public void new_method()
{
#region doc_learn
// Suppose we would like to compute descriptive
// statistics from the following data samples:
double[][] data =
{
new double[] { 1, 52, 5 },
new double[] { 2, 12, 5 },
new double[] { 1, 65, 5 },
new double[] { 1, 25, 5 },
new double[] { 2, 62, 5 },
};
// Create the descriptive analysis
var analysis = new DescriptiveAnalysis();
// Learn the data
analysis.Learn(data);
// Query different measures
double[] means = analysis.Means;
double[] variance = analysis.Variances;
DoubleRange[] quartiles = analysis.Quartiles;
#endregion
test(analysis);
}
public void DescriptiveAnalysisConstructorTest1()
{
// Suppose we would like to compute descriptive
// statistics from the following data samples:
double[,] data =
{
{ 1, 52, 5 },
{ 2, 12, 5 },
{ 1, 65, 5 },
{ 1, 25, 5 },
{ 2, 62, 5 },
};
// Create the analysis
DescriptiveAnalysis analysis = new DescriptiveAnalysis(data);
// Compute
analysis.Compute();
// Retrieve interest measures
double[] means = analysis.Means; // { 1.4, 43.2, 5.0 }
double[] modes = analysis.Modes; // { 1.0, 52.0, 5.0 }
Assert.AreEqual(3, means.Length);
Assert.AreEqual(1.4, means[0]);
Assert.AreEqual(43.2, means[1]);
Assert.AreEqual(5.0, means[2]);
Assert.AreEqual(1.0, modes[0]);
Assert.AreEqual(52.0, modes[1]);
Assert.AreEqual(5.0, modes[2]);
}
public void new_method()
{
#region doc_learn
// Suppose we would like to compute descriptive
// statistics from the following data samples:
double[][] data =
{
new double[] { 1, 52, 5 },
new double[] { 2, 12, 5 },
new double[] { 1, 65, 5 },
new double[] { 1, 25, 5 },
new double[] { 2, 62, 5 },
};
// Create the descriptive analysis
var analysis = new DescriptiveAnalysis();
// Learn the data
analysis.Learn(data);
// Query different measures
double[] means = analysis.Means;
double[] variance = analysis.Variances;
DoubleRange[] quartiles = analysis.Quartiles;
#endregion
test(analysis);
}
public void DescriptiveAnalysisConstructorTest4()
{
double[][] data =
{
new double[] { 1, 52, 5 },
new double[] { 2, 12, 5 },
new double[] { 1, 65, 5 },
new double[] { 1, 25, 5 },
new double[] { 2, 62, 5 },
};
// Create the analysis
DescriptiveAnalysis analysis = new DescriptiveAnalysis(data);
analysis.Compute();
double[] means = analysis.Means;
double[] modes = analysis.Modes;
Assert.AreEqual(3, means.Length);
Assert.AreEqual(1.4, means[0]);
Assert.AreEqual(43.2, means[1]);
Assert.AreEqual(5.0, means[2]);
Assert.AreEqual(1.0, modes[0]);
Assert.AreEqual(52.0, modes[1]);
Assert.AreEqual(5.0, modes[2]);
Assert.AreEqual(3, analysis.ColumnNames.Length);
Assert.AreEqual("Column 0", analysis.ColumnNames[0]);
Assert.AreEqual("Column 1", analysis.ColumnNames[1]);
Assert.AreEqual("Column 2", analysis.ColumnNames[2]);
}
/// <summary>
/// Creates a Multinomial Logistic Regression Analysis.
/// </summary>
///
private void btnCreate_Click(object sender, EventArgs e)
{
if (dgvLearningSource.DataSource == null)
{
MessageBox.Show("Please load some data first.");
return;
}
// Finishes and save any pending changes to the given data
dgvLearningSource.EndEdit();
// Creates a matrix from the entire source data table
double[,] table = (dgvLearningSource.DataSource as DataTable).ToMatrix(out columnNames);
// Get only the input vector values (first two columns)
double[][] inputs = table.GetColumns(new int[] { 0, 1 }).ToArray();
// Get only the output labels (last column)
int[] outputs = table.GetColumn(2).Subtract(1).ToInt32();
// Create and compute a new Simple Descriptive Analysis
var sda = new DescriptiveAnalysis(table, columnNames);
sda.Compute();
// Show the descriptive analysis on the screen
dgvDistributionMeasures.DataSource = sda.Measures;
// Creates the Support Vector Machine for 2 input variables
mlr = new MultinomialLogisticRegressionAnalysis(inputs, outputs);
try
{
// Run
mlr.Compute();
lbStatus.Text = "Analysis complete!";
}
catch (ConvergenceException)
{
lbStatus.Text = "Convergence could not be attained. " +
"The learned machine might still be usable.";
}
createSurface(table);
// Populate details about the fitted model
tbChiSquare.Text = mlr.ChiSquare.Statistic.ToString("N5");
tbPValue.Text = mlr.ChiSquare.PValue.ToString("N5");
checkBox1.Checked = mlr.ChiSquare.Significant;
tbDeviance.Text = mlr.Deviance.ToString("N5");
tbLogLikelihood.Text = mlr.LogLikelihood.ToString("N5");
dgvCoefficients.DataSource = mlr.Coefficients;
}
public void DataBindTest()
{
double[,] data =
{
{ 1, 52, 5 },
{ 2, 12, 5 },
{ 1, 65, 5 },
{ 1, 25, 5 },
{ 2, 62, 5 },
};
DescriptiveAnalysis analysis = new DescriptiveAnalysis(data);
analysis.Compute();
var m0 = analysis.Measures[0];
var m1 = analysis.Measures[1];
var m2 = analysis.Measures[2];
Assert.AreEqual(0, m0.Index);
Assert.AreEqual(1, m1.Index);
Assert.AreEqual(2, m2.Index);
Assert.AreEqual("Column 0", m0.Name);
Assert.AreEqual("Column 1", m1.Name);
Assert.AreEqual("Column 2", m2.Name);
Assert.AreEqual(m0, analysis.Measures["Column 0"]);
Assert.AreEqual(m1, analysis.Measures["Column 1"]);
Assert.AreEqual(m2, analysis.Measures["Column 2"]);
// var box = Accord.Controls.DataGridBox.Show(analysis.Measures);
// Assert.AreEqual(21, box.DataGridView.Columns.Count);
}
public void DescriptiveAnalysisConstructorTest1()
{
// Suppose we would like to compute descriptive
// statistics from the following data samples:
double[,] data =
{
{ 1, 52, 5 },
{ 2, 12, 5 },
{ 1, 65, 5 },
{ 1, 25, 5 },
{ 2, 62, 5 },
};
// Create the analysis
DescriptiveAnalysis analysis = new DescriptiveAnalysis(data);
// Compute
analysis.Compute();
// Retrieve interest measures
double[] means = analysis.Means; // { 1.4, 43.2, 5.0 }
double[] modes = analysis.Modes; // { 1.0, 52.0, 5.0 }
Assert.AreEqual(3, means.Length);
Assert.AreEqual(1.4, means[0]);
Assert.AreEqual(43.2, means[1]);
Assert.AreEqual(5.0, means[2]);
Assert.AreEqual(1.0, modes[0]);
Assert.AreEqual(52.0, modes[1]);
Assert.AreEqual(5.0, modes[2]);
}
private ArrayDataView AnalysisData(DataTable dataTable)
{
DescriptiveAnalysis analysis;
string[] columnNames;
double[,] arrayData = dataTable.ToMatrix(out columnNames);
// Analysis Data
analysis = new DescriptiveAnalysis(arrayData, columnNames);
analysis.Compute();
double[,] analysisData = new double[0, arrayData.GetLength(1)];
analysisData = analysisData.InsertRow <double>(analysis.Distinct.ToDouble(), analysisData.GetLength(0));
analysisData = analysisData.InsertRow <double>(analysis.Means, analysisData.GetLength(0));
analysisData = analysisData.InsertRow <double>(analysis.Medians, analysisData.GetLength(0));
analysisData = analysisData.InsertRow <double>(analysis.Modes, analysisData.GetLength(0));
analysisData = analysisData.InsertRow <double>(analysis.StandardDeviations, analysisData.GetLength(0));
analysisData = analysisData.InsertRow <double>(analysis.Variances, analysisData.GetLength(0));
analysisData = analysisData.InsertRow <double>(analysis.Sums, analysisData.GetLength(0));
string[] rowNames = { "Distinct", "Means", "Medians", "Modes", "StandardDeviations", "Variances", "Sums" };
return(new ArrayDataView(analysisData, columnNames, rowNames));
}
public void DescriptiveAnalysisConstructorTest()
{
double[,] data = Matrix.Magic(3);
string[] columnNames = { "x", "y", "z" };
DescriptiveAnalysis target = new DescriptiveAnalysis(data, columnNames);
target.Compute();
Assert.AreEqual("x", target.ColumnNames[0]);
Assert.AreEqual("y", target.ColumnNames[1]);
Assert.AreEqual("z", target.ColumnNames[2]);
Assert.IsTrue(target.CorrelationMatrix.IsEqual(new double[, ]
{
{ 1.0000, -0.7559, 0.1429 },
{ -0.7559, 1.0000, -0.7559 },
{ 0.1429, -0.7559, 1.0000 },
}, 0.0001));
Assert.IsTrue(target.CovarianceMatrix.IsEqual(new double[, ]
{
{ 7, -8, 1 },
{ -8, 16, -8 },
{ 1, -8, 7 },
}, 0.00000001));
Assert.IsTrue(target.StandardScores.IsEqual(new double[, ]
{
{ 1.1339, -1.0000, 0.3780 },
{ -0.7559, 0, 0.7559 },
{ -0.3780, 1.0000, -1.1339 },
}, 0.001));
Assert.IsTrue(target.Means.IsEqual(new double[] { 5, 5, 5 }));
Assert.IsTrue(target.StandardDeviations.IsEqual(new double[] { 2.6458, 4.0000, 2.6458 }, 0.001));
Assert.IsTrue(target.Medians.IsEqual(new double[] { 4, 5, 6 }));
Assert.AreEqual(3, target.Ranges[0].Min);
Assert.AreEqual(8, target.Ranges[0].Max);
Assert.AreEqual(1, target.Ranges[1].Min);
Assert.AreEqual(9, target.Ranges[1].Max);
Assert.AreEqual(2, target.Ranges[2].Min);
Assert.AreEqual(7, target.Ranges[2].Max);
Assert.AreEqual(3, target.Samples);
Assert.AreEqual(3, target.Variables);
Assert.IsTrue(target.Source.IsEqual(Matrix.Magic(3)));
Assert.IsTrue(target.Sums.IsEqual(new double[] { 15, 15, 15 }));
Assert.IsTrue(target.Variances.IsEqual(new double[] { 7, 16, 7 }));
}
protected override void EndProcessing()
{
var d = new DescriptiveAnalysis(_data.ColumnNames.ToArray());
d.Learn(_data.ToDoubleJaggedArray());
// TODO: Convert output to prettyprint or define format data
WriteObject(d);
}
public static PerformanceResult RunConcurrentPerformanceTest(int numIterations, int degreeParallelism,
Action operation)
{
int i;
var taskList = new Task <PerformanceResult> [degreeParallelism];
long startTime = HiResTimer.Ticks;
int subIterations = numIterations / degreeParallelism;
for (i = 0; i < degreeParallelism; i++)
{
