/// <summary>
/// Returns a new settings object with the settings specified in the file as key value pair. Settings not beeing specified in this file will have the default value.
/// </summary>
/// <param name="settingLocation">Full qualified name of the settings file.</param>
/// <returns>A settings object with the values specified in the file.</returns>
public static ML_Settings readSettingsFromFile(string settingLocation)
{
ML_Settings mls = new ML_Settings();
if (System.IO.File.Exists(settingLocation) == false)
{
GlobalState.logError.logLine("Could not load ML settings file! File (" + settingLocation + ") does not exit.");
return(mls);
}
System.IO.StreamReader file = new System.IO.StreamReader(settingLocation);
string line;
while ((line = file.ReadLine()) != null)
{
string[] nameAndValue = line.Split(new char[] { ' ' }, 2);
if (!mls.setSetting(nameAndValue[0], nameAndValue[1]))
{
GlobalState.logError.logLine("MlSetting " + nameAndValue[0] + " not found!");
}
}
file.Close();
if (GlobalState.varModel != null && mls.blacklisted.Count > 0)
{
mls.checkAndCleanBlacklisted();
}
return(mls);
}
private void addMlSettingsBoxContent()
{
MachineLearning.Learning.ML_Settings settingsObject = new MachineLearning.Learning.ML_Settings();
FieldInfo[] fields = settingsObject.GetType().GetFields();
for (int i = 0; i < fields.Length; i++)
{
Label l = new Label();
mlSettingsPanel.Controls.Add(l);
l.AutoSize = true;
l.Location = new System.Drawing.Point(5, 5 + ML_FIELDS_OFFSET * i);
l.Name = fields[i].Name + "_label";
l.Size = new System.Drawing.Size(35, 15);
l.TabIndex = i * 2;
l.Text = fields[i].Name;
TextBox t = new TextBox();
mlSettingsPanel.Controls.Add(t);
t.Location = new System.Drawing.Point(150, 5 + ML_FIELDS_OFFSET * i);
t.Name = fields[i].Name + "_textBox";
t.Size = new System.Drawing.Size(150, 20);
t.TabIndex = i * 2 + 1;
t.Text = fields[i].GetValue(settingsObject).ToString();
}
}
private void addMlSettingsBoxContent()
{
MachineLearning.Learning.ML_Settings settingsObject = new MachineLearning.Learning.ML_Settings();
FieldInfo[] fields = settingsObject.GetType().GetFields();
for (int i = 0; i < fields.Length; i++)
{
Label l = new Label();
mlSettingsPanel.Controls.Add(l);
l.AutoSize = true;
l.Location = new System.Drawing.Point(5, 5 + ML_FIELDS_OFFSET * i);
l.Name = fields[i].Name + "_label";
l.Size = new System.Drawing.Size(35, 15);
l.TabIndex = i * 2;
l.Text = fields[i].Name;
TextBox t = new TextBox();
mlSettingsPanel.Controls.Add(t);
t.Location = new System.Drawing.Point(150, 5 + ML_FIELDS_OFFSET * i);
t.Name = fields[i].Name + "_textBox";
t.Size = new System.Drawing.Size(150, 20);
t.TabIndex = i * 2 + 1;
t.Text = fields[i].GetValue(settingsObject).ToString();
}
}
private void AddMlSetting_Click(object sender, EventArgs e)
{
MachineLearning.Learning.ML_Settings setting = new MachineLearning.Learning.ML_Settings();
foreach (Control c in mlSettingsPanel.Controls)
{
if (c.Name.EndsWith("_textBox"))
{
string fieldName = c.Name.Substring(0, c.Name.Length - "_textBox".Length);
setting.setSetting(fieldName, ((TextBox)c).Text);
}
}
addedElementsList.Items.Add(new Container(CONTAINERKEY_MLSETTING, setting));
}
private void AddMlSetting_Click(object sender, EventArgs e)
{
MachineLearning.Learning.ML_Settings setting = new MachineLearning.Learning.ML_Settings();
foreach (Control c in mlSettingsPanel.Controls)
{
if (c.Name.EndsWith("_textBox"))
{
string fieldName = c.Name.Substring(0, c.Name.Length - "_textBox".Length);
setting.setSetting(fieldName, ((TextBox)c).Text);
}
}
addedElementsList.Items.Add(new Container(CONTAINERKEY_MLSETTING, setting));
}
/// <summary>
/// Returns a new settings object with the settings specified in the file as key value pair. Settings not beeing specified in this file will have the default value.
