public static LinguisticObjectDetectionMetrics MetricsFor(LinguisticObjectMatch objectMatch,
Sentence targetSentence, Sentence sampleSentence, LinguisticObjectType objectType)
{
if (objectMatch.TargetObjects == null) return _metricsForMissedObject(objectMatch, sampleSentence);
if (objectMatch.SampleObjects == null)
return _metricsForSurplusTargetObject(objectMatch, sampleSentence, targetSentence, objectType);
var targetWords = objectMatch.TargetObjects.Words;
var sampleWords = objectMatch.SampleObjects.Words;
var detectedWords = _getDetectedWords(targetWords, sampleWords);
var surplusWords = targetWords.Where(word => !detectedWords.Contains(word)).ToList();
var missedWords =
sampleWords.Where(word => targetWords.All(targetWord => targetWord.Text != word.Text)).ToList();
var essentialSurpluses = surplusWords.Where(word => !word.IsAuxilary).ToList();
var essentialSurplusText = essentialSurpluses.Select(word => word.Text).ToList();
var essentialSurplusIndexes = essentialSurpluses.Select(targetSentence.WordIndex).ToList();
var nonEssentialSurpluses = surplusWords.Where(word => word.IsAuxilary).ToList();
var nonEssentialSurplusTexts = nonEssentialSurpluses.Select(word => word.Text).ToList();
var nonEssentialSurplusIndexes = nonEssentialSurpluses.Select(targetSentence.WordIndex).ToList();
var essentialMises = missedWords.Where(word => !word.IsAuxilary).ToList();
var essentialMissTexts = essentialMises.Select(word => word.Text).ToList();
var essentialMissIndexes = essentialMises.Select(sampleSentence.WordIndex).ToList();
var nonEssentialMises = missedWords.Where(word => word.IsAuxilary).ToList();
var nonEssentialMissTexts = nonEssentialMises.Select(word => word.Text).ToList();
var nonEssentialMissIndexes = nonEssentialMises.Select(sampleSentence.WordIndex).ToList();
return new LinguisticObjectDetectionMetrics
{
SampleWords = sampleWords.Select(word => word.Text).ToArray(),
TargetWords = targetWords.Select(word => word.Text).ToArray(),
SampleWordsCount = sampleWords.Count,
SampleWordIndexes = sampleWords.Select(sampleSentence.WordIndex).ToArray(),
TargetWordsCount = targetWords.Count,
TargetWordIndexes = targetWords.Select(targetSentence.WordIndex).ToArray(),
NonEssentialErrors = nonEssentialSurplusTexts.Concat(nonEssentialMissTexts).ToArray(),
NonEssentialErrorIndexes = nonEssentialSurplusIndexes.Concat(nonEssentialMissIndexes).ToArray(),
EssentialErrors = essentialSurplusText.Concat(essentialMissTexts).ToArray(),
EssentialErrorIndexes = essentialSurplusIndexes.Concat(essentialMissIndexes).ToArray(),
SurplusNonEssentialWords = nonEssentialSurplusTexts.ToArray(),
SurplusNonEssentialWordIndexes = nonEssentialSurplusIndexes.ToArray(),
MissedNonEssentialWords = nonEssentialMissTexts.ToArray(),
MissedNonEssentialWordIndexes = nonEssentialMissIndexes.ToArray(),
SurplusEssentialWords = essentialSurplusText.ToArray(),
SurplusEssentialWordIndexes = essentialSurplusIndexes.ToArray(),
MissedEssentialWords = essentialMissTexts.ToArray(),
MissedEssentialWordIndexes = essentialMissIndexes.ToArray(),
CorrectDetectionsCount = detectedWords.Count,
Type = ErrorType.DetectionDefect,
DetectionQuality =
detectedWords.Any()
? _getQualityMeasure(detectedWords.Count, essentialSurpluses.Count, sampleWords.Count)
: 0d
};
}
private static LinguisticObjectDetectionMetrics _metricsForMissedObject(LinguisticObjectMatch objectMatch,
Sentence sampleSentence)
{
var sampleWords = objectMatch.SampleObjects.Words;
var essentialMises = sampleWords.Where(word => !word.IsAuxilary).ToList();
var essentialMissTexts = essentialMises.Select(word => word.Text).ToList();
var essentialMissIndexes = essentialMises.Select(sampleSentence.WordIndex).ToList();
var nonEssentialMises = sampleWords.Where(word => word.IsAuxilary).ToList();
var nonEssentialMissTexts = nonEssentialMises.Select(word => word.Text).ToList();
var nonEssentialMissIndexes = nonEssentialMises.Select(sampleSentence.WordIndex).ToList();
return new LinguisticObjectDetectionMetrics
{
SampleWords = sampleWords.Select(word => word.Text).ToArray(),
TargetWords = new string[] { },
SampleWordsCount = sampleWords.Count,
SampleWordIndexes = sampleWords.Select(sampleSentence.WordIndex).ToArray(),
TargetWordsCount = 0,
TargetWordIndexes = new int[] { },
NonEssentialErrors = nonEssentialMissTexts.ToArray(),
NonEssentialErrorIndexes = nonEssentialMissIndexes.ToArray(),
EssentialErrors = essentialMissTexts.ToArray(),
EssentialErrorIndexes = essentialMissIndexes.ToArray(),
SurplusNonEssentialWords = new string[] { },
