public TextMiningEngine(PhenotypeEngine phenotypeEngine)
{
Console.WriteLine("TextMiningEngine initialization ...");
stringBuilder = new System.Text.StringBuilder();
client = new HttpClient();
symptomsList = phenotypeEngine.SymptomsList;
//////////////////
//symptomsList = new List<Symptom>();
//GetSymptomsList();
///////////////
//getSymptomsListBeta();
//Preparing dictionary
//Construct dictionnary for symptoms
TrieDictionary dict = new TrieDictionary();
foreach (Symptom pheno in symptomsList)
{
dict.addEntry(new com.aliasi.dict.DictionaryEntry(pheno.Name, "PHENOTYPE"));
foreach (string synonym in pheno.Synonyms)
{
dict.addEntry(new com.aliasi.dict.DictionaryEntry(synonym, "PHENOTYPE"));
}
}
TokenizerFactory tokenizerFactory = IndoEuropeanTokenizerFactory.INSTANCE;
WeightedEditDistance editDistance = new FixedWeightEditDistance(0, -1, -1, -1, System.Double.NaN);
double maxDistance = 0.0;
chunker = new ApproxDictionaryChunker(dict, tokenizerFactory, editDistance, maxDistance);
/*
* //////////////////////////////////////////
* //FOR HMM PREPARATION
* string pathWithoutSettings = Environment.GetEnvironmentVariable("RD_AGGREGATOR_SETTINGS").Substring(0, Environment.GetEnvironmentVariable("RD_AGGREGATOR_SETTINGS").Length - 14);
* string completePath = $"{pathWithoutSettings}\\Aggregator\\tools\\model.test";
* Console.WriteLine(completePath);
* java.io.File modelFile = new java.io.File(completePath);
* //chunkerHMM = Conversion.Converter.Convert($"{pathWithoutSettings}\\Aggregator\\tools\\model.test");
* //java.io.File modelFile = new java.io.File(@"C: \Users\CharlesCOUSYN\Desktop\qhskdjhq.txt");
* chunkerHMM = (Chunker)AbstractExternalizable.readObject(modelFile);
*
* //////////////////////////////////////////
*/
Console.WriteLine("TextMiningEngine initialization finished");
}
static void Main(string[] args)
{
//Environnement variables
//Environment.SetEnvironmentVariable("RD_AGGREGATOR_SETTINGS", @"C:\Users\Psycho\Source\Repos\RDSearch4\settings.json");
Environment.SetEnvironmentVariable("RD_AGGREGATOR_SETTINGS", @"C:\Users\CharlesCOUSYN\source\repos\Aggregator\settings.json");
var path = Environment.GetEnvironmentVariable("RD_AGGREGATOR_SETTINGS");
ConfigurationManager.Instance.Init(path);
//Obtain all symptoms/phenotypes
PhenotypeEngine phenotypeEngine = new PhenotypeEngine();
phenotypeEngine.GetSymptomsList();
/*
* //TESTED AND DONE
* //Update Orphanet (diseases/real datasets)
* OrphaEngine orphaEngine = new OrphaEngine(phenotypeEngine);
* orphaEngine.Start();*/
//Retrieving diseases from DB
List <Disease> lst_diseases = new List <Disease>();
using (var db = new MongoRepository.DiseaseRepository())
{
//lst_diseases = db.selectAll().Take(50).ToList();
lst_diseases = db.selectAll();
}
//TESTED AND DONE
/*
* //Update Publications
* PubmedEngine pubmedEngine = new PubmedEngine();
* Console.WriteLine("Starting requests at PMC this can take some time...");
* pubmedEngine.Start2(lst_diseases);
*/
/*
* //Update number of publications per disease
* Console.WriteLine("Update number of publications per disease.....");
* using (var dbDisease = new MongoRepository.DiseaseRepository())
* using (var dbPublication = new MongoRepository.PublicationRepository())
* {
* //Update all diseases
* foreach (var disease in lst_diseases)
* {
* long numberPublications = dbPublication.countForOneDisease(disease.OrphaNumber);
* disease.NumberOfPublications = (int)numberPublications;
* dbDisease.updateDisease(disease);
* }
* }
* Console.WriteLine("Update number of publications per disease finished");
*/
//Retrieving related entities by disease AND TextMine
/*
* TextMiningEngine textMiningEngine = new TextMiningEngine(phenotypeEngine);
* RecupSymptomsAndTextMine(lst_diseases, textMiningEngine);*/
//Retrieving PredictionData and RealData from DB (DiseasesData with type Symptom)
DiseasesData PredictionData = null;
DiseasesData RealData = null;
using (var dbPred = new MongoRepository.PredictionDataRepository())
using (var dbReal = new MongoRepository.RealDataRepository())
{
PredictionData = dbPred.selectByType(type.Symptom);
RealData = dbReal.selectByType(type.Symptom);
}
//Evaluation...
if (PredictionData != null && RealData != null)
{
Console.WriteLine("Evaluation....");
//Testing all combinaisons
MetaResults metaResults = Evaluator.MetaEvaluate(PredictionData, RealData, Evaluation.entities.Criterion.MeanRankRealPositives);
Evaluator.WriteMetaResultsJSONFile(metaResults);
//Having best combinaison and evaluate with it
Tuple <TFType, IDFType> tupleToTest = new Tuple <TFType, IDFType>(metaResults.bestInfos.TFType, metaResults.bestInfos.IDFType);
//Evaluate basically
Results resultsOfBestCombinaison = Evaluator.Evaluate(PredictionData, RealData, tupleToTest);
Evaluator.WriteResultsJSONFile(resultsOfBestCombinaison);
//Evaluate best combinaison with threshold search
MetaResultsWeight metaResultsWeight = Evaluator.MetaWeightEvaluate(PredictionData, RealData, tupleToTest, 0.0005, Evaluation.entities.Criterion.F_Score);
Evaluator.WriteMetaResultsWeightJSONFile(metaResultsWeight);
Console.WriteLine("Evaluation finished!");
}
Console.WriteLine("Finished :)");
Console.ReadLine();
}
