public ForwardBackwordAlgo(List<string> inputSentence, WeightVector wc, List<string> tagList)
{
_inputSentence = inputSentence;
_wc = wc;
_tagList = tagList;
_alphaDictionary = new Dictionary<int, Dictionary<string, double>>();
_betaDictionary = new Dictionary<int, Dictionary<string, double>>();
_uDictionary = new Dictionary<int, Dictionary<string, double>>();
UabDictionary = new Dictionary<int, Dictionary<string, double>>();
Z = 0;
_weightedFeaturesum = new WeightedFeatureSum(wc, inputSentence, true);
cList = new List<double>(_inputSentence.Count);
dList = new List<double>(_inputSentence.Count);
_useScaling = true;
_useLog = false;
_twoGramsList = new 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);
}
string[] split = ngram.Split(new[] { ':' });
_twoGramsList[index] = split[0] + "@#" + split[1];
index++;
}
}
public void Setup(bool debug)
{
var readModel = new ReadModel(InputModelFile);
var temp = new ReadModel(string.Concat(InputModelFile, ".featuresToK"));
_weightVector = new WeightVector(temp.GetFeatureToKdDictionary());
foreach (var pair in readModel.ModelIterator())
{
_weightVector.Add(pair);
}
_tags = new Tags(_tagList);
_viterbiForGlobalLinearModel = new ViterbiForGlobalLinearModel(_weightVector, _tags);
// read input file in a class and per line iterator.
var inputData = new ReadInputData(InputTestFile);
var writeModel = new WriteModel(_outputTestFile);
foreach (var line in inputData.GetSentence())
{
List<string> debugList;
var outputTags = _viterbiForGlobalLinearModel.Decode(line, debug, out debugList);
if (debug)
{
writeModel.WriteDataWithTagDebug(line, outputTags, debugList);
}
else
{
writeModel.WriteDataWithTag(line, outputTags);
}
}
writeModel.Flush();
}
public ViterbiForGlobalLinearModel(WeightVector weightVector, Tags tags)
{
WeightVector = weightVector;
Tags = tags;
Pi = new List<Dictionary<string, double>>();
Bp = new List<Dictionary<string, string>>();
}
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 MapFeaturesToK(string outputFile, List<string> tagList)
{
_writeModel = new WriteModel(outputFile);
_tagList = tagList;
DictFeaturesToK = new Dictionary<string, int>();
DictKToFeatures = new Dictionary<int, string>();
FeatureCount = 0;
_tags = new Tags(tagList);
}
public ForwardBackwordAlgo(List<string> inputSentence, WeightVector wc, List<string> tagList)
{
_inputSentence = inputSentence;
_wc = wc;
_tagList = tagList;
_tags = new Tags(tagList);
_alphaDictionary = new Dictionary<int, Dictionary<string, double>>();
_betaDictionary = new Dictionary<int, Dictionary<string, double>>();
_uDictionary = new Dictionary<int, Dictionary<string, double>>();
UabDictionary = new Dictionary<int, Dictionary<string, double>>();
Z = 0;
_weightedFeaturesum = new WeightedFeatureSum(wc, inputSentence, true);
}
public Perceptron(string inputFile, string outputFile, List<string> tagList)
{
_inputFile = inputFile;
_outputFile = outputFile;
var tags = new Tags(tagList);
MapFeatures = new MapFeaturesToK(inputFile, string.Concat(outputFile, ".featuresToK"), tagList);
MapFeatures.StartMapping();
WeightVector = new WeightVector(MapFeatures.DictFeaturesToK, MapFeatures.FeatureCount);
_viterbiForGlobalLinearModel = new ViterbiForGlobalLinearModel(WeightVector, tags);
InputSentences = new List<List<string>>();
TagsList = new List<List<string>>();
ReadInputs();
}
public Perceptron(List<string> inputFiles, string outputFile, List<string> tagList, bool useAvg = false)
{
_outputFile = outputFile;
_useAvg = useAvg;
var tags = new Tags(tagList);
MapFeatures = new MapFeaturesToK(string.Concat(outputFile, ".featuresToK"), tagList);
MapFeatures.StartMapping(inputFiles);
WeightVector = new WeightVector(MapFeatures.DictFeaturesToK, MapFeatures.FeatureCount);
AvgWeightVector = new WeightVector(MapFeatures.DictFeaturesToK, MapFeatures.FeatureCount);
_viterbiForGlobalLinearModel = new ViterbiForGlobalLinearModel(WeightVector, tags);
InputSentences = new List<List<string>>();
TagsList = new List<List<string>>();
//ReadInputs();
}
