static private void initializeEkmanAsSource(Corpus experiment, int startIndex, int endIndex, IList <Sentence> sentences, ref IList <SourceWorker> sourceWorkerList)
{
string[] data = File.ReadAllLines(experiment + "/EkmanData" + startIndex + "-" + endIndex + ".csv");
foreach (string row in data)
{
string[] labels = row.Split(',');
SourceWorker worker = new SourceWorker(labels[0]);
if (!sourceWorkerList.Contains(worker))//重复的人不再添加
{
sourceWorkerList.Add(worker);
}
else
{
worker = sourceWorkerList.First(x => x.Equals(worker));
}
IList <Label> trueLabels = new List <Label>();
for (int i = 1; i <= (endIndex - startIndex + 1) * (Constant.EkmanLabelArray.Length + 1); ++i)
{
switch (labels[i])
{
case "Anger":
trueLabels.Add(Label.Anger);
break;
case "Sadness":
trueLabels.Add(Label.Sadness);
break;
case "Joy":
trueLabels.Add(Label.Joy);
break;
case "Disgust":
trueLabels.Add(Label.Disgust);
break;
case "Surprise":
trueLabels.Add(Label.Surprise);
break;
case "Fear":
trueLabels.Add(Label.Fear);
break;
}
if (i % (Constant.EkmanLabelArray.Length + 1) == 0)
{
//取出SentenceList里的一个Sentence
Sentence sentence = sentences[startIndex + (i - 1) / (Constant.EkmanLabelArray.Length + 1)];
SourceAnnotation sourceAnnotation = new SourceAnnotation(trueLabels.ToArray());
trueLabels.Clear();
worker.SentenceSourceAnnotationDic.Add(sentence, sourceAnnotation);
sentence.SourceWorkerSourceAnnotationDic.Add(worker, sourceAnnotation);
}
}
}
}
/// <summary>
/// 只过滤标注Nakamura的worker，不管Train还是NotTrain，Source还是Target
/// </summary>
static public void FilterTargetWorker()
{
if (Constant.SourceTaxonomy.Name == TaxonomyType.Nakamura)
{
foreach (Sentence sentence in TrainConstant.SentenceList)
{
for (int i = sentence.SourceWorkerSourceAnnotationDic.Count - 1; i >= 30; --i)//用.Count就不用管sentence被标了40次还是41次
{
SourceWorker sourceWorker = sentence.SourceWorkerSourceAnnotationDic.ElementAt(i).Key;
sentence.SourceWorkerSourceAnnotationDic.Remove(sourceWorker);
sourceWorker.SentenceSourceAnnotationDic.Remove(sentence);
}
}
foreach (SourceWorker sourceWorker in TrainConstant.SourceWorkerList.ToArray())
{
if (sourceWorker.SentenceSourceAnnotationDic.Count == 0)
{
TrainConstant.SourceWorkerList.Remove(sourceWorker);
}
}
foreach (Sentence sentence in NotTrainConstant.SentenceList)
{
for (int i = sentence.SourceWorkerSourceAnnotationDic.Count - 1; i >= 30; --i)//用.Count就不用管sentence被标了40次还是41次
{
SourceWorker sourceWorker = sentence.SourceWorkerSourceAnnotationDic.ElementAt(i).Key;
sentence.SourceWorkerSourceAnnotationDic.Remove(sourceWorker);
sourceWorker.SentenceSourceAnnotationDic.Remove(sentence);
}
}
foreach (SourceWorker sourceWorker in NotTrainConstant.SourceWorkerList.ToArray())
{
if (sourceWorker.SentenceSourceAnnotationDic.Count == 0)
{
NotTrainConstant.SourceWorkerList.Remove(sourceWorker);
}
}
}
else if (Constant.TargetTaxonomy.Name == TaxonomyType.Nakamura)
{
foreach (Sentence sentence in TrainConstant.SentenceList)
{
for (int i = sentence.TargetWorkerTargetAnnotationDic.Count - 1; i >= 30; --i)
{
TargetWorker targetWorker = sentence.TargetWorkerTargetAnnotationDic.ElementAt(i).Key;
sentence.TargetWorkerTargetAnnotationDic.Remove(targetWorker);
targetWorker.SentenceTargetAnnotationDic.Remove(sentence);
}
}
foreach (TargetWorker targetWorker in TrainConstant.TargetWorkerList.ToArray())
{
if (targetWorker.SentenceTargetAnnotationDic.Count == 0)
{
TrainConstant.TargetWorkerList.Remove(targetWorker);
}
}
foreach (Sentence sentence in NotTrainConstant.SentenceList)
{
for (int i = sentence.TargetWorkerTargetAnnotationDic.Count - 1; i >= 30; --i)
{
TargetWorker targetWorker = sentence.TargetWorkerTargetAnnotationDic.ElementAt(i).Key;
sentence.TargetWorkerTargetAnnotationDic.Remove(targetWorker);
targetWorker.SentenceTargetAnnotationDic.Remove(sentence);
}
}
foreach (TargetWorker targetWorker in NotTrainConstant.TargetWorkerList.ToArray())
{
if (targetWorker.SentenceTargetAnnotationDic.Count == 0)
{
NotTrainConstant.TargetWorkerList.Remove(targetWorker);
}
}
}
}
static private void initializeNakaAsSource(Corpus corpus, int startIndex, int endIndex, IList <Sentence> sentences, ref IList <SourceWorker> sourceWorkerList)
{
string[] data = File.ReadAllLines(corpus + "/NakaData" + startIndex + "-" + endIndex + ".csv");//不需要单独做一个data-sample,因为sentence-sample以外的sentence在下面的for循环里遍历不到。
foreach (string row in data)
{
string[] labels = row.Split(','); //labels[0]是用户名
SourceWorker worker = new SourceWorker(labels[0]);
if (!sourceWorkerList.Contains(worker)) //重复的人不再添加
{
sourceWorkerList.Add(worker);
}
else
{
worker = sourceWorkerList.First(x => x.Equals(worker));
}
IList <Label> trueLabels = new List <Label>();
for (int i = 1; i <= (endIndex - startIndex + 1) * (Constant.NakaLabelArray.Length + 1); ++i)
{
switch (labels[i])
{
case "happiness":
trueLabels.Add(Label.喜Joy);
break;
case "fondness":
trueLabels.Add(Label.好Fondness);
break;
case "relief":
trueLabels.Add(Label.安Relief);
break;
case "anger":
trueLabels.Add(Label.怒Anger);
break;
case "sadness":
trueLabels.Add(Label.哀Sadness);
break;
case "fear":
trueLabels.Add(Label.怖Fear);
break;
case "shame":
trueLabels.Add(Label.恥Shame);
break;
case "disgust":
trueLabels.Add(Label.厭Disgust);
break;
case "excitement":
trueLabels.Add(Label.昂Excitement);
break;
case "surprise":
trueLabels.Add(Label.驚Surprise);
break;
}
if (i % (Constant.NakaLabelArray.Length + 1) == 0)
{
//取出SentenceList里的一个Sentence
Sentence sentence = sentences[startIndex + (i - 1) / (Constant.NakaLabelArray.Length + 1)];
SourceAnnotation targetAnnotation = new SourceAnnotation(trueLabels.ToArray());
trueLabels.Clear();
worker.SentenceSourceAnnotationDic.Add(sentence, targetAnnotation);
sentence.SourceWorkerSourceAnnotationDic.Add(worker, targetAnnotation);
}
}
}
}