var t = new Task <PerformanceResult>(() => RunPerformanceTest(subIterations, operation, true));
taskList[i] = t;
}
for (i = 0; i < degreeParallelism; i++)
{
taskList[i].Start();
}
Task.WaitAll(taskList);
long stopTime = HiResTimer.Ticks;
var rawData = new List <double>();
for (i = 0; i < degreeParallelism; i++)
{
rawData.AddRange(taskList[i].Result.DescriptiveResult.RawData);
}
var desc = new DescriptiveAnalysis(rawData);
desc.Analyze(false);
desc.AnalyzeHistogram(cHistogramBuckets);
var res = new PerformanceResult
{
IsValid = true,
Iterations = taskList.Sum(p => p.Result.Iterations),
DegreeOfParallelism = degreeParallelism,
TotalMilliseconds = ConvertToMs(startTime, stopTime),
TotalSeconds = ConvertToSeconds(startTime, stopTime),
TotalTicks = stopTime - startTime,
DescriptiveResult = desc.Result
};
for (i = 0; i < degreeParallelism; i++)
{
taskList[i].Dispose();
}
return(res);
}
public static PerformanceResult RunConcurrentPerformanceTest(int numIterations, int degreeParallelism,
Func <bool> operation)
{
int i;
var taskList = new Task <PerformanceResult> [degreeParallelism];
int subIterations = numIterations / degreeParallelism;
for (i = 0; i < degreeParallelism; i++)
{
var t = new Task <PerformanceResult>(() => RunPerformanceTest(subIterations, operation, true));
taskList[i] = t;
}
for (i = 0; i < degreeParallelism; i++)
{
taskList[i].Start();
}
Task.WaitAll(taskList);
var rawData = new List <double>();
bool valid = true;
for (i = 0; i < degreeParallelism; i++)
{
valid &= taskList[i].Result.IsValid;
rawData.AddRange(taskList[i].Result.DescriptiveResult.RawData);
}
var desc = new DescriptiveAnalysis(rawData);
desc.Analyze(false);
desc.AnalyzeHistogram(cHistogramBuckets);
var res = new PerformanceResult
{
IsValid = valid,
TotalMilliseconds = taskList.Max(p => p.Result.TotalMilliseconds),
TotalSeconds = taskList.Max(p => p.Result.TotalSeconds),
TotalTicks = taskList.Max(p => p.Result.TotalTicks),
DescriptiveResult = desc.Result
};
for (i = 0; i < degreeParallelism; i++)
{
taskList[i].Dispose();
}
return(res);
}
private void btnRunAnalysis_Click(object sender, EventArgs e)
{
if (dgvAnalysisSource.DataSource == null)
{
MessageBox.Show("Please load some data first.");
return;
}
// Finishes and save any pending changes to the given data
dgvAnalysisSource.EndEdit();
// Creates a matrix from the source data table
double[,] sourceMatrix = (dgvAnalysisSource.DataSource as DataTable).ToMatrix(out sourceColumnNames);
// Creates the Simple Descriptive Analysis of the given source
sda = new DescriptiveAnalysis(sourceMatrix, sourceColumnNames);
sda.Compute();
// Populates statistics overview tab with analysis data
dgvStatisticCenter.DataSource = new ArrayDataView(sda.DeviationScores, sourceColumnNames);
dgvStatisticStandard.DataSource = new ArrayDataView(sda.StandardScores, sourceColumnNames);
dgvStatisticCovariance.DataSource = new ArrayDataView(sda.CovarianceMatrix, sourceColumnNames);
dgvStatisticCorrelation.DataSource = new ArrayDataView(sda.CorrelationMatrix, sourceColumnNames);
dgvDistributionMeasures.DataSource = sda.Measures;
// Creates the Principal Component Analysis of the given source
pca = new PrincipalComponentAnalysis(sda.Source,
(AnalysisMethod)cbMethod.SelectedValue);
// Compute the Principal Component Analysis
pca.Compute();
// Populates components overview with analysis data
dgvFeatureVectors.DataSource = new ArrayDataView(pca.ComponentMatrix);
dgvPrincipalComponents.DataSource = pca.Components;
dgvProjectionComponents.DataSource = pca.Components;
numComponents.Maximum = pca.Components.Count;
numComponents.Value = 1;
numThreshold.Value = (decimal)pca.Components[0].CumulativeProportion * 100;
CreateComponentCumulativeDistributionGraph(graphCurve);
CreateComponentDistributionGraph(graphShare);
}
/// <summary>
/// Launched when the user clicks the "Run analysis" button.
/// </summary>
///
private void btnCompute_Click(object sender, EventArgs e)
{
// Save any pending changes
dgvAnalysisSource.EndEdit();
if (dgvAnalysisSource.DataSource == null)
{
MessageBox.Show("Please load some data using File > Open!");
return;
}
// Create a matrix from the source data table
double[,] sourceMatrix = (dgvAnalysisSource.DataSource as DataTable).ToMatrix(out columnNames);
// Create and compute a new Simple Descriptive Analysis
sda = new DescriptiveAnalysis(sourceMatrix, columnNames);
sda.Compute();
// Show the descriptive analysis on the screen
dgvDistributionMeasures.DataSource = sda.Measures;
// Populates statistics overview tab with analysis data
dgvStatisticCenter.DataSource = new ArrayDataView(sda.DeviationScores, columnNames);
dgvStatisticStandard.DataSource = new ArrayDataView(sda.StandardScores, columnNames);
dgvStatisticCovariance.DataSource = new ArrayDataView(sda.CovarianceMatrix, columnNames);
dgvStatisticCorrelation.DataSource = new ArrayDataView(sda.CorrelationMatrix, columnNames);
AnalysisMethod method = (AnalysisMethod)cbMethod.SelectedValue;
// Create the Principal Component Analysis of the data
pca = new PrincipalComponentAnalysis(sda.Source, method);
pca.Compute(); // Finally, compute the analysis!
// Populate components overview with analysis data
dgvFeatureVectors.DataSource = new ArrayDataView(pca.ComponentMatrix);
dgvPrincipalComponents.DataSource = pca.Components;
dgvProjectionComponents.DataSource = pca.Components;
distributionView.DataSource = pca.Components;
cumulativeView.DataSource = pca.Components;
numComponents.Maximum = pca.Components.Count;
numComponents.Value = 1;
numThreshold.Value = (decimal)pca.Components[0].CumulativeProportion * 100;
}
private string outDescripAnalysis(Sitio s, DescriptiveAnalysis da)
{
StringBuilder sb = new StringBuilder();
sb.Append(s.name + ",");
sb.Append(s.gridPoints.Count + ",");
sb.Append(da.Means[0] + ",");
sb.Append(da.Medians[0] + ",");
sb.Append(da.Modes[0] + ",");
sb.Append(da.Ranges[0].Min + ",");
sb.Append(da.Ranges[0].Max + ",");
return(sb.ToString());
}
public KPCAResult Analyze()
{
string[] columnNames;
double[,] inputDataMatrix = options.InputData.ToMatrix(out columnNames);
var da = new DescriptiveAnalysis(inputDataMatrix, columnNames);
da.Compute();
IKernel kernel = null;
switch (options.KpcaKernel)
{
case KPCAKernelKind.Gaussian:
kernel = new Gaussian(options.Sigma.Value);
break;
case KPCAKernelKind.Polynomial:
kernel = new Polynomial(options.Degree.Value, options.Constant.Value);
break;
}
double[,] inputs = inputDataMatrix.GetColumns(0, 1);
var kpca = new KernelPrincipalComponentAnalysis(inputs, kernel, options.Method);
kpca.Center = options.Center;
kpca.Compute();
double[,] result;
if (kpca.Components.Count >= 2)
{
result = kpca.Transform(inputs, 2);
}
else
{
result = kpca.Transform(inputs, 1);
result = result.InsertColumn(Matrix.Vector(result.GetLength(0), 0.0));
}
//double[,] points = result.InsertColumn(inputDataMatrix.GetColumn(2));
return(new KPCAResult(options.InputData,
da.DeviationScores,
da.StandardScores,
columnNames,
options.Method,
da.Measures,
inputDataMatrix,
kpca.ComponentMatrix,
kpca.Components));
}
public void DescriptiveAnalysisConstructorTest4()
{
double[][] data =
{
new double[] { 1, 52, 5 },
new double[] { 2, 12, 5 },
new double[] { 1, 65, 5 },
new double[] { 1, 25, 5 },
new double[] { 2, 62, 5 },
};
// Create the analysis
DescriptiveAnalysis analysis = new DescriptiveAnalysis(data);
analysis.Compute();
test(analysis);
}
/// <summary>
/// Tests whether the means of two samples are different.
/// </summary>
/// <param name="sample1">The first sample.</param>
/// <param name="sample2">The second sample.</param>
/// <param name="hypothesizedDifference">The hypothesized sample difference.</param>
/// <param name="assumeEqualVariances">True to assume equal variances, false otherwise. Default is true.</param>
/// <param name="alternate">The alternative hypothesis (research hypothesis) to test.</param>
public TwoSampleTTest(List <double> sample1, List <double> sample2,
bool assumeEqualVariances = true, double hypothesizedDifference = 0,
TwoSampleHypothesis alternate = TwoSampleHypothesis.ValuesAreDifferent)
{
// References: http://en.wikipedia.org/wiki/Student's_t-test#Worked_examples
var s1 = new DescriptiveAnalysis(sample1);
var s2 = new DescriptiveAnalysis(sample2);
s1.Analyze(false);
s2.Analyze(false);
var r1 = s1.Result;
var r2 = s2.Result;
Compute(r1.Mean, r1.Variance, r1.Count, r2.Mean, r2.Variance, r2.Count,
hypothesizedDifference, assumeEqualVariances, alternate);
}
public static PerformanceResult RunPerformanceTest(int numIterations, Func <bool> operation,
bool isParallel = false)
{
bool isResultValid = true;
var measures = new List <double>(numIterations);
// grab the start time
long startTime = HiResTimer.Ticks;
// Same operation as the functional test, we just
// do a lot of them.
for (int i = 0; ((i < numIterations) && (isResultValid)); i++)
{
long aStart = HiResTimer.Ticks;
isResultValid &= (operation());
long aStop = HiResTimer.Ticks;
if (isResultValid)
{
measures.Add(ConvertToMs(aStart, aStop));
}
}
// grab the stop time
long stopTime = HiResTimer.Ticks;
var descriptive = new DescriptiveAnalysis(measures);
descriptive.Analyze(isParallel);
if (!isParallel)
{
descriptive.AnalyzeHistogram(cHistogramBuckets);
}
// If they all worked, we can report a valid result.
