private bool RestoreKeywordClusterer()
{
List <MechanicQuery> mechanicQueries = DataSource.LoadMechanicQueries();
List <KeywordExample> trainingExamples = new List <KeywordExample>();
foreach (MechanicQuery query in mechanicQueries)
{
List <List <string> > complaintTags = PartOfSpeechTagger.Tag(
SentenceTokenizer.TokenizeSentence(query.Complaint.ToLower())
);
List <string> keywords = KeywordPredictor.PredictKeywords(complaintTags);
KeywordExample example = new KeywordExample();
foreach (string s in keywords)
{
example.AddKeyword(s);
}
trainingExamples.Add(example);
}
KeywordClusterer.Train(trainingExamples);
try
{
AnsEncoderStream streamOut = new AnsEncoderStream(
new FileStream(DefaultModelFileLocations.KEYWORD_SIMILARITY_CLUSTERER_FILE, FileMode.Create, FileAccess.Write),
1048576,
4096
);
KeywordClusterer.Save(streamOut);
streamOut.Close();
} catch (IOException)
{
return(false);
}
return(true);
}
private static bool TrainModel(KeywordPredictorFileMapping mapping)
{
IKeywordPredictor predictor = mapping.KeywordPredictorType.GetMethod("GetGlobalModel").Invoke(null, null) as IKeywordPredictor;
var keywordData = new FileSystemDataSource().LoadKeywordTrainingExamples();
var X = KeywordPredictorTrainingUtils.GenerateKeywordTrainingData(keywordData);
var Y = KeywordPredictorTrainingUtils.GenerateKeywordTargetData(keywordData);
predictor.Train(X, Y);
AnsEncoderStream stream;
try
{
stream = new AnsEncoderStream(
new FileStream(mapping.DefaultFileLocation, FileMode.Create, FileAccess.Write),
1048576,
4096);
} catch (IOException)
{
return(false);
}
using (stream)
{
bool res = predictor.Save(stream);
stream.Flush();
return(res);
}
}
private bool RestoreProblemPredictor()
{
List <MechanicQuery> mechanicQueries = DataSource.LoadMechanicQueries();
List <List <object> > trainingExamples = new List <List <object> >();
List <object> targetExamples = new List <object>();
foreach (MechanicQuery query in mechanicQueries)
{
List <object> currExample = new List <object>();
currExample.Add(query.Make);
currExample.Add(query.Model);
List <List <string> > complaintTags = PartOfSpeechTagger.Tag(
SentenceTokenizer.TokenizeSentence(query.Complaint.ToLower())
);
List <string> keywords = KeywordPredictor.PredictKeywords(complaintTags);
KeywordExample example = new KeywordExample();
foreach (string s in keywords)
{
example.AddKeyword(s);
}
List <int> groupsOut = KeywordClusterer.PredictTopNSimilarGroups(example, NUMBER_COMPLAINT_GROUPS);
foreach (int i in groupsOut)
{
currExample.Add(i);
}
trainingExamples.Add(currExample);
targetExamples.Add(query.Problem.ToLower());
}
ProblemPredictor.Train(trainingExamples, targetExamples);
try
{
AnsEncoderStream saveStream = new AnsEncoderStream(
new FileStream(DefaultModelFileLocations.KNN_QUERY_PROBLEM_PREDICTOR_FILE, FileMode.Create, FileAccess.Write),
1048576,
4096
);
ProblemPredictor.Save(saveStream);
saveStream.Flush();
saveStream.Close();
} catch (IOException)
{
return(false);
}
return(true);
}
private bool RestoreKeywordPredictor()
{
var examplesIn = DataSource.LoadKeywordTrainingExamples();
var X = KeywordPredictorTrainingUtils.GenerateKeywordTrainingData(examplesIn);
var Y = KeywordPredictorTrainingUtils.GenerateKeywordTargetData(examplesIn);
KeywordPredictor.Train(X, Y);
try
{
AnsEncoderStream stream = new AnsEncoderStream(
new FileStream(DefaultModelFileLocations.NAIVE_BAYES_KEYWORD_PREDICTOR_FILE, FileMode.Create, FileAccess.Write),
1048576,
4096);
KeywordPredictor.Save(stream);
stream.Flush();
stream.Close();
} catch (IOException)
{
return(false);
}
return(true);
}
