private void ButtonSettingTrainingData_Click(object sender, EventArgs e)
{
classifier = new NaiveBayesClassifier();
var allLines = TextTrainingData.Text.Split(new char[] { '\n' }, StringSplitOptions.RemoveEmptyEntries).Select(x => x.TrimEnd('\n'));
SelectClass.Enabled = true;
classifier.LoadAttribute(
allLines.Where(x => x.StartsWith("@attribute"))
.Select(x =>
{
var name = x.Split(' ')[1].Trim();
int ia = x.LastIndexOf('{');
int ib = x.IndexOf('}', ia);
return(new NaiveBayesClassifier.AttributeData
{
AttributeName = name,
NominalOption = x.Substring(ia + 1, ib - ia - 1)
.Split(SplitChars, StringSplitOptions.RemoveEmptyEntries),
});
}));
foreach (var o in allLines.Where(x => x.StartsWith("@attribute")))
{
var name = o.Split(' ')[1].Trim();
SelectClass.Items.Add(name);
}
SelectClass.SelectedIndex = SelectClass.Items.Count - 1;
data = allLines.SkipWhile(x => !x.StartsWith("@data")).Skip(1)
.Select(x => x.Split(SplitChars, StringSplitOptions.RemoveEmptyEntries)
.Select(y => y.Trim(SplitChars)));
}
public void NaiveBayesIrisTest()
{
DataSetLoader dataSetLoader = new DataSetLoader();
Console.WriteLine(" Reading DataSet.. ");
var irisis = dataSetLoader.SelectIrises();
for (double i = 0; i < 1; i = i + 1)
{
NaiveBayesClassifier naiveBayes =
new NaiveBayesClassifier(irisis, new LinearBayesKernel(irisis));
var irisesTests = dataSetLoader.SelectIrises();
var trueCounter = 0;
var counter = 0;
foreach (var item in irisesTests)
{
var outputValue = naiveBayes.Classify(item.Item1);
if (outputValue == item.Item2)
{
trueCounter++;
}
Debug.WriteLine(string.Format("Value {0} - Predicted {1} = {2}",
item.Item2, outputValue, (outputValue == item.Item2) ? "true" : "false"));
counter++;
}
Debug.WriteLine(string.Format(" i = {0} Data {1} - True {2} Verhältnis: {3}", i,
counter.ToString(), trueCounter.ToString(), (Convert.ToDouble(trueCounter) / Convert.ToDouble(counter)).ToString()));
}
}
public void CreditDataNaiveBayesTest()
{
DataSetLoader dataSetLoader = new DataSetLoader();
Console.WriteLine(" Reading DataSet.. ");
var creditData = dataSetLoader.SelectCreditData();
NaiveBayesClassifier naiveBayes =
new NaiveBayesClassifier(creditData);
var creditDataTest = dataSetLoader.SelectCreditData();
var trueCounter = 0;
var counter = 0;
foreach (var item in creditDataTest)
{
var outputValue = naiveBayes.Classify(item.Item1);
if (outputValue == item.Item2)
{
trueCounter++;
}
Debug.WriteLine(string.Format("Value {0} - Predicted {1} = {2}",
item.Item2, outputValue, (outputValue == item.Item2) ? "true" : "false"));
counter++;
}
Debug.WriteLine(string.Format("Data {0} - True {1} Verhältnis: {2}",
counter.ToString(), trueCounter.ToString(), (Convert.ToDouble(trueCounter) / Convert.ToDouble(counter)).ToString()));
}
private static void TestNaiveBayes()
{
var data = LoadDataFromfCSV("Data.csv");
var fixedData = TableFixedData.FromTableData(data);
var samples = TableFixedData.ToSample(fixedData);
var columnsTypes = fixedData.ColumnDataTypes;
var algorithm = new NaiveBayesClassifierOld(fixedData);
var algorithm1 = new NaiveBayesClassifier(samples, fixedData.ClassesValue.Length, columnsTypes);
var dataRow = data.ToList()[2];
var className = algorithm.Compute(dataRow);
var classId = algorithm1.Compute(fixedData.GetSample(dataRow));
