public static MyEvaluation TestInstances(Instances testInstances, Classifier cls, CostMatrix costMatrix = null)
{
//Evaluation eval = new Evaluation(testInstances, new CostMatrix(new BufferedReader(new FileReader(m_costFileName))));
MyEvaluation eval;
if (costMatrix != null)
{
eval = new MyEvaluation(costMatrix);
}
else
{
eval = new MyEvaluation();
}
//eval.crossValidateModel(cls, origInstances, 5, new java.util.Random(1));
//WriteLog(eval.toSummaryString());
//WriteLog("Confusion matrix is " + eval.toMatrixString());
//WriteLog("total cose is " + eval.totalCost());
//WriteLog("Crossvalidate is done.");
//using (System.IO.StreamWriter sw = new StreamWriter(string.Format("{0}\\crossValidateResult.txt", m_baseDir), true))
//{
// sw.WriteLine(string.Format("CrossValidate Data from {0} to {1}", m_trainTimeStart.ToString(m_dateTimeFormat), m_trainTimeEnd.ToString(m_dateTimeFormat)));
// sw.WriteLine(eval.toSummaryString());
// sw.WriteLine("Confusion matrix is " + eval.toMatrixString());
//}
//eval.evaluateModel(cls, origInstances);
//WriteEvalSummary(eval, string.Format("Train Data from {0} to {1}", m_trainTimeStart.ToString(m_dateFormat), m_trainTimeEnd.ToString(m_dateFormat)));
eval.evaluateModel(cls, testInstances);
return(eval);
}
public void BuildExcludeModels()
{
Parameters.TotalCanUseMemory = 600 * 1000 * 1000;
TestParameters.SaveDataFile = false;
//m_batchBufferMinutes = (new TimeSpan(365 + 5, 0, 0, 0)).TotalMinutes;
weka.classifiers.Classifier cls = new weka.classifiers.functions.LibSVM();
(cls as weka.classifiers.AbstractClassifier).setOptions(weka.core.Utils.splitOptions("-S 0 -K 2"));
//Classifier cls = new MincostLiblinearClassifier();
//Classifier cls = new weka.classifiers.functions.LibLINEAR();
//(cls as AbstractClassifier).setOptions(weka.core.Utils.splitOptions("-S 0 -P -C 1 -B 1"));
//var cls = new SvmLightClassifier();
//cls.setOptions(weka.core.Utils.splitOptions("-c 20 -l 4 -w 1 --p 1 --b 1"));
var cp = new CandidateParameter("BuildExcludeModels");
cp.DeleteUnusedIndicators();
ParameterdCandidateStrategy realDealCandidate = new ParameterdCandidateStrategy(cp);
SetTrainTime(new DateTime(2009, 1, 1), new DateTime(2009, 4, 30));
//m_generateOneClassHp = 0;
realDealCandidate.IterateClassifierInfos2(new Func<CandidateClassifier, bool>((clsInfo) =>
{
string modelFileName = clsInfo.WekaData.GetExcludeModelFileName(clsInfo.Name);
//if (!System.IO.File.Exists(modelFileName))
{
WekaUtils.Instance.WriteLog(string.Format("{0} is building exclude model.", clsInfo.Name));
//clsInfo.WekaData.m_currentTestHour = clsInfo.Hour;
clsInfo.WekaData.GenerateData(true, false);
WekaUtils.TrainInstances(clsInfo.WekaData.CurrentTrainInstancesNew, modelFileName, cls);
MyEvaluation eval = new MyEvaluation();
eval.evaluateModel(cls, clsInfo.WekaData.CurrentTrainInstancesNew);
return true;
}
//else
//{
// m_currentTestHour = h;
// GenerateData(true, false);
// cls = WekaUtils.TryLoadClassifier(modelFileName);
// var eval = WekaUtils.TestInstances(m_trainInstancesNew[k], cls);
//}
}));
}
public void ExecuteBest(DateTime nowDate, List<CandidateClassifier> minScoreInfos)
{
OutputRealDealSummary(nowDate);
float totalCost = 0;
int totalDeal = 0;
if (minScoreInfos != null)
{
List<DealInfo> candidateDeals = new List<DealInfo>();
foreach (var minScoreInfo in minScoreInfos)
{
minScoreInfo.WekaData.GenerateData(false, true);