// If they didn't then we call the perf test inconclusive.
return(new PerformanceResult
{
IsValid = isResultValid,
TotalSeconds = ConvertToSeconds(startTime, stopTime),
TotalMilliseconds = ConvertToMs(startTime, stopTime),
TotalTicks = (stopTime - startTime),
DescriptiveResult = descriptive.Result
});
}
public void DescriptiveAnalysisConstructorTest1()
{
// Suppose we would like to compute descriptive
// statistics from the following data samples:
double[,] data =
{
{ 1, 52, 5 },
{ 2, 12, 5 },
{ 1, 65, 5 },
{ 1, 25, 5 },
{ 2, 62, 5 },
};
// Create the analysis
DescriptiveAnalysis analysis = new DescriptiveAnalysis(data);
// Compute
analysis.Compute();
test(analysis);
}
public PCAResult Analyze()
{
string[] columnNames;
double[,] inputMatrix = options.InputData.ToMatrix(out columnNames);
var da = new DescriptiveAnalysis(inputMatrix, columnNames);
da.Compute();
var pca = new PrincipalComponentAnalysis(da.Source, options.Method);
pca.Compute();
return(new PCAResult(options.InputData,
da.DeviationScores,
da.StandardScores,
columnNames,
options.Method,
da.Measures,
da.CorrelationMatrix,
da.CovarianceMatrix,
pca.ComponentMatrix,
pca.Components));
}
public void DescriptiveAnalysisConstructorTest1()
{
// Suppose we would like to compute descriptive
// statistics from the following data samples:
double[,] data =
{
{ 1, 52, 5 },
{ 2, 12, 5 },
{ 1, 65, 5 },
{ 1, 25, 5 },
{ 2, 62, 5 },
};
// Create the analysis
DescriptiveAnalysis analysis = new DescriptiveAnalysis(data);
// Compute
analysis.Compute();
test(analysis);
}
private void zTest(List <double> scores, double hypothesismean)
{
// Creates the Simple Descriptive Analysis of the given source
DescriptiveAnalysis da = new DescriptiveAnalysis(scores.ToArray());
int sampleSize = scores.Count;
double sampleMean = da.Means[0];
double standardDeviation = da.StandardDeviations[0];
double hypothesizedMean = hypothesismean;
ZTest test = new ZTest(sampleMean, standardDeviation, sampleSize,
hypothesizedMean, OneSampleHypothesis.ValueIsSmallerThanHypothesis);
// Now, we can check whether this result would be
// unlikely under a standard significance level:
bool significant = test.Significant;
// We can also check the test statistic and its P-Value
double statistic = test.Statistic;
double pvalue = test.PValue;
}
internal void compute()
{
// Create and compute a new Simple Descriptive Analysis
var sda = new DescriptiveAnalysis(_data, _columnNames);
sda.Compute();
// Create the Principal Component Analysis of the data
_pca = new PrincipalComponentAnalysis(sda.Source, _configuration.Method);
_pca.Compute();
if (_configuration.PCAExportUseForcedNumComponents &&
(_pca.Components.Count > _configuration.PCAExportForcedNumComponents))
{
_transformedData = _pca.Transform(_data, _configuration.PCAExportForcedNumComponents);
}
else
{
_transformedData = _pca.Transform(_data, _pca.Components.Count);
}
}
/// <summary>
/// Constructs a Z test.
/// </summary>
/// <param name="sample1">The first data sample.</param>
/// <param name="sample2">The second data sample.</param>
/// <param name="hypothesizedDifference">The hypothesized sample difference.</param>
/// <param name="alternate">The alternative hypothesis (research hypothesis) to test.</param>
public TwoSampleZTest(List <double> sample1, List <double> sample2, double hypothesizedDifference = 0,
TwoSampleHypothesis alternate = TwoSampleHypothesis.ValuesAreDifferent)
{
int samples1 = sample1.Count;
int samples2 = sample2.Count;
if (samples1 < 30 || samples2 < 30)
{
Trace.TraceWarning(
"Warning: running a Z test for less than 30 samples. Consider running a Student's T Test instead.");
}
var s1 = new DescriptiveAnalysis(sample1);
var s2 = new DescriptiveAnalysis(sample2);
s1.Analyze(false);
s2.Analyze(false);
var r1 = s1.Result;
var r2 = s2.Result;
Compute(r1.Mean, r2.Mean, r1.Variance / r1.Count, r2.Variance / r2.Count,
hypothesizedDifference, alternate);
}
public void DescriptiveAnalysisConstructorTest3()
{
// Suppose we would like to compute descriptive
// statistics from the following data samples:
double[] data = { 52, 12, 65, 25, 62, 12 };
// Create the analysis
DescriptiveAnalysis analysis = new DescriptiveAnalysis(data);
// Compute
analysis.Compute();
var columnNames = analysis.ColumnNames;
var correlation = analysis.CorrelationMatrix;
var covariance = analysis.CovarianceMatrix;
var deviationScores = analysis.DeviationScores;
var distinct = analysis.Distinct;
var kurtosis = analysis.Kurtosis;
var means = analysis.Means;
var medians = analysis.Medians;
var modes = analysis.Modes;
var ranges = analysis.Ranges;
var samples = analysis.Samples;
var skewness = analysis.Skewness;
var source = analysis.Source;
var standardDeviation = analysis.StandardDeviations;
var standardErrors = analysis.StandardErrors;
var standardScores = analysis.StandardScores;
var sums = analysis.Sums;
var variables = analysis.Variables;
var variances = analysis.Variances;
var confidence = analysis.Confidence;
var quartiles = analysis.Quartiles;
Assert.IsTrue(columnNames.IsEqual(new string[]
{
"Column 0",
}));
Assert.IsTrue(correlation.IsEqual(new double[, ] {
{ 1 }
}));
Assert.IsTrue(covariance.IsEqual(new double[, ] {
{ 604.39999999999998 }
}));
Assert.IsTrue(deviationScores.IsEqual(new double[, ]
{
{ 14.0 },
{ -26.0 },
{ 27.0 },
{ -13.0 },
{ 24.0 },
{ -26.0 }
}));
Assert.IsTrue(distinct.IsEqual(new int[] { 5 }));
Assert.IsTrue(kurtosis.IsEqual(new double[] { -2.7161799571726601 }));
Assert.IsTrue(means.IsEqual(new double[] { 38.0 }));
Assert.IsTrue(medians.IsEqual(new double[] { 38.5 }));
Assert.IsTrue(modes.IsEqual(new double[] { 12.0 }));
Assert.IsTrue(ranges.Apply(p => p.Min).IsEqual(new double[] { 12 }));
Assert.IsTrue(ranges.Apply(p => p.Max).IsEqual(new double[] { 65 }));
Assert.IsTrue(samples == 6);
Assert.IsTrue(skewness.IsEqual(new double[] { -0.022168530787350427 }));
Assert.IsTrue(source.IsEqual(new double[, ]
{
{ 52 },
{ 12 },
{ 65 },
{ 25 },
{ 62 },
{ 12 },
}));
Assert.IsTrue(standardDeviation.IsEqual(new double[] { 24.584547992590792 }));
Assert.IsTrue(standardErrors.IsEqual(new double[] { 10.036599689801987 }));
Assert.IsTrue(standardScores.IsEqual(new double[, ]
{
{ 0.5694633883128245 },
{ -1.0575748640095313 },
{ 1.09825082031759 },
{ -0.52878743200476563 },
{ 0.97622295139341342 },
{ -1.0575748640095313 },
}));
Assert.IsTrue(sums.IsEqual(new double[] { 228.0 }));
Assert.IsTrue(variables == 1);
Assert.IsTrue(variances.IsEqual(new double[] { 604.39999999999998 }));
Assert.AreEqual(1, confidence.Length);
Assert.AreEqual(18.328626080742229, confidence[0].Min);
Assert.AreEqual(57.671373919257775, confidence[0].Max);
DoubleRange q;
double q2 = Measures.Quartiles(data, out q, alreadySorted: false);
Assert.AreEqual(1, quartiles.Length);
Assert.AreEqual(q.Min, quartiles[0].Min);
Assert.AreEqual(q.Max, quartiles[0].Max);
Assert.AreEqual(12, quartiles[0].Min);
Assert.AreEqual(62, quartiles[0].Max);
}
private void btnGenerateInputData_Click(object sender, EventArgs e)
{
//if (this.strProjectPath.Trim() == "")
// return;
//if (this.cmbBoundary.Text.Trim() == "")
// return;
//if (this.cmbRstraint.Text.Trim() == "")
// return;
//if (this.txtParameter.Text.Trim() == "")
// return;
if (lsbLayerLandUse.Items.Count == 0)
return;
//if (lsbLayerDriverFactor.Items.Count == 0)
// return;
int iLanduseType = 5;
ILayer pLayer = null;
IRaster pRaster =new RasterClass();
IGeoDataset pGdsMask = null;
IGeoDataset pGdsRstraint = null;
IGeoDataset pGdsLanduse = null;
IGeoDataset pGdsDriverFactor = null;
IRasterBandCollection pRasterBandColection=(new RasterClass()) as IRasterBandCollection;
//try
//{
string sLyrMask = this.cmbBoundary.Text;
//boundaty-->mask
for (int i = 0; i < pMap.LayerCount; i++)
{
ILayer pLyr = pMap.get_Layer(i);
if (pLyr is IRasterLayer)
{
if (pLyr.Name == sLyrMask)
{
pRaster = (pLyr as IRasterLayer).Raster;
pGdsMask = pRaster as IGeoDataset;
}
}
}
//data
//限制区
string sLyrRstraint = this.cmbBoundary.Text;
//土地利用数据
string sLyrLanduse = this.lsbLayerLandUse.Items[0].ToString();
//驱动因子
string[] arr = new string[this.lsbLayerDriverFactor.Items.Count];
for (int i = 0; i < this.lsbLayerDriverFactor.Items.Count; i++)
{
arr[i]=this.lsbLayerDriverFactor.Items[i].ToString();
}
for (int i = 0; i < pMap.LayerCount; i++)
{
ILayer pLyr = pMap.get_Layer(i);
if (pLyr is IRasterLayer)
{
if (pLyr.Name == sLyrRstraint)
{
pRaster = (pLyr as IRasterLayer).Raster;
pGdsRstraint = pRaster as IGeoDataset;
}
//土地利用数据
if (pLyr.Name == sLyrLanduse)
{
this.rtxtState.AppendText("读取土地利用参数数据...\n");
this.rtxtState.ScrollToCaret();
pRaster = (pLyr as IRasterLayer).Raster;
pGdsLanduse = pRaster as IGeoDataset;
//land use 添加到 IRasterBandCollection
pRasterBandColection=pRaster as IRasterBandCollection;
//pRasterBandColection.AppendBand(pRaster as IRasterBand);
string ascFileNameLanduse = strProjectPath + "\\cov1_all.0";
//cov1_0.0;cov1_1.0;
Rater2Ascii(pGdsMask, 100, pGdsLanduse, ascFileNameLanduse);
//将土地利用数据拆分
StreamReader sr = new StreamReader(ascFileNameLanduse, System.Text.Encoding.Default);
//try
//{
//使用StreamReader类来读取文件
sr.BaseStream.Seek(0, SeekOrigin.Begin);
// 从数据流中读取每一行，直到文件的最后一行，并在richTextBox1中显示出内容
//读取头文件
string[] header = new string[6];
for (int j = 0; j < 6; j++)
{
header[j] = sr.ReadLine();
}
//行列数
string[] ncols = header[0].Split(' ');
string[] nrows = header[1].Split(' ');
int icol = int.Parse(ncols[ncols.Length - 1]);
int irow = int.Parse(nrows[nrows.Length - 1]);
int[,] iLanduse = new int[irow, icol];
//
string strLine = sr.ReadLine();
string[] strData;
int ir = 0;
while (ir < irow)
//while (strLine != null)
{
strData = strLine.Split(' ');
for (int ic = 0; ic < icol; ic++)
{
iLanduse[ir, ic] = int.Parse(strData[ic]);
}
strLine = sr.ReadLine();
ir++;
}
//关闭此StreamReader对象
sr.Close();
//输出相应的土地利用数据
DataTable2Txt(header, iLanduseType, iLanduse, strProjectPath);
//}
//catch (Exception ex)
//{
//MessageBox.Show(ex.Message);
sr.Close();
//}
}
}
}
this.rtxtState.AppendText("输出土地利用参数数据成功。\n");
this.rtxtState.AppendText("读取驱动因子数据...\n");
