/**
* Returns a sub sequence of the specified {@link CharSequence}, with leading and trailing whitespace omitted. If
* the CharSequence has length zero, this returns a reference to the CharSequence. If the CharSequence represents
* and empty character sequence, this returns an empty CharSequence.
*
* @param charSequence the CharSequence to trim.
*
* @return a sub sequence with leading and trailing whitespace omitted.
*
* @throws ArgumentException if the charSequence is null.
*/
public static CharSequence trimCharSequence(CharSequence charSequence)
{
if (charSequence == null)
{
String message = Logging.getMessage("nullValue.CharSequenceIsNull");
Logging.logger().severe(message);
throw new ArgumentException(message);
}
int len = charSequence.length();
if (len == 0)
{
return(charSequence);
}
int start, end;
for (start = 0; (start < len) && charSequence.charAt(start) == ' '; start++)
{
}
for (end = charSequence.length() - 1; (end > start) && charSequence.charAt(end) == ' '; end--)
{
}
return(charSequence.subSequence(start, end + 1));
}
private static string extractTagName(CharSequence tagChars)
{
int fromOffset = 1;
if (tagChars.length() > 1 && tagChars.charAt(1) == '/')
{
fromOffset = 2;
}
for (int ci = 1; ci < tagChars.length(); ci++)
{
if (tagChars.charAt(ci) == '>' || StringUtil.isWhitespace(tagChars.charAt(ci)))
{
return(tagChars.subSequence(fromOffset, ci).ToString());
}
}
throw new InvalidFormatException("Failed to extract tag name!");
}
//Apply to one disease only
public DiseaseData GetPredictionDataCountFromPublicationsOfOneDisease(List <Publication> publications, Disease disease)
{
DiseaseData PredictionData = new DiseaseData(disease,
new RelatedEntities(
type.Symptom,
new List <RelatedEntity>()
)
);
List <RelatedEntity> relatedEntities = PredictionData.RelatedEntities.RelatedEntitiesList;
List <System.String> texts = new List <System.String>();
foreach (Publication publication in publications)
{
stringBuilder.Clear();
stringBuilder.Append(publication.title);
stringBuilder.Append(" ");
stringBuilder.Append(publication.abstractText);
stringBuilder.Append(" ");
stringBuilder.Append(publication.fullText);
string text = stringBuilder.ToString();
//Text preprocessing
text = text.ToLower();
//NAMED ENTITY RECOGNITION
Chunking chunking = chunker.chunk(text);
CharSequence cs = chunking.charSequence();
Set chunkSet = chunking.chunkSet();
Iterator iterator = chunkSet.iterator();
while (iterator.hasNext())
{
Chunk chunk = (Chunk)iterator.next();
int start = chunk.start();
int end = chunk.end();
string str = cs.subSequence(start, end).toString();
int index = relatedEntities.FindIndex(symptom => symptom.Name.Equals(str) || symptom.Synonyms.IndexOf(str) != -1);
if (index != -1)
{
//relatedEntities[index].Weight++;
relatedEntities[index].TermFrequencies.Where(tf => tf.TFType == TFType.RawCount).FirstOrDefault().Value++;
}
else
{
//Find infos from phenotypes lists
Symptom symptomFromPhetotypes = symptomsList.Where(x => x.Name.Equals(str) || x.Synonyms.IndexOf(str) != -1).FirstOrDefault();
//Add the real Symptom if it exists
if (symptomFromPhetotypes != null)
{
RelatedEntity myRealEntity = new RelatedEntity(
type.Symptom,
symptomFromPhetotypes.Name,
1.0,
symptomFromPhetotypes.Synonyms
);
myRealEntity.TermFrequencies.Where(tf => tf.TFType == TFType.RawCount).FirstOrDefault().Value = 1.0;
relatedEntities.Add(myRealEntity);
