/// <summary>
/// Constructs an active learning instance with a specified data set and model instance.
/// </summary>
/// <param name="data">The data.</param>
/// <param name="model">The model instance.</param>
/// <param name="results">The results instance.</param>
/// <param name="numCommunities">The number of communities (only for CBCC).</param>
public ActiveLearning(IList<Datum> data, BCC model, Results results, int numCommunities)
{
this.bcc = model;
CBCC communityModel = model as CBCC;
IsCommunityModel = (communityModel != null);
ActiveLearningResults = results;
BatchResults = results;
isExperimentCompleted = false;
// Builds the full matrix of data from every task and worker
PredictionData = new List<Datum>();
}
/// <summary>
/// Runs a model with the full gold set.
/// </summary>
/// <param name="dataSet">The dataset name.</param>
/// <param name="data">The data.</param>
/// <param name="runType">The model run type.</param>
/// <param name="model">The model instance.</param>
/// <param name="numCommunities">The number of communities (only for CBCC).</param>
/// <returns>The inference results</returns>
public static Results RunGold(string dataSet, IList<Datum> data, RunType runType, BCC model, int numCommunities = 2)
{
string modelName = Program.GetModelName(dataSet, runType);
Results results = new Results();
switch (runType)
{
case RunType.VoteDistribution:
results.RunMajorityVote(data, data, true, true);
break;
case RunType.MajorityVote:
results.RunMajorityVote(data, data, true, false);
break;
case RunType.DawidSkene:
results.RunDawidSkene(data, data, true);
break;
default:
results.RunBCC(modelName, data, data, model, RunMode.ClearResults, true, numCommunities, false, false);
break;
}
return results;
}
/// <summary>
/// Runs the standard active learning procedure in parallel on an array of model instances and an input data set.
/// </summary>
/// <param name="data">The data.</param>
/// <param name="modelName">The model name.</param>
/// <param name="runType">The model run type.</param>
/// <param name="model">The model instance.</param>
/// <param name="taskSelectionMethod">The method for selecting tasks (Random / Entropy).</param>
/// <param name="workerSelectionMethod">The method for selecting workers (only Random is implemented).</param>
/// <param name="numIncremData">The number of data points to add at each iteration.</param>
/// <param name="communityCount">The number of communities (only for CBCC).</param>
/// <param name="initialNumLabelsPerTask">The initial number of exploratory labels that are randomly selected for each task.</param>
public static void RunParallelActiveLearning(IList<Datum> data,
string[] modelName,
RunType[] runType,
BCC[] model,
TaskSelectionMethod[] taskSelectionMethod,
WorkerSelectionMethod[] workerSelectionMethod,
int communityCount = -1,
int initialNumLabelsPerTask = 1,
int numIncremData = 1)
{
int numModels = runType.Length;
Stopwatch stopWatch = new Stopwatch();
int totalLabels = data.Count();
// Dictionary keyed by task Id, with randomly order labelings
var groupedRandomisedData =
data.GroupBy(d => d.TaskId).