this.rtxtState.ScrollToCaret();
for (int ifac = 0; ifac < lsbLayerDriverFactor.Items.Count; ifac++)
{
for (int i = 0; i < pMap.LayerCount; i++)
{
ILayer pLyr = pMap.get_Layer(i);
if (pLyr is IRasterLayer)
{
//输出驱动因子数据 sc1gr0.grid
string sFacName = lsbLayerDriverFactor.Items[ifac].ToString();
if (pLyr.Name == sFacName)
{
pRaster = (pLyr as IRasterLayer).Raster;
pGdsDriverFactor = pRaster as IGeoDataset;
string ascFileNameFac = strProjectPath + "\\sc1gr"+ifac.ToString()+".grid";
//cov1_0.0;cov1_1.0;
this.rtxtState.AppendText("输出驱动因子数据【" + sFacName + "】\n");
Rater2Ascii(pGdsMask, 100, pGdsDriverFactor, ascFileNameFac);
this.rtxtState.AppendText("输出驱动因子数据【" + sFacName + "】成功。\n");
this.rtxtState.ScrollToCaret();
//mask 添加到 IRasterBandCollection
IRasterBandCollection rasterbands = (IRasterBandCollection)pRaster;
IRasterBand rasterband = rasterbands.Item(0);
pRasterBandColection.AppendBand(rasterband);
//pRasterBandColection.Add(pRaster as IRasterBand,ifac+1);
}
}
}
}
this.rtxtState.AppendText("开始制备驱动因子参数...\n");
this.rtxtState.ScrollToCaret();
//sample data
ITable itFactors=ExportSample(pGdsMask,pRasterBandColection);
//logistic 回归分析
DataTable dtFactors = ITable2DTable(itFactors);
itFactors = null;
//制备驱动力参数文件
this.rtxtState.AppendText("读取驱动因子数据表格数据...\n");
this.rtxtState.ScrollToCaret();
LogisticRegressionAnalysis lra;
// Gets the columns of the independent variables
List<string> names = new List<string>();
foreach (string name in lsbLayerDriverFactor.Items)
names.Add(name);
String[] independentNames = names.ToArray();
DataTable independent = dtFactors.DefaultView.ToTable(false, independentNames);
// Creates the input and output matrices from the source data table
double[][] input = independent.ToArray();
double[,] sourceMatrix = dtFactors.ToMatrix(independentNames);
for(int ild=0;ild<iLanduseType;ild++)
{
String landuseName = (string)this.lsbLayerLandUse.Items[0].ToString();
this.rtxtState.AppendText("开始制备土地利用类型【" + ild.ToString() + "】驱动因子参数...\n");
this.rtxtState.ScrollToCaret();
DataColumn taxColumn =new DataColumn();
taxColumn.DataType = System.Type.GetType("System.Int32");
taxColumn.ColumnName ="sysland"+ild.ToString();//列名
taxColumn.Expression = "iif("+landuseName+" = "+ild.ToString()+",1,0)";//设置该列得表达式，用于计算列中的值或创建聚合列
dtFactors.Columns.Add(taxColumn);
string dependentName = "sysland" + ild.ToString();
DataTable dependent = dtFactors.DefaultView.ToTable(false, dependentName);
double[] output = dependent.Columns[dependentName].ToArray();
// Creates the Simple Descriptive Analysis of the given source
DescriptiveAnalysis sda = new DescriptiveAnalysis(sourceMatrix, independentNames);
sda.Compute();
// Populates statistics overview tab with analysis data
//dgvDistributionMeasures.DataSource = sda.Measures;
// Creates the Logistic Regression Analysis of the given source
lra = new LogisticRegressionAnalysis(input, output, independentNames, dependentName);
// Compute the Logistic Regression Analysis
lra.Compute();
// Populates coefficient overview with analysis data
//lra.Coefficients;
MessageBox.Show(lra.Coefficients.Count.ToString());
//// Populate details about the fitted model
//tbChiSquare.Text = lra.ChiSquare.Statistic.ToString("N5");
//tbPValue.Text = lra.ChiSquare.PValue.ToString("N5");
//checkBox1.Checked = lra.ChiSquare.Significant;
//tbDeviance.Text = lra.Deviance.ToString("N5");
//tbLogLikelihood.Text = lra.LogLikelihood.ToString("N5");
}
this.rtxtState.AppendText("制备驱动因子参数成功。\n");
this.rtxtState.ScrollToCaret();
MessageBox.Show(dtFactors.Rows.Count.ToString());
//}
//catch (Exception ex)
//{
// MessageBox.Show(ex.Message);
//}
}
/// <summary>
/// Creates a Multinomial Logistic Regression Analysis.
/// </summary>
///
private void btnCreate_Click(object sender, EventArgs e)
{
if (dgvLearningSource.DataSource == null)
{
MessageBox.Show("Please load some data first.");
return;
}
// Finishes and save any pending changes to the given data
dgvLearningSource.EndEdit();
// Creates a matrix from the entire source data table
double[,] table = (dgvLearningSource.DataSource as DataTable).ToMatrix(out columnNames);
// Get only the input vector values (first two columns)
double[][] inputs = table.GetColumns(0, 1).ToArray();
// Get only the output labels (last column)
int[] outputs = table.GetColumn(2).Subtract(1).ToInt32();
// Create and compute a new Simple Descriptive Analysis
var sda = new DescriptiveAnalysis(table, columnNames);
sda.Compute();
// Show the descriptive analysis on the screen
dgvDistributionMeasures.DataSource = sda.Measures;
// Creates the Support Vector Machine for 2 input variables
mlr = new MultinomialLogisticRegressionAnalysis(inputs, outputs);
try
{
// Run
mlr.Compute();
lbStatus.Text = "Analysis complete!";
}
catch (ConvergenceException)
{
lbStatus.Text = "Convergence could not be attained. " +
"The learned machine might still be usable.";
}
createSurface(table);
// Populate details about the fitted model
tbChiSquare.Text = mlr.ChiSquare.Statistic.ToString("N5");
tbPValue.Text = mlr.ChiSquare.PValue.ToString("N5");
checkBox1.Checked = mlr.ChiSquare.Significant;
tbDeviance.Text = mlr.Deviance.ToString("N5");
tbLogLikelihood.Text = mlr.LogLikelihood.ToString("N5");
dgvCoefficients.DataSource = mlr.Coefficients;
}
private void button1_Click(object sender, EventArgs e)
{
// Finishes and save any pending changes to the given data
dgvAnalysisSource.EndEdit();
if (dgvAnalysisSource.DataSource == null) return;
// Creates a matrix from the source data table
double[,] sourceMatrix = (dgvAnalysisSource.DataSource as DataTable).ToMatrix(out sourceColumns);
int rows = sourceMatrix.GetLength(0);
int cols = sourceMatrix.GetLength(1);
// Creates a new Simple Descriptive Analysis
sda = new DescriptiveAnalysis(sourceMatrix, sourceColumns);
sda.Compute();
// Populates statistics overview tab with analysis data
dgvDistributionMeasures.DataSource = sda.Measures;
// Get only the input values (exclude the class label indicator column)
double[,] data = sourceMatrix.Submatrix(null, startColumn: 0, endColumn: 1);
// Get only the associated labels
int[] labels = sourceMatrix.GetColumn(2).ToInt32();
// Creates the Linear Discriminant Analysis of the given source
lda = new LinearDiscriminantAnalysis(data, labels);
// Computes the analysis
lda.Compute();
// Performs the transformation of the data using two dimensions
double[,] result = lda.Transform(data, 2);
// Create a new plot with the original Z column
double[,] points = result.InsertColumn(sourceMatrix.GetColumn(2));
// Create output scatter plot
outputScatterplot.DataSource = points;
// Create output table
dgvProjectionResult.DataSource = new ArrayDataView(points, sourceColumns);
// Populates discriminants overview with analysis data
dgvPrincipalComponents.DataSource = lda.Discriminants;
dgvFeatureVectors.DataSource = new ArrayDataView(lda.DiscriminantMatrix);
dgvScatterBetween.DataSource = new ArrayDataView(lda.ScatterBetweenClass);
dgvScatterWithin.DataSource = new ArrayDataView(lda.ScatterWithinClass);
dgvScatterTotal.DataSource = new ArrayDataView(lda.ScatterMatrix);
// Populates classes information
dgvClasses.DataSource = lda.Classes;
CreateComponentCumulativeDistributionGraph(graphCurve);
CreateComponentDistributionGraph(graphShare);
}
public void DescriptiveAnalysisOneSampleTest()
{
double[] data = { 52 };
// Create the analysis
DescriptiveAnalysis analysis = new DescriptiveAnalysis(data);
// Compute
analysis.Compute();
var columnNames = analysis.ColumnNames;
var correlation = analysis.CorrelationMatrix;
var covariance = analysis.CovarianceMatrix;
var deviationScores = analysis.DeviationScores;
var distinct = analysis.Distinct;
var kurtosis = analysis.Kurtosis;
var means = analysis.Means;
var medians = analysis.Medians;
var modes = analysis.Modes;
var ranges = analysis.Ranges;
var samples = analysis.Samples;
var skewness = analysis.Skewness;
var source = analysis.Source;
var standardDeviation = analysis.StandardDeviations;
var standardErrors = analysis.StandardErrors;
var standardScores = analysis.StandardScores;
var sums = analysis.Sums;
var variables = analysis.Variables;
var variances = analysis.Variances;
var confidence = analysis.Confidence;
var quartiles = analysis.Quartiles;
var innerFence = analysis.InnerFences;
var outerFence = analysis.OuterFences;
Assert.IsTrue(columnNames.IsEqual(new string[]
{
"Column 0",
}));
Assert.IsTrue(correlation.IsEqual(new double[, ] {
{ Double.NaN }
}));
Assert.IsTrue(covariance.IsEqual(new double[, ] {
{ Double.NaN }
}));
Assert.IsTrue(deviationScores.IsEqual(0));
Assert.IsTrue(distinct.IsEqual(new int[] { 1 }));
Assert.IsTrue(kurtosis.IsEqual(new double[] { Double.NaN }));
Assert.IsTrue(means.IsEqual(new double[] { 52 }));
Assert.IsTrue(medians.IsEqual(new double[] { 52.0 }));
Assert.IsTrue(modes.IsEqual(new double[] { 52.0 }));
Assert.IsTrue(samples == 1);
Assert.IsTrue(skewness.IsEqual(new double[] { Double.NaN }));
Assert.IsTrue(source.IsEqual(new double[, ]
{
{ 52 },
}));
Assert.IsTrue(standardDeviation.IsEqual(new double[] { double.NaN }));
Assert.IsTrue(standardErrors.IsEqual(new double[] { double.NaN }));
Assert.IsTrue(standardScores.IsEqual(new double[, ]
{
{ 0.0 },
}));
Assert.IsTrue(sums.IsEqual(new double[] { 52 }));
Assert.IsTrue(variables == 1);
Assert.IsTrue(variances.IsEqual(new double[] { double.NaN }));
Assert.AreEqual(1, ranges.Length);
Assert.AreEqual(52, ranges[0].Min);
Assert.AreEqual(52, ranges[0].Max);
Assert.AreEqual(1, confidence.Length);
Assert.AreEqual(double.NaN, confidence[0].Min);
Assert.AreEqual(double.NaN, confidence[0].Max);
Assert.AreEqual(1, quartiles.Length);
Assert.AreEqual(52, quartiles[0].Min);
Assert.AreEqual(52, quartiles[0].Max);
Assert.AreEqual(1, innerFence.Length);
Assert.AreEqual(52, innerFence[0].Min);
Assert.AreEqual(52, innerFence[0].Max);
Assert.AreEqual(1, outerFence.Length);
Assert.AreEqual(52, outerFence[0].Min);
Assert.AreEqual(52, outerFence[0].Max);
}
/// <summary>
/// Launched when the user clicks the "Run analysis" button.