}
}
}
}
/*
* //Sort and Take only a the best symptoms (see config file)
* PredictionData.RelatedEntities.RelatedEntitiesList =
* PredictionData.RelatedEntities.RelatedEntitiesList
* .OrderByDescending(x => x.TermFrequencies.Where(tf => tf.TFType == TFType.RawCount).FirstOrDefault().Value)
* .Take(ConfigurationManager.Instance.config.MaxNumberSymptoms)
* .ToList();
*/
/*
* ///TEEEEEEEEEEEST
* extractedSymptoms = new List<Symptom>();
* for (int k = 0; k < 42; k++)
* {
* Symptom symptom = new Symptom();
* symptom.Name = "Paul";
* symptom.OrphaNumber = "caca";
* symptom.Weight = 42;
* extractedSymptoms.Add(symptom);
* }*/
return(PredictionData);
}
//Apply to one disease only
public DiseaseData GetPredictionDataFromPublicationsOfOneDisease(List <Publication> publications, Disease disease)
{
DiseaseData PredictionData = new DiseaseData(disease,
new RelatedEntities(
type.Symptom,
new List <RelatedEntity>()
)
);
List <RelatedEntity> relatedEntities = PredictionData.RelatedEntities.RelatedEntitiesList;
List <System.String> texts = new List <System.String>();
foreach (Publication publication in publications)
{
string text = publication.title + " " + publication.abstractText + " " + publication.fullText;
//Text preprocessing
text = text.ToLower();
//NAMED ENTITY RECOGNITION
Chunking chunking = chunkerHMM.chunk(text);
CharSequence cs = chunking.charSequence();
Set chunkSet = chunking.chunkSet();
Iterator iterator = chunkSet.iterator();
while (iterator.hasNext())
{
Chunk chunk = (Chunk)iterator.next();
int start = chunk.start();
int end = chunk.end();
string str = cs.subSequence(start, end).toString();
int index = relatedEntities.FindIndex(symptom => symptom.Name.Equals(str) || symptom.Synonyms.IndexOf(str) != -1);
if (index != -1)
{
relatedEntities[index].Weight++;
}
else
{
//Find infos from phenotypes lists
Symptom symptomFromPhetotypes = symptomsList.Where(x => x.Name.Equals(str) || x.Synonyms.IndexOf(str) != -1).FirstOrDefault();
//Add the real Symptom
relatedEntities.Add(
new RelatedEntity(
type.Symptom,
symptomFromPhetotypes.Name,
1.0,
symptomFromPhetotypes.Synonyms
)
);
}
}
}
//Symptom Weight Normalization from 0 to 100
for (int i = 0; i < relatedEntities.Count; i++)
{
//Find Min and Max for Normalization
double max = relatedEntities.Max(x => x.Weight);
double min = relatedEntities.Min(x => x.Weight);
//Normalization
if (max == min)//If size==1
{
if (relatedEntities[i].Weight > 100.0)
{
relatedEntities[i].Weight = 100.0;
}
}
else
{
relatedEntities[i].Weight = 100 * (relatedEntities[i].Weight - min) / (max - min);
}
}
//Sort related entities by descending weight
PredictionData.RelatedEntities.RelatedEntitiesList.OrderByDescending(x => x.Weight).ToList();
//Take only a the best symptoms (see config file)
PredictionData.RelatedEntities.RelatedEntitiesList =
PredictionData.RelatedEntities.RelatedEntitiesList
.OrderByDescending(x => x.Weight)
.Take(ConfigurationManager.Instance.config.MaxNumberSymptoms)
.ToList();
/*
* ///TEEEEEEEEEEEST
* extractedSymptoms = new List<Symptom>();
* for (int k = 0; k < 42; k++)
* {
* Symptom symptom = new Symptom();
* symptom.Name = "Paul";
* symptom.OrphaNumber = "caca";
* symptom.Weight = 42;
* extractedSymptoms.Add(symptom);
* }*/
return(PredictionData);
}
internal CharSequence getSubSequence(int beginIndex, int endIndex)
{
return(text.subSequence(beginIndex, endIndex));
}