Add word vector interface for NB text classifier.

BotSharp.NLP.UnitTest/NaiveBayesClassifierTest.cs

@@ -47,6 +47,8 @@ namespace BotSharp.NLP.UnitTest
             var classifier = new ClassifierFactory<NaiveBayesClassifier, SentenceFeatureExtractor>(options, SupportedLanguage.English);
             
             var dataset = sentences.Split(0.9M);
+            classifier.TrainInVector(dataset.Item1);
+
             classifier.Train(dataset.Item1);
 
             int correct = 0;

BotSharp.NLP/Classify/ClassifierFactory.cs

@@ -50,5 +50,14 @@ namespace BotSharp.NLP.Classify
 
             _classifier.Train(sents, _options);
         }
+
+        public void TrainInVector(List<Sentence> sentences)
+        {
+            var vectors = new List<Tuple<string, double[]>>();
+
+            var sents = sentences.Select(x => new Tuple<string, double[]>(x.Label, x.Vector)).ToList();
+
+            _classifier.Train(sents, _options);
+        }
     }
 }

BotSharp.NLP/Classify/IClassifier.cs

@@ -10,5 +10,20 @@ namespace BotSharp.NLP.Classify
         void Train(List<FeaturesWithLabel> featureSets, ClassifyOptions options);
 
         List<Tuple<string, double>> Classify(List<Feature> features, ClassifyOptions options);
+
+        /// <summary>
+        /// Training by feature vector
+        /// </summary>
+        /// <param name="featureSets"></param>
+        /// <param name="options"></param>
+        void Train(List<Tuple<string, double[]>> featureSets, ClassifyOptions options);
+
+        /// <summary>
+        /// Predict by feature vector
+        /// </summary>
+        /// <param name="features"></param>
+        /// <param name="options"></param>
+        /// <returns></returns>
+        List<Tuple<string, double>> Classify(double[] features, ClassifyOptions options);
     }
 }

BotSharp.NLP/Classify/NaiveBayesClassifier.cs

@@ -138,6 +138,22 @@ namespace BotSharp.NLP.Classify
 
             return labelDist.Select(x => new Tuple<string, double>(x.Value, x.Prob)).ToList();
         }
+
+        public void Train(List<Tuple<string, double[]>> featureSets, ClassifyOptions options)
+        {
+            labelDist = featureSets.GroupBy(x => x.Item1)
+                .Select(x => new Probability
+                {
+                    Value = x.Key,
+                    Freq = x.Count()
+                })
+                .ToList();
+        }
+
+        public List<Tuple<string, double>> Classify(double[] features, ClassifyOptions options)
+        {
+            throw new NotImplementedException();
+        }
     }
 
     public class FeaturesWithLabel

BotSharp.NLP/Classify/SVMClassifier.cs

@@ -154,6 +154,16 @@ 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();
+        }
     }