/// </summary>
/// <param name="settings">All settings to be changed in a string with whitespaces as separator .</param>
/// <returns>A settings object with the values specified in the file.</returns>
public static ML_Settings readSettings(string settings)
{
ML_Settings mls = new ML_Settings();
String[] settingArray = settings.Split(' ');
for (int i = 0; i < settingArray.Length; i++)
{
string[] nameAndValue = settingArray[i].Split(new char[] { ':' }, 2);
if (!mls.setSetting(nameAndValue[0], nameAndValue[1]))
{
GlobalState.logError.log("MlSetting " + nameAndValue[0] + " not found!");
}
}
return(mls);
}
/// <summary>
/// Returns a new settings object with the settings specified in the file as key value pair. Settings not beeing specified in this file will have the default value.
/// </summary>
/// <param name="settings">All settings to be changed in a string with whitespaces as separator .</param>
/// <returns>A settings object with the values specified in the file.</returns>
public static ML_Settings readSettings(string settings)
{
settings = settings.Trim();
settings = settings.Replace(System.Environment.NewLine, "");
ML_Settings mls = new ML_Settings();
String[] settingArray = settings.Split(' ');
for (int i = 0; i < settingArray.Length; i++)
{
string[] nameAndValue = settingArray[i].Split(new char[] { ':' }, 2);
if (!mls.setSetting(nameAndValue[0], nameAndValue[1]))
{
GlobalState.logError.logLine("MlSetting " + nameAndValue[0] + " not found!");
}
}
if (GlobalState.varModel != null && mls.blacklisted.Count > 0)
{
mls.checkAndCleanBlacklisted();
}
return(mls);
}
/// <summary>
/// Clears the binary and numeric selections and the machine learning settings stored in this object.
/// </summary>
public void clear()
{
mlSettings = new ML_Settings();
clearSampling();
}
private static void defineParameterSpace(string[] parameters, Dictionary <string, List <bool> > boolSettings,
Dictionary <string, List <int> > intSettings, Dictionary <string, List <double> > doubleSettings,
Dictionary <string, List <LossFunction> > lossFuncInterval, Dictionary <string, List <ScoreMeasure> > scoreMeasureInterval,
Dictionary <string, List <TimeSpan> > learnTimeLimitInterval)
{
foreach (string parameter in parameters)
{
//dummy
int y;
double x;
TimeSpan z;
//setting name and values that should be within the parameter space
Tuple <string, string[]> nameAndValues = extractSettings(parameter);
ML_Settings referenceSetting = new ML_Settings();
System.Reflection.FieldInfo fi = referenceSetting.GetType().GetField(nameAndValues.Item1);
if (fi == null)
{
GlobalState.logInfo.logLine("Invalid variable name: " + nameAndValues.Item1 +
". This setting will be ignored.");
}
else if (isBool(nameAndValues.Item2[0]) && fi.FieldType.FullName.Equals("System.Boolean"))
{
List <bool> toAdd = new List <bool>();
foreach (string value in nameAndValues.Item2)
{
toAdd.Add(toBool(value));
}
boolSettings.Add(nameAndValues.Item1, toAdd);
}
else if (int.TryParse(nameAndValues.Item2[0], out y) &&
(fi.FieldType.FullName.Equals("System.Int32") || fi.FieldType.FullName.Equals("System.Int64")))
{
List <int> toAdd = new List <int>();
foreach (string value in nameAndValues.Item2)
{
toAdd.Add(int.Parse(value));
}
intSettings.Add(nameAndValues.Item1, toAdd);
}
else if (Double.TryParse(nameAndValues.Item2[0], out x) && fi.FieldType.FullName.Equals("System.Double"))
{
List <double> toAdd = new List <double>();
foreach (string value in nameAndValues.Item2)
{
toAdd.Add(Double.Parse(value, CultureInfo.InvariantCulture));
}
doubleSettings.Add(nameAndValues.Item1, toAdd);