Select(g =>
{
var arr = g.ToArray();
int cnt = arr.Length;
var perm = Rand.Perm(cnt);
return new
{
key = g.Key,
arr = g.Select((t, i) => arr[perm[i]]).ToArray()
};
}).ToDictionary(a => a.key, a => a.arr);
// Dictionary keyed by task Id, with label counts
Dictionary<string, int> totalCounts = groupedRandomisedData.ToDictionary(kvp => kvp.Key, kvp => kvp.Value.Length);
Dictionary<string, int> currentCounts = groupedRandomisedData.ToDictionary(kvp => kvp.Key, kvp => initialNumLabelsPerTask);
// Keyed by task, value is a HashSet containing all the remaining workers with a label - workers are removed after adding a new datum
Dictionary<string, HashSet<string>> remainingWorkersPerTask = groupedRandomisedData.ToDictionary(kvp => kvp.Key, kvp => new HashSet<string>(kvp.Value.Select(dat => dat.WorkerId)));
int numTaskIds = totalCounts.Count();
int totalInstances = data.Count - initialNumLabelsPerTask * numTaskIds;
//throw an exception if the totalInstances is less than or equals to zero
if (totalInstances <= 0)
{
throw new System.Exception("The variable 'totalInstances' should be greater than zero");
}
//only creates accuracy list when it's null (for GUI Use)
if (accuracyArray == null)
{
accuracyArray = Util.ArrayInit<List<double>>(numModels, i => new List<double>());
}
List<double>[] avgRecallArray = Util.ArrayInit(numModels, i => new List<double>());
taskValueListArray = Util.ArrayInit(numModels, i => new List<ActiveLearningResult>());
int[] indexArray = new int[numModels];
Debug.WriteLine("Parallel Active Learning");
Debug.WriteLine("\tModel\tAcc\tAvgRec");
// Get initial data
//make the results variable be global for GUi
results = Util.ArrayInit<Results>(numModels, i => new Results());
List<Datum> subData = GetSubdata(groupedRandomisedData, currentCounts, remainingWorkersPerTask);
List<Datum>[] subDataArray = Util.ArrayInit<List<Datum>>(numModels, i => new List<Datum>(subData));
List<Datum>[] nextData = new List<Datum>[numModels];
ActiveLearning[] activeLearning = new ActiveLearning[numModels];
isExperimentCompleted = false;
// Main loop
for (int iter = 0; ; iter++)
{
bool calculateAccuracy = true;
bool doSnapShot = iter % 100 == 0; // Frequency of snapshots
//stop Active Learning if the user requests to stop
if (isExperimentCompleted) {
return;
}
// Run all the models
for (int indexModel = 0; indexModel < numModels; indexModel++ )
{
if (subDataArray[indexModel] != null || nextData[indexModel] != null)
{
switch (runType[indexModel])
{
case RunType.VoteDistribution:
results[indexModel].RunMajorityVote(subDataArray[indexModel], data, calculateAccuracy, true);
break;
case RunType.MajorityVote:
results[indexModel].RunMajorityVote(subDataArray[indexModel], data, calculateAccuracy, false);
break;
case RunType.DawidSkene:
results[indexModel].RunDawidSkene(subDataArray[indexModel], data, calculateAccuracy);
break;
default: // Run BCC models
results[indexModel].RunBCC(modelName[indexModel], subDataArray[indexModel], data, model[indexModel], RunMode.ClearResults, calculateAccuracy, communityCount, false);
break;
}
} //end for running all the data
if (activeLearning[indexModel] == null)
{
activeLearning[indexModel] = new ActiveLearning(data, model[indexModel], results[indexModel], communityCount);
}
else
{
activeLearning[indexModel].UpdateActiveLearningResults(results[indexModel]);
}
// Select next task
Dictionary<string, ActiveLearningResult> TaskUtility = new Dictionary<string, ActiveLearningResult>();
switch (taskSelectionMethod[indexModel])
{
case TaskSelectionMethod.EntropyTask:
TaskUtility = activeLearning[indexModel].EntropyTrueLabel();
break;
case TaskSelectionMethod.RandomTask:
TaskUtility = data.GroupBy(d => d.TaskId).ToDictionary(a => a.Key, a => new ActiveLearningResult
{
TaskValue = Rand.Double()
});
break;
case TaskSelectionMethod.UniformTask:
//add task value according to the count left
TaskUtility = currentCounts.OrderBy(kvp => kvp.Value).ToDictionary(a => a.Key, a => new ActiveLearningResult
{
TaskValue = 1
});
break;
default: // Entropy task selection
TaskUtility = activeLearning[indexModel].EntropyTrueLabel();
break;
}
// We create a list of worker utilities
Dictionary<string, double> WorkerAccuracy = null;
// Best worker selection is only allowed for methods that infer worker confusion matrices.
if (results[indexModel].WorkerConfusionMatrix == null)
workerSelectionMethod[indexModel] = WorkerSelectionMethod.RandomWorker;
switch (workerSelectionMethod[indexModel])
{
case WorkerSelectionMethod.BestWorker:
// Assign worker accuracies to the maximum value on the diagonal of the confusion matrix (conservative approach).
// Alternative ways are also possible.