/// </summary>
///
private void btnCompute_Click(object sender, EventArgs e)
{
// Save any pending changes
dgvAnalysisSource.EndEdit();
if (dgvAnalysisSource.DataSource == null)
{
MessageBox.Show("Please load some data using File > Open!");
return;
}
// Create a matrix from the source data table
double[][] sourceMatrix = (dgvAnalysisSource.DataSource as DataTable).ToArray(out columnNames);
// Create and compute a new Simple Descriptive Analysis
sda = new DescriptiveAnalysis(columnNames);
sda.Learn(sourceMatrix);
// Show the descriptive analysis on the screen
dgvDistributionMeasures.DataSource = sda.Measures;
// Get the input values (the two first columns)
double[][] inputs = sourceMatrix.GetColumns(0, 1);
// Get only the associated labels (last column)
int[] outputs = sourceMatrix.GetColumn(2).ToInt32();
outputs = outputs.Subtract(outputs.Min()); // start at 0
// Create a Linear Discriminant Analysis for the data
lda = new LinearDiscriminantAnalysis()
{
NumberOfOutputs = 2
};
// Compute the analysis!
lda.Learn(inputs, outputs);
// Perform the transformation of the data
double[][] result = lda.Transform(inputs);
// Create a new plot with the original Z column
double[][] points = result.InsertColumn(sourceMatrix.GetColumn(2));
// Create output scatter plot
outputScatterplot.DataSource = points;
// Create the output table
dgvProjectionResult.DataSource = new ArrayDataView(points, columnNames);
// Populate discriminants overview with analysis data
dgvFeatureVectors.DataSource = new ArrayDataView(lda.DiscriminantVectors);
dgvScatterBetween.DataSource = new ArrayDataView(lda.ScatterBetweenClass);
dgvScatterWithin.DataSource = new ArrayDataView(lda.ScatterWithinClass);
dgvScatterTotal.DataSource = new ArrayDataView(lda.ScatterMatrix);
dgvPrincipalComponents.DataSource = lda.Discriminants;
distributionView.DataSource = lda.Discriminants;
cumulativeView.DataSource = lda.Discriminants;
// Populate classes information
dgvClasses.DataSource = lda.Classes;
lbStatus.Text = "Good! Feel free to browse the other tabs to see what has been found.";
}
private void btnSampleRunAnalysis_Click(object sender, EventArgs e)
{
// Check requirements
if (sourceTable == null)
{
MessageBox.Show("A sample spreadsheet can be found in the " +
"Resources folder in the same directory as this application.",
"Please load some data before attempting an analysis");
return;
}
// Finishes and save any pending changes to the given data
dgvAnalysisSource.EndEdit();
sourceTable.AcceptChanges();
// Gets the column of the dependent variable
String dependentName = (string)cbTimeName.SelectedItem;
String censorName = (string)cbEventName.SelectedItem;
DataTable timeTable = sourceTable.DefaultView.ToTable(false, dependentName);
DataTable censorTable = sourceTable.DefaultView.ToTable(false, censorName);
// Gets the columns of the independent variables
List<string> names = new List<string>();
foreach (string name in checkedListBox1.CheckedItems)
names.Add(name);
String[] independentNames = names.ToArray();
// Creates the input and output matrices from the source data table
double[][] input;
double[] time = timeTable.Columns[dependentName].ToArray();
int[] censor = censorTable.Columns[censorName].ToArray().ToInt32();
if (independentNames.Length == 0)
{
input = new double[time.Length][];
for (int i = 0; i < input.Length; i++)
input[i] = new double[0];
}
else
{
DataTable independent = sourceTable.DefaultView.ToTable(false, independentNames);
input = independent.ToArray();
}
String[] sourceColumns;
double[,] sourceMatrix = sourceTable.ToMatrix(out sourceColumns);
// Creates the Simple Descriptive Analysis of the given source
DescriptiveAnalysis sda = new DescriptiveAnalysis(sourceMatrix, sourceColumns);
sda.Compute();
// Populates statistics overview tab with analysis data
dgvDistributionMeasures.DataSource = sda.Measures;
// Creates the Logistic Regression Analysis of the given source
pha = new ProportionalHazardsAnalysis(input, time, censor,
independentNames, dependentName, censorName);
// Compute the Logistic Regression Analysis
pha.Compute();
// Populates coefficient overview with analysis data
dgvLogisticCoefficients.DataSource = pha.Coefficients;
// Populate details about the fitted model
tbChiSquare.Text = pha.ChiSquare.Statistic.ToString("N5");
tbPValue.Text = pha.ChiSquare.PValue.ToString("N5");
checkBox1.Checked = pha.ChiSquare.Significant;
tbDeviance.Text = pha.Deviance.ToString("N5");
tbLogLikelihood.Text = pha.LogLikelihood.ToString("N5");
// Populate projection source table
string[] cols = independentNames;
if (!independentNames.Contains(dependentName))
cols = cols.Concatenate(dependentName);
if (!independentNames.Contains(censorName))
cols = cols.Concatenate(censorName);
DataTable projSource = sourceTable.DefaultView.ToTable(false, cols);
dgvProjectionSource.DataSource = projSource;
}
public void DescriptiveAnalysisTwoSampleTest()
{
double[][] data =
{
new [] { 52.0 },
new [] { 42.0 }
};
// Create the analysis
DescriptiveAnalysis analysis = new DescriptiveAnalysis(data);
// Compute
analysis.Compute();
var columnNames = analysis.ColumnNames;
var correlation = analysis.CorrelationMatrix;
var covariance = analysis.CovarianceMatrix;
var deviationScores = analysis.DeviationScores;
var distinct = analysis.Distinct;
var kurtosis = analysis.Kurtosis;
var means = analysis.Means;
var medians = analysis.Medians;
var modes = analysis.Modes;
var ranges = analysis.Ranges;
var samples = analysis.Samples;
var skewness = analysis.Skewness;
var source = analysis.Source;
var standardDeviation = analysis.StandardDeviations;
var standardErrors = analysis.StandardErrors;
var standardScores = analysis.StandardScores;
var sums = analysis.Sums;
var variables = analysis.Variables;
var variances = analysis.Variances;
var confidence = analysis.Confidence;
var quartiles = analysis.Quartiles;
var innerFence = analysis.InnerFences;
var outerFence = analysis.OuterFences;
Assert.IsTrue(columnNames.IsEqual(new string[]
{
"Column 0"
}));
Assert.IsTrue(correlation.IsEqual(Matrix.Create(1, 1, 0.99999999999999978)));
Assert.IsTrue(covariance.IsEqual(Matrix.Create(1, 1, 50.0)));
Assert.IsTrue(deviationScores.IsEqual(new double[,] { { 5 }, { -5 } }));
Assert.IsTrue(distinct.IsEqual(new int[] { 2 }));
Assert.IsTrue(kurtosis.IsEqual(new double[] { Double.NaN }));
Assert.IsTrue(means.IsEqual(new double[] { 47 }));
Assert.IsTrue(medians.IsEqual(new double[] { 94 }));
Assert.IsTrue(modes.IsEqual(new double[] { 52.0 })
|| modes.IsEqual(new double[] { 42.0 }));
Assert.IsTrue(samples == 2);
Assert.IsTrue(skewness.IsEqual(new double[] { Double.NaN }));
Assert.IsTrue(source.IsEqual(new double[,]
{
{ 52 },
{ 42 },
}));
Assert.IsTrue(standardDeviation.IsEqual(new double[] { 7.0710678118654755 }));
Assert.IsTrue(standardErrors.IsEqual(new double[] { 5.0 }));
Assert.IsTrue(standardScores.IsEqual(new double[,]
{
{ 0.70710678118654746 }, { -0.70710678118654746 },
}));
Assert.IsTrue(sums.IsEqual(new double[] { 94 }));
Assert.IsTrue(variables == 1);
Assert.IsTrue(variances.IsEqual(new double[] { 50 }));
Assert.AreEqual(1, ranges.Length);
Assert.AreEqual(42, ranges[0].Min);
Assert.AreEqual(52, ranges[0].Max);
Assert.AreEqual(1, confidence.Length);
Assert.AreEqual(37.200180077299734, confidence[0].Min);
Assert.AreEqual(56.799819922700266, confidence[0].Max);
Assert.AreEqual(1, quartiles.Length);
Assert.AreEqual(73, quartiles[0].Min);
Assert.AreEqual(68, quartiles[0].Max);
Assert.AreEqual(1, innerFence.Length);
Assert.AreEqual(80.5, innerFence[0].Min);
Assert.AreEqual(60.5, innerFence[0].Max);
Assert.AreEqual(1, outerFence.Length);
Assert.AreEqual(88, outerFence[0].Min);
Assert.AreEqual(53, outerFence[0].Max);
}
public void DescriptiveAnalysisConstructorTest4()
{
double[][] data =
{
new double[] { 1, 52, 5 },
new double[] { 2, 12, 5 },
new double[] { 1, 65, 5 },
new double[] { 1, 25, 5 },
new double[] { 2, 62, 5 },
};
// Create the analysis
DescriptiveAnalysis analysis = new DescriptiveAnalysis(data);
analysis.Compute();
test(analysis);
}
public void DescriptiveAnalysisNSampleTest()
{
for (int i = 1; i < 100; i++)
{
double[] data = Matrix.Random(i, 0.0, 1.0);
// Create the analysis
DescriptiveAnalysis analysis = new DescriptiveAnalysis(data);
// Compute
analysis.Compute();
var columnNames = analysis.ColumnNames;
var correlation = analysis.CorrelationMatrix;
var covariance = analysis.CovarianceMatrix;
var deviationScores = analysis.DeviationScores;
var distinct = analysis.Distinct;
var kurtosis = analysis.Kurtosis;
var means = analysis.Means;
var medians = analysis.Medians;
var modes = analysis.Modes;
var ranges = analysis.Ranges;
var samples = analysis.Samples;
var skewness = analysis.Skewness;
var source = analysis.Source;
var standardDeviation = analysis.StandardDeviations;
var standardErrors = analysis.StandardErrors;
var standardScores = analysis.StandardScores;
var sums = analysis.Sums;
var variables = analysis.Variables;
var variances = analysis.Variances;
var confidence = analysis.Confidence;
var quartiles = analysis.Quartiles;
var innerFence = analysis.InnerFences;
var outerFence = analysis.OuterFences;
Assert.AreEqual(1, columnNames.Length);
Assert.AreEqual(1, correlation.Length);
Assert.AreEqual(1, covariance.Length);
Assert.AreEqual(i, deviationScores.Length);