var className1 = fixedData.ClassesValue[classId];
int missed = 0;
for (int index = 0; index < 50; index++)
{
var row = data.ToList()[index];
var estimatedClassName = algorithm.Compute(row);
if (estimatedClassName != row.Class)
{
missed++;
}
}
}
public void AnimalClassifyMethod()
{
DataSetLoader dataSetLoader = new DataSetLoader();
var animals = dataSetLoader.SelectAnimals();
var data = dataSetLoader.CalculatePercent(50, animals);
DecisionTreeClassifier decisionTreeClassifier =
new DecisionTreeClassifier(data.Item1, new ShannonEntropySplitter());
NaiveBayesClassifier naiveBayes =
new NaiveBayesClassifier(data.Item1);
var list = new List <NetML.Classification>();
Kernel kernel = new LinearKernel();
SVMClassifier animalSVMClassifier =
new SVMClassifier(animals, kernel, 0.001, 10.0);
var neuronalAnimals = dataSetLoader.SelectNeuronalNetworkAnimals();
NeuronalNetworkClassifier neuronalNetworkClassifier =
new NeuronalNetworkClassifier(neuronalAnimals, 16, 7, 16, 500, 0.1);
list.Add(decisionTreeClassifier);
list.Add(naiveBayes);
list.Add(animalSVMClassifier);
list.Add(neuronalNetworkClassifier);
Classifier classifier = new Classifier();
classifier.Classify(list, data.Item2);
}
public void CreditDataClassifyMethod()
{
DataSetLoader dataSetLoader = new DataSetLoader();
var creditData = dataSetLoader.SelectCreditData();
var data = dataSetLoader.CalculatePercent(100, creditData);
DecisionTreeClassifier decisionTreeClassifier =
new DecisionTreeClassifier(data.Item1, new ShannonEntropySplitter());
NaiveBayesClassifier naiveBayes =
new NaiveBayesClassifier(data.Item1);
var list = new List <NetML.Classification>();
Kernel kernel = new LinearKernel();
SVMClassifier SVMClassifier =
new SVMClassifier(creditData, kernel, 0.001, 10.0);
var neuronalCreditData = dataSetLoader.SelectNeuronalNetworksCreditData();
NeuronalNetworkClassifier neuronalNetworkClassifier =
new NeuronalNetworkClassifier(neuronalCreditData, 20, 2, 20, 5000, 0.1);
list.Add(decisionTreeClassifier);
list.Add(naiveBayes);
list.Add(SVMClassifier);
//list.Add(neuronalNetworkClassifier);
Classifier classifier = new Classifier();
classifier.Classify(list, creditData);
}
public NaiveBayesLanguageIdentifier(IEnumerable <LanguageModel <string> > languageModels, int maxNGramLength, int onlyReadFirstNLines)
{
MaxNGramLength = maxNGramLength;
OnlyReadFirstNLines = onlyReadFirstNLines;
_classifier = new NaiveBayesClassifier <IEnumerable <string>, string, LanguageInfo>(
languageModels.ToDictionary(lm => lm.Language, lm => lm.Features), 1);
}
public NaiveBayesLanguageIdentifier(IEnumerable<LanguageModel<ValueString>> languageModels, int maxNGramLength, int onlyReadFirstNLines)
{
MaxNGramLength = maxNGramLength;
OnlyReadFirstNLines = onlyReadFirstNLines;
_classifier = new NaiveBayesClassifier<IEnumerable<ValueString>, ValueString, LanguageInfo>(
languageModels.ToDictionary(lm => lm.Language, lm => lm.Features), 1);
}
// Start is called before the first frame update
void Start()
{
guard = GetComponent <Guard>();
nGramPredictor = new NGramPredictor(nValue);
bayesClassifier = new NaiveBayesClassifier();
roomsEntered = 0;
lastRoomsVisited = new List <int>();
}
