public void Setup(bool debug)
{
var readModel = new ReadModel(InputModelFile);
_weightVector = new WeightVector();
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 string Evalulate(string keyFile, string devFile, string dumpFile)
{
var keyModel = new ReadModel(keyFile);
var devModel = new ReadModel(devFile);
var dumpOutputModel = new WriteModel(dumpFile);
var keyIter = keyModel.ModelIterator().GetEnumerator();
var devIter = devModel.ModelIterator().GetEnumerator();
float expected = 0;
float correct = 0;
float found = 0;
float line = 0;
string dump;
while (keyIter.MoveNext() && devIter.MoveNext())
{
var key = keyIter.Current;
var dev = devIter.Current;
line++;
if (!key.Key.Equals(dev.Key))
{
dump = "line: " + line + " " + key.Key + " doesn't match " + dev.Key+"\r\n";
dumpOutputModel.WriteLine(dump);
dumpOutputModel.Flush();
return dump;
}
if (key.Value.Contains("LOCATION"))
{
expected++;
if (!dev.Value.Contains("LOCATION")) continue;
found++;
correct++;
}
else if (dev.Value.Contains("LOCATION"))
{
found++;
}
}
dump = "found: " + found + " expected: " + expected + " correct: " + correct +"\r\n";
dumpOutputModel.WriteLine(dump);
float precision = correct/found;
float recall = correct/expected;
float f1Score = (2*precision*recall)/(precision + recall);
dump += "precision\t recall \t f1score\t\r\n";
dumpOutputModel.WriteLine("precision\t recall \t f1score\t");
dump += precision.ToString(CultureInfo.InvariantCulture) + "\t" +
recall.ToString(CultureInfo.InvariantCulture) + "\t" +
f1Score.ToString(CultureInfo.InvariantCulture) +"\r\n";
dumpOutputModel.WriteLine(precision.ToString(CultureInfo.InvariantCulture)+"\t"+
recall.ToString(CultureInfo.InvariantCulture)+ "\t" +
f1Score.ToString(CultureInfo.InvariantCulture));
dumpOutputModel.Flush();
return dump;
}
public void Parse(string input, string output)
{
var readModel= new ReadModel(input);
var writeModel = new WriteModel(output);
var writeDevModel = new WriteModel(output+".dev");
//var tempWrite = new WriteModel(output + "tempWrite");
var temp = new List<string>();
foreach (var line in readModel.GetNextLine())
{
var newLine = RemoveTags(line);
newLine = ReplaceTags(newLine);
newLine = RemoveAllTags(newLine);
if (string.IsNullOrEmpty(newLine)) continue;
//tempWrite.WriteLine(newLine);
var split = newLine.Split(new char[] {' '});
temp.AddRange(split.ToList());
//temp.Add("##NEWLINE##");
}
//tempWrite.Flush();
bool location = false;
var lastStr = string.Empty;
foreach (var tempStr in temp)
{
var str = tempStr.Trim();
if (string.IsNullOrEmpty(str))
{
lastStr = "";
continue;
}
//if (str.Equals("##NEWLINE##"))
{
if (!location && lastStr.EndsWith(".") && !IsSalutationAbbr(lastStr))
{
lastStr = string.Empty;
writeModel.WriteLine("");
writeDevModel.WriteLine("");
continue;
}
}
if (location)
{
if (str.Equals("##ENDTAG##"))
{
location = false;
lastStr = "";
continue;
}
writeModel.WriteLine(str + " " + "LOCATION");
writeDevModel.WriteLine(str);
lastStr = str;
continue;
}
if (str.Equals("##LOCATIONSTARTTAG##"))
{
lastStr = "";
location = true;
continue;
}
if (str.Equals("##ENDTAG##"))
{
lastStr = "";
continue;
}
writeModel.WriteLine(str + " "+ "OTHER");
writeDevModel.WriteLine(str);
lastStr = str;
}
writeModel.Flush();
writeDevModel.Flush();
}