WorkerAccuracy = results[indexModel].WorkerConfusionMatrixMean.ToDictionary(
kvp => kvp.Key,
kvp => Results.GetConfusionMatrixDiagonal(kvp.Value).Max());
break;
case WorkerSelectionMethod.RandomWorker:
// Assign worker accuracies to random values
WorkerAccuracy = results[indexModel].FullMapping.WorkerIdToIndex.ToDictionary(kvp => kvp.Key, kvp => Rand.Double());
break;
default:
throw new ApplicationException("No worker selection method selected");
}
// Create a list of tuples (TaskId, WorkerId, ActiveLearningResult)
List<Tuple<string, string, ActiveLearningResult>> LabelValue = new List<Tuple<string, string, ActiveLearningResult>>();
foreach (var kvp in TaskUtility)
{
foreach (var workerId in remainingWorkersPerTask[kvp.Key])
{
var labelValue = new ActiveLearningResult
{
WorkerId = workerId,
TaskId = kvp.Key,
TaskValue = kvp.Value.TaskValue,
WorkerValue = WorkerAccuracy[workerId]
};
LabelValue.Add(Tuple.Create(labelValue.TaskId, labelValue.WorkerId, labelValue));
}
}
// Increment tha active set with new data
nextData[indexModel] = GetNextData(groupedRandomisedData, LabelValue, currentCounts, totalCounts, remainingWorkersPerTask, numIncremData);
if (nextData[indexModel] == null || nextData[indexModel].Count == 0)
break;
indexArray[indexModel] += nextData[indexModel].Count;
subDataArray[indexModel].AddRange(nextData[indexModel]);
// Logs
if (calculateAccuracy)
{
accuracyArray[indexModel].Add(results[indexModel].Accuracy);
avgRecallArray[indexModel].Add(results[indexModel].AvgRecall);
if (TaskUtility == null)
{
var sortedLabelValue = LabelValue.OrderByDescending(kvp => kvp.Item3.TaskValue).ToArray();
taskValueListArray[indexModel].Add(sortedLabelValue.First().Item3);
}
else
{
//Adding WorkerId into taskValueListArray
ActiveLearningResult nextTaskValueItem = TaskUtility[nextData[indexModel].First().TaskId];
nextTaskValueItem.WorkerId = nextData[indexModel].First().WorkerId;
nextTaskValueItem.TaskId = nextData[indexModel].First().TaskId;
taskValueListArray[indexModel].Add(nextTaskValueItem);
}
if (doSnapShot)
{
Debug.WriteLine("{0} of {1}:\t{2}\t{3:0.000}\t{4:0.0000}", indexArray[indexModel], totalInstances, modelName[indexModel], accuracyArray[indexModel].Last(), avgRecallArray[indexModel].Last());
}
}
}//end of models
}//end for all data
}
/// <summary>
/// Runs the standard active learning procedure on a model instance and an input data set.
/// </summary>
/// <param name="data">The data.</param>
/// <param name="modelName">The model name.</param>
/// <param name="runType">The model run type.</param>
/// <param name="model">The model instance.</param>
/// <param name="taskSelectionMethod">The method for selecting tasks (Random / Entropy).</param>
/// <param name="workerSelectionMethod">The method for selecting workers (only Random is implemented).</param>
/// <param name="resultsDir">The directory to save the log files.</param>
/// <param name="communityCount">The number of communities (only for CBCC).</param>
/// <param name="initialNumLabelsPerTask">The initial number of exploratory labels that are randomly selected for each task.</param>
/// <param name="numIncremData">The number of data points to add at each round.</param>
public static void RunActiveLearning(
IList<Datum> data,
string modelName,
RunType runType,
BCC model,
TaskSelectionMethod taskSelectionMethod,
WorkerSelectionMethod workerSelectionMethod,
string resultsDir,
int communityCount = -1,
int initialNumLabelsPerTask = 1,
int numIncremData = 1)
{
//Count elapsed time
Stopwatch stopWatchTotal = new Stopwatch();
stopWatchTotal.Start();
int totalLabels = data.Count();
// Dictionary keyed by task Id, with randomly order labelings
var groupedRandomisedData =
data.GroupBy(d => d.TaskId).