public void SelectFeaturesAndCheckClasification(double[,] correlationTable, int featureCount, List <List <double> > dataSet, string collectionName, string method)
{
NaiveBayesClassifier naiveBayesClassifier = new NaiveBayesClassifier();
var selectedFeatures = SelectFeatures(correlationTable, featureCount, 0.5);
var probabilityOfFeatureValues = naiveBayesClassifier.GetProbabilityOfFeatureValuesFormFile(collectionName);
CheckNewModel(selectedFeatures, dataSet, probabilityOfFeatureValues, collectionName, false, method);
var selectedFeaturesBetter = SelectFeaturesBetter(correlationTable, featureCount, 0.5);
CheckNewModel(selectedFeaturesBetter, dataSet, probabilityOfFeatureValues, collectionName, true, method);
}
public void CheckNewModel(List <IdNumber> selectedFeaturesWithCorrelation, List <List <double> > dataSet, List <ProbabilityOfFeatureValue> probabilityOfFeatureValues, string collectionName, bool better, string method)
{
NaiveBayesClassifier naiveBayesClassifier = new NaiveBayesClassifier();
var classProbabilty = naiveBayesClassifier.GetClassProbabilty(dataSet);
Console.WriteLine("classificationResult start ");
var classificationResult = naiveBayesClassifier.ClassifyTableWithSelectedFeatures(dataSet, classProbabilty, probabilityOfFeatureValues, selectedFeaturesWithCorrelation);
Console.WriteLine("classificationResult end ");
var csv = new StringBuilder();
var newLine = string.Empty;
csv.AppendLine("Wynik klasyfikacji:");
var sumPercent = 0;
Console.WriteLine("sprawdzanie korelacji");
List <bool> classToCheck = new List <bool>();
foreach (var item in dataSet[0])
{
if (item.Equals(1.00))
{
classToCheck.Add(true);
}
else
{
classToCheck.Add(false);
}
}
for (int i = 0; i < classificationResult.Count; i++)
{
newLine = $"{classificationResult[i] == classToCheck[i]} -------> {(classificationResult[i]? 1 : -1)};{dataSet[0][i]}";
if (classificationResult[i] == classToCheck[i])
{
sumPercent++;
}
csv.AppendLine(newLine);
}
csv.AppendLine("Zgodność wyników z ograinalnym zbiorem:");
csv.AppendLine($"{(double)sumPercent/ (double)classificationResult.Count * 100} %");
csv.AppendLine($"Wybrano {selectedFeaturesWithCorrelation.Count} cechy:");
foreach (var item in selectedFeaturesWithCorrelation)
{
newLine = $"Column{item.Id}";
csv.AppendLine(newLine);
}
File.WriteAllText($"E://cos//wynikiDobreDoMGR//Classification_After_FS_{(better? 2 : 1)}_{collectionName}_{method}.txt", csv.ToString());
}
// Method for initializing the AI
private void InitAI()
{
// Create two attributes and specify their possible values
enemyTypeAttrib =
new Attrib("enemyType", Enum.GetNames(typeof(EnemyType)));
speedAttrib =
new Attrib("speed", Enum.GetNames(typeof(SpeedClassification)));
// Create a naive Bayes classifier with a set of labels and a
// set of attributes
nbClassifier = new NaiveBayesClassifier(
Enum.GetNames(typeof(PlayerWeapon)),
new Attrib[] { enemyTypeAttrib, speedAttrib });
}
private void Button_Click_3(object sender, RoutedEventArgs e)
{
string collectionName = CollectionName.Text;
int featureCount = int.Parse(FeatureCount.Text);
//int featureToSelectCount = int.Parse(FeatureToSelectCount.Text);
DatabaseService databaseService = new DatabaseService();
var dataSet = databaseService.ConvertMongoColectionToListOfLists(featureCount, collectionName);
