public SimpleLinearClassifier(SimpleLinearClassifier.ILoss loss, SimpleLinearClassifier.ILearningRateSchedule learningRateSchedule, double regularizationStrength, string modelFile)
{
if (modelFile != null)
{
try
{
if (modelFile.EndsWith(".tab.gz"))
{
Timing.StartDoing("Reading " + modelFile);
this.weights = Counters.DeserializeStringCounter(modelFile);
Timing.EndDoing("Reading " + modelFile);
}
else
{
this.weights = IOUtils.ReadObjectAnnouncingTimingFromURLOrClasspathOrFileSystem(log, "Loading coref model", modelFile);
}
}
catch (Exception e)
{
throw new Exception("Error leading weights from " + modelFile, e);
}
}
else
{
this.weights = new ClassicCounter <string>();
}
this.defaultLoss = loss;
this.regularizationStrength = regularizationStrength;
this.learningRateSchedule = learningRateSchedule;
accessTimes = new ClassicCounter <string>();
examplesSeen = 0;
}
public DistSimClassifier(string filename, string format, string encoding, int distSimMaxBits, bool cased, bool numberEquivalence, string unknownWordClass)
{
this.cased = cased;
this.numberEquivalence = numberEquivalence;
this.unknownWordClass = unknownWordClass;
Timing.StartDoing("Loading distsim lexicon from " + filename);
lexicon = Generics.NewHashMap(1 << 15);
// make a reasonable starting size
bool terryKoo = "terryKoo".Equals(format);
foreach (string line in ObjectBank.GetLineIterator(filename, encoding))
{
string word;
string wordClass;
if (terryKoo)
{
string[] bits = line.Split("\\t");
word = bits[1];
wordClass = bits[0];
if (distSimMaxBits > 0 && wordClass.Length > distSimMaxBits)
{
wordClass = Sharpen.Runtime.Substring(wordClass, 0, distSimMaxBits);
}
}
else
{
// "alexClark"
string[] bits = line.Split("\\s+");
word = bits[0];
wordClass = bits[1];
}
if (!cased)
{
word = word.ToLower();
}
if (numberEquivalence)
{
word = WordShapeClassifier.WordShape(word, WordShapeClassifier.Wordshapedigits);
}
lexicon[word] = wordClass;
}
Timing.EndDoing();
}