public void Init()
{
var readModel = new ReadModel(InputModelFile + ".preceptron");
var temp = new ReadModel(string.Concat(InputModelFile, ".featuresToK"));
var dict = temp.GetFeatureToKdDictionary();
_weightVector = new WeightVector(dict, dict.Count);
foreach (var pair in readModel.ModelIterator())
{
_weightVector.Add(pair);
}
_tags = new Tags(_tagList);
ViterbiForGLM = new ViterbiForGlobalLinearModel(_weightVector, _tags);
}
public void CreateCache()
{
Console.WriteLine(DateTime.Now + "creating Cache begin");
var ngramTags = new Tags(_tags);
foreach (var ngramTag in ngramTags.GetNGramTags(2))
{
string[] split = ngramTag.Split(new[] { ':' });
for (var lineIndex = 0; lineIndex < Sentences.Count; lineIndex++)
{
for (var pos = 0; pos < Sentences[lineIndex].Count; pos++)
{
if (pos == 0)
{
StoreFeature("*", split[1], pos, lineIndex);
}
else
{
StoreFeature(split[0], split[1], pos, lineIndex);
}
}
}
}
Console.WriteLine(DateTime.Now + "creating Cache end");
}
/*
static void Test()
{
const string inputFile = "../../data/tag.model";
//const string outputFile = "../../test.output1";
var readModel = new ReadModel(inputFile);
//var writeModel = new WriteModel(outputFile);
var weightVector = new WeightVector();
var tags = new List<string> {"I-GENE", "O"};
PrintFeatureList(tags);
foreach (var pair in readModel.ModelIterator())
{
weightVector.Add(pair);
}
//writeModel.WriteLine(line);
//writeModel.Flush();
}
*/
static void PrintFeatureList(List<string> tags)
{
var featureTags = new Tags(tags);
featureTags.Dump(3);
}
private double CalculateGradient(List<string> outputTags,
int k, Tags ngramTags, int lineIndex)
{
double output = 0;
double secondTerm = 0;
//output += weightedFeatureSum.GetAllFeatureK(outputTags, k, sentence);
output += GetAllFeatureKFromCache(outputTags, k, lineIndex);
// second term.
for (var pos = 0; pos < outputTags.Count; pos++)
{
//double sum = 0;
secondTerm += GetSecondTerm(ngramTags, lineIndex, pos, k);
//foreach (var ngramTag in ngramTags.GetNGramTags(2))
//{
// string[] split = ngramTag.Split(new[] { ':' });
// sum += (forwardBackwordAlgos[i].GetQ(j, split[0], split[1]) *
// weightedFeatureSum.GetFeatureK(split[0], split[1], j, k, sentence));
//}
//secondTerm += sum;
}
return output - secondTerm;
}
private double GetSecondTerm(Tags ngramTags,
int lineIndex, int pos, int k)
{
double sum = 0;
foreach (var ngramTag in ngramTags.GetNGramTags(2))
{
string[] split = ngramTag.Split(new[] { ':' });
if (_cache.Contains(split[0], split[1], k, pos, lineIndex))
{
sum += (forwardBackwordAlgos[lineIndex].GetQ(pos, split[0], split[1]) *
_weightVector.Get(k));
}
//else
//{
// sum += (forwardBackwordAlgos[lineIndex].GetQ(j, split[0], split[1]) *
// weightedFeatureSum.GetFeatureK(split[0], split[1], j, k, sentence));
//}
}
return sum;
}
private double Compute(int k, WeightVector weightVector)
{
double output = 0;
//double secondTerm = 0;
int lineIndex = 0;
//var weightedFeaturesum = new WeightedFeatureSum(weightVector, null, true);
if (_inputSentence.Count != _outputTagsList.Count)
{
throw new Exception("counts dont match "+ _inputSentence.Count + "with "+ _outputTagsList.Count);
}
var ngramTags = new Tags(_tagList);
// first term.
foreach (var sentence in _inputSentence)
{
var outputTags = _outputTagsList[lineIndex];
if (sentence.Count != outputTags.Count)
{
throw new Exception("compute counts dont match " + sentence.Count + "with " + outputTags.Count);
}
output += CalculateGradient(outputTags, k,
ngramTags, lineIndex);
//output += weightedFeaturesum.GetAllFeatureK(outputTags, k, sentence);
//// second term.
//for (var j = 0; j < outputTags.Count; j++)
//{
// double sum = 0;
// foreach (var ngramTag in ngramTags.GetNGramTags(2))
// {
// string[] split = ngramTag.Split(new[] {':'});
// sum += (forwardBackwordAlgos[i].GetQ(j, split[0], split[1]) *
// weightedFeaturesum.GetFeatureK(split[0], split[1], j, k, sentence));
// }
// secondTerm += sum;
//}
lineIndex++;
}
output = output - (_lambda*weightVector.Get(k));
return output;
}