NaiveBayesClassifier naiveBayesClassifier = new NaiveBayesClassifier();
Stopwatch stopWatch = new Stopwatch();
stopWatch.Start();
naiveBayesClassifier.GenerateProbabilites(dataSet, collectionName);
stopWatch.Stop();
//var result = naiveBayesClassifier.GetProbabilityOfFeatureValuesFormFile(collectionName);
}
public void NaiveBayesGaussianTest()
{
Tuple <double[], double> tuple1 = new Tuple <double[], double>(new double[] { 5.0, 1.0, 1.0 }, 0);
Tuple <double[], double> tuple2 = new Tuple <double[], double>(new double[] { 1.0, 5.0, 1.0 }, 1);
Tuple <double[], double> tuple3 = new Tuple <double[], double>(new double[] { 1.0, 1.0, 5.0 }, 2);
List <Tuple <double[], double> > movies =
new List <Tuple <double[], double> >()
{
tuple1, tuple2, tuple3
};
NaiveBayesClassifier naiveBayes =
new NaiveBayesClassifier(movies, new GaussianBayesKernel(movies));
var result = naiveBayes.Classify(new double[] { 5.0, 1.0, 1.0 });
result = naiveBayes.Classify(new double[] { 1.0, 5.0, 1.0 });
result = naiveBayes.Classify(new double[] { 1.0, 1.0, 5.0 });
result = naiveBayes.Classify(new double[] { 0.5, 9.0, 0.1 });
result = naiveBayes.Classify(new double[] { 0.4, 0.2, 2.1 });
result = naiveBayes.Classify(new double[] { 0.3, 0.3, 2.5 });
}
public void ClassifyTest()
{
var classifier = new NaiveBayesClassifier();
var trainingData = new List <Tuple <string, IEnumerable <string> > >
{
new Tuple <string, IEnumerable <string> >("Food", new[] { "apple", "orange" }),
new Tuple <string, IEnumerable <string> >("Food", new[] { "apple", "cake", "banana" }),
new Tuple <string, IEnumerable <string> >("Animal", new[] { "cat", "dog" }),
new Tuple <string, IEnumerable <string> >("Animal", new[] { "bird", "cat", "apple" }),
};
classifier.Train(trainingData);
var category = classifier.Classify(new[] { "dog" });
Assert.AreEqual("Animal", category);
category = classifier.Classify(new[] { "apple", "banana" });
Assert.AreEqual("Food", category);
}
public ApplicationProtocolClassificationStatisticsMeter BayesianClassify(AppIdentDataSource appIdentDataSource, double trainingToVerificationRatio, double precisionTrashHold, AppIdentTestContext appIdentTestContext = null)
{
var precMeasure = new ApplicationProtocolClassificationStatisticsMeter();
//this.CreateDatasetAndTestset(appIdentDataSource, trainingToVerificationRatio, out var trainingSet, out var verificationSet);
var classifier = new NaiveBayesClassifier(appIdentDataSource.TrainingSet);
foreach (var featureVector in appIdentDataSource.VerificationSet)
{
var appTag = featureVector.Label.Replace("_", "").Replace("-", "");
featureVector.Label = "Unknown";
classifier.Normalizator.Normalize(featureVector);
var cl = classifier.ClassifierModel.Predict(featureVector, true);
if (cl.Precision > precisionTrashHold)
{
precMeasure.UpdateStatistics(cl.Label, appTag);
}
}
appIdentTestContext?.Save(precMeasure);
return(precMeasure);
}
private void btn_testDatafromFiles_Click(object sender, EventArgs e)
{
int[] countOfTrainingTweetforLanguage = { 374, 1493, 456, 12855, 971, 2169 };
FileWriter uniGramResultWriter = new FileWriter("results-unigram");
FileWriter biGramResultWriter = new FileWriter("results-bigram");
StringBuilder builderUniResult = new StringBuilder();
StringBuilder builderBiResult = new StringBuilder();