Select(g =>
{
var arr = g.ToArray();
int cnt = arr.Length;
var perm = Rand.Perm(cnt);
return new
{
key = g.Key,
arr = g.Select((t, i) => arr[perm[i]]).ToArray()
};
}).ToDictionary(a => a.key, a => a.arr);
// Dictionary keyed by task Id, with label counts
Dictionary<string, int> totalCounts = groupedRandomisedData.ToDictionary(kvp => kvp.Key, kvp => kvp.Value.Length);
// Keyed by task, value is a HashSet containing all the remaining workers with a label - workers are removed after adding a new datum
Dictionary<string, HashSet<string>> remainingWorkersPerTask = groupedRandomisedData.ToDictionary(kvp => kvp.Key, kvp => new HashSet<string>(kvp.Value.Select(dat => dat.WorkerId)));
int numTaskIds = totalCounts.Count();
int totalInstances = initialNumLabelsPerTask > 0 ? data.Count - initialNumLabelsPerTask * numTaskIds : data.Count - numIncremData;
//throw an exception if the totalInstances is less than or equals to zero
if (totalInstances <= 0)
{
throw new System.Exception("The variable 'totalInstances' should be greater than zero");
}
string[] WorkerIds = data.Select(d => d.WorkerId).Distinct().ToArray();
//only creat accuracy list when it's null (for GUI Use)
if (accuracy == null)
{
accuracy = new List<double>();
}
List<double> avgRecall = new List<double>();
//List<ActiveLearningResult> taskValueList = new List<ActiveLearningResult>();
taskValueList = new List<ActiveLearningResult>();
int index = 0;
Console.WriteLine("Active Learning: {0}", modelName);
Console.WriteLine("\t\t\t\t\t\tAcc\tAvgRec");
// Get initial data
Results results = new Results();
Dictionary<string, int> currentCounts = groupedRandomisedData.ToDictionary(kvp => kvp.Key, kvp => initialNumLabelsPerTask);
List<Datum> subData = GetSubdata(groupedRandomisedData, currentCounts, remainingWorkersPerTask);
var s = remainingWorkersPerTask.Select(w => w.Value.Count).Sum();
List<Datum> nextData = null;
ActiveLearning activeLearning = null;
isExperimentCompleted = false;
for (int iter = 0; ; iter++) //run until data run out
{
bool calculateAccuracy = true;
bool doSnapShot = iter % 1 == 0;
if (subData != null || nextData != null)
{
switch (runType)
{
case RunType.VoteDistribution:
results.RunMajorityVote(subData, data, calculateAccuracy, true);
break;
case RunType.MajorityVote:
results.RunMajorityVote(subData, data, calculateAccuracy, false);
break;
case RunType.DawidSkene:
results.RunDawidSkene(subData, data, calculateAccuracy);
break;
default: // Run BCC models
results.RunBCC(modelName, subData, data, model, RunMode.ClearResults, calculateAccuracy, communityCount, false);
break;
}
}
if (activeLearning == null)
{
activeLearning = new ActiveLearning(data, model, results, communityCount);
}
else
{
activeLearning.UpdateActiveLearningResults(results);
}
// We create a list of task utilities
// TaskValue: Dictionary keyed by task, the value is an active learning result.
Dictionary<string, ActiveLearningResult> TaskUtility = null;
switch (taskSelectionMethod)
{
case TaskSelectionMethod.EntropyTask:
TaskUtility = activeLearning.EntropyTrueLabel();
break;
case TaskSelectionMethod.RandomTask:
TaskUtility = data.GroupBy(d => d.TaskId).ToDictionary(a => a.Key, a => new ActiveLearningResult
{
TaskValue = Rand.Double()
});
break;
case TaskSelectionMethod.UniformTask:
// Reproduce uniform task selection by picking the task with the lowest number of current labels. That is, minus the current count.
TaskUtility = currentCounts.OrderBy(kvp => kvp.Value).ToDictionary(a => a.Key, a => new ActiveLearningResult
{
TaskId = a.Key,
TaskValue = -a.Value
});
break;
default:
TaskUtility = activeLearning.EntropyTrueLabel();
break;
}
// We create a list of worker utilities.
