x => float.Parse(x.Value)).ToArray())[0]));
}
PreprocessingManager preprocessing = new PreprocessingManager();
outputValues = preprocessing.getAppropriateValuesAfterInversePreprocessing(curOutputValues, SelectionID, ParameterID);
foreach (var item in SolvingList)
{
for (int i = 0; i < item.Y.Count; i++)
{
item.Y[i] = outputValues[i];
}
}
}
/// <summary>Initializes a new instance of the <see cref="WebGreaseContext"/> class. The web grease context.</summary>
/// <param name="configuration">The configuration</param>
/// <param name="logManager">The log Manager.</param>
/// <param name="parentCacheSection">The parent Cache Section.</param>
/// <param name="preprocessingManager">The preprocessing Manager.</param>
public WebGreaseContext(WebGreaseConfiguration configuration, LogManager logManager, ICacheSection parentCacheSection = null, PreprocessingManager preprocessingManager = null)
{
var runStartTime = DateTimeOffset.Now;
configuration.Validate();
var timeMeasure = configuration.Measure ? new TimeMeasure() as ITimeMeasure : new NullTimeMeasure();
var cacheManager = configuration.CacheEnabled ? new CacheManager(configuration, logManager, parentCacheSection) as ICacheManager : new NullCacheManager();
this.Initialize(
configuration,
logManager,
cacheManager,
preprocessingManager != null ? new PreprocessingManager(preprocessingManager) : new PreprocessingManager(configuration, logManager, timeMeasure),
runStartTime,
timeMeasure);
}