builderUniResult.Append("TweetID" + " " + "Likely Language").Append("\n");
builderBiResult.Append("TweetID" + " " + "Likely Language").Append("\n");
for (int i = 0; i < 6; i++)
for (int j = 0; j < 6; j++)
{
labelingUniMatrixFrequency[i, j] = 0.0;
labelingBiMatrixFrequency[i, j] = 0.0;
}
for (int i = 0; i < Languages.Length; i++)
{
FetchFromFolderFiles fetchFromFolder = new FetchFromFolderFiles("Testingnlp");
Hashtable languageTweetsClean = new Hashtable();
languageTweetsClean = fetchFromFolder.getTestingDataFor(Languages[i]);
NaiveBayesClassifier NBC = new NaiveBayesClassifier(countOfTrainingTweetforLanguage, totalTweet, gramDictionary);
foreach (DictionaryEntry entry in languageTweetsClean)
{
Double[] uniConfidence = NBC.ApplyBayesOnUnigram(entry.Value.ToString());
int IndexOfMaxUniConfidence = NBC.getMaxConfidence(uniConfidence);
labelingUniMatrixFrequency[i, IndexOfMaxUniConfidence] = labelingUniMatrixFrequency[i, IndexOfMaxUniConfidence] + 1;
builderUniResult.Append(entry.Key.ToString() + " " + Languages[IndexOfMaxUniConfidence]);
builderUniResult.Append("\n");
Double[] biConfidence = NBC.ApplyBayesOnBigram(entry.Value.ToString());
int IndexOfMaxBiiConfidence = NBC.getMaxConfidence(biConfidence);
labelingBiMatrixFrequency[i, IndexOfMaxBiiConfidence] = labelingBiMatrixFrequency[i, IndexOfMaxBiiConfidence] + 1;
builderBiResult.Append(entry.Key.ToString() + " " + Languages[IndexOfMaxBiiConfidence]);
builderBiResult.Append("\n");
}
}
uniGramResultWriter.resultsWriter(builderUniResult.ToString());
biGramResultWriter.resultsWriter(builderBiResult.ToString());
uniGramResultWriter.closeAnalysisWriter();
biGramResultWriter.closeAnalysisWriter();
MessageBox.Show("Done");
}
public BowNaiveBayesModel()
{
mModel = new NaiveBayesClassifier <LblT>();
}
public BowNaiveBayesModel(NaiveBayesClassifier <LblT> model)
{
mModel = Preconditions.CheckNotNull(model);
}
static void Main(string[] args)
{
List <double[]> continuousTrainData = DataWrangler.LoadContinuousDataAsync(TrainingCsv, _indexToIgnore).Result;
List <double[]> continuousTestData = DataWrangler.LoadContinuousDataAsync(TestingCsv, _indexToIgnore).Result;
// Print continuous columns for calculating elbows in external tool(https://bl.ocks.org/rpgove/0060ff3b656618e9136b)
foreach (int i in _continuousIndexes)
{
using (StreamWriter sw = new StreamWriter($"{i}.txt"))
{
sw.WriteLine(string.Join(",", continuousTrainData.Select(array => array[i])));
}
}
// Convert continuous to discrete
Dictionary <int, GaussianClusterCollection> indexClusterMapping = DataWrangler.GetIndexClustersMap(continuousTrainData, _indexElbowMap);
List <int[]> discreteTrainData = DataWrangler.ConvertContinuesToDiscrete(continuousTrainData, indexClusterMapping);
List <int[]> discreteTestData = DataWrangler.ConvertContinuesToDiscrete(continuousTestData, indexClusterMapping);
var problem = ProblemHelper.ReadProblem(discreteTrainData.Select(arr =>
{
// Move class to front as it is expected by libsvm.
int temp = arr[0];
arr[SVMSupportedClassIndex] = arr[OriginalClassIndex];
arr[OriginalClassIndex] = temp;
return(arr.Select(i => (double)i).ToList());
}).ToList());
var test = ProblemHelper.ReadProblem(discreteTestData.Select(arr =>
{
// Move class to front as it is expected by libsvm.
