SemianiakaVY/BotSharp
1
0
Fork 0
Code Issues Pull requests Actions Packages Projects Releases Wiki Activity

define bin model

Browse source
This commit is contained in:
Oceania2018 2018-09-11 17:29:36 -05:00
parent f87e506417
commit aec1984ab8
8 changed files with 81 additions and 53 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

55
BotSharp.Algorithm/Bayes/MultinomiaNaiveBayes.cs
View file

@ -35,7 +35,12 @@ namespace BotSharp.Algorithm.Bayes
public List<Tuple<string, double[]>> FeatureSet { get; set; }
public double Alpha { get; set; }
private double alpha { get; set; }
public MultinomiaNaiveBayes(double alpha = 0.5)
{
this.alpha = alpha;
}
/// <summary>
/// prior probability
@ -48,7 +53,29 @@ namespace BotSharp.Algorithm.Bayes
int k = LabelDist.Count;
int Nyk = LabelDist.First(x => x.Value == Y).Freq;
return (Nyk + Alpha) / (N + k * Alpha);
return (Nyk + alpha) / (N + k * alpha);
}
public double CalCondProb(int x, string Y, double feature)
{
// posterior probability P(X1,...,Xn|Y) = Sum(P(X1|Y) +...+ P(Xn|Y)
var featuresIfY = FeatureSet.Where(fd => fd.Item1 == Y).ToList();
var matrix = ConstructMatrix(featuresIfY);
int freq = 0;
for (int y = 0; y < featuresIfY.Count; y++)
{
if (matrix[y, x] == feature)
{
freq++;
}
}
int Nyk = featuresIfY.Count;
int n = featuresIfY.Count;
int Nykx = freq;
return Math.Log((Nykx + alpha) / (Nyk + n * alpha));
}
/// <summary>
@ -57,35 +84,17 @@ namespace BotSharp.Algorithm.Bayes
/// P(X1,...,Xn|Y) = Sum(P(X1|Y) +...+ P(Xn|Y)
/// P(X, Y) = P(Y|X)P(X) = P(X|Y)P(Y) => P(Y|X) = P(Y)P(X|Y)/P(X)
/// </summary>
public double PosteriorProb(string Y, double[] features, double priorProb)
public double CalPosteriorProb(string Y, double[] features, double priorProb, Dictionary<string, double> condProbDictionary)
{
Alpha = 0.5;
int featureCount = features.Length;
double postProb = priorProb;
// posterior probability P(X1,...,Xn|Y) = Sum(P(X1|Y) +...+ P(Xn|Y)
var featuresIfY = FeatureSet.Where(fd => fd.Item1 == Y).ToList();
var matrix = ConstructMatrix(featuresIfY);
// loop features
for (int x = 0; x < featureCount; x++)
{
int freq = 0;
for (int y = 0; y < featuresIfY.Count; y++)
{
if(matrix[y, x] == features[x])
{
freq++;
}
}
int Nyk = featuresIfY.Count;
int n = featureCount;
int Nykx = freq;
postProb += Math.Log((Nykx + Alpha) / (Nyk + n * Alpha));
string key = $"{Y} f{x} {features[x]}";
postProb += condProbDictionary[key];
}
return Math.Pow(2, postProb);

14
BotSharp.Algorithm/Bayes/MultinomiaNaiveBayesModel.cs Normal file
View file

@ -0,0 +1,14 @@
using BotSharp.Algorithm.Statistics;
using System;
using System.Collections.Generic;
using System.Text;
namespace BotSharp.Algorithm.Bayes
{
public class MultinomiaNaiveBayesModel
{
public List<Probability> LabelDist { get; set; }
public Dictionary<string, double> CondProbDictionary { get; set; }
}
}

2
BotSharp.Core/Engines/BotSharp/BotSharpSVMClassifier.cs
View file

@ -129,7 +129,7 @@ namespace BotSharp.Core.Engines.BotSharp
ClassifyOptions classifyOptions = new ClassifyOptions();
classifyOptions.ModelFilePath = Path.Combine(Settings.ModelDir, "svm_classifier_model");
classifyOptions.TransformFilePath = Path.Combine(Settings.ModelDir, "transform_obj_data");
svmClassifier.Train(featureSetList, classifyOptions);
// svmClassifier.Train(featureSetList, classifyOptions);
meta.Meta = new JObject();
meta.Meta["compiled at"] = "Aug 31, 2018";

4
BotSharp.NLP.UnitTest/NaiveBayesClassifierTest.cs
View file

@ -32,9 +32,9 @@ namespace BotSharp.NLP.UnitTest
{
newSentences[i].Label = sentences[i].Label;
}
sentences = newSentences.Take(10).ToList();
sentences = newSentences.ToList();
//sentences.Shuffle();
// sentences.Shuffle();
var encoder = new OneHotEncoder();
encoder.Sentences = sentences;