Assert.AreEqual(1, distinct.Length);
Assert.AreEqual(1, kurtosis.Length);
Assert.AreEqual(1, means.Length);
Assert.AreEqual(1, medians.Length);
Assert.AreEqual(1, modes.Length);
Assert.AreEqual(1, ranges.Length);
Assert.AreEqual(i, samples);
Assert.AreEqual(1, skewness.Length);
Assert.AreEqual(i, source.Length);
Assert.AreEqual(1, standardDeviation.Length);
Assert.AreEqual(1, standardErrors.Length);
Assert.AreEqual(i, standardScores.Length);
Assert.AreEqual(1, sums.Length);
Assert.AreEqual(1, variables);
Assert.AreEqual(1, variances.Length);
Assert.AreEqual(1, confidence.Length);
Assert.AreEqual(1, innerFence.Length);
Assert.AreEqual(1, outerFence.Length);
Assert.AreEqual(1, quartiles.Length);
}
}
private static void test(DescriptiveAnalysis analysis)
{
var columnNames = analysis.ColumnNames;
var correlation = analysis.CorrelationMatrix;
var covariance = analysis.CovarianceMatrix;
var deviationScores = analysis.DeviationScores;
var distinct = analysis.Distinct;
var kurtosis = analysis.Kurtosis;
var means = analysis.Means;
var medians = analysis.Medians;
var modes = analysis.Modes;
var ranges = analysis.Ranges;
var samples = analysis.Samples;
var skewness = analysis.Skewness;
var source = analysis.Source;
var standardDeviation = analysis.StandardDeviations;
var standardErrors = analysis.StandardErrors;
var standardScores = analysis.StandardScores;
var sums = analysis.Sums;
var variables = analysis.Variables;
var variances = analysis.Variances;
Assert.IsTrue(columnNames.IsEqual(new string[]
{
"Column 0",
"Column 1",
"Column 2",
}));
Assert.IsTrue(correlation.IsEqual(new double[,]
{
{ 1.00000000000000000, -0.24074447786944278, 0 },
{ -0.24074447786944278, 1.00000000000000000, 0 },
{ 0.00000000000000000, 0.00000000000000000, 0 }
}));
Assert.IsTrue(covariance.IsEqual(new double[,]
{
{ 0.3, -3.1, 0.0 },
{ -3.1, 552.7, 0.0 },
{ 0.0, 0.0, 0.0 }
}));
Assert.IsTrue(deviationScores.IsEqual(new double[,]
{
{ -0.39999999999999991, 8.7999999999999972, 0.0 },
{ 0.60000000000000009, -31.200000000000003, 0.0 },
{ -0.39999999999999991, 21.799999999999997, 0.0 },
{ -0.39999999999999991, -18.200000000000003, 0.0 },
{ 0.60000000000000009, 18.799999999999997, 0.0 }
}));
Assert.IsTrue(distinct.IsEqual(new int[] { 2, 5, 1 }));
Assert.IsTrue(kurtosis.IsEqual(new double[] { -3.3333333333333321, -2.213664721197441, double.NaN }));
Assert.IsTrue(means.IsEqual(new double[] { 1.4, 43.2, 5.0 }));
Assert.IsTrue(medians.IsEqual(new double[] { 1.0, 52.0, 5.0 }));
Assert.IsTrue(modes.IsEqual(new double[] { 1.0, 52.0, 5.0 }));
Assert.IsTrue(ranges.Apply(p => p.Min).IsEqual(new double[] { 1, 12, 5 }));
Assert.IsTrue(ranges.Apply(p => p.Max).IsEqual(new double[] { 2, 65, 5 }));
Assert.IsTrue(samples == 5);
Assert.IsTrue(skewness.IsEqual(new double[] { 0.60858061945018527, -0.60008123614710385, double.NaN }));
Assert.IsTrue(source.IsEqual(new double[,]
{
{ 1, 52, 5 },
{ 2, 12, 5 },
{ 1, 65, 5 },
{ 1, 25, 5 },
{ 2, 62, 5 },
}));
Assert.IsTrue(standardDeviation.IsEqual(new double[] { 0.54772255750516607, 23.509572518444482, 0.0 }));
Assert.IsTrue(standardErrors.IsEqual(new double[] { 0.24494897427831777, 10.513800454640558, 0.0 }));
Assert.IsTrue(standardScores.IsEqual(new double[,]
{
{ -0.73029674334022132, 0.37431561093235277, 0.0 },
{ 1.0954451150103324, -1.3271189842147058, 0.0 },
{ -0.73029674334022132, 0.92728185435514676, 0.0 },
{ -0.73029674334022132, -0.77415274079191176, 0.0 },
{ 1.0954451150103324, 0.79967425971911732, 0.0 },
}));
Assert.IsTrue(sums.IsEqual(new double[] { 7, 216.0, 25 }));
Assert.IsTrue(variables == 3);
Assert.IsTrue(variances.IsEqual(new double[] { 0.3, 552.7, 0.0 }));
}
private void btnGenerateInputData_Click(object sender, EventArgs e)
{
//if (this.strProjectPath.Trim() == "")
// return;
if (this.cmbBoundary.Text.Trim() == "")
{
MessageBox.Show("请添加边界数据！","提示！",MessageBoxButtons.OK);
return;
}
if (this.cmbRstraint.Text.Trim() == "")
{
MessageBox.Show("请添加限制区域数据！", "提示！", MessageBoxButtons.OK);
return;
}
//if (this.txtParameter.Text.Trim() == "")
// return;
if (lsbLayerLandUse.Items.Count == 0)
return;
//if (lsbLayerDriverFactor.Items.Count == 0)
// return;
int iLanduseType = 6;
//ILayer pLayer = null;
IRaster pRaster = new RasterClass();
IGeoDataset pGdsMask = null;
IGeoDataset pGdsRstraint = null;
IGeoDataset pGdsLanduse = null;
IGeoDataset pGdsDriverFactor = null;
IRasterBandCollection pRasterBandColection=(new RasterClass()) as IRasterBandCollection;
//读取
double cellSize = 1000;
//try
//{
string sLyrMask = this.cmbBoundary.Text;
//boundaty-->mask
for (int i = 0; i < pMap.LayerCount; i++)
{
ILayer pLyr = pMap.get_Layer(i);
if (pLyr is IRasterLayer)
{
if (pLyr.Name == sLyrMask)
{
IRasterProps pRasterP = (pLyr as IRasterLayer).Raster as IRasterProps;
cellSize = pRasterP.MeanCellSize().X;
pGdsMask = (pLyr as IRasterLayer).Raster as IGeoDataset;
}
}
}
//data
//限制区
string sLyrRstraint = this.cmbRstraint.Text;
//土地利用数据
string sLyrLanduse = this.lsbLayerLandUse.Items[0].ToString();
// 土地利用数据与驱动因子 数据名称(去除格式名)
// 顺序不能改变 后面 ITable2DTable 使用这个列表进行了名称替换
lsbNames.Add(sLyrLanduse.Remove(sLyrLanduse.LastIndexOf(".")));
foreach (string name in lsbLayerDriverFactor.Items)
{
lsbNames.Add(name.Remove(name.LastIndexOf("."))); //去除文件格式
}
//驱动因子
//string[] arr = new string[this.lsbLayerDriverFactor.Items.Count];
//for (int i = 0; i < this.lsbLayerDriverFactor.Items.Count; i++)
//{
// arr[i]=this.lsbLayerDriverFactor.Items[i].ToString();
//}
for (int i = 0; i < pMap.LayerCount; i++)
{
ILayer pLyr = pMap.get_Layer(i);
if (pLyr is IRasterLayer)
{
//IRaster curRaster = new RasterClass();
if (pLyr.Name == sLyrRstraint)
{
//curRaster = (pLyr as IRasterLayer).Raster;
//(pLyr as IRasterLayer).Raster.
pGdsRstraint = (pLyr as IRasterLayer).Raster as IGeoDataset;
//限制数据 region.grid
string ascFileNameRstraint = strProjectPath + "\\region.grid";
Rater2Ascii(pGdsMask,cellSize , pGdsRstraint, ascFileNameRstraint);
}
//土地利用数据
if (pLyr.Name == sLyrLanduse)
{
this.rtxtState.AppendText("读取土地利用参数数据...\n");
this.rtxtState.ScrollToCaret();
//curRaster = (pLyr as IRasterLayer).Raster;
pGdsLanduse = (pLyr as IRasterLayer).Raster as IGeoDataset;
//land use 添加到 IRasterBandCollection
IRasterBandCollection rasterbands = (IRasterBandCollection)(pLyr as IRasterLayer).Raster;
IRasterBand rasterband = rasterbands.Item(0);
pRasterBandColection.AppendBand(rasterband);
//pRasterBandColection = curRaster as IRasterBandCollection;
//pRasterBandColection.AppendBand(pRaster as IRasterBand);
string ascFileNameLanduse = strProjectPath + "\\cov1_all.0";
//cov1_0.0;cov1_1.0;
Rater2Ascii(pGdsMask, cellSize, pGdsLanduse, ascFileNameLanduse);
//
//将土地利用数据拆分
StreamReader sr = new StreamReader(ascFileNameLanduse, System.Text.Encoding.Default);
//try
//{
//使用StreamReader类来读取文件
sr.BaseStream.Seek(0, SeekOrigin.Begin);
// 从数据流中读取每一行，直到文件的最后一行，并在richTextBox1中显示出内容
//读取头文件
string[] header = new string[6];
for (int j = 0; j < 6; j++)
{
header[j] = sr.ReadLine();
}
//行列数
string[] ncols = header[0].Split(' ');
string[] nrows = header[1].Split(' ');
int icol = int.Parse(ncols[ncols.Length - 1]);
int irow = int.Parse(nrows[nrows.Length - 1]);
int[,] iLanduse = new int[irow, icol];
//
string strLine = sr.ReadLine();
string[] strData;
int ir = 0;
while (ir < irow)
//while (strLine != null)
{
strData = strLine.Split(' ');
for (int ic = 0; ic < icol; ic++)
{
iLanduse[ir, ic] = int.Parse(strData[ic]);
}
strLine = sr.ReadLine();
ir++;
}
//关闭此StreamReader对象
sr.Close();
//输出相应的土地利用数据
DataTable2Txt(header, iLanduseType, iLanduse, strProjectPath);
//}
//catch (Exception ex)
//{
//MessageBox.Show(ex.Message);
sr.Close();
//}
}
}
}
this.rtxtState.AppendText("输出土地利用参数数据成功。\n");
this.rtxtState.AppendText("读取驱动因子数据...\n");
this.rtxtState.ScrollToCaret();
for (int ifac = 0; ifac < lsbLayerDriverFactor.Items.Count; ifac++)
{
for (int i = 0; i < pMap.LayerCount; i++)
{
ILayer pLyr = pMap.get_Layer(i);
if (pLyr is IRasterLayer)
{
//输出驱动因子数据 sc1gr0.grid
string sFacName = lsbLayerDriverFactor.Items[ifac].ToString();
if (pLyr.Name == sFacName)
{
//IRaster curRaster = new RasterClass();
//curRaster = (pLyr as IRasterLayer).Raster;
pGdsDriverFactor = (pLyr as IRasterLayer).Raster as IGeoDataset;
string ascFileNameFac = strProjectPath + "\\sc1gr"+ifac.ToString()+".grid";
//cov1_0.0;cov1_1.0;
this.rtxtState.AppendText("输出驱动因子数据【" + sFacName + "】\n");
//IGeoDataset curMask = null;
//curMask = pGdsMask;
Rater2Ascii(pGdsMask, cellSize, pGdsDriverFactor, ascFileNameFac);
this.rtxtState.AppendText("输出驱动因子数据【" + sFacName + "】成功。\n");
this.rtxtState.ScrollToCaret();
//mask 添加到 IRasterBandCollection
IRasterBandCollection rasterbands = (IRasterBandCollection)(pLyr as IRasterLayer).Raster;
IRasterBand rasterband = rasterbands.Item(0);
pRasterBandColection.AppendBand(rasterband);
//pRasterBandColection.Add(pRaster as IRasterBand,ifac+1);
}
}
}
}
this.rtxtState.AppendText("开始制备驱动因子参数...\n");
this.rtxtState.ScrollToCaret();
//IGeoDataset curtestGeo = null;
////boundaty-->mask
//for (int i = 0; i < pMap.LayerCount; i++)
//{
// ILayer pLyr = pMap.get_Layer(i);
// if (pLyr is IRasterLayer)
// {
// if (pLyr.Name == sLyrMask)
// {
// curtestGeo = ((pLyr as IRasterLayer).Raster) as IGeoDataset;
// }
// }
//}
//sample data
ITable itFactors = ExportSample(pGdsMask, pRasterBandColection);
//logistic 回归分析