weka.core.Instances minTestInstances = minScoreInfo.WekaData.CurrentTestInstances;
weka.core.Instances minTestInstancesNew = minScoreInfo.WekaData.CurrentTestInstancesNew;
if (minTestInstances.numInstances() > 0)
{
MyEvaluation eval = new MyEvaluation(minScoreInfo.CostMatrix);
eval.evaluateModel(minScoreInfo.CurrentTestRet, minScoreInfo.CurrentClassValue);
float vol;
// vol = (float)minScoreInfo.MoneyManagement.GetVolume(null);
vol = 0.1F;
//vol = (float)Math.Round(minScore / -20000.0, 1);
//WekaUtils.DebugAssert(vol > 0);
int tp = (int)eval.numTruePositives(1);
int fp = (int)eval.numFalsePositives(1);
double minScore = minScoreInfo.Deals.NowScore;
//WekaUtils.Instance.WriteLog(string.Format("Best Classifier: N={0},TC={1},TP={2},FP={3},TD={4},TV={5},TTP={6},TFP={7},",
// minScoreInfo.Name, minScoreInfo.Deals.NowScore.ToString(Parameters.DoubleFormatString),
// minScoreInfo.Deals.NowTp, minScoreInfo.Deals.NowFp, minScoreInfo.Deals.NowDeal,
// minScoreInfo.Deals.TotalVolume.ToString("N2"), tp, fp),
// true, ConsoleColor.DarkGreen);
// Exclude
//if (TestParameters.EnableExcludeClassifier)
//{
//if (minScoreInfo.ExcludeClassifier == null)
//{
// string modelFileName4Exclude = GetExcludeModelFileName(minScoreInfo.Name);
// minScoreInfo.ExcludeClassifier = WekaUtils.TryLoadClassifier(modelFileName4Exclude);
//}
//}
for (int i = 0; i < minScoreInfo.CurrentTestRet.Length; i++)
{
if (minScoreInfo.CurrentTestRet[i] == 2)
{
if (minScoreInfo.ExcludeClassifier != null)
{
double cv2 = minScoreInfo.ExcludeClassifier.classifyInstance(minTestInstancesNew.instance(i));
if (cv2 != 2)
continue;
}
candidateDeals.Add(new DealInfo(WekaUtils.GetDateValueFromInstances(minTestInstances, 0, i),
(float)WekaUtils.GetValueFromInstance(minTestInstances, "mainClose", i),
minScoreInfo.DealType,
(float)vol,
(float)(minScoreInfo.CurrentClassValue[i] == 2 ? -minScoreInfo.Tp : minScoreInfo.Sl),
WekaUtils.GetDateValueFromInstances(minTestInstances, 1, i)));
}
}
float nowCost = (float)eval.totalCost();
int nowDeal = tp + fp;
totalCost += nowCost * vol;
totalDeal += nowDeal;
//float diff = Math.Abs(totalCost - realDealsInfo.TotalCost);
//WekaUtils.DebugAssert(diff < 5);
//WekaUtils.DebugAssert(Math.Abs(totalDeal - (realDealsInfo.NowDeal + realDealsInfo.CurrentDeal)) == 0);
//if (diff > 0.5)
// totalCost = realDealsInfo.TotalCost;
IterateClassifierInfos((k, i, j, h) =>
{
if (m_classifierInfoIdxs[k, i, j, h] == minScoreInfo)
{
m_totalScores[k, i, j, h] += nowCost;
m_totalDeals[k, i, j, h] += nowDeal;
return false;
}
else
{
return true;
}
});
}
}
int selectCount = 50;
for (int i = 0; i < selectCount; ++i)
{
if (candidateDeals.Count == 0)
break;
int selectedDealIdx = (int)Math.Round(m_randomGenerator.NextDouble() * candidateDeals.Count);
if (selectedDealIdx == candidateDeals.Count)
selectedDealIdx = candidateDeals.Count - 1;
m_realDealsInfo.AddDeal(candidateDeals[selectedDealIdx]);
candidateDeals.RemoveAt(selectedDealIdx);
}
}
//if (m_enableDetailLogLevel2)
//{
// IterateClassifierInfos((k, i, j, h) =>
// {
// if (h == m_currentTestHour && m_totalScores[k, i, j, h] != 0)
// {
// WekaUtils.Instance.WriteLog(string.Format("Predict score for {0}: TC={1}, TD={2}", m_classifierInfoIdxs[k, i, j, h].Name, m_totalScores[k, i, j, h].ToString(Parameters.DoubleFormatString), m_totalDeals[k, i, j, h]));
// }
// });
//}
if (!string.IsNullOrEmpty(currentSummary))