Dictionary<string, double> WorkerAccuracy = null;
// Best worker selection is only allowed for methods that infer worker confusion matrices.
if (results.WorkerConfusionMatrix == null)
workerSelectionMethod = WorkerSelectionMethod.RandomWorker;
switch (workerSelectionMethod)
{
case WorkerSelectionMethod.BestWorker:
// Assign worker accuracies to the maximum value on the diagonal of the confusion matrix (conservative approach).
// Alternative ways are also possible.
WorkerAccuracy = results.WorkerConfusionMatrixMean.ToDictionary(
kvp => kvp.Key,
kvp => Results.GetConfusionMatrixDiagonal(kvp.Value).Max());
break;
case WorkerSelectionMethod.RandomWorker:
// Assign worker accuracies to random values
WorkerAccuracy = results.FullMapping.WorkerIdToIndex.ToDictionary(kvp => kvp.Key, kvp => Rand.Double());
break;
default:
throw new ApplicationException("No worker selection method selected");
}
// Create a list of tuples (TaskIds, WorkerId, ActiveLearningResult).
List<Tuple<string, string, ActiveLearningResult>> LabelValue = new List<Tuple<string,string,ActiveLearningResult>>();
foreach (var kvp in TaskUtility)
{
foreach (var workerId in remainingWorkersPerTask[kvp.Key])
{
var labelValue = new ActiveLearningResult
{
WorkerId = workerId,
TaskId = kvp.Key,
TaskValue = kvp.Value.TaskValue,
WorkerValue = WorkerAccuracy[workerId]
};
LabelValue.Add(Tuple.Create(labelValue.TaskId, labelValue.WorkerId, labelValue));
}
}
// Increment tha active set with new data
nextData = GetNextData(groupedRandomisedData, LabelValue, currentCounts, totalCounts, remainingWorkersPerTask, numIncremData);
if (nextData == null || nextData.Count == 0)
break;
index += nextData.Count;
subData.AddRange(nextData);
// Logs
if (calculateAccuracy)
{
accuracy.Add(results.Accuracy);
avgRecall.Add(results.AvgRecall);
if (TaskUtility == null)
{
var sortedLabelValue = LabelValue.OrderByDescending(kvp => kvp.Item3.TaskValue).ToArray();
taskValueList.Add(sortedLabelValue.First().Item3);
}
else
{
//Adding WorkerId into taskValueList
ActiveLearningResult nextTaskValueItem = TaskUtility[nextData.First().TaskId];
nextTaskValueItem.WorkerId = nextData.First().WorkerId;
//add taskID
nextTaskValueItem.TaskId = nextData.First().TaskId;
taskValueList.Add(nextTaskValueItem);
}
if (doSnapShot)
{
Console.WriteLine("{0} (label {1} of {2}):\t{3:0.000}\t{4:0.0000}", modelName, index, totalInstances, accuracy.Last(), avgRecall.Last());
//DoSnapshot(accuracy, nlpd, avgRecall, taskValueList, results, modelName, "interim", resultsDir, initialNumLabelsPerTask);
}
}//end if logs
}//end for all data
isExperimentCompleted = true;
stopWatchTotal.Stop();
DoSnapshot(accuracy, avgRecall, taskValueList, results, modelName, "final", resultsDir, initialNumLabelsPerTask);
ResetAccuracyList();
Console.WriteLine("Elapsed time: {0}\n", stopWatchTotal.Elapsed);
}
/// <summary>
/// Run the BCC models
/// </summary>
/// <param name="modelName"></param>
/// <param name="data"></param>
/// <param name="fullData"></param>
/// <param name="model"></param>
/// <param name="mode"></param>
/// <param name="calculateAccuracy"></param>
/// <param name="numCommunities"></param>
/// <param name="serialize"></param>
/// <param name="serializeCommunityPosteriors"></param>
public void RunBCC(string modelName,
IList<Datum> data,
IList<Datum> fullData,
BCC model,
RunMode mode,
bool calculateAccuracy,
int numCommunities = -1,
bool serialize = false,
bool serializeCommunityPosteriors = false)
{
CBCC communityModel = model as CBCC;
IsCommunityModel = communityModel != null;
bool IsBCC = !(IsCommunityModel);
if (this.Mapping == null)
{
this.Mapping = new DataMapping(fullData, numCommunities);
this.FullMapping = Mapping;
this.GoldLabels = this.Mapping.GetGoldLabelsPerTaskId();
}