//lsbNames.AddRange(names);
DataTable dtFactors = ITable2DTable(itFactors);
itFactors = null;
//MessageBox.Show(dtFactors.Columns[0].ColumnName + ";" + dtFactors.Columns[1].ColumnName + ";" + dtFactors.Columns[2].ColumnName);
//制备驱动力参数文件
this.rtxtState.AppendText("读取驱动因子数据表格数据...\n");
this.rtxtState.ScrollToCaret();
LogisticRegressionAnalysis lra;
// Gets the columns of the independent variables
List<string> names = new List<string>();
foreach (string name in lsbLayerDriverFactor.Items)
{
names.Add(name.Remove(name.LastIndexOf("."))); //去除文件格式
}
String[] independentNames = names.ToArray();
DataTable independent = dtFactors.DefaultView.ToTable(false, independentNames);
// Creates the input and output matrices from the source data table
double[][] input = independent.ToArray();
double[,] sourceMatrix = dtFactors.ToMatrix(independentNames);
StreamWriter sw = new StreamWriter(strProjectPath + "\\alloc1.reg", false);
for(int ild=1; ild< iLanduseType; ild++)
{
String landuseName = (string)this.lsbLayerLandUse.Items[0].ToString();
this.rtxtState.AppendText("开始制备土地利用类型【" + ild.ToString() + "】驱动因子参数...\n");
this.rtxtState.ScrollToCaret();
DataColumn taxColumn =new DataColumn();
taxColumn.DataType = System.Type.GetType("System.Int32");
taxColumn.ColumnName ="sysland"+ild.ToString();//列名
taxColumn.Expression = "iif("+lsbNames[0]+" = "+ild.ToString()+",1,0)";//设置该列得表达式，用于计算列中的值或创建聚合列
dtFactors.Columns.Add(taxColumn);
string dependentName = "sysland" + ild.ToString();
DataTable dependent = dtFactors.DefaultView.ToTable(false, dependentName);
double[] output = dependent.Columns[dependentName].ToArray();
// Creates the Simple Descriptive Analysis of the given source
DescriptiveAnalysis sda = new DescriptiveAnalysis(sourceMatrix, independentNames);
sda.Compute();
// Populates statistics overview tab with analysis data
//dgvDistributionMeasures.DataSource = sda.Measures;
// Creates the Logistic Regression Analysis of the given source
lra = new LogisticRegressionAnalysis(input, output, independentNames, dependentName);
// Compute the Logistic Regression Analysis
lra.Compute();
// Populates coefficient overview with analysis data
//lra.Coefficients;
//MessageBox.Show(lra.Coefficients.Count.ToString());
//MessageBox.Show(lra.CoefficientValues[0].ToString());
//string str_check = listBox_deVar.Items[var_count].ToString().ToLower();
string st = ild.ToString();
int Relength = lra.CoefficientValues.Length;
int number = 0;
for (int i = 1; i < Relength; i++)
{
//if (< 0.05)
//{
number++;
//}
}
RegressionResult.Items.Add(st);
RegressionResult.Items.Add("\t" + Math.Round(lra.CoefficientValues[1], 6));
RegressionResult.Items.Add(number);
int var_number = 0;
for (int i = 0; i < Relength; i++)//改过了0=1
{
//if ( < 0.05)
//{
RegressionResult.Items.Add("\t" + Math.Round(lra.CoefficientValues[i], 6) + "\t" + var_number);
//}
var_number = var_number + 1;
}
// 保存alloc1.reg 文件
sw.WriteLine(st);
sw.WriteLine("\t" + Math.Round(lra.CoefficientValues[1], 6));//改过了1=0
sw.WriteLine(number);
int var_number2 = 0;
for (int i = 0; i < Relength; i++)//改过了0=1
{
//if ( < 0.05)
//{
sw.WriteLine("\t" + Math.Round(lra.CoefficientValues[i],6) + "\t" + var_number2);
//}
var_number2 = var_number2 + 1;
}
//progressBar1.Value = var_count + 1;
}
sw.Close();
this.rtxtState.AppendText("制备驱动因子参数成功。\n");
this.rtxtState.ScrollToCaret();
MessageBox.Show("制备驱动因子参数成功!","提示",MessageBoxButtons.OK);
//}
//catch (Exception ex)
//{
// MessageBox.Show(ex.Message);
//}
}
private void btnSampleRunAnalysis_Click(object sender, EventArgs e)
{
// Check requirements
if (sourceTable == null)
{
MessageBox.Show("A sample spreadsheet can be found in the " +
"Resources folder in the same directory as this application.",
"Please load some data before attempting an analysis");
return;
}
if (checkedListBox1.CheckedItems.Count == 0)
{
MessageBox.Show("Please select the dependent input variables to be used in the regression model.",
"Please choose at least one input variable");
}
// Finishes and save any pending changes to the given data
dgvAnalysisSource.EndEdit();
sourceTable.AcceptChanges();
// Gets the column of the dependent variable
String dependentName = (string)comboBox1.SelectedItem;
DataTable dependent = sourceTable.DefaultView.ToTable(false, dependentName);
// Gets the columns of the independent variables
List <string> names = new List <string>();
foreach (string name in checkedListBox1.CheckedItems)
{
names.Add(name);
}
String[] independentNames = names.ToArray();
DataTable independent = sourceTable.DefaultView.ToTable(false, independentNames);
// Creates the input and output matrices from the source data table
double[][] input = independent.ToArray();
double[] output = dependent.Columns[dependentName].ToArray();
double[,] sourceMatrix = sourceTable.ToMatrix(independentNames);
// Creates the Simple Descriptive Analysis of the given source
var sda = new DescriptiveAnalysis(sourceMatrix, independentNames);
sda.Compute();
// Populates statistics overview tab with analysis data
dgvDistributionMeasures.DataSource = sda.Measures;
// Creates the Logistic Regression Analysis of the given source
lra = new LogisticRegressionAnalysis(input, output, independentNames, dependentName);
// Compute the Logistic Regression Analysis
lra.Compute();
// Populates coefficient overview with analysis data
dgvLogisticCoefficients.DataSource = lra.Coefficients;
// Populate details about the fitted model
tbChiSquare.Text = lra.ChiSquare.Statistic.ToString("N5");
tbPValue.Text = lra.ChiSquare.PValue.ToString("N5");
checkBox1.Checked = lra.ChiSquare.Significant;
tbDeviance.Text = lra.Deviance.ToString("N5");
tbLogLikelihood.Text = lra.LogLikelihood.ToString("N5");
// Create the Multiple Linear Regression Analysis of the given source
mlr = new MultipleLinearRegressionAnalysis(input, output, independentNames, dependentName, true);
// Compute the Linear Regression Analysis
mlr.Compute();
dgvLinearCoefficients.DataSource = mlr.Coefficients;
dgvRegressionAnova.DataSource = mlr.Table;
tbRSquared.Text = mlr.RSquared.ToString("N5");
tbRSquaredAdj.Text = mlr.RSquareAdjusted.ToString("N5");
tbChiPValue.Text = mlr.ChiSquareTest.PValue.ToString("N5");
tbFPValue.Text = mlr.FTest.PValue.ToString("N5");
tbZPValue.Text = mlr.ZTest.PValue.ToString("N5");
tbChiStatistic.Text = mlr.ChiSquareTest.Statistic.ToString("N5");
tbFStatistic.Text = mlr.FTest.Statistic.ToString("N5");
tbZStatistic.Text = mlr.ZTest.Statistic.ToString("N5");
cbChiSignificant.Checked = mlr.ChiSquareTest.Significant;
cbFSignificant.Checked = mlr.FTest.Significant;
cbZSignificant.Checked = mlr.ZTest.Significant;
// Populate projection source table
string[] cols = independentNames;
if (!independentNames.Contains(dependentName))
{
cols = independentNames.Concatenate(dependentName);
}
DataTable projSource = sourceTable.DefaultView.ToTable(false, cols);
dgvProjectionSource.DataSource = projSource;
}
public void DataBindTest()
{
double[,] data =
{
{ 1, 52, 5 },
{ 2, 12, 5 },
{ 1, 65, 5 },
{ 1, 25, 5 },
{ 2, 62, 5 },
};
DescriptiveAnalysis analysis = new DescriptiveAnalysis(data);
analysis.Compute();
var m0 = analysis.Measures[0];
var m1 = analysis.Measures[1];
var m2 = analysis.Measures[2];
Assert.AreEqual(0, m0.Index);
Assert.AreEqual(1, m1.Index);
Assert.AreEqual(2, m2.Index);
Assert.AreEqual("Column 0", m0.Name);
Assert.AreEqual("Column 1", m1.Name);
Assert.AreEqual("Column 2", m2.Name);
Assert.AreEqual(m0, analysis.Measures["Column 0"]);
Assert.AreEqual(m1, analysis.Measures["Column 1"]);
Assert.AreEqual(m2, analysis.Measures["Column 2"]);
// var box = Accord.Controls.DataGridBox.Show(analysis.Measures);
// Assert.AreEqual(21, box.DataGridView.Columns.Count);
}
public void DescriptiveAnalysisConstructorTest4()
{
double[][] data =
{
new double[] { 1, 52, 5 },
new double[] { 2, 12, 5 },
new double[] { 1, 65, 5 },
new double[] { 1, 25, 5 },
new double[] { 2, 62, 5 },
};
// Create the analysis
DescriptiveAnalysis analysis = new DescriptiveAnalysis(data);
analysis.Compute();
double[] means = analysis.Means;
double[] modes = analysis.Modes;
Assert.AreEqual(3, means.Length);
Assert.AreEqual(1.4, means[0]);
Assert.AreEqual(43.2, means[1]);
Assert.AreEqual(5.0, means[2]);
Assert.AreEqual(1.0, modes[0]);
Assert.AreEqual(52.0, modes[1]);
Assert.AreEqual(5.0, modes[2]);
Assert.AreEqual(3, analysis.ColumnNames.Length);
Assert.AreEqual("Column 0", analysis.ColumnNames[0]);
Assert.AreEqual("Column 1", analysis.ColumnNames[1]);
Assert.AreEqual("Column 2", analysis.ColumnNames[2]);
}
public void DescriptiveAnalysisConstructorTest3()
{
// Suppose we would like to compute descriptive
// statistics from the following data samples:
double[] data = { 52, 12, 65, 25, 62 };
// Create the analysis
DescriptiveAnalysis analysis = new DescriptiveAnalysis(data);
// Compute
analysis.Compute();
var columnNames = analysis.ColumnNames;
var correlation = analysis.CorrelationMatrix;
var covariance = analysis.CovarianceMatrix;
var deviationScores = analysis.DeviationScores;
var distinct = analysis.Distinct;
var kurtosis = analysis.Kurtosis;
var means = analysis.Means;
var medians = analysis.Medians;
var modes = analysis.Modes;
var ranges = analysis.Ranges;
var samples = analysis.Samples;
var skewness = analysis.Skewness;
var source = analysis.Source;
var standardDeviation = analysis.StandardDeviations;