{
WekaUtils.Instance.WriteLog(currentSummary, true, ConsoleColor.Red);
System.Console.Title = nowDate.ToString(Parameters.DateTimeFormat) + ":" + currentSummary;
}
//if (m_enableDetailLogLevel2)
//{
// if (TestParameters.EnablePerhourTrain)
// {
// double[] totalCostPerHour = new double[m_classifierInfoIdxs.GetLength(3)];
// int[] totalDealPerHour = new int[m_classifierInfoIdxs.GetLength(3)];
// IterateClassifierInfos((k, i, j, h) =>
// {
// totalCostPerHour[h] += m_totalScores[k, i, j, h];
// totalDealPerHour[h] += m_totalDeals[k, i, j, h];
// });
// for (int i = 0; i < totalCostPerHour.Length; ++i)
// {
// if (totalCostPerHour[i] == 0)
// continue;
// WekaUtils.Instance.WriteLog(string.Format("Predict score Per hour of {0}: TC={1}, TD={2}", i, totalCostPerHour[i].ToString(Parameters.DoubleFormatString), totalDealPerHour[i]));
// }
// }
//if ((m_testTimeStart.Month == 4 || m_testTimeStart.Month == 3) && m_testTimeStart.Day == 20)
//{
// foreach (var cls in m_classifierInfos)
// {
// WekaUtils.Instance.WriteLog(cls.Value.Deals.PrintAll());
// }
//}
//if (m_currentTestHour == 0)
//{
// var cls = m_classifierInfoIdxs[0, 0, 0, 0];
// WekaUtils.Instance.WriteLog((cls.Classifier as RandomClassifier).GetCountInfo());
//}
//}
//if (m_saveDataFile)
//{
// var files = System.IO.Directory.GetFiles(m_baseDir, "*.arff");
// if (files.Length > 100)
// {
// foreach (string fileName in files)
// {
// try
// {
// System.IO.File.Delete(fileName);
// }
// catch (Exception)
// {
// }
// }
// }
//}
}
public void ExecuteBest(DateTime nowDate, List <CandidateClassifier> minScoreInfos)
{
OutputRealDealSummary(nowDate);
float totalCost = 0;
int totalDeal = 0;
if (minScoreInfos != null)
{
List <DealInfo> candidateDeals = new List <DealInfo>();
foreach (var minScoreInfo in minScoreInfos)
{
minScoreInfo.WekaData.GenerateData(false, true);
weka.core.Instances minTestInstances = minScoreInfo.WekaData.CurrentTestInstances;
weka.core.Instances minTestInstancesNew = minScoreInfo.WekaData.CurrentTestInstancesNew;
if (minTestInstances.numInstances() > 0)
{
MyEvaluation eval = new MyEvaluation(minScoreInfo.CostMatrix);
eval.evaluateModel(minScoreInfo.CurrentTestRet, minScoreInfo.CurrentClassValue);
float vol;
// vol = (float)minScoreInfo.MoneyManagement.GetVolume(null);
vol = 0.1F;
//vol = (float)Math.Round(minScore / -20000.0, 1);
//WekaUtils.DebugAssert(vol > 0);
int tp = (int)eval.numTruePositives(1);
int fp = (int)eval.numFalsePositives(1);
double minScore = minScoreInfo.Deals.NowScore;
//WekaUtils.Instance.WriteLog(string.Format("Best Classifier: N={0},TC={1},TP={2},FP={3},TD={4},TV={5},TTP={6},TFP={7},",
// minScoreInfo.Name, minScoreInfo.Deals.NowScore.ToString(Parameters.DoubleFormatString),
// minScoreInfo.Deals.NowTp, minScoreInfo.Deals.NowFp, minScoreInfo.Deals.NowDeal,
// minScoreInfo.Deals.TotalVolume.ToString("N2"), tp, fp),
// true, ConsoleColor.DarkGreen);
// Exclude
//if (TestParameters.EnableExcludeClassifier)
//{
//if (minScoreInfo.ExcludeClassifier == null)
//{
// string modelFileName4Exclude = GetExcludeModelFileName(minScoreInfo.Name);
// minScoreInfo.ExcludeClassifier = WekaUtils.TryLoadClassifier(modelFileName4Exclude);
//}
//}
for (int i = 0; i < minScoreInfo.CurrentTestRet.Length; i++)
{
if (minScoreInfo.CurrentTestRet[i] == 2)
{
if (minScoreInfo.ExcludeClassifier != null)
{