bool createModel = (Mapping.LabelCount != model.LabelCount) || (Mapping.TaskCount != model.TaskCount);
if (IsCommunityModel)
{
//Console.WriteLine("--- CBCC ---");
CommunityCount = numCommunities;
createModel = createModel || (numCommunities != communityModel.CommunityCount);
if (createModel)
{
communityModel.CreateModel(Mapping.TaskCount, Mapping.LabelCount, numCommunities);
}
}
else if (createModel)
{
model.CreateModel(Mapping.TaskCount, Mapping.LabelCount);
}
BCCPosteriors priors = null;
switch (mode)
{
case RunMode.Prediction:
priors = ToPriors();
break;
default:
ClearResults();
if (mode == RunMode.LoadAndUseCommunityPriors && IsCommunityModel)
{
priors = DeserializeCommunityPosteriors(modelName, numCommunities);
}
break;
}
// Get data structures
int[][] taskIndices = Mapping.GetTaskIndicesPerWorkerIndex(data);
int[][] workerLabels = Mapping.GetLabelsPerWorkerIndex(data);
if (mode == RunMode.Prediction)
{
// Signal prediction mode by setting all labels to null
workerLabels = workerLabels.Select(arr => (int[])null).ToArray();
}
// Call inference
BCCPosteriors posteriors = model.Infer(
taskIndices,
workerLabels,
priors);
UpdateResults(posteriors, mode);
if (calculateAccuracy)
{
UpdateAccuracy();
}
if (serialize)
{
using (FileStream stream = new FileStream(modelName + ".xml", FileMode.Create))
{
var serializer = new System.Xml.Serialization.XmlSerializer(IsCommunityModel ? typeof(CBCCPosteriors) : typeof(BCCPosteriors));
serializer.Serialize(stream, posteriors);
}
}
if (serializeCommunityPosteriors && IsCommunityModel)
{
SerializeCommunityPosteriors(modelName);
}
}
}//end function RunParallelActiveLearning
/// <summary>
/// RunBatchRunning experiment in background thread
/// </summary>
/// <param name="worker"></param>
/// <param name="e"></param>
public void RunBatchRunningExperiment(
System.ComponentModel.BackgroundWorker worker,
System.ComponentModel.DoWorkEventArgs e)
{
CurrentParallelState currentState;
//Get the number of the total experiment Items
int totalNumberOfModels = GetNumberOfExperiemntModels();
//A List of Results array ofreport all experimentItems
results = new List<Results>();
currentState = new CurrentParallelState();
//Running the current experimentSetting lists and runGold accordinglyb
foreach (ExperimentModel currentExpItem in experimentModels)
{
//currentState.currentExperimentModel = currentExpItem;
if (MainPage.mainPageForm.isExperimentComplete)
{
return;
}
currentState = new CurrentParallelState();
currentState.currentExperimentModelIndex = GetExperimenModelIndex(currentExpItem);
currentState.isCurrentModelCompleted = false;
//Pass the started currentIndex to the mainpage, such that this currentExpItem is started
worker.ReportProgress(0, currentState);
//Create a BCC/CBCC model of the Batch Running Experiment
BCC currentModel = null;
if( currentExpItem.runType == RunType.BCC)
{
currentModel = new BCC();
}
else if(currentExpItem.runType == RunType.CBCC)
{
currentModel = new CBCC();
((CBCC)currentModel).SetCommunityCount(MainPage.mainPageForm.currentExperimentSetting.communityCount);
}
//When the experiment is not running
while (!MainPage.mainPageForm.isExperimentRunning )
{
}
if (MainPage.mainPageForm.isExperimentComplete)
{
return;
}
results.Add(CrowdsourcingModels.Program.RunBatchLearning(currentDataset.DatasetPath, currentExpItem.runType, currentModel, MainPage.mainPageForm.currentExperimentSetting.communityCount));
//When the experiment is not running
while (!MainPage.mainPageForm.isExperimentRunning)
{
}
if (MainPage.mainPageForm.isExperimentComplete)
{
return;
}
//add the results into the List<Results[]>
//convert the lists into a single array of results (using LINQ)
//notify the mainPage UI while it is completed
currentState.isCurrentModelCompleted = true;
worker.ReportProgress(0, currentState);
} // For each experimentItem