SurplusNonEssentialWordIndexes = new int[] { },
MissedNonEssentialWords = nonEssentialMissTexts.ToArray(),
MissedNonEssentialWordIndexes = nonEssentialMissIndexes.ToArray(),
SurplusEssentialWords = new string[] { },
SurplusEssentialWordIndexes = new int[] { },
MissedEssentialWords = essentialMissTexts.ToArray(),
MissedEssentialWordIndexes = essentialMissIndexes.ToArray(),
CorrectDetectionsCount = 0,
DetectionQuality = 0d,
Type = ErrorType.MissedLinguisticObject
};
}
private static LinguisticObjectDetectionMetrics _metricsForSurplusTargetObject(LinguisticObjectMatch objectMatch, Sentence sampleSentence, Sentence targetSentence, LinguisticObjectType type)
{
var magicNumber = _getArageWordsCountInObjectsOfType(sampleSentence, type);
var targetWords = objectMatch.TargetObjects.Words;
var essentialSurpluses = targetWords.Where(word => !word.IsAuxilary).ToList();
var essentialSurplusText = essentialSurpluses.Select(word => word.Text).ToList();
var essentialSurplusIndexes = essentialSurpluses.Select(targetSentence.WordIndex).ToList();
var nonEssentialSurpluses = targetWords.Where(word => word.IsAuxilary).ToList();
var nonEssentialSurplusTexts = nonEssentialSurpluses.Select(word => word.Text).ToList();
var nonEssentialSurplusIndexes = nonEssentialSurpluses.Select(targetSentence.WordIndex).ToList();
return new LinguisticObjectDetectionMetrics
{
SampleWords = new string[]{},
TargetWords = targetWords.Select(word => word.Text).ToArray(),
SampleWordsCount = 0,
SampleWordIndexes = new int[]{},
TargetWordsCount = targetWords.Count,
TargetWordIndexes = targetWords.Select(targetSentence.WordIndex).ToArray(),
NonEssentialErrors = nonEssentialSurplusTexts.ToArray(),
NonEssentialErrorIndexes = nonEssentialSurplusIndexes.ToArray(),
EssentialErrors = essentialSurplusText.ToArray(),
EssentialErrorIndexes = essentialSurplusIndexes.ToArray(),
SurplusNonEssentialWords = nonEssentialSurplusTexts.ToArray(),
SurplusNonEssentialWordIndexes = nonEssentialSurplusIndexes.ToArray(),
MissedNonEssentialWords = new string[] { },
MissedNonEssentialWordIndexes = new int[] { },
SurplusEssentialWords = essentialSurplusText.ToArray(),
SurplusEssentialWordIndexes = essentialSurplusIndexes.ToArray(),
MissedEssentialWords = new string[] { },
MissedEssentialWordIndexes = new int[] { },
CorrectDetectionsCount = 0,
DetectionQuality = magicNumber/(magicNumber + 0.5*essentialSurpluses.Count),
Type = ErrorType.SurplusLinguisticObject
};
}
private void _processSubject(LinguisticObjectMatch subjectsMatch)
{
_processSimpleObjectMatch(subjectsMatch, stats => stats.Subjects.Objects, LinguisticObjectType.Subject);
}
private void _processUniforms(LinguisticObjectMatch uniformsMatch)
{
_processSimpleObjectMatch(uniformsMatch, stats => stats.Uniforms.Objects, LinguisticObjectType.Uniform);
}
private void _processSimpleObjectMatch(LinguisticObjectMatch match, Func<SimpleSentenceStats, List<LinguisticObject>> statsGroupSelector, LinguisticObjectType objectType)
{
var senteceId = _getSenteceId(match);
if(senteceId == -1) return;
var simpleSentenceStats = _simpleSentencesStats[senteceId];
statsGroupSelector(simpleSentenceStats).Add(new LinguisticObject
{
MappedObjects = match,
Metrics = LoMatchMetricsCalculator.MetricsFor(match, _target, _sample, objectType)
});
}
private void _processPredicate(LinguisticObjectMatch predicateMatch)
{
_processSimpleObjectMatch(predicateMatch, stats => stats.Predicates.Objects, LinguisticObjectType.Predicate);
}
private void _processMeaningPart(LinguisticObjectMatch meaningPartMatch)
{
_processSimpleObjectMatch(meaningPartMatch, stats => stats.MeaningAuxParts.Objects, LinguisticObjectType.MeaningPart);
}
private int _getSenteceId(LinguisticObjectMatch match)
{
return match.SampleObjects != null ? _getSenteceId(match.SampleObjects, _sample) : _getSenteceId(match.TargetObjects, _target);
}
private static LinguisticObjectMatch _processBestMatch(List<SimplePartsSimilarity> similarityTable, SimplePartsSimilarity bestMatch)
{
var result = new LinguisticObjectMatch
{
SampleObjects = bestMatch.Sample,
TargetObjects = bestMatch.Target
};
similarityTable.Remove(bestMatch);
similarityTable.Where(similarity => similarity.Sample == bestMatch.Sample).ForEach(similarity =>
{
similarity.Sample = null;
similarity.Value = 0;
});
similarityTable.Where(similarity => similarity.Target == bestMatch.Target).ForEach(similarity =>
{
similarity.Target = null;
similarity.Value = 0;
});
similarityTable.RemoveAll(similarity => similarity.Sample == null && similarity.Target == null);
return result;
}