/// <summary>
/// creates learning curve after learning+deciding about given precentage of pictures according to percent[]
/// </summary>
/// <param name="folderAll">folder of all images</param>
/// <param name="folderTrue">folder of true images</param>
/// <param name="learn">data learning object for learning</param>
/// <param name="decide">decision making object for deciding</param>
/// <param name="percent">percentages to use for learning (percent.length is number of points in learning curve)</param>
/// <returns>true if succeeded creating the curve</returns>
public static CurvePoint[] LearningCurve(string folderAll, string folderTrue, DataLearning learning, DecisionMaking deciding, int[] percent, out double[] simpleAlgo,
Testing.HandleIdenticalMethod identical, bool excludeTrainingSet)
{
_progress = 0;
int itrCount=0;
simpleAlgo = new double[3];
//randomLearningCurve = null;
const int ITERATIONS_PER_POINT = 5;
// Make All, True & False files lists
List<string> allFiles, falseFiles, trueFiles;
try
{
allFiles = LoadImages(folderAll).ToList();
trueFiles = LoadImages(folderTrue).ToList();
falseFiles = SubstractListsByFileName(allFiles, trueFiles);
trueFiles = SubstractListsByFileName(allFiles, falseFiles); // In order for the path to be via 'allFiles' folder
}
catch (Exception exc)
{
MessageBox.Show(exc.Message);
return null;
}
// Handle duplicates
ProgressString = "Checking for identicals with different choise";
HandleIdenticalVectorWithDifferentChoise(ref allFiles, ref trueFiles, ref falseFiles, learning.Repository, identical);
//create curve of percent.length number of points
ProgressString = "Calculating Curves";
CurvePoint[] learningCurve = new CurvePoint[percent.Length]; //for main graph
//randomLearningCurve = new CurvePoint[percent.Length]; //for random algorithm graph
for (int k = 0; k < percent.Length; k++)
{
learningCurve[k] = new CurvePoint(percent[k]);
// randomLearningCurve[k] = new CurvePoint(percent[k]);
for (int itr = 0; itr < ITERATIONS_PER_POINT; itr++)
{
//get wanted amount of randome images
List<string> chosenFiles;
do chosenFiles = getRandomImages(allFiles, percent[k]);
while (SubstractListsByFileName(chosenFiles, trueFiles).Count == 0 || SubstractListsByFileName(chosenFiles, falseFiles).Count == 0); // incase only true or only false was chosen
//get new lists of true and false files (Used for learning in current curve point)
List<string> subsetTrueFiles = SubstractListsByFileName(chosenFiles, falseFiles);
List<string> subsetFalseFiles = SubstractListsByFileName(chosenFiles, trueFiles);
//-------------------------------------
//learn from subsets
learning.LearnForTesting(chosenFiles, subsetTrueFiles);
//-------------------------------------
//decide for all files
double[] results;
deciding.DecideForTesting(allFiles, learning.Repository, out results);
//-------------------------------------
//make true and false lists according to results
List<string> resultsTrue = new List<string>();
List<string> resultsFalse = new List<string>();
for (int i = 0; i < results.Length; i++)
if (results[i]>0) //*******here deside for testing*******/
resultsTrue.Add(allFiles[i]);
else
resultsFalse.Add(allFiles[i]);
//-------------------------------------
//calculate success precentage
CurvePoint.SingleCurvePointCalc currentIteration = new CurvePoint.SingleCurvePointCalc(trueFiles, falseFiles, subsetTrueFiles, subsetFalseFiles, resultsTrue, resultsFalse, excludeTrainingSet);
learningCurve[k].AddSingleCurvePointCalc(currentIteration);
//-------------------------------------
//get simple algorithms calculations
double simpleFalseNegative,
simpleFalsePositive,
simpleSuccess;
Testing.SimpleAlgorithm.CalcStatisticalAlgorithm(allFiles.Count, trueFiles.Count, out simpleSuccess, out simpleFalseNegative, out simpleFalsePositive);
