private static LoSummaryStats _emulatedStatsForLObjects(SentencesPack pack,
Func<SimpleSentenceStats, int> statsLoCounter, Func<SimpleSentenceStats, double> sentenceLoAverageQuality,
int sentecesCount,
IEnumerable<ClasterizedSentenceError> packClasterizedErrors,
int correctionClass, LinguisticObjectType loType)
{
var simpleSentencesStats =
pack.ComparisonResults.SelectMany(result => result.SimpleSentenceStats)
.Select(stats => new {Stats = stats, LoCount = statsLoCounter(stats)})
.ToList();
var totalLoCount = simpleSentencesStats.Aggregate(0, (i, stats) => i + stats.LoCount);
var normalAverageTotalQuality = simpleSentencesStats.Aggregate(0d,
(statsQualitySum, stats) =>
statsQualitySum + (stats.LoCount != 0 ? sentenceLoAverageQuality(stats.Stats) : 0));
var normalAverageQuality = normalAverageTotalQuality/totalLoCount;
var defectsShare = 1d - normalAverageQuality;
var emulationEffect = _calcEmulationEffect(packClasterizedErrors, correctionClass, loType);
return new LoSummaryStats
{
AverageCount = ((double) totalLoCount)/sentecesCount,
AverageQuality = 1d - (defectsShare*(1d - emulationEffect)),
WasEmulated = Math.Abs(emulationEffect) > 0.05
};
}
private static PackSummary _emulatedSummaryFor(SentencesPack sentencesPack,
IEnumerable<ClasterizedSentenceError> packClasterizedErrors, int correctionClass)
{
return _summaryFor(sentencesPack,
(pack, sentenceLoCounter, sentenceLoAverageQuality, sentecesCount, loType) =>
_emulatedStatsForLObjects(pack, sentenceLoCounter, sentenceLoAverageQuality, sentecesCount,
packClasterizedErrors, correctionClass, loType));
}
public static SentencesPack CorrectErrors(SentencesPack originalPack, IEnumerable<IGrouping<int, ClasterizedSentenceError>> analyzedErrors, int correctionClass)
{
var errorsBySentenceId = analyzedErrors != null
? analyzedErrors.ToDictionary(errors => errors.Key)
: new Dictionary<int, IGrouping<int, ClasterizedSentenceError>>();
var resultPack = new SentencesPack
{
Sample = originalPack.Sample,
Target = originalPack.Target,
ComparisonResults =
originalPack.ComparisonResults.Select(
(result, i) => errorsBySentenceId.ContainsKey(i + 1)
? _correctErrors(result, errorsBySentenceId[i + 1], correctionClass)
: result).ToList()
};
return resultPack;
}
private static List<string> _runComparison(SentencesPack sentencesPack)
{
List<string> errors;
sentencesPack.ComparisonResults = Core.Compare(sentencesPack.Target, sentencesPack.Sample, out errors);
return errors;
}
private static void _exportSimpleSentences(SentencesPack dataPack, string resultsDir, string s)
{
DataExporter.WriteSSToFile(dataPack.ComparisonResults, Path.Combine(resultsDir, s));
}
private static void _exportPackSimpleSentencesSummary(SentencesPack dataPack, PackSummary summary, string resultsDir, string fileName)
{
DataExporter.WritePackSimpleSentencesSummary(dataPack.ComparisonResults, summary, Path.Combine(resultsDir, fileName));
}
private static void _exportPackData(SentencesPack sentencesPack, string resultsDir, string fileName)
{
DataExporter.WriteToFile(sentencesPack.ComparisonResults, Path.Combine(resultsDir, fileName));
}
public static List<SentenceErrors> Process(SentencesPack sentences)
{
return sentences.ComparisonResults.SelectMany(_getErrors).ToList();
}
private static LoSummaryStats _statsForLObjects(SentencesPack pack, Func<SimpleSentenceStats, int> statsLoCounter,
Func<SimpleSentenceStats, double> sentenceLoAverageQuality, int sentecesCount, LinguisticObjectType loType)
{
var simpleSentencesStats =
pack.ComparisonResults.SelectMany(result => result.SimpleSentenceStats)
.Select(stats => new {Stats = stats, LoCount = statsLoCounter(stats)})
.ToList();
var totalLoCount = simpleSentencesStats.Aggregate(0, (i, stats) => i + stats.LoCount);
//var totalQuality = simpleSentencesStats.Aggregate(0d,