//The Batch Running is completed
currentState.isRunningComplete = true;
}
/// <summary>
/// Background Thread for running the active learning experiment
/// <param name="worker"></param>
/// <param name="e"></param>
public void RunParallelActiveLearning(
System.ComponentModel.BackgroundWorker worker,
System.ComponentModel.DoWorkEventArgs e)
{
//Create a state of the Thread
CurrentParallelState currentState = new CurrentParallelState();
//Set setting in the experimentSetting Class
int totalNumberOfModels = GetNumberOfExperiemntModels();
//Clear previous results
ActiveLearning.ResetParallelAccuracyList(totalNumberOfModels);
//obtain the accuracy list reference
accuracyArrayOfAllExperimentModels = ActiveLearning.accuracyArray;
//The RunTypes that have Worker Confusion Matrices
RunType[] runTypesHaveWorkerMatrices = { RunType.DawidSkene, RunType.BCC, RunType.CBCC };
//Set the models selected in the setting pane
string[] currentModelNames = new string[totalNumberOfModels];
RunType[] currentRunTypes = new RunType[totalNumberOfModels];
TaskSelectionMethod[] currentTaskSelectionMethods = new TaskSelectionMethod[totalNumberOfModels];
WorkerSelectionMethod[] currentWorkerSelectionMethods = new WorkerSelectionMethod[totalNumberOfModels];
BCC[] currentBCCModels = new BCC[totalNumberOfModels];
//for each ExperimentModel, set runTypeArray, taskSelectionMethodArray, workerSelectionMethodArray...
for (int i = 0; i < totalNumberOfModels; i++)
{
ExperimentModel currentExperimentModel = GetExperimentModel(i);
RunType currentRunType = currentExperimentModel.runType;
currentRunTypes[i] = currentRunType;
//set the task selection method
currentTaskSelectionMethods[i] = currentExperimentModel.taskSelectionMethod;
//Add into worker selection method array if the runType can have worker selection
if (runTypesHaveWorkerMatrices.Contains(currentRunType))
{
currentWorkerSelectionMethods[i] = currentExperimentModel.WorkerSelectionMethod;
//Add corresponding model
//if the RunType is BCC, add into BCC model array
if (currentRunType == RunType.BCC)
{
currentBCCModels[i] = new BCC();
}//CBCC Model
else if(currentRunType == RunType.CBCC)
{
CBCC currentBCCmodel = new CBCC();
currentBCCModels[i] = currentBCCmodel;
}
} //end if the runType has worker confusion matrices
} //end for
currentModelNames = currentModelNames.Select((s, i) => CrowdsourcingModels.Program.GetModelName(currentDataset.GetDataSetNameWithoutExtension(), currentRunTypes[i])).ToArray();
//run RunParallelActiveLearning in the ActiveLearning
ActiveLearning.RunParallelActiveLearning(currentDataset.LoadData(), currentModelNames, currentRunTypes,
currentBCCModels, currentTaskSelectionMethods, currentWorkerSelectionMethods,
communityCount, numberOfLabellingRound);
currentState.isRunningComplete = true;
Debug.WriteLine("RunParallelActiveLearning Complete");
//isSimulationComplete = true;
//worker.ReportProgress(0, currentState);
}//end function RunParallelActiveLearning
/// <summary>
/// Run the BCC models
/// </summary>
/// <param name="modelName"></param>
/// <param name="data"></param>
/// <param name="fullData"></param>
/// <param name="model"></param>
/// <param name="mode"></param>
/// <param name="calculateAccuracy"></param>
/// <param name="numCommunities"></param>
/// <param name="serialize"></param>
/// <param name="serializeCommunityPosteriors"></param>
public void RunBCC(string modelName,
IList <Datum> data,
IList <Datum> fullData,
BCC model,
RunMode mode,
bool calculateAccuracy,
int numCommunities = -1,
bool serialize = false,
bool serializeCommunityPosteriors = false)
{
CBCC communityModel = model as CBCC;
IsCommunityModel = communityModel != null;
bool IsBCC = !(IsCommunityModel);
if (this.Mapping == null)
{
this.Mapping = new DataMapping(fullData, numCommunities);