}
else if (isLossFunction(nameAndValues.Item2[0]) &&
fi.FieldType.FullName.Equals("MachineLearning.Learning.ML_Settings+LossFunction"))
{
List <LossFunction> toAdd = new List <LossFunction>();
foreach (string value in nameAndValues.Item2)
{
toAdd.Add(toLossFunction(value));
}
lossFuncInterval[nameAndValues.Item1] = toAdd;
}
else if (isScoreMeasure(nameAndValues.Item2[0]) &&
fi.FieldType.FullName.Equals("MachineLearning.Learning.ML_Settings+ScoreMeasure"))
{
List <ScoreMeasure> toAdd = new List <ScoreMeasure>();
foreach (string value in nameAndValues.Item2)
{
toAdd.Add(toScoreMeasure(value));
}
scoreMeasureInterval[nameAndValues.Item1] = toAdd;
}
else if (TimeSpan.TryParse(nameAndValues.Item2[0], out z) &&
fi.FieldType.FullName.Equals("System.TimeSpan"))
{
List <TimeSpan> toAdd = new List <TimeSpan>();
foreach (string value in nameAndValues.Item2)
{
toAdd.Add(TimeSpan.Parse(value));
}
learnTimeLimitInterval[nameAndValues.Item1] = toAdd;
}
else
{
GlobalState.logInfo.logLine("Invalid setting-value pair: " + nameAndValues.Item1 + " "
+ string.Join(",", nameAndValues.Item2) + ". This setting will be ignored.");
}
}
}
/// <summary>
/// Performs the functionality of one command. If no functionality is found for the command, the command is retuned by this method.
/// </summary>
/// <param name="line">One command with its parameters.</param>
/// <returns>Returns an empty string if the command could be performed by the method. If the command could not be performed by the method, the original command is returned.</returns>
public string performOneCommand(string line)
{
GlobalState.logInfo.logLine(COMMAND + line);
// remove comment part of the line (the comment starts with an #)
line = line.Split(new Char[] { '#' }, 2)[0];
if (line.Length == 0)
return "";
// split line in command and parameters of the command
string[] components = line.Split(new Char[] { ' ' }, 2);
string command = components[0];
string task = "";
if (components.Length > 1)
task = components[1];
string[] taskAsParameter = task.Split(new Char[] { ' ' });
switch (command.ToLower())
{
case COMMAND_START_ALLMEASUREMENTS:
{
InfluenceModel infMod = new InfluenceModel(GlobalState.varModel, GlobalState.currentNFP);
List<Configuration> configurations_Learning = new List<Configuration>();
foreach (Configuration config in GlobalState.allMeasurements.Configurations)
{
if (config.nfpValues.ContainsKey(GlobalState.currentNFP))
configurations_Learning.Add(config);
}
if (configurations_Learning.Count == 0)
{
GlobalState.logInfo.logLine("The learning set is empty! Cannot start learning!");
break;
}
GlobalState.logInfo.logLine("Learning: " + "NumberOfConfigurationsLearning:" + configurations_Learning.Count);
// prepare the machine learning
exp = new MachineLearning.Learning.Regression.Learning(configurations_Learning, configurations_Learning);
exp.metaModel = infMod;
exp.mLsettings = this.mlSettings;
exp.learn();
}
break;
case COMMAND_TRUEMODEL:
StreamReader readModel = new StreamReader(task);
String model = readModel.ReadLine().Trim();
readModel.Close();
this.trueModel = new InfluenceFunction(model.Replace(',', '.'), GlobalState.varModel);
NFProperty artificalProp = new NFProperty("artificial");
GlobalState.currentNFP = artificalProp;
//computeEvaluationDataSetBasedOnTrueModel();
break;
case COMMAND_SUBSCRIPT:
{
FileInfo fi = new FileInfo(task);
StreamReader reader = null;
if (!fi.Exists)
throw new FileNotFoundException(@"Automation script not found. ", fi.ToString());
reader = fi.OpenText();
Commands co = new Commands();
co.exp = this.exp;
