private static void Vectorize()
{
string trainDataFolder = "data";
string outputDataFolder = "vectorizedData";
_vectorizer = new Vectorizer();
_vectorizer.Vectorizing(trainDataFolder, outputDataFolder);
}
static void Main(string[] args)
{
Dictionary <string, string> config = new Dictionary <string, string>();
string relativeLocation = "..\\..\\..\\..\\";
config.Add("idPath", System.IO.Path.Combine(relativeLocation, "Experiment\\Rhino\\RhinoCorpusMapping.txt"));
config.Add("docPath", System.IO.Path.Combine(relativeLocation, "Experiment\\Rhino\\RhinoCorpus.txt"));
config.Add("qidPath", System.IO.Path.Combine(relativeLocation, "Experiment\\Rhino\\RhinoListOfFeatures.txt"));
config.Add("qdocPath", System.IO.Path.Combine(relativeLocation, "Experiment\\Rhino\\RhinoQueries.txt"));
config.Add("goldSetDir", System.IO.Path.Combine(relativeLocation, "Experiment\\Rhino\\RhinoFeaturesToGoldSetMethodsMapping"));
config.Add("effAllPath", System.IO.Path.Combine(relativeLocation, "Experiment\\EffectivenessAllMethods.txt"));
config.Add("effBestPath", System.IO.Path.Combine(relativeLocation, "Experiment\\EffectivenessBestMethods.txt"));
Console.WriteLine("Running experiment...");
Console.WriteLine("Importing corpus...");
TLArtifactsCollection corpusArtifacts = Corpus.Import(config["idPath"], config["docPath"]);
Console.WriteLine("Computing corpus vectors...");
Vectorizer corpusVectors = new Vectorizer(corpusArtifacts, "Ordinal");
Console.WriteLine("Computing corpus tf, df...");
Normalizer corpusTF = new Normalizer(corpusVectors.Vectors);
Console.WriteLine("Computing corpus idf...");
NormalizedVector corpusIDF = InverseDocumentFrequency.Compute(corpusVectors.Frequencies, corpusVectors.Vectors.Count);
Console.WriteLine("Computing corpus tf-idf...");
NormalizedVectorCollection corpusTFIDF = TFIDF.Compute(corpusTF.Vectors, corpusIDF);
Console.WriteLine("Importing queries...");
TLArtifactsCollection queryArtifacts = Corpus.Import(config["qidPath"], config["qdocPath"]);
Console.WriteLine("Computing corpus vectors...");
Vectorizer queryVectors = new Vectorizer(queryArtifacts, "Boolean");
Console.WriteLine("Computing similarities...");
TLSimilarityMatrix sims = CosineSimilarity.Compute(corpusTF.Vectors, corpusTF.Lengths, queryVectors.Vectors);
Console.WriteLine("Importing gold set...");
TLSimilarityMatrix goldset = AnswerMapping.Import(config["goldSetDir"]);
Console.WriteLine("Calculating effectiveness measures...");
Effectiveness.Export(queryArtifacts, sims, goldset, config["effAllPath"], config["effBestPath"]);
Console.WriteLine("Effectiveness measures written to:\n\t" + config["effAllPath"] + "\n\t" + config["effBestPath"]);
Console.WriteLine("Experiment complete.");
Console.WriteLine("\nPress enter key to continue...");
Console.ReadLine();
}
private static IEnumerable <CorrectionData> LoadCorpus()
{
var res = new List <CorrectionData>();
foreach (string fn in Directory.EnumerateFiles(CorpusPath, "*.txt"))
{
var lines = File.ReadAllText(fn);
var firstChar = lines[0];
if (firstChar == '*' || firstChar == '+')
{
Console.WriteLine($"File '{fn}' has annotations, process it.");
var featurizedText = Vectorizer.FeaturizeTextWithAnnotation(lines);
res.AddRange(featurizedText);
}
else
{
Console.WriteLine($"File '{fn}' doesn't have annotations, skipped.");
}
}
return(res);
}
public Scene(Settings settings, Vectorizer vectorizer)
{
this.settings = settings;
this.vectorizer = vectorizer;
}