simpleAlgo[0] = simpleSuccess*100;
simpleAlgo[1] = simpleFalseNegative * 100;
simpleAlgo[2] = simpleFalsePositive * 100;
// Update progress indicators
itrCount++;
_progress = (int)((itrCount * 100)/(ITERATIONS_PER_POINT * percent.Length));
}
}
ProgressString = "Done Calculating Curves";
return learningCurve;
}
private void threadCalcLearningCurve()
{
// Make Learning & Deciding objects
const string USERNAME = "******";
DataLearning learning;
if (_rdoKNN.Checked)
{
//K = int.Parse(_txtK.Text);
K = 1;
learning = new DataLearning(USERNAME, LearningAlgorithm.Algorithm.KNN, ParamDictionary, K);
}
else if (_rdoTree.Checked)
{
K = 0;
learning = new DataLearning(USERNAME, LearningAlgorithm.Algorithm.DecisionTree, ParamDictionary, K);
}
else // if (_rdoTreeNum.Checked)
{
K = 0;
learning = new DataLearning(USERNAME, LearningAlgorithm.Algorithm.DecisionTreeNumerical, ParamDictionary, K);
}
DecisionMaking deciding = new DecisionMaking(USERNAME, learning.Algorithm, ParamDictionary);
// Load vectors to repository
learning.Repository.loadList();
// Scan pictures
Testing.scanPicturesIntoReporistory(txtFolderAllTesting3.Text, txtFolderTrueTesting3.Text, learning.Repository, ParamDictionary);
// Set X-Axis points for learning curve
int nPoints = Convert.ToInt16(txtNumOfPointsTesting3.Text);
int[] percent = new int[nPoints];
for (int i = 0; i < nPoints; i++)
if (!chkExclude.Checked)
percent[i] = (int)(((i + 1) * 100) / (nPoints));
else
percent[i] = (int)(((i + 1) * 100) / (nPoints+1));
// Set method for handeling identical vectors with different choice
double[] simpleAlgorithm = new double[3];
// Set method for handeling identical vectors with different choice
Testing.HandleIdenticalMethod identicalMethod = Testing.HandleIdenticalMethod.Ignore;
if (rdoSameRemove.Checked)
identicalMethod = Testing.HandleIdenticalMethod.Remove;
// Set if training set should be excluded from testing set
_excludeTrainingSet = chkExclude.Checked;
// Calc learning curves
_learningCurve = Testing.LearningCurve(txtFolderAllTesting3.Text, txtFolderTrueTesting3.Text, learning, deciding, percent, out simpleAlgorithm, identicalMethod, _excludeTrainingSet);
_statisticAlgoCurve = simpleAlgorithm;
_trdTest.Abort();
}
private void _btnUser_Click(object sender, EventArgs e)
{
if (User.Equals("") || _lstParameters.CheckedItems.Count == 0)
MessageBox.Show("Fill User, Learning Algorithm and Parameter fields");
else
{
//check if user already exists
Boolean isNewUser = true;
if (Directory.Exists(User + "'sVectorData"))
{
String[] files = Directory.GetFiles(User + "'sVectorData");
//if empty directory
if (files.Length != 0)
isNewUser = false;
else
{
//check if files (only 2 vector files) have data in them
foreach (string file in files)
{
Stream s = File.Open(file, FileMode.Open);
if (s.Length == 0)
{
isNewUser = true;
s.Close();
break;
}
s.Close();
}
}
}
K = 1;
_data = new DataLearning(User, SelectedAlgorithm, ParametersDictionary, K);
if (SelectedAlgorithm == LearningAlgorithm.Algorithm.KNN)
{
_knn = new KNN(K, _data.Repository);
_btnBrowsePredict.Enabled = true;
//_btnPredict.Enabled = true;
}
/*if (_rdoKNNweight.Checked)
_btnPredictUser.Enabled = true;*/
//else
//{
// _tree = new DecisionTree();
//}
//if user exists: loads repository and algorithm. and enables to train or predict.
if (!isNewUser)
{
if (!(SelectedAlgorithm == LearningAlgorithm.Algorithm.KNN))
{
_data.Algorithm.LoadData(User);
}
_data.Repository.loadList();
_btnBrowsePredict.Enabled = true;
//_btnPredict.Enabled = true;
}
//if doesn't exist: enables only to train. files will be created
_btnBrowseAll.Enabled = true;
_btnBrowseTrue.Enabled = true;
//_btnTrain.Enabled = true;
}
}