var standardErrors = analysis.StandardErrors;
var standardScores = analysis.StandardScores;
var sums = analysis.Sums;
var variables = analysis.Variables;
var variances = analysis.Variances;
var confidence = analysis.Confidence;
Assert.IsTrue(columnNames.IsEqual(new string[]
{
"Column 0",
}));
Assert.IsTrue(correlation.IsEqual(new double[,] { { 1 } }));
Assert.IsTrue(covariance.IsEqual(new double[,] { { 552.7 } }));
Assert.IsTrue(deviationScores.IsEqual(new double[,]
{
{ 8.7999999999999972 },
{ -31.200000000000003 },
{ 21.799999999999997 },
{ -18.200000000000003 },
{ 18.799999999999997 }
}));
Assert.IsTrue(distinct.IsEqual(new int[] { 5 }));
Assert.IsTrue(kurtosis.IsEqual(new double[] { -2.213664721197441 }));
Assert.IsTrue(means.IsEqual(new double[] { 43.2 }));
Assert.IsTrue(medians.IsEqual(new double[] { 52.0 }));
Assert.IsTrue(modes.IsEqual(new double[] { 52.0 }));
Assert.IsTrue(ranges.Apply(p => p.Min).IsEqual(new double[] { 12 }));
Assert.IsTrue(ranges.Apply(p => p.Max).IsEqual(new double[] { 65 }));
Assert.IsTrue(samples == 5);
Assert.IsTrue(skewness.IsEqual(new double[] { -0.60008123614710385 }));
Assert.IsTrue(source.IsEqual(new double[,]
{
{ 52 },
{ 12 },
{ 65 },
{ 25 },
{ 62 },
}));
Assert.IsTrue(standardDeviation.IsEqual(new double[] { 23.509572518444482 }));
Assert.IsTrue(standardErrors.IsEqual(new double[] { 10.513800454640558 }));
Assert.IsTrue(standardScores.IsEqual(new double[,]
{
{ 0.37431561093235277 },
{ -1.3271189842147058 },
{ 0.92728185435514676 },
{ -0.77415274079191176 },
{ 0.79967425971911732 },
}));
Assert.IsTrue(sums.IsEqual(new double[] { 216.0 }));
Assert.IsTrue(variables == 1);
Assert.IsTrue(variances.IsEqual(new double[] { 552.7 }));
Assert.AreEqual(1, confidence.Length);
Assert.AreEqual(22.593329768263665, confidence[0].Min);
Assert.AreEqual(63.806670231736341, confidence[0].Max);
}
private void btnSampleRunAnalysis_Click(object sender, EventArgs e)
{
// Check requirements
if (sourceTable == null)
{
MessageBox.Show("A sample spreadsheet can be found in the " +
"Resources folder in the same directory as this application.",
"Please load some data before attempting an analysis");
return;
}
// Finishes and save any pending changes to the given data
dgvAnalysisSource.EndEdit();
sourceTable.AcceptChanges();
// Gets the column of the dependent variable
String dependentName = (string)cbTimeName.SelectedItem;
String censorName = (string)cbEventName.SelectedItem;
DataTable timeTable = sourceTable.DefaultView.ToTable(false, dependentName);
DataTable censorTable = sourceTable.DefaultView.ToTable(false, censorName);
// Gets the columns of the independent variables
List <string> names = new List <string>();
foreach (string name in checkedListBox1.CheckedItems)
{
names.Add(name);
}
String[] independentNames = names.ToArray();
// Creates the input and output matrices from the source data table
this.time = timeTable.Columns[dependentName].ToArray();
this.censor = censorTable.Columns[censorName].ToArray().ToInt32();
if (independentNames.Length == 0)
{
this.inputs = Jagged.Zeros(time.Length, 0);
}
else
{
DataTable independent = sourceTable.DefaultView.ToTable(false, independentNames);
this.inputs = independent.ToJagged();
}
String[] sourceColumns;
this.sourceMatrix = sourceTable.ToJagged(out sourceColumns);
// Creates the Simple Descriptive Analysis of the given source
var sda = new DescriptiveAnalysis(sourceColumns).Learn(sourceMatrix);
// Populates statistics overview tab with analysis data
dgvDistributionMeasures.DataSource = sda.Measures;
// Creates the Logistic Regression Analysis of the given source
pha = new ProportionalHazardsAnalysis(independentNames, dependentName, censorName);
// Compute the Logistic Regression Analysis
ProportionalHazards model = pha.Learn(inputs, time, censor);
// Populates coefficient overview with analysis data
dgvLogisticCoefficients.DataSource = pha.Coefficients;
// Populate details about the fitted model
tbChiSquare.Text = pha.ChiSquare.Statistic.ToString("N5");
tbPValue.Text = pha.ChiSquare.PValue.ToString("N5");
checkBox1.Checked = pha.ChiSquare.Significant;
tbDeviance.Text = pha.Deviance.ToString("N5");
tbLogLikelihood.Text = pha.LogLikelihood.ToString("N5");
// Populate projection source table
string[] cols = independentNames;
if (!independentNames.Contains(dependentName))
{
cols = cols.Concatenate(dependentName);
}
if (!independentNames.Contains(censorName))
{
cols = cols.Concatenate(censorName);
}
DataTable projSource = sourceTable.DefaultView.ToTable(false, cols);
dgvProjectionSource.DataSource = projSource;
}
public void DescriptiveAnalysisOneSampleTest()
{
double[] data = { 52 };
// Create the analysis
DescriptiveAnalysis analysis = new DescriptiveAnalysis(data);
// Compute
analysis.Compute();
var columnNames = analysis.ColumnNames;
var correlation = analysis.CorrelationMatrix;
var covariance = analysis.CovarianceMatrix;
var deviationScores = analysis.DeviationScores;
var distinct = analysis.Distinct;
var kurtosis = analysis.Kurtosis;
var means = analysis.Means;
var medians = analysis.Medians;
var modes = analysis.Modes;
var ranges = analysis.Ranges;
var samples = analysis.Samples;
var skewness = analysis.Skewness;
var source = analysis.Source;
var standardDeviation = analysis.StandardDeviations;
var standardErrors = analysis.StandardErrors;
var standardScores = analysis.StandardScores;
var sums = analysis.Sums;
var variables = analysis.Variables;
var variances = analysis.Variances;
var confidence = analysis.Confidence;
var quartiles = analysis.Quartiles;
var innerFence = analysis.InnerFences;
var outerFence = analysis.OuterFences;
Assert.IsTrue(columnNames.IsEqual(new string[]
{
"Column 0",
}));
Assert.IsTrue(correlation.IsEqual(new double[,] { { Double.NaN } }));
Assert.IsTrue(covariance.IsEqual(new double[,] { { Double.NaN } }));
Assert.IsTrue(deviationScores.IsEqual(0));
Assert.IsTrue(distinct.IsEqual(new int[] { 1 }));
Assert.IsTrue(kurtosis.IsEqual(new double[] { Double.NaN }));
Assert.IsTrue(means.IsEqual(new double[] { 52 }));
Assert.IsTrue(medians.IsEqual(new double[] { 52.0 }));
Assert.IsTrue(modes.IsEqual(new double[] { 52.0 }));
Assert.IsTrue(samples == 1);
Assert.IsTrue(skewness.IsEqual(new double[] { Double.NaN }));
Assert.IsTrue(source.IsEqual(new double[,]
{
{ 52 },
}));
Assert.IsTrue(standardDeviation.IsEqual(new double[] { double.NaN }));
Assert.IsTrue(standardErrors.IsEqual(new double[] { double.NaN }));
Assert.IsTrue(standardScores.IsEqual(new double[,]
{
{ 0.0 },
}));
Assert.IsTrue(sums.IsEqual(new double[] { 52 }));
Assert.IsTrue(variables == 1);
Assert.IsTrue(variances.IsEqual(new double[] { double.NaN }));
Assert.AreEqual(1, ranges.Length);
Assert.AreEqual(52, ranges[0].Min);
Assert.AreEqual(52, ranges[0].Max);
Assert.AreEqual(1, confidence.Length);
Assert.AreEqual(double.NaN, confidence[0].Min);
Assert.AreEqual(double.NaN, confidence[0].Max);
Assert.AreEqual(1, quartiles.Length);
Assert.AreEqual(52, quartiles[0].Min);
Assert.AreEqual(52, quartiles[0].Max);
Assert.AreEqual(1, innerFence.Length);
Assert.AreEqual(52, innerFence[0].Min);
Assert.AreEqual(52, innerFence[0].Max);
Assert.AreEqual(1, outerFence.Length);
Assert.AreEqual(52, outerFence[0].Min);
Assert.AreEqual(52, outerFence[0].Max);
}
/// <summary>
/// Launched when the user clicks the "Run analysis" button.
/// </summary>
///
private void btnCompute_Click(object sender, EventArgs e)
{
// Save any pending changes
dgvAnalysisSource.EndEdit();
if (dgvAnalysisSource.DataSource == null)
{
MessageBox.Show("Please load some data using File > Open!");
return;
}
// Creates a matrix from the source data table
double[,] sourceMatrix = (dgvAnalysisSource.DataSource as DataTable).ToMatrix(out columnNames);
// Create and compute a new Simple Descriptive Analysis
sda = new DescriptiveAnalysis(sourceMatrix, columnNames);
sda.Compute();
// Show the descriptive analysis on the screen
dgvDistributionMeasures.DataSource = sda.Measures;
// Create the kernel function
IKernel kernel = createKernel();
// Get the input values (the two first columns)
double[,] inputs = sourceMatrix.GetColumns(0, 1);
// Get only the associated labels (last column)
int[] outputs = sourceMatrix.GetColumn(2).ToInt32();
// Creates the Kernel Discriminant Analysis of the given data
kda = new KernelDiscriminantAnalysis(inputs, outputs, kernel);
// Keep only the important components
kda.Threshold = (double)numThreshold.Value;
kda.Compute(); // Finally, compute the analysis!
if (kda.Discriminants.Count < 2)
{
MessageBox.Show("Could not gather enough components to create"
+ "create a 2D plot. Please try a smaller threshold value.");
return;
}
// Perform the transformation of the data using two components
double[,] result = kda.Transform(inputs, 2);
// Create a new plot with the original Z column
double[,] points = result.InsertColumn(sourceMatrix.GetColumn(2));
// Create output scatter plot
outputScatterplot.DataSource = points;
createMappingScatterplot(graphMapFeature, points);
// Create output table
dgvProjectionResult.DataSource = new ArrayDataView(points, columnNames);
// Populates components overview with analysis data
dgvFeatureVectors.DataSource = new ArrayDataView(kda.DiscriminantMatrix);
dgvScatterBetween.DataSource = new ArrayDataView(kda.ScatterBetweenClