public void RunPipelineTest()
{
// Creates learning api object
LearningApi api = new LearningApi(TestHelpers.GetDescriptor());
// Initialize data provider
api.UseCsvDataProvider(m_iris_data_path, ',', 1);
// Use mapper for data, which will extract (map) required columns
api.UseDefaultDataMapper();
// Use MinMax data normalizer
//api.UseMinMaxNormalizer(m_stats.Select(x => x.Min).ToArray(), m_stats.Select(x => x.Max).ToArray());
// We could also use some other normalizer like Gaus data normalizer
//api.UseGaussNormalizer(m_stats.Select(x => x.Mean).ToArray(), m_stats.Select(x => x.StDev).ToArray());
// Prepares the ML Algoritm and setup parameters
api.UseBackPropagation(1, 0.2, 1.0, null);
//start process of learning
api.Run();
// api.Train();
// api.TrainSample();
IScore status = api.GetScore();
//api.Train(vector)
return;
}
public bool InitNeuralBackPropagationTest()
{
// InitIrisMapperInJsonFormat_helper();
// Creates learning api object
LearningApi api = new LearningApi(TestHelpers.GetDescriptor());
// Initialize data provider
api.UseCsvDataProvider(m_IrisDataPath, ',', false, 1);
// Use mapper for data, which will extract (map) required columns
api.UseDefaultDataMapper();
// Use MinMax data normalizer
//api.UseMinMaxNormalizer();
// We could also use some other normalizer like Gaus data normalizer
//api.UseGaussNormalizer(m_stats.Select(x => x.Mean).ToArray(), m_stats.Select(x => x.StDev).ToArray());
// Prepares the ML Algoritm and setup parameters
api.UseBackPropagation(1, 0.2, 1.0, null);
api.Run();
IScore status = api.GetScore();
//api.Train(vector)
return(true);
}
public void MinMaxNormalization_test1()
{
// Creates learning api object
LearningApi api = new LearningApi(loadMetaData1());
//Real dataset must be defined as object type, because data can be numeric, binary and classification
api.UseActionModule <object[][], object[][]>((input, ctx) =>
{
return(GetRealDataSample());
});
//this call must be first in the pipeline
api.UseDefaultDataMapper();
//
api.UseMinMaxNormalizer();
//
var result = api.Run() as double [][];
//Test result for normalization
var expected = GetNormalizedDataSample();
for (int i = 0; i < expected.Length; i++)
{
for (int j = 0; j < expected[0].Length; j++)
{
Assert.Equal(Math.Round(result[i][j], 5), expected[i][j]);
}
}
//
return;
}
public void TestWithNormalize_MinMax()
{
// Creates learning api object
LearningApi api = new LearningApi(loadMetaData1());
//Real dataset must be defined as object type, because data can be numeric, binary and classification
api.UseActionModule <object[][], object[][]>((input, ctx) =>
{
return(getRealDataSample(@"C:\Data\First.csv"));
});
//this call must be first in the pipeline
api.UseDefaultDataMapper();
//
api.UseMinMaxNormalizer();
////use denormalizer on normalized data
//api.UseMinMaxDeNormalizer();
//
var result = api.Run() as double[][];
Helpers.WriteToCSVFile(result);
}
public void RBMDataSample1Test()
{
var dataPath = System.IO.Path.Combine(Directory.GetCurrentDirectory(), @"RestrictedBolzmannMachine2\Data\rbm_sample1.csv");
LearningApi api = new LearningApi(this.getDescriptorForRbm_sample1());
// Initialize data provider
api.UseCsvDataProvider(dataPath, ',', false, 1);
api.UseDefaultDataMapper();
api.UseRbm(0.2, 1000, 6, 3);
RbmResult score = api.Run() as RbmResult;
double[][] testData = new double[4][];
testData[0] = new double[] { 1, 1, 0, 0, 0, 0 };
testData[1] = new double[] { 0, 0, 0, 0, 1, 1 };
testData[2] = new double[] { 0, 1, 0, 0, 0, 0 };
testData[3] = new double[] { 0, 0, 0, 0, 1, 1 };
var result = api.Algorithm.Predict(testData, api.Context);
// NOT FINISHED.
//Assert.True(result[0] == 1);
//Assert.True(result[1] == 0);
//Assert.True(result[2] == 0);
//Assert.True(result[3] == 0);
//Assert.True(result[4] == 1);
//Assert.True(result[5] == 0);
}
public void Feature_and_LabelIndex_Mapping_Test2()
{
var desc = loadMetaData_with_CategoricFeature();
// Creates learning api object
LearningApi api = new LearningApi(desc);
//Real dataset must be defined as object type, because data can be numeric, binary and classification
api.UseActionModule <object[][], object[][]>((input, ctx) =>
{
return(loadRealDataSample());
});
//this call must be first in the pipeline
api.UseDefaultDataMapper();
//
var result = api.Run() as double[][];
var featureNumber = result[0].Count() - 1;//- labelcolumn
//string column is not counted because it is ignored column
//there is one category column in features so the number of features is increased with (calssCount-1)
// featureCount = columnCount- strinCoulumnCount-LabelColumn + calssCount-1
var featureCount = 4 - 1 - 1 + (3 - 1);
Assert.Equal(featureNumber, featureCount);
}
public void LogisticRegression_Test_iterations_20_learningrate_015()
{
var desc = loadMetaData();
LearningApi api = new LearningApi(desc);
//Real dataset must be defined as object type, because data can be numeric, binary and classification
api.UseActionModule <object[][], object[][]>((input, ctx) =>
{
return(loadRealDataSample());
});
// Use mapper for data, which will extract (map) required columns
api.UseDefaultDataMapper();
api.UseMinMaxNormalizer();
//run logistic regression for 10 iteration with learningRate=0.15
api.UseLogisticRegression(0.15, 20);
api.Run();
IScore score = api.GetScore();
//Errors during each iteration
Assert.Equal(Math.Round(score.Errors[0], 5), 0.24236);
Assert.Equal(Math.Round(score.Errors[1], 5), 0.23707);
Assert.Equal(Math.Round(score.Errors[2], 5), 0.23358);
Assert.Equal(Math.Round(score.Errors[3], 5), 0.23001);
Assert.Equal(Math.Round(score.Errors[4], 5), 0.22806);
Assert.Equal(Math.Round(score.Errors[5], 5), 0.22506);
Assert.Equal(Math.Round(score.Errors[6], 5), 0.22409);
Assert.Equal(Math.Round(score.Errors[7], 5), 0.22134);
Assert.Equal(Math.Round(score.Errors[8], 5), 0.22105);
Assert.Equal(Math.Round(score.Errors[9], 5), 0.21840);
Assert.Equal(Math.Round(score.Errors[10], 5), 0.21857);
Assert.Equal(Math.Round(score.Errors[11], 5), 0.21595);
Assert.Equal(Math.Round(score.Errors[12], 5), 0.21640);
Assert.Equal(Math.Round(score.Errors[13], 5), 0.21381);
Assert.Equal(Math.Round(score.Errors[14], 5), 0.21439);
Assert.Equal(Math.Round(score.Errors[15], 5), 0.21189);
Assert.Equal(Math.Round(score.Errors[16], 5), 0.21251);
Assert.Equal(Math.Round(score.Errors[17], 5), 0.21015);
Assert.Equal(Math.Round(score.Errors[18], 5), 0.21076);
Assert.Equal(Math.Round(score.Errors[19], 5), 0.20860);
//LG Model Best Found model in 20 iteration
Assert.Equal(Math.Round(score.Weights[0], 5), 0.28363);
Assert.Equal(Math.Round(score.Weights[1], 5), 0.37424);
Assert.Equal(Math.Round(score.Weights[2], 5), 1.41890);
Assert.Equal(Math.Round(score.Weights[3], 5), 1.01207);
Assert.Equal(Math.Round(score.Weights[4], 5), -0.33841);
Assert.Equal(Math.Round(score.Weights[5], 5), -0.33841);
Assert.Equal(Math.Round(score.Weights[6], 5), -1.62489);
}
public void LogisticRegression_Test_Real_Example()
{
string m_binary_data_path = @"SampleData\binary\admit_binary.csv";
var binary_path = System.IO.Path.Combine(Directory.GetCurrentDirectory(), m_binary_data_path);
LearningApi api = new LearningApi(loadMetaData1());
api.UseCsvDataProvider(binary_path, ',', false, 1);
// Use mapper for data, which will extract (map) required columns
api.UseDefaultDataMapper();
api.UseMinMaxNormalizer();
//run logistic regression for 10 iteration with learningRate=0.15
api.UseLogisticRegression(0.00012, 200);
var score = api.Run();
///**************PREDICTION AFTER MODEL IS CREATED*********////
/////define data for testing (prediction)
LearningApi apiPrediction = new LearningApi(loadMetaData1());
//Real dataset must be defined as object type, because data can be numeric, binary and classification
apiPrediction.UseActionModule <object[][], object[][]>((input, ctx) =>
{
var data = new object[5][]
{
new object[] { 660, 3.88, 2, 1 },
new object[] { 580, 3.36, 2, 0 },
new object[] { 640, 3.17, 2, 0 },
new object[] { 640, 3.51, 2, 0 },
new object[] { 800, 3.05, 2, 1 },
};
return(data);
});
// Use mapper for data, which will extract (map) required columns
apiPrediction.UseDefaultDataMapper();
apiPrediction.UseMinMaxNormalizer();
var testData = apiPrediction.Run();
//use previous trained model
var result = api.Algorithm.Predict(testData as double[][], api.Context) as LogisticRegressionResult;
//
Assert.Equal(Math.Round(result.PredictedValues[0], 0), 0);
Assert.Equal(Math.Round(result.PredictedValues[1], 0), 0);
Assert.Equal(Math.Round(result.PredictedValues[2], 0), 0);
Assert.Equal(Math.Round(result.PredictedValues[3], 0), 0);
Assert.Equal(Math.Round(result.PredictedValues[3], 0), 0);
}
public void ContinuousTrainData()
{
double[][] initialCentroids = new double[4][];
initialCentroids[0] = new double[] { 0.2, -4.0 };
initialCentroids[1] = new double[] { 0.2, -6.0 };
initialCentroids[2] = new double[] { 0.4, -4.0 };
initialCentroids[3] = new double[] { 0.4, -6.0 };
string[] attributes = new string[] { "x", "y" };
int numAttributes = attributes.Length; // 2 in this demo (x,y)
int numClusters = 4;
int maxCount = 300;
SaveLoadSettings sett;
var resp = SaveLoadSettings.JSON_Settings(@"C:\Data\Function1.json", out sett, true);
AnomalyDetectionAPI kmeanApi = new AnomalyDetectionAPI(null, numClusters);
LearningApi api = new LearningApi(loadMetaData1());
api.UseActionModule <object[][], object[][]>((input, ctx) =>
{
var rawDatalist = getRealDataSample(@"C:\Data\Function1.csv").ToList();
double[][] oldSamples;
var nn = kmeanApi.GetPreviousSamples(sett, out oldSamples);
if (oldSamples != null)
{
foreach (var old in oldSamples)
{
var row = old.Cast <object>().ToArray();
rawDatalist.Add(row);
}
}
return(rawDatalist.ToArray());
});
//this call must be first in the pipeline
api.UseDefaultDataMapper();
api.UseGaussNormalizer();
var rawData = api.Run() as double[][];
Helpers.WriteToCSVFile(rawData);
ClusteringSettings Settings = new ClusteringSettings(rawData, maxCount, numClusters, numAttributes, sett, KmeansAlgorithm: 1, InitialGuess: true, Replace: true);
AnomalyDetectionResponse response = kmeanApi.ImportNewDataForClustering(Settings);
}
public void movieRecommendationTestCRbm(int iterations, double learningRate, int visNodes, int hidNodes)
{
Debug.WriteLine($"{iterations}-{visNodes}-{hidNodes}");
LearningApi api = new LearningApi(getDescriptorForRbm(3898));
// Initialize data provider
api.UseCsvDataProvider(Path.Combine(Directory.GetCurrentDirectory(), @"RestrictedBolzmannMachine2\Data\movieDatasetTrain.csv"), ',', false, 0);
api.UseDefaultDataMapper();
double[] featureVector = new double[] { 0, 0.05, 0.1, 0.15, 0.2, 0.25, 0.3, 0.35, 0.4, 0.45, 0.5, 0.55, 0.6, 0.65, 0.7, 0.75, 0.8, 0.85 };
api.UseCRbm(featureVector, learningRate, iterations, visNodes, hidNodes);
Stopwatch watch = new Stopwatch();
watch.Start();
RbmScore score = api.Run() as RbmScore;
watch.Stop();
var hiddenNodes = score.HiddenValues;
var hiddenWeight = score.HiddenBisases;
double[] learnedFeatures = new double[hidNodes];
double[] hiddenWeights = new double[hidNodes];
for (int i = 0; i < hidNodes; i++)
{
learnedFeatures[i] = hiddenNodes[i];
hiddenWeights[i] = hiddenWeight[i];
}
StreamWriter tw = new StreamWriter($"PredictedDigit_I{iterations}_V{visNodes}_H{hidNodes}_learnedbias.txt");
foreach (var item in score.HiddenBisases)
{
tw.WriteLine(item);
}
tw.Close();
var testData = ReadData(Path.Combine(Directory.GetCurrentDirectory(), @"RestrictedBolzmannMachine2\Data\movieDatasetTest.csv"));
var result = api.Algorithm.Predict(testData, api.Context);
var predictedData = ((RbmResult)result).VisibleNodesPredictions;
var predictedHiddenNodes = ((RbmResult)result).HiddenNodesPredictions;
var acc = testData.GetHammingDistance(predictedData);
WriteDeepResult(iterations, new int[] { visNodes, hidNodes }, learningRate, acc, watch.ElapsedMilliseconds * 1000, predictedHiddenNodes);
WriteOutputMatrix(iterations, new int[] { visNodes, hidNodes }, learningRate, predictedData, testData);
}
public void Training()
{
int cnt = 0;
double[][] initialCentroids = new double[4][];
initialCentroids[0] = new double[] { 0.4, 25.0 };
initialCentroids[1] = new double[] { 0.4, 15.0 };
initialCentroids[2] = new double[] { 0.6, 15.0 };
initialCentroids[3] = new double[] { 0.6, 25.0 };
string[] attributes = new string[] { "x", "y" };
int numAttributes = attributes.Length;
int numClusters = 4;
int maxCount = 300;
ClusteringSettings clusterSettings = new ClusteringSettings(maxCount, numClusters, numAttributes, KmeansAlgorithm: 1, Replace: true);
AnomalyDetectionAPI kmeanApi = new AnomalyDetectionAPI(clusterSettings); //AnomalyDetectionAPI(clusterSettings), Constractor should not be null when run Training()
AnomalyDetectionResponse response;
// Creates learning api object
LearningApi api = new LearningApi(loadMetaData1());
api.UseActionModule <object[][], object[][]>((input, ctx) =>
{
var rawDataArray = getData(cnt);
return(rawDataArray);
});
api.UseDefaultDataMapper();
api.UseGaussNormalizer();
//
for (int i = 0; i < 15; i++)
{
cnt = i;
var rawData = api.Run() as double[][];
response = kmeanApi.Training(rawData, initialCentroids);
Helpers.WriteToCSVFile(kmeanApi.GetCentroid(), $"Data\\Centroid{i}.csv");
//response = kmeanApi.Save($"Function{i}.json");
}
}
public void smileyTestCRbm(int iterations, double learningRate, int visNodes, int hidNodes)
{
LearningApi api = new LearningApi(getDescriptorForRbm(1600));
// Initialize data provider
api.UseCsvDataProvider(Path.Combine(Directory.GetCurrentDirectory(), @"RestrictedBolzmannMachine2\Data\Smiley.csv"), ',', false, 0);
api.UseDefaultDataMapper();
double[] featureVector = new double[] { 0.1, 0.2 };
api.UseCRbm(featureVector, learningRate, iterations, visNodes, hidNodes);
Stopwatch watch = new Stopwatch();
watch.Start();
RbmScore score = api.Run() as RbmScore;
watch.Stop();
var hiddenNodes = score.HiddenValues;
var hiddenWeight = score.HiddenBisases;
double[] learnedFeatures = new double[hidNodes];
double[] hiddenWeights = new double[hidNodes];
for (int i = 0; i < hidNodes; i++)
{
learnedFeatures[i] = hiddenNodes[i];
hiddenWeights[i] = hiddenWeight[i];
}
var testData = ReadData(Path.Combine(Directory.GetCurrentDirectory(), @"RestrictedBolzmannMachine2\Data\SmileyTest.csv"));
var result = api.Algorithm.Predict(testData, api.Context);
var predictedData = ((RbmResult)result).VisibleNodesPredictions;
var predictedHiddenNodes = ((RbmResult)result).HiddenNodesPredictions;
var acc = testData.GetHammingDistance(predictedData);
var ValTest = calcDelta(predictedData, testData);
var lossTest = ValTest / (visNodes);
Debug.WriteLine($"lossTest: {lossTest}");
WriteDeepResult(iterations, new int[] { visNodes, hidNodes }, acc, watch.ElapsedMilliseconds * 1000, predictedHiddenNodes);
WriteOutputMatrix(iterations, new int[] { visNodes, hidNodes }, predictedData, testData);
}
public void ContinuousTrainData2()
{
int cnt = 0;
double[][] initialCentroids = new double[4][];
initialCentroids[0] = new double[] { 40.0, 10.0 };
initialCentroids[1] = new double[] { 20.0, 10.0 };
initialCentroids[2] = new double[] { 40.0, 20.0 };
initialCentroids[3] = new double[] { 20.0, 20.0 };
string[] attributes = new string[] { "x", "y" };
int numAttributes = attributes.Length; // 2 in this demo (x,y)
int numClusters = 4;
int maxCount = 300;
SaveLoadSettings sett;
var resp = SaveLoadSettings.JSON_Settings(@"C:\Data\Function1.json", out sett, true);
AnomalyDetectionAPI kmeanApi = new AnomalyDetectionAPI(null, numClusters, initialCentroids);
LearningApi api = new LearningApi(loadMetaData1());
api.UseActionModule <object[][], object[][]>((input, ctx) =>
{
var rawDatalist = getData(cnt);
return(rawDatalist);
});
//this call must be first in the pipeline
api.UseDefaultDataMapper();
api.UseGaussNormalizer();
for (int i = 0; i < 15; i++)
{
cnt = i;
var rawData = api.Run() as double[][];
ClusteringSettings Settings = new ClusteringSettings(rawData, maxCount, numClusters, numAttributes, sett, KmeansAlgorithm: 1, InitialGuess: true, Replace: true);
AnomalyDetectionResponse response = kmeanApi.ImportNewDataForClustering(Settings);
}
}
public void CRbm_ClassifierTest()
{
var dataPath = System.IO.Path.Combine(Directory.GetCurrentDirectory(), @"RestrictedBolzmannMachine2\Data\rbm_twoclass_sample.csv");
LearningApi api = new LearningApi(this.getDescriptorForRbmTwoClassesClassifier());
// Initialize data provider
api.UseCsvDataProvider(dataPath, ';', false, 1);
api.UseDefaultDataMapper();
double[] featureVector = new double[] { 0.1, 0.2, 0.3 };
api.UseCRbm(featureVector, 0.01, 1000, 10, 2);
RbmResult score = api.Run() as RbmResult;
double[][] testData = new double[5][];
//
// This test data contains two patterns. One is grouped at left and one at almost right.
testData[0] = new double[] { 1, 1, 1, 0, 0, 0, 0, 0, 0, 0 };
testData[1] = new double[] { 1, 0, 1, 0, 0, 0, 0, 0, 0, 0 };
testData[2] = new double[] { 0, 0, 0, 0, 0, 1, 1, 1, 0, 0 };
testData[3] = new double[] { 0, 0, 0, 0, 0, 1, 0, 1, 0, 0 };
// This will be classified as third class.
testData[4] = new double[] { 1, 1, 1, 0, 0, 1, 1, 1, 0, 0 };
var result = api.Algorithm.Predict(testData, api.Context) as RbmResult;
//
// 2 * BIT1 + BIT2 of [0] and [1] should be same.
// We don't know how RBM will classiffy data. We only expect that
// same or similar pattern of data will be assigned to the same class.
// Note, we have here two classes (two hiddne nodes).
// First and second data sample are of same class. Third and fourth are also of same class.
// Here we check first classs.
Assert.True(2 * result.HiddenNodesPredictions[0][0] + result.HiddenNodesPredictions[0][1] ==
2 * result.HiddenNodesPredictions[1][0] + result.HiddenNodesPredictions[1][1]);
// Here is test for second class.
Assert.True(2 * result.HiddenNodesPredictions[2][0] + result.HiddenNodesPredictions[2][1] ==
2 * result.HiddenNodesPredictions[3][0] + result.HiddenNodesPredictions[3][1]);
printVector("Weights", result.Weights);
}
public void LogisticsRegression_Test_iterations_10_learningrate_013()
{
var desc = loadMetaData();
LearningApi api = new LearningApi(desc);
//Real dataset must be defined as object type, because data can be numeric, binary and classification
api.UseActionModule <object[][], object[][]>((input, ctx) =>
{
return(loadRealDataSample());
});
// Use mapper for data, which will extract (map) required columns
api.UseDefaultDataMapper();
api.UseMinMaxNormalizer();
//run logistic regression for 10 iterations with learningRate=0.13
api.UseLogisticRegression(0.13, 10);
api.Run();
IScore score = api.GetScore();
//Errors during each iteration. IF the learningRate is suitable erros is descrising for every next iteration
Assert.Equal(Math.Round(score.Errors[0], 5), 0.24278);
Assert.Equal(Math.Round(score.Errors[1], 5), 0.23749);
Assert.Equal(Math.Round(score.Errors[2], 5), 0.23359);
Assert.Equal(Math.Round(score.Errors[3], 5), 0.23010);
Assert.Equal(Math.Round(score.Errors[4], 5), 0.22740);
Assert.Equal(Math.Round(score.Errors[5], 5), 0.22476);
Assert.Equal(Math.Round(score.Errors[6], 5), 0.22271);
Assert.Equal(Math.Round(score.Errors[7], 5), 0.22065);
Assert.Equal(Math.Round(score.Errors[8], 5), 0.21902);
Assert.Equal(Math.Round(score.Errors[9], 5), 0.21739);
//LG Model Best Found model in 10 iteration
Assert.Equal(Math.Round(score.Weights[0], 5), 0.06494);
Assert.Equal(Math.Round(score.Weights[1], 5), 0.21584);
Assert.Equal(Math.Round(score.Weights[2], 5), 0.89901);
Assert.Equal(Math.Round(score.Weights[3], 5), 0.51497);
Assert.Equal(Math.Round(score.Weights[4], 5), -0.30213);
Assert.Equal(Math.Round(score.Weights[5], 5), -0.30213);
Assert.Equal(Math.Round(score.Weights[6], 5), -0.85624);
}
public void DigitRecognitionDeepTest(int iterations, double learningRate, int[] layers)
{
Debug.WriteLine($"{iterations}-{String.Join("", layers)}");
LearningApi api = new LearningApi(getDescriptorForRbmTwoClassesClassifier(4096));
// Initialize data provider
// TODO: Describe Digit Dataset.
api.UseCsvDataProvider(Path.Combine(Directory.GetCurrentDirectory(), @"RestrictedBolzmannMachine2\Data\DigitDataset.csv"), ',', false, 0);
api.UseDefaultDataMapper();
api.UseDeepRbm(learningRate, iterations, layers);
Stopwatch watch = new Stopwatch();
watch.Start();
RbmDeepScore score = api.Run() as RbmDeepScore;
watch.Stop();
var testData = RbmHandwrittenDigitUnitTests.ReadData(Path.Combine(Directory.GetCurrentDirectory(), @"RestrictedBolzmannMachine2\Data\predictiondigitdata.csv"));
var result = api.Algorithm.Predict(testData, api.Context) as RbmDeepResult;
var accList = new double[result.Results.Count];
var predictions = new double[result.Results.Count][];
var predictedHiddenNodes = new double[result.Results.Count][];
var Time = watch.ElapsedMilliseconds / 1000;
int i = 0;
foreach (var item in result.Results)
{
predictions[i] = item.First().VisibleNodesPredictions;
predictedHiddenNodes[i] = item.Last().HiddenNodesPredictions;
accList[i] = testData[i].GetHammingDistance(predictions[i]);
i++;
}
RbmHandwrittenDigitUnitTests.WriteDeepResult(iterations, layers, accList, Time * 1000, predictedHiddenNodes);
/// write predicted hidden nodes.......
RbmHandwrittenDigitUnitTests.WriteOutputMatrix(iterations, layers, predictions, testData);
}
public void smileyTestDeepRbm(int iterations, double learningRate, int[] layers)
{
LearningApi api = new LearningApi(getDescriptorForRbm(1600));
// Initialize data provider
api.UseCsvDataProvider(Path.Combine(Directory.GetCurrentDirectory(), @"RestrictedBolzmannMachine2\Data\Smiley.csv"), ',', false, 0);
api.UseDefaultDataMapper();
api.UseDeepRbm(learningRate, iterations, layers);
Stopwatch watch = new Stopwatch();
watch.Start();
RbmDeepScore score = api.Run() as RbmDeepScore;
watch.Stop();
var testData = ReadData(Path.Combine(Directory.GetCurrentDirectory(), @"RestrictedBolzmannMachine2\Data\SmileyTest.csv"));
var result = api.Algorithm.Predict(testData, api.Context) as RbmDeepResult;
var accList = new double[result.Results.Count];
var predictions = new double[result.Results.Count][];
var predictedHiddenNodes = new double[result.Results.Count][];
var Time = watch.ElapsedMilliseconds / 1000;
int i = 0;
foreach (var item in result.Results)
{
predictions[i] = item.First().VisibleNodesPredictions;
predictedHiddenNodes[i] = item.Last().HiddenNodesPredictions;
accList[i] = testData[i].GetHammingDistance(predictions[i]);
i++;
}
var ValTest = calcDelta(predictions, testData);
var lossTest = ValTest / (layers.First());
Debug.WriteLine($"lossTest: {lossTest}");
WriteDeepResult(iterations, layers, accList, Time / 60.0, predictedHiddenNodes);
/// write predicted hidden nodes.......
WriteOutputMatrix(iterations, layers, predictions, testData);
}
public void Save_Test()
{
// Creates learning api object
LearningApi api = new LearningApi(TestHelpers.GetDescriptor());
// Initialize data provider
api.UseCsvDataProvider(m_IrisDataPath, ',', false, 1);
// Use mapper for data, which will extract (map) required columns
api.UseDefaultDataMapper();
// Prepares the ML Algorithm and setup parameters
api.UseBackPropagation(1, 0.2, 1.0, null);
api.Save("model1");
var loadedApi = LearningApi.Load("model1");
Assert.True(((BackPropagationNetwork)loadedApi.Algorithm).learningRate == ((BackPropagationNetwork)api.Algorithm).learningRate);
}
public void TestWithNormalize_GaussAndCentroid()
{
double[][] initialCentroids = new double[4][];
initialCentroids[0] = new double[] { 0.2, -4.0 };
initialCentroids[1] = new double[] { 0.2, -6.0 };
initialCentroids[2] = new double[] { 0.4, -4.0 };
initialCentroids[3] = new double[] { 0.4, -6.0 };
string[] attributes = new string[] { "x", "y" };
// Creates learning api object
LearningApi api = new LearningApi(loadMetaData1());
//Real dataset must be defined as object type, because data can be numeric, binary and classification
api.UseActionModule <object[][], object[][]>((input, ctx) =>
{
return(getRealDataSample(@"C:\Data\Function15.csv"));
});
//this call must be first in the pipeline
api.UseDefaultDataMapper();
api.UseGaussNormalizer();
var rawData = api.Run() as double[][];
int numAttributes = attributes.Length; // 2 in this demo (height,weight)
int numClusters = 4; // vary this to experiment (must be between 2 and number data tuples)
int maxCount = 300; // trial and error
SaveLoadSettings sett;
var resp = SaveLoadSettings.JSON_Settings(@"C:\Data\Function15.json", out sett, true);
AnomalyDetectionAPI kmeanApi = new AnomalyDetectionAPI(rawData, numClusters);
ClusteringSettings Settings = new ClusteringSettings(rawData, maxCount, numClusters, numAttributes, sett, KmeansAlgorithm: 1, InitialGuess: true, Replace: true);
AnomalyDetectionResponse response = kmeanApi.ImportNewDataForClustering(Settings);
}
public void Rbm_ClassifierTest2()
{
var dataPath = System.IO.Path.Combine(Directory.GetCurrentDirectory(), @"RestrictedBolzmannMachine2\Data\rbm_sample2.csv");
LearningApi api = new LearningApi(this.getDescriptorForRbmTwoClassesClassifier(21));
// Initialize data provider
api.UseCsvDataProvider(dataPath, ',', false, 1);
api.UseDefaultDataMapper();
api.UseDeepRbm(0.2, 10000, new int[] { 21, 9, 6, 2 });
RbmResult score = api.Run() as RbmResult;
var expectedResults = new Dictionary <int, List <double[]> >();
// All test data, which belong to the sam class.
List <double[]> testListClass1 = new List <double[]>();
List <double[]> testListClass2 = new List <double[]>();
//
// This test data contains two patterns. One is grouped at left and one at almost right.
// testListClass1 contains class 1
// testListClass2 contains class 2
testListClass1.Add(new double[] { 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 });
testListClass1.Add(new double[] { 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 });
testListClass1.Add(new double[] { 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 });
testListClass2.Add(new double[] { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0 });
testListClass2.Add(new double[] { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0 });
testListClass2.Add(new double[] { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0 });
expectedResults.Add(1, testListClass1);
expectedResults.Add(2, testListClass2);
validateClassificationResult(api, expectedResults);
}
public void LogisticsRegression_Test_iterations_10_learningrate_013()
{
var desc = loadMetaData();
LearningApi api = new LearningApi(desc);
//Real dataset must be defined as object type, because data can be numeric, binary and classification
api.UseActionModule <object[][], object[][]>((input, ctx) =>
{
return(loadRealDataSample());
});
// Use mapper for data, which will extract (map) required columns
api.UseDefaultDataMapper();
api.UseMinMaxNormalizer();
//run logistic regression for 10 iterations with learningRate=0.13
api.UseLogisticRegression(0.13, 10);
api.Run();
LogisticRegressionScore score = api.GetScore() as LogisticRegressionScore;
//Errors during each iteration. IF the learningRate is suitable errors is describing for every next iteration
Assert.Equal(Math.Round(score.Errors[0], 5), 0.24278);
Assert.Equal(Math.Round(score.Errors[1], 5), 0.23749);
Assert.Equal(Math.Round(score.Errors[2], 5), 0.23359);
Assert.Equal(Math.Round(score.Errors[3], 5), 0.23010);
Assert.Equal(Math.Round(score.Errors[4], 5), 0.22740);
Assert.Equal(Math.Round(score.Errors[5], 5), 0.22476);
Assert.Equal(Math.Round(score.Errors[6], 5), 0.22271);
Assert.Equal(Math.Round(score.Errors[7], 5), 0.22065);
Assert.Equal(Math.Round(score.Errors[8], 5), 0.21902);
Assert.Equal(Math.Round(score.Errors[9], 5), 0.21739);
//LG Model Best Found model in 10 iteration
Assert.Equal(Math.Round(score.Weights[0], 5), 0.06494);
Assert.Equal(Math.Round(score.Weights[1], 5), 0.21584);
Assert.Equal(Math.Round(score.Weights[2], 5), 0.89901);
Assert.Equal(Math.Round(score.Weights[3], 5), 0.51497);
Assert.Equal(Math.Round(score.Weights[4], 5), -0.30213);
Assert.Equal(Math.Round(score.Weights[5], 5), -0.30213);
Assert.Equal(Math.Round(score.Weights[6], 5), -0.85624);
//define data for testing (prediction)
LearningApi apiPrediction = new LearningApi(desc);
//Real dataset must be defined as object type, because data can be numeric, binary and classification
apiPrediction.UseActionModule <object[][], object[][]>((input, ctx) =>
{
var data = new object[4][]
{
new object[] { 0.202, "blue", "male", 13, "yes" },
new object[] { 0.447, "green", "female", 37, "no" },
new object[] { 0.120, "red", "male", "21", "yes" },
new object[] { 0.313, "green", "male", 22, "yes" },
};
return(data);
});
// Use mapper for data, which will extract (map) required columns
apiPrediction.UseDefaultDataMapper();
var testData = apiPrediction.Run();
//use previous trained model
var result = api.Algorithm.Predict(testData as double[][], api.Context) as LogisticRegressionResult;
Assert.Equal(Math.Round(result.PredictedValues[0], 5), 1E-05);
Assert.Equal(Math.Round(result.PredictedValues[1], 5), 0);
Assert.Equal(Math.Round(result.PredictedValues[2], 5), 0);
Assert.Equal(Math.Round(result.PredictedValues[3], 5), 0);
}
public void Rbm_ClassifierTest()
{
var dataPath = System.IO.Path.Combine(Directory.GetCurrentDirectory(), @"RestrictedBolzmannMachine2\Data\rbm_twoclass_sample.csv");
LearningApi api = new LearningApi(this.getDescriptorForRbmTwoClassesClassifier(10));
// Initialize data provider
api.UseCsvDataProvider(dataPath, ';', false, 1);
api.UseDefaultDataMapper();
api.UseDeepRbm(0.2, 1000, new int[] { 10, 2 });
RbmResult score = api.Run() as RbmResult;
double[][] trainData = new double[6][];
// All test data, which belong to the sam class.
List <double[]> testListClass1 = new List <double[]>();
List <double[]> testListClass2 = new List <double[]>();
//
// This test data contains two patterns. One is grouped at left and one at almost right.
trainData[0] = new double[] { 1, 1, 1, 0, 0, 0, 0, 0, 0, 0 };
testListClass1.Add(trainData[0]);
trainData[1] = new double[] { 1, 0, 1, 0, 0, 0, 0, 0, 0, 0 };
testListClass1.Add(trainData[1]);
trainData[2] = new double[] { 0, 1, 1, 0, 0, 0, 0, 0, 0, 0 };
testListClass1.Add(trainData[2]);
trainData[3] = new double[] { 0, 0, 0, 0, 0, 1, 1, 1, 0, 0 };
testListClass2.Add(trainData[3]);
trainData[4] = new double[] { 0, 0, 0, 0, 0, 1, 0, 1, 0, 0 };
testListClass2.Add(trainData[4]);
trainData[5] = new double[] { 0, 0, 0, 0, 0, 1, 1, 0, 0, 0 };
testListClass2.Add(trainData[5]);
// This will be classified as third class.
//testData[4] = new double[] { 1, 1, 1, 0, 0, 1, 1, 1, 0, 0 };
RbmDeepResult result = api.Algorithm.Predict(trainData, api.Context) as RbmDeepResult;
var expectedResults = new Dictionary <int, List <double[]> >();
expectedResults.Add(1, testListClass1);
expectedResults.Add(2, testListClass2);
validateClassificationResult(api, expectedResults);
//
// 2 * BIT1 + BIT2 of [0] and [1] should be same.
// We don't know how RBM will classiffy data. We only expect that
// same or similar pattern of data will be assigned to the same class.
// Note, we have here two classes (two hiddne nodes).
// First and second data sample are of the same class.
// Third and fourth are also of same class. See data.
//// Here we check first classs.
//Assert.True(result.Results[0].ToArray()[0].HiddenNodesPredictions[0] == result.Results[1].ToArray()[0].HiddenNodesPredictions[0] &&
// result.Results[0].ToArray()[0].HiddenNodesPredictions[1] == result.Results[1].ToArray()[0].HiddenNodesPredictions[1]);
//// Here is test for second class.
//Assert.True(result.Results[2].ToArray()[0].HiddenNodesPredictions[0] == result.Results[3].ToArray()[0].HiddenNodesPredictions[0] &&
// result.Results[2].ToArray()[0].HiddenNodesPredictions[1] == result.Results[3].ToArray()[0].HiddenNodesPredictions[1]);
}
