public ComputeGradient(List<List<string>> inputSentence, List<List<string>> tagsList,
List<string> tagList, double lambda, double learningParam, FeatureCache cache, WriteModel logger)
{
Logger = logger;
_inputSentence = inputSentence;
_outputTagsList = tagsList;
_tagList = tagList;
_lambda = lambda;
_learningParam = learningParam;
_cache = cache;
forwardBackwordAlgos = new List<ForwardBackwordAlgo>();
_weightVector = null;
_twoGramsList = new string[4];
_twoGramPair = new KeyValuePair<string, string>[4];
var ngramTags = new Tags(_tagList);
int index = 0;
foreach (var ngram in ngramTags.GetNGramTags(2))
{
if (index >= _twoGramsList.Length)
{
Array.Resize(ref _twoGramsList, index+1);
Array.Resize(ref _twoGramPair, index + 1);
}
string[] split = ngram.Split(new[] { ':' });
_twoGramsList[index] = split[0] +"@#"+ split[1];
_twoGramPair[index] = new KeyValuePair<string, string>(split[0], split[1]);
index++;
}
}
public ComputeGradient(List<List<string>> inputSentence, List<List<string>> tagsList,
List<string> tagList, double lambda, FeatureCache cache)
{
_inputSentence = inputSentence;
_outputTagsList = tagsList;
_tagList = tagList;
_lambda = lambda;
_cache = cache;
forwardBackwordAlgos = new List<ForwardBackwordAlgo>();
_weightVector = null;
}
static void TrainingTest(List<string> tags)
{
//const string modelFile = "../../data/gene.key.model";
//const string input = "../../data/gene.key";
const string modelFile = "../../data/training/tag.model.trial1";
const string input = "../../data/training/NYT_19980403_parsed.key";
string LoggerFile = "../../Logs/Log_"+DateTime.Now.ToFileTime()+".txt";
const int threadCount = 1;
var perceptron = new Perceptron(input, modelFile, tags);
perceptron.Train();
perceptron.ReMapFeatureToK();
//perceptron.Dump();
perceptron.MapFeatures.Dump();
perceptron.ReadInputs();
var featureCache = new FeatureCache(perceptron.InputSentences, tags,
perceptron.MapFeatures.DictFeaturesToK);
featureCache.CreateCache();
var logger = new WriteModel(LoggerFile);
var gradient = new ComputeGradient(perceptron.InputSentences, perceptron.TagsList,
tags, .1, featureCache, logger);
//perceptron.WeightVector.ResetAllToZero();
gradient.RunIterations(perceptron.WeightVector, 10, threadCount);
gradient.Dump(modelFile, perceptron.MapFeatures.DictKToFeatures);
}
static void TrainingTest(List<string> tags)
{
//const string modelFile = "../../data/gene.key.model";
//const string input = "../../data/gene.key";
const string modelFile = "../../data/training/tag.model.trial1";
const string input = "../../data/training/NYT_19980403_parsed.key";
var perceptron = new Perceptron(input, modelFile, tags);
perceptron.Train();
perceptron.ReMapFeatureToK();
perceptron.Dump();
perceptron.MapFeatures.Dump();
perceptron.ReadInputs();
var featureCache = new FeatureCache(perceptron.InputSentences, tags,
perceptron.MapFeatures.DictFeaturesToK);
featureCache.CreateCache();
var gradient = new ComputeGradient(perceptron.InputSentences, perceptron.TagsList,
tags, .1, featureCache);
gradient.RunIterations(perceptron.WeightVector, 10);
gradient.Dump(modelFile, perceptron.MapFeatures.DictKToFeatures);
}