2
BotSharp.NLP/Classify/ClassifierFactory.cs
View file

@ -33,7 +33,7 @@ namespace BotSharp.NLP.Classify
var sents = sentences.Select(x => new Tuple<string, double[]>(x.Label, x.Vector)).ToList();
_classifier.Train(sents, _options);
_classifier.Train(sents, new double[] { 0, 1 }, _options);
}
public List<Tuple<string, double>> Classify(Sentence sentence)

2
BotSharp.NLP/Classify/IClassifier.cs
View file

@ -12,7 +12,7 @@ namespace BotSharp.NLP.Classify
/// </summary>
/// <param name="featureSets"></param>
/// <param name="options"></param>
void Train(List<Tuple<string, double[]>> featureSets, ClassifyOptions options);
void Train(List<Tuple<string, double[]>> featureSets, double[] values, ClassifyOptions options);
/// <summary>
/// Predict by feature vector

29
BotSharp.NLP/Classify/NaiveBayesClassifier.cs
View file

@ -44,12 +44,9 @@ namespace BotSharp.NLP.Classify
private MultinomiaNaiveBayes nb = new MultinomiaNaiveBayes();
/// <summary>
/// Cache all categories' prior probability
/// </summary>
private Dictionary<string, double> PriorPropDictionary = new Dictionary<string, double>();
private Dictionary<string, double> condProbDictionary = new Dictionary<string, double>();
public void Train(List<Tuple<string, double[]>> featureSets, ClassifyOptions options)
public void Train(List<Tuple<string, double[]>> featureSets, double[] values, ClassifyOptions options)
{
labelDist = featureSets.GroupBy(x => x.Item1)
.Select(x => new Probability
@ -66,7 +63,27 @@ namespace BotSharp.NLP.Classify
labelDist.ForEach(l => l.Prob = nb.CalPriorProb(l.Value));
// calculate posterior prob
// loop features
var featureCount = nb.FeatureSet[0].Item2.Length;
labelDist.ForEach(label =>
{
for (int x = 0; x < featureCount; x++)
{
for (int v = 0; v < values.Length; v++)
{
string key = $"{label.Value} f{x} {values[v]}";
condProbDictionary[key] = nb.CalCondProb(x, label.Value, values[v]);
}
}
});
// save the model
var model = new MultinomiaNaiveBayesModel
{
LabelDist = labelDist,
CondProbDictionary = condProbDictionary
};
}
public List<Tuple<string, double>> Classify(double[] features, ClassifyOptions options)
@ -76,7 +93,7 @@ namespace BotSharp.NLP.Classify
// calculate prop
labelDist.ForEach(lf =>
{
var prob = nb.PosteriorProb(lf.Value, features, lf.Prob);
var prob = nb.CalPosteriorProb(lf.Value, features, lf.Prob, condProbDictionary);
results.Add(new Tuple<string, double>(lf.Value, prob));
});

26
BotSharp.NLP/Classify/SVMClassifier.cs
View file

@ -32,11 +32,6 @@ namespace BotSharp.NLP.Classify
/// </summary>
public class SVMClassifier : IClassifier
{
public List<Tuple<string, double>> Classify(List<Feature> features, ClassifyOptions options)
{
return null;
}
public double[][] Predict(FeaturesWithLabel featureSet, ClassifyOptions options)
{
Problem predict = new Problem();
@ -53,9 +48,14 @@ namespace BotSharp.NLP.Classify
return Prediction.PredictLabelsProbability(options.Model, scaled);
}
public void Train(List<FeaturesWithLabel> featureSets, ClassifyOptions options)
public void Train(List<Tuple<string, double[]>> featureSets, double[] values, ClassifyOptions options)
{
SVMClassifierTrain(featureSets, options);
// SVMClassifierTrain(featureSets, options);
}
public List<Tuple<string, double>> Classify(double[] features, ClassifyOptions options)
{
throw new NotImplementedException();
}
public void SVMClassifierTrain(List<FeaturesWithLabel> featureSets, ClassifyOptions options, SvmType svm = SvmType.C_SVC, KernelType kernel = KernelType.RBF, bool probability = true, string outputFile = null)
@ -154,17 +154,5 @@ namespace BotSharp.NLP.Classify
return labeledFeatureSet;
}
public void Train(List<Tuple<string, double[]>> featureSets, ClassifyOptions options)
{
throw new NotImplementedException();
}
public List<Tuple<string, double>> Classify(double[] features, ClassifyOptions options)
{
throw new NotImplementedException();
}
}
}