double cv2 = minScoreInfo.ExcludeClassifier.classifyInstance(minTestInstancesNew.instance(i));
if (cv2 != 2)
{
continue;
}
}
candidateDeals.Add(new DealInfo(WekaUtils.GetDateValueFromInstances(minTestInstances, 0, i),
(float)WekaUtils.GetValueFromInstance(minTestInstances, "mainClose", i),
minScoreInfo.DealType,
(float)vol,
(float)(minScoreInfo.CurrentClassValue[i] == 2 ? -minScoreInfo.Tp : minScoreInfo.Sl),
WekaUtils.GetDateValueFromInstances(minTestInstances, 1, i)));
}
}
float nowCost = (float)eval.totalCost();
int nowDeal = tp + fp;
totalCost += nowCost * vol;
totalDeal += nowDeal;
//float diff = Math.Abs(totalCost - realDealsInfo.TotalCost);
//WekaUtils.DebugAssert(diff < 5);
//WekaUtils.DebugAssert(Math.Abs(totalDeal - (realDealsInfo.NowDeal + realDealsInfo.CurrentDeal)) == 0);
//if (diff > 0.5)
// totalCost = realDealsInfo.TotalCost;
IterateClassifierInfos((k, i, j, h) =>
{
if (m_classifierInfoIdxs[k, i, j, h] == minScoreInfo)
{
m_totalScores[k, i, j, h] += nowCost;
m_totalDeals[k, i, j, h] += nowDeal;
return(false);
}
else
{
return(true);
}
});
}
}
int selectCount = 50;
for (int i = 0; i < selectCount; ++i)
{
if (candidateDeals.Count == 0)
{
break;
}
int selectedDealIdx = (int)Math.Round(m_randomGenerator.NextDouble() * candidateDeals.Count);
if (selectedDealIdx == candidateDeals.Count)
{
selectedDealIdx = candidateDeals.Count - 1;
}
m_realDealsInfo.AddDeal(candidateDeals[selectedDealIdx]);
candidateDeals.RemoveAt(selectedDealIdx);
}
}
//if (m_enableDetailLogLevel2)
//{
// IterateClassifierInfos((k, i, j, h) =>
// {
// if (h == m_currentTestHour && m_totalScores[k, i, j, h] != 0)
// {
// WekaUtils.Instance.WriteLog(string.Format("Predict score for {0}: TC={1}, TD={2}", m_classifierInfoIdxs[k, i, j, h].Name, m_totalScores[k, i, j, h].ToString(Parameters.DoubleFormatString), m_totalDeals[k, i, j, h]));
// }
// });
//}
if (!string.IsNullOrEmpty(currentSummary))
{
WekaUtils.Instance.WriteLog(currentSummary, true, ConsoleColor.Red);
System.Console.Title = nowDate.ToString(Parameters.DateTimeFormat) + ":" + currentSummary;
}
//if (m_enableDetailLogLevel2)
//{
// if (TestParameters.EnablePerhourTrain)
// {
// double[] totalCostPerHour = new double[m_classifierInfoIdxs.GetLength(3)];
// int[] totalDealPerHour = new int[m_classifierInfoIdxs.GetLength(3)];
// IterateClassifierInfos((k, i, j, h) =>
// {
// totalCostPerHour[h] += m_totalScores[k, i, j, h];
// totalDealPerHour[h] += m_totalDeals[k, i, j, h];
// });
// for (int i = 0; i < totalCostPerHour.Length; ++i)
// {
// if (totalCostPerHour[i] == 0)
// continue;
// WekaUtils.Instance.WriteLog(string.Format("Predict score Per hour of {0}: TC={1}, TD={2}", i, totalCostPerHour[i].ToString(Parameters.DoubleFormatString), totalDealPerHour[i]));
// }
// }
//if ((m_testTimeStart.Month == 4 || m_testTimeStart.Month == 3) && m_testTimeStart.Day == 20)
//{
// foreach (var cls in m_classifierInfos)
// {
// WekaUtils.Instance.WriteLog(cls.Value.Deals.PrintAll());
// }
//}
//if (m_currentTestHour == 0)
//{
// var cls = m_classifierInfoIdxs[0, 0, 0, 0];
// WekaUtils.Instance.WriteLog((cls.Classifier as RandomClassifier).GetCountInfo());
//}
//}
//if (m_saveDataFile)
//{
// var files = System.IO.Directory.GetFiles(m_baseDir, "*.arff");
// if (files.Length > 100)
// {
// foreach (string fileName in files)
// {
// try
// {
// System.IO.File.Delete(fileName);
// }
// catch (Exception)
// {
// }
// }
// }
//}
}