static void TestNameEntityRecognizer()
{
string text = "WASHINGTON -- In the wake of a string of abuses by New York police officers in the 1990s, Loretta E. Lynch, " +
"the top federal prosecutor in Brooklyn, spoke forcefully about the pain of a broken trust that African-Americans " +
"felt and said the responsibility for repairing generations of miscommunication and mistrust fell to law enforcement.";
var tokens = Nltk.Tokenize.WordTokenize(text);
var posTaggedWords = Nltk.PosTag(tokens.AsNet);
// NOTE: This operation requires NumPy library for IronPython
var neChunks = Nltk.NeChunk(posTaggedWords);
BuiltIns.Print($"NER output for text: '{text}'");
BuiltIns.Print(neChunks);
}
static void TestCondFreqDist()
{
var words = Nltk.Tokenize.WordTokenize(text);
var cfdist = new Nltk.Probability.ConditionalFreqDist();
foreach (string word in words.AsNet)
{
var condition = word.Length;
cfdist[condition][word] += 1;
}
foreach (var condition in cfdist.PyObject)
{
foreach (var word in cfdist[condition])
{
BuiltIns.Print("Cond. frequency of " + word + " " + cfdist[condition].freq(word) + " [condition is word length =" + condition + "]");
}
}
}