int temp = arr[0];
arr[SVMSupportedClassIndex] = arr[OriginalClassIndex];
arr[OriginalClassIndex] = temp;
return(arr.Select(i => (double)i).ToList());
}).ToList());
// defaults taken from documentation http://weka.sourceforge.net/doc.stable/weka/classifiers/functions/LibSVM.html
double c = 1; // default C is 1
double gamma = 1.0 / problem.l; // default gamma is 1/k
double r = 0; // default coef0 is 0
int degree = 3; // default degree is 3
Dictionary <string, Kernel> nameKernelMap = new Dictionary <string, Kernel>(StringComparer.OrdinalIgnoreCase)
{
{ "Linear", KernelHelper.LinearKernel() },
{ "Polynomial", KernelHelper.PolynomialKernel(degree, gamma, r) },
{ "Radial", KernelHelper.RadialBasisFunctionKernel(gamma) },
{ "Sigmoid", KernelHelper.SigmoidKernel(gamma, r) },
};
// Get accuracies for base comparison
// DON'T DO PARALLEL. We don't know if the underlying implementation is MT safe or not.
//Parallel.ForEach(nameKernelMap.Keys, (kernelName) =>
foreach (string kernelName in nameKernelMap.Keys)
{
Console.WriteLine($"{kernelName}: {GetSVMAccuracy(problem, test, nameKernelMap[kernelName], c)}");
}
;
// Get accuracy of with Naive Bayes
double[] classWeightPrior = new[] { 1.0, 1.0 };
double[] classPriorProbability = new[] { 0.5, 0.5 };
NaiveBayesClassifier naiveBayes = NaiveBayesClassifier.Load(discreteTrainData, SVMSupportedClassIndex, classWeightPrior, classPriorProbability);
Console.WriteLine($"Naive Bayes: {naiveBayes.GetPredictionAccuracy(discreteTestData, SVMSupportedClassIndex)}");
// Calculate SVMs Bias and Variance
List <List <int[]> > samples = Sampler.SampleData(discreteTrainData, BiasVarianceNumOfSamples);
ConcurrentDictionary <string, ConcurrentDictionary <int, ConcurrentDictionary <int, int> > > kernelInstanceClassifierPredictionsMappings = new ConcurrentDictionary <string, ConcurrentDictionary <int, ConcurrentDictionary <int, int> > >(StringComparer.OrdinalIgnoreCase);
foreach (string kernelName in nameKernelMap.Keys)
{
ConcurrentDictionary <int, ConcurrentDictionary <int, int> > instanceClassifierPredictionMappings = kernelInstanceClassifierPredictionsMappings.GetOrAdd(kernelName, new ConcurrentDictionary <int, ConcurrentDictionary <int, int> >());
for (int classifierIndex = 0; classifierIndex < BiasVarianceNumOfSamples; classifierIndex++)
{
problem = ProblemHelper.ReadProblem(samples[classifierIndex].Select(arr => arr.Select(i => (double)i).ToList()).ToList());
var svm = new C_SVC(problem, nameKernelMap[kernelName], c);
for (int instanceIndex = 0; instanceIndex < discreteTestData.Count; instanceIndex++)
{
ConcurrentDictionary <int, int> classifierPredictionMappings = instanceClassifierPredictionMappings.GetOrAdd(instanceIndex, new ConcurrentDictionary <int, int>());
test = ProblemHelper.ReadProblem(new List <List <double> > {
discreteTestData[instanceIndex].Select(i => (double)i).ToList()
});
for (int i = 0; i < test.l; i++)
{
var x = test.x[i];
var y = test.y[i];
classifierPredictionMappings.GetOrAdd(classifierIndex, (int)svm.Predict(x));
}
}
}
}
Console.WriteLine("Kernel, Bias, Variance, Accuracy");
foreach (string kernelName in nameKernelMap.Keys)
{
ConcurrentDictionary <int, ConcurrentDictionary <int, int> > instanceClassifierPredictionMappings = kernelInstanceClassifierPredictionsMappings.GetOrAdd(kernelName, new ConcurrentDictionary <int, ConcurrentDictionary <int, int> >());