while (!reader.EndOfStream)
{
String oneLine = reader.ReadLine().Trim();
co.performOneCommand(oneLine);
}
}
break;
case COMMAND_EVALUATION_SET:
{
GlobalState.evalutionSet.Configurations = ConfigurationReader.readConfigurations(task, GlobalState.varModel);
GlobalState.logInfo.logLine("Evaluation set loaded.");
}
break;
case COMMAND_CLEAR_GLOBAL:
SPLConqueror_Core.GlobalState.clear();
toSample.Clear();
toSampleValidation.Clear();
break;
case COMMAND_CLEAR_SAMPLING:
exp.clearSampling();
toSample.Clear();
toSampleValidation.Clear();
break;
case COMMAND_CLEAR_LEARNING:
exp.clear();
toSample.Clear();
toSampleValidation.Clear();
break;
case COMMAND_LOAD_CONFIGURATIONS:
GlobalState.allMeasurements.Configurations = (GlobalState.allMeasurements.Configurations.Union(ConfigurationReader.readConfigurations(task, GlobalState.varModel))).ToList();
GlobalState.logInfo.logLine(GlobalState.allMeasurements.Configurations.Count + " configurations loaded.");
break;
case COMMAND_SAMPLE_ALLBINARY:
{
if (taskAsParameter.Contains(COMMAND_VALIDATION))
{
this.toSampleValidation.Add(SamplingStrategies.ALLBINARY);
this.exp.info.binarySamplings_Validation = "ALLBINARY";
}
else
{
this.toSample.Add(SamplingStrategies.ALLBINARY);
this.exp.info.binarySamplings_Learning = "ALLBINARY";
}
break;
}
case COMMAND_ANALYZE_LEARNING:
{//TODO: Analyzation is not supported in the case of bagging
GlobalState.logInfo.logLine("Models:");
if (this.mlSettings.bagging)
{
for (int i = 0; i < this.exp.models.Count; i++)
{
FeatureSubsetSelection learnedModel = exp.models[i];
if (learnedModel == null)
{
GlobalState.logError.logLine("Error... learning was not performed!");
break;
}
GlobalState.logInfo.logLine("Termination reason: " + learnedModel.LearningHistory.Last().terminationReason);
foreach (LearningRound lr in learnedModel.LearningHistory)
{
double relativeError = 0;
if (GlobalState.evalutionSet.Configurations.Count > 0)
{
double relativeErro2r = learnedModel.computeError(lr.FeatureSet, GlobalState.evalutionSet.Configurations, out relativeError);
}
else
{
double relativeErro2r = learnedModel.computeError(lr.FeatureSet, GlobalState.allMeasurements.Configurations, out relativeError);
}
GlobalState.logInfo.logLine(lr.ToString() + relativeError);
}
}
}
else
{
FeatureSubsetSelection learnedModel = exp.models[0];
if (learnedModel == null)
{
GlobalState.logError.logLine("Error... learning was not performed!");
break;
}
GlobalState.logInfo.logLine("Termination reason: " + learnedModel.LearningHistory.Last().terminationReason);
foreach (LearningRound lr in learnedModel.LearningHistory)
{
double relativeError = 0;
if (GlobalState.evalutionSet.Configurations.Count > 0)
{
double relativeErro2r = learnedModel.computeError(lr.FeatureSet, GlobalState.evalutionSet.Configurations, out relativeError);
}
else
{
double relativeErro2r = learnedModel.computeError(lr.FeatureSet, GlobalState.allMeasurements.Configurations, out relativeError);
}
GlobalState.logInfo.logLine(lr.ToString() + relativeError);
}
}
break;
}
case COMMAND_EXERIMENTALDESIGN:
performOneCommand_ExpDesign(task);
break;
case COMMAND_SAMPLING_OPTIONORDER:
parseOptionOrder(task);
break;
case COMMAND_VARIABILITYMODEL:
GlobalState.varModel = VariabilityModel.loadFromXML(task);
if (GlobalState.varModel == null)
GlobalState.logError.logLine("No variability model found at " + task);
break;
case COMMAND_SET_NFP:
GlobalState.currentNFP = GlobalState.getOrCreateProperty(task.Trim());
break;
case COMMAND_SAMPLE_OPTIONWISE:
if (taskAsParameter.Contains(COMMAND_VALIDATION))
{