this.FullMapping = Mapping;
this.GoldLabels = this.Mapping.GetGoldLabelsPerTaskId();
}
bool createModel = (Mapping.LabelCount != model.LabelCount) || (Mapping.TaskCount != model.TaskCount);
if (IsCommunityModel)
{
//Console.WriteLine("--- CBCC ---");
CommunityCount = numCommunities;
createModel = createModel || (numCommunities != communityModel.CommunityCount);
if (createModel)
{
communityModel.CreateModel(Mapping.TaskCount, Mapping.LabelCount, numCommunities);
}
}
else if (createModel)
{
model.CreateModel(Mapping.TaskCount, Mapping.LabelCount);
}
BCCPosteriors priors = null;
switch (mode)
{
case RunMode.Prediction:
priors = ToPriors();
break;
default:
ClearResults();
if (mode == RunMode.LoadAndUseCommunityPriors && IsCommunityModel)
{
priors = DeserializeCommunityPosteriors(modelName, numCommunities);
}
break;
}
// Get data structures
int[][] taskIndices = Mapping.GetTaskIndicesPerWorkerIndex(data);
int[][] workerLabels = Mapping.GetLabelsPerWorkerIndex(data);
if (mode == RunMode.Prediction)
{
// Signal prediction mode by setting all labels to null
workerLabels = workerLabels.Select(arr => (int[])null).ToArray();
}
// Call inference
BCCPosteriors posteriors = model.Infer(
taskIndices,
workerLabels,
priors);
UpdateResults(posteriors, mode);
if (calculateAccuracy)
{
UpdateAccuracy();
}
if (serialize)
{
using (FileStream stream = new FileStream(modelName + ".xml", FileMode.Create))
{
var serializer = new System.Xml.Serialization.XmlSerializer(IsCommunityModel ? typeof(CBCCPosteriors) : typeof(BCCPosteriors));
serializer.Serialize(stream, posteriors);
}
}
if (serializeCommunityPosteriors && IsCommunityModel)
{
SerializeCommunityPosteriors(modelName);
}
}
/// <summary>
/// Run a batch learning experiment.
/// </summary>
/// <param name="dataSetPath">The path of the dataset.</param>
/// <param name="runType">The run type.</param>
/// <param name="model">The model.</param>
/// <param name="numCommunities">The number of communities (only for CBCC)</param>
/// <returns></returns>
public static Results RunBatchLearning(string dataSetPath, RunType runType, BCC model, int numCommunities = 3)
{
var data = Datum.LoadData(dataSetPath);
return RunGold(dataSetPath, data, runType, model, numCommunities);
}
/// <summary>
/// Run a batch learning experiment.
/// </summary>
/// <param name="dataSetPath">The path of the dataset.</param>
/// <param name="runType">The run type.</param>
/// <param name="model">The model.</param>
/// <param name="numCommunities">The number of communities (only for CBCC)</param>
/// <returns></returns>
public static Results RunBatchLearning(string dataSetPath, RunType runType, BCC model, int numCommunities = 3)
{
var data = Datum.LoadData(dataSetPath);
return(RunGold(dataSetPath, data, runType, model, numCommunities));
}
/// <summary>
/// Runs a model with the full gold set.
/// </summary>
/// <param name="dataSet">The dataset name.</param>
/// <param name="data">The data.</param>
/// <param name="runType">The model run type.</param>
/// <param name="model">The model instance.</param>
/// <param name="numCommunities">The number of communities (only for CBCC).</param>
/// <returns>The inference results</returns>
public static Results RunGold(string dataSet, IList <Datum> data, RunType runType, BCC model, int numCommunities = 2)
{
string modelName = Program.GetModelName(dataSet, runType);
Results results = new Results();
switch (runType)
{
case RunType.VoteDistribution:
results.RunMajorityVote(data, data, true, true);
break;
case RunType.MajorityVote:
results.RunMajorityVote(data, data, true, false);
break;
case RunType.DawidSkene:
results.RunDawidSkene(data, data, true);
break;
default:
results.RunBCC(modelName, data, data, model, RunMode.ClearResults, true, numCommunities, false, false);
break;
}
return(results);
}