Tuple <double, double, double> biasVarianceAccuracy = BiasVarianceHelper.GetBiasVarianceAccuracy(discreteTestData, SVMSupportedClassIndex, instanceClassifierPredictionMappings);
Console.WriteLine($"{kernelName}, {biasVarianceAccuracy.Item1}, {biasVarianceAccuracy.Item2}, {biasVarianceAccuracy.Item3}");
}
Console.WriteLine("Press ENTER to continue...");
Console.ReadLine();
}
public void Train(IEnumerable <Tuple <string, string> > trainingSet, int count)
{
_wordDictionary = new Dictionary <string, int>();
_classes = new Dictionary <string, int>();
DataSample[] samples = new DataSample[count];
int wordId = 0;
int classId = 0;
var trainingItemIndex = 0;
trainingSet = trainingSet.Take(count);
foreach (var trainingItem in trainingSet)
{
string[] sentences = { trainingItem.Item1 };
var classValue = trainingItem.Item2;
if (!_classes.ContainsKey(classValue))
{
_classes.Add(classValue, classId);
classId++;
}
var dataSample = new DataSample
{
ClassId = _classes[classValue]
};
var sampleDataPoints = new List <DataPoint>();
foreach (var sentence in sentences)
{
var sentenceWords = TextParser.SplitToWords(sentence);
var isNegated = false;
for (int index = 0; index < sentenceWords.Count; index++)
{
var currentWord = sentenceWords[index].ToLower();
if (currentWord.StartsWith("@"))
{
continue;
}
if (_negationWords.Contains(currentWord))
{
isNegated = !isNegated;
}
else
{
if (currentWord.EndsWith("n't"))
{
isNegated = !isNegated;
}
else
{
currentWord = isNegated ? "not_" + currentWord : currentWord;
}
if (!_wordDictionary.ContainsKey(currentWord))
{
_wordDictionary.Add(currentWord, wordId);
wordId++;
}
sampleDataPoints.Add(new DataPoint {
ColumnId = _wordDictionary[currentWord], Value = 1
});
}
}
}
dataSample.DataPoints = sampleDataPoints.ToArray();
samples[trainingItemIndex] = dataSample;
trainingItemIndex++;
}
_columnsDataTypes = new ColumnDataType[wordId];
for (var index = 0; index < wordId; index++)
{
_columnsDataTypes[index] = new ColumnDataType {
IsDiscrete = true, NumberOfCategories = 2
};
}
_naiveBayesClassifier = new NaiveBayesClassifier(samples, 2, _columnsDataTypes);
}
static void Main(string[] args)
{
// Create two attributes and specify their possible values
Attrib distance =
new Attrib("distance", new string[] { "near", "far" });
Attrib speed =
new Attrib("speed", new string[] { "slow", "fast" });
// Create a naive Bayes classifier with a set of labels and a
// set of attributes
NaiveBayesClassifier nbc = new NaiveBayesClassifier(
new string[] { "Y", "N" },
new Attrib[] { distance, speed });
// Pass a few observations to the naive Bayes classifier
nbc.Update("Y", new Dictionary <Attrib, string>()
{
{ distance, "near" },
{ speed, "slow" }
});
nbc.Update("Y", new Dictionary <Attrib, string>()
{
{ distance, "near" },
{ speed, "fast" }
});
nbc.Update("N", new Dictionary <Attrib, string>()
{
{ distance, "far" },
{ speed, "fast" }
});
nbc.Update("Y", new Dictionary <Attrib, string>()
{
{ distance, "far" },
{ speed, "fast" }
});
nbc.Update("N", new Dictionary <Attrib, string>()
{
{ distance, "near" },
{ speed, "slow" }
});
nbc.Update("Y", new Dictionary <Attrib, string>()
{
{ distance, "far" },
{ speed, "slow" }
});
nbc.Update("Y", new Dictionary <Attrib, string>()
{
{ distance, "near" },
{ speed, "fast" }
});
// Make a prediction given a set of attribute-value pairs
string prediction = nbc.Predict(new Dictionary <Attrib, string>()
{
{ distance, "far" },
{ speed, "slow" }
});
// Show prediction
Console.WriteLine($"Brake? {prediction}");
}