// (statsQualitySum, stats) => statsQualitySum + (stats.LoCount != 0 ? sentenceLoAverageQuality(stats.Stats) : 0));
var totalQuality = simpleSentencesStats.Aggregate(0d,
(statsQualitySum, stats) => statsQualitySum + (stats.LoCount != 0 ? stats.LoCount* sentenceLoAverageQuality(stats.Stats) : 0));
return new LoSummaryStats
{
AverageCount = ((double) totalLoCount)/sentecesCount,
//AverageQuality = totalQuality / simpleSentencesStats.Count(stats => stats.LoCount != 0)
AverageQuality = totalQuality / totalLoCount
};
}
private static PackSummary _summaryFor(SentencesPack pack,
Func<SentencesPack, Func<SimpleSentenceStats, int>,
Func<SimpleSentenceStats, double>, int, LinguisticObjectType, LoSummaryStats> statsForLObjects)
{
var result = new PackSummary
{
SentencesCount = pack.Sample.Count,
Stats = new Dictionary<LinguisticObjectType, LoSummaryStats>()
};
var simpleSentences =
pack.ComparisonResults.SelectMany(comparisonResult => comparisonResult.SimpleSentenceStats).ToList();
var simpleSentecesCount = simpleSentences.Count();
result.Stats[LinguisticObjectType.Subject] = statsForLObjects(pack, stats => stats.Subjects.Objects.Count,
stats => stats.Subjects.AverageDetectionQuality, simpleSentecesCount, LinguisticObjectType.Subject);
result.Stats[LinguisticObjectType.Predicate] = statsForLObjects(pack, stats => stats.Predicates.Objects.Count,
stats => stats.Predicates.AverageDetectionQuality, simpleSentecesCount, LinguisticObjectType.Predicate);
result.Stats[LinguisticObjectType.Uniform] = statsForLObjects(pack, stats => stats.Uniforms.Objects.Count,
stats => stats.Uniforms.AverageDetectionQuality, simpleSentecesCount, LinguisticObjectType.Uniform);
result.Stats[LinguisticObjectType.MeaningPart] = statsForLObjects(pack,
stats => stats.MeaningAuxParts.Objects.Count,
stats => stats.MeaningAuxParts.AverageDetectionQuality, simpleSentecesCount,
LinguisticObjectType.MeaningPart);
result.Stats[LinguisticObjectType.ChainFromSubject] = statsForLObjects(pack,
stats => stats.ChainsFromSubjects.Values.SelectMany(list => list).Count(),
stats => stats.ChainsFromSubjects.AverageDetectionQuality, simpleSentecesCount,
LinguisticObjectType.ChainFromSubject);
result.Stats[LinguisticObjectType.ChainFromPredicate] = statsForLObjects(pack,
stats => stats.ChainsFromPredicates.Values.SelectMany(list => list).Count(),
stats => stats.ChainsFromPredicates.AverageDetectionQuality, simpleSentecesCount,
LinguisticObjectType.ChainFromPredicate);
result.Stats[LinguisticObjectType.ChainFromMeaningPart] = statsForLObjects(pack,
stats => stats.ChainsFromMeaningParts.Values.SelectMany(list => list).Count(),
stats => stats.ChainsFromMeaningParts.AverageDetectionQuality, simpleSentecesCount,
LinguisticObjectType.ChainFromMeaningPart);
result.Stats[LinguisticObjectType.SimpleSentence] = _statsForSimpleSentences(pack, simpleSentecesCount);
result.AverageLoCount =
simpleSentences.Aggregate(0d, (sampleObjectsCount, stats) => sampleObjectsCount + stats.AllObjects.Count)/
simpleSentecesCount;
//result.AverageSentenceQuality = simpleSentences.Aggregate(0d,
// (d, stats) => d + stats.AverageDetectionQuality) / simpleSentecesCount;
result.AverageSentenceQuality = _calcAverageAverageQuality(result.Stats);
return result;
}
private static PackSummary _summaryFor(SentencesPack pack)
{
return _summaryFor(pack, _statsForLObjects);
}
private static LoSummaryStats _statsForSimpleSentences(SentencesPack pack, int simpleSentecesCount)
{
var sampleSimpleSentences =
pack.ComparisonResults.SelectMany(result => result.SimpleSentecesComparison.Objects)
.Where(o => o.MappedObjects.SampleObjects != null)
.ToList();
return new LoSummaryStats
{
AverageCount = ((double) simpleSentecesCount)/pack.Sample.Count,
AverageQuality =
sampleSimpleSentences.Aggregate(0d, (d, o) => d + o.Metrics.DetectionQuality) /
sampleSimpleSentences.Count
};
}
