// TODO refactor
public void TrainModel(List <string> ids, int numExamplesToClassify, int numAdjacentExamples)
{
// At least 2 ids to train on.
if (ids.Count < 2)
{
throw new Exception("At least 2 ids must be specified.");
}
var trainingBooks = _books.Where(book => ids.Contains(book.Key)).ToList();
// Classify all sentences.
var allSentences = new List <SentenceExample>();
foreach (var book in trainingBooks)
{
allSentences.AddRange(book.Value.sentences);
}
var rand = new Random();
RandomUtil.Shuffle(allSentences, rand);
// TODO -> magic number, should be hyperparam
var clusteringModel = new KMeans(4);
clusteringModel.Fit(ClassificationUtil.ConstructMatrixX(_bagOfWords,
allSentences.Take(allSentences.Count / 2).ToList()));
var clusterList = clusteringModel.Predict(ClassificationUtil.ConstructMatrixX(_bagOfWords, allSentences));
for (int i = 0; i < clusterList.Count; i++)
{
allSentences[i].classification = clusterList[i];
}
// Get random assortment of sentences to train on.
var sentencesToClassify = new List <SentenceExample>();
for (int i = 0; i < allSentences.Count && i < numExamplesToClassify; i++)
{
sentencesToClassify.Add(allSentences[i]);
}
// Get training data using sentences from user input.
var trainingData = DisplayAdjacentSentences(sentencesToClassify, numAdjacentExamples, rand);
var bookCol = new BookCollection(ids);
bookCol.sentences = allSentences;
bookCol.trainingExamples = trainingData.Item1;
bookCol.trainingLabels = trainingData.Item2;
bookCol.bagOfWords = _bagOfWords;
_bookCollections.Add(bookCol.id, bookCol);
}
void Start()
{
//Generate Data
GenerateRandomData();
//Create Classifier
kMeans = new KMeans(numOfClusters);
kMeans.Fit(tempData);
CreateSpheres();
CreateClusters();
StartCoroutine(startFit());
}