this.toSampleValidation.Add(SamplingStrategies.OPTIONWISE);
this.exp.info.binarySamplings_Validation = "OPTIONSWISE";
}
else
{
this.toSample.Add(SamplingStrategies.OPTIONWISE);
this.exp.info.binarySamplings_Learning = "OPTIONSWISE";
}
break;
case COMMAND_LOG:
string location = task.Trim();
GlobalState.logInfo.close();
GlobalState.logInfo = new InfoLogger(location);
GlobalState.logError.close();
GlobalState.logError = new ErrorLogger(location + "_error");
break;
case COMMAND_SET_MLSETTING:
this.mlSettings = ML_Settings.readSettings(task);
break;
case COMMAND_LOAD_MLSETTINGS:
this.mlSettings = ML_Settings.readSettingsFromFile(task);
break;
case COMMAND_SAMPLE_PAIRWISE:
if (taskAsParameter.Contains(COMMAND_VALIDATION))
{
this.toSampleValidation.Add(SamplingStrategies.PAIRWISE);
this.exp.info.binarySamplings_Validation = "PAIRWISE";
}
else
{
this.toSample.Add(SamplingStrategies.PAIRWISE);
this.exp.info.binarySamplings_Learning = "PAIRWISE";
}
break;
case COMMAND_PRINT_MLSETTINGS:
GlobalState.logInfo.logLine(this.mlSettings.ToString());
break;
case COMMAND_PRINT_CONFIGURATIONS:
{
/* List<Dictionary<NumericOption, double>> numericSampling = exp.NumericSelection_Learning;
List<List<BinaryOption>> binarySampling = exp.BinarySelections_Learning;
List<Configuration> configurations = new List<Configuration>();
foreach (Dictionary<NumericOption, double> numeric in numericSampling)
{
foreach (List<BinaryOption> binary in binarySampling)
{
Configuration config = Configuration.getConfiguration(binary, numeric);
if (!configurations.Contains(config) && GlobalState.varModel.configurationIsValid(config))
{
configurations.Add(config);
}
}
}*/
var configs = ConfigurationBuilder.buildConfigs(GlobalState.varModel, this.toSample);
string[] para = task.Split(new char[] { ' ' });
// TODO very error prone..
ConfigurationPrinter printer = new ConfigurationPrinter(para[0], para[1], para[2], GlobalState.optionOrder);
printer.print(configs);
break;
}
case COMMAND_SAMPLE_BINARY_RANDOM:
{
string[] para = task.Split(new char[] { ' ' });
ConfigurationBuilder.binaryThreshold = Convert.ToInt32(para[0]);
ConfigurationBuilder.binaryModulu = Convert.ToInt32(para[1]);
VariantGenerator vg = new VariantGenerator(null);
if (taskAsParameter.Contains(COMMAND_VALIDATION))
{
this.toSampleValidation.Add(SamplingStrategies.BINARY_RANDOM);
this.exp.info.binarySamplings_Validation = "BINARY_RANDOM";
}
else
{
this.toSample.Add(SamplingStrategies.BINARY_RANDOM);
this.exp.info.binarySamplings_Learning = "BINARY_RANDOM " + task;
}
break;
}
case COMMAND_START_LEARNING:
{
InfluenceModel infMod = new InfluenceModel(GlobalState.varModel, GlobalState.currentNFP);
List<Configuration> configurationsLearning = buildSet(this.toSample);
List<Configuration> configurationsValidation = buildSet(this.toSampleValidation);
if (configurationsLearning.Count == 0)
{
configurationsLearning = configurationsValidation;
}
if (configurationsLearning.Count == 0)
{
GlobalState.logInfo.logLine("The learning set is empty! Cannot start learning!");
break;
}
if (configurationsValidation.Count == 0)
{
configurationsValidation = configurationsLearning;
}
GlobalState.logInfo.logLine("Learning: " + "NumberOfConfigurationsLearning:" + configurationsLearning.Count + " NumberOfConfigurationsValidation:" + configurationsValidation.Count);
//+ " UnionNumberOfConfigurations:" + (configurationsLearning.Union(configurationsValidation)).Count()); too costly to compute
// We have to reuse the list of models because of NotifyCollectionChangedEventHandlers that might be attached to the list of models.
exp.models.Clear();
var mod = exp.models;
exp = new MachineLearning.Learning.Regression.Learning(configurationsLearning, configurationsValidation);
exp.models = mod;
exp.metaModel = infMod;
exp.mLsettings = this.mlSettings;
exp.learn();
GlobalState.logInfo.logLine("Average model: \n" + exp.metaModel.printModelAsFunction());
double relativeError = 0;
if (GlobalState.evalutionSet.Configurations.Count > 0)
{
relativeError = FeatureSubsetSelection.computeError(exp.metaModel, GlobalState.evalutionSet.Configurations, ML_Settings.LossFunction.RELATIVE);
}
else
{
relativeError = FeatureSubsetSelection.computeError(exp.metaModel, GlobalState.allMeasurements.Configurations, ML_Settings.LossFunction.RELATIVE);
}
GlobalState.logInfo.logLine("Error :" + relativeError);
}
break;
case COMMAND_SAMPLE_NEGATIVE_OPTIONWISE:
// TODO there are two different variants in generating NegFW configurations.
if (taskAsParameter.Contains(COMMAND_VALIDATION))
{
this.toSampleValidation.Add(SamplingStrategies.NEGATIVE_OPTIONWISE);
this.exp.info.binarySamplings_Validation = "NEGATIVE_OPTIONWISE";
}
else
{
this.toSample.Add(SamplingStrategies.NEGATIVE_OPTIONWISE);
this.exp.info.binarySamplings_Learning = "NEGATIVE_OPTIONWISE";
}
break;
default:
return command;
}
return "";
}
private string mlSettingsContent(ML_Settings settings)
{
return CommandLine.Commands.COMMAND_LOAD_MLSETTINGS+" " + settings.ToString();
}
/// <summary>
/// Returns a new settings object with the settings specified in the file as key value pair. Settings not beeing specified in this file will have the default value.
/// </summary>
/// <param name="settingLocation">Full qualified name of the settings file.</param>
/// <returns>A settings object with the values specified in the file.</returns>
public static ML_Settings readSettingsFromFile(string settingLocation)
{
ML_Settings mls = new ML_Settings();
if (System.IO.File.Exists(settingLocation) == false)
{
GlobalState.logError.logLine("Could not load ML settings file! File (" + settingLocation + ") does not exit.");
return mls;
}
System.IO.StreamReader file = new System.IO.StreamReader(settingLocation);
string line;
while ((line = file.ReadLine()) != null)
{
string[] nameAndValue = line.Split(new char[] { ' ' }, 2);
if (!mls.setSetting(nameAndValue[0], nameAndValue[1]))
{
GlobalState.logError.logLine("MlSetting " + nameAndValue[0] + " not found!");
}
}
file.Close();
return mls;
}
/// <summary>
/// Returns a new settings object with the settings specified in the file as key value pair. Settings not beeing specified in this file will have the default value.
/// </summary>
/// <param name="settings">All settings to be changed in a string with whitespaces as separator .</param>
/// <returns>A settings object with the values specified in the file.</returns>
public static ML_Settings readSettings(string settings)
{
settings = settings.Trim();
settings = settings.Replace(System.Environment.NewLine, "");
ML_Settings mls = new ML_Settings();
String[] settingArray = settings.Split(' ');
for (int i = 0; i < settingArray.Length; i++)
{
string[] nameAndValue = settingArray[i].Split(new char[] { ':' }, 2);
if (!mls.setSetting(nameAndValue[0], nameAndValue[1]))
{
GlobalState.logError.logLine("MlSetting " + nameAndValue[0] + " not found!");
}
}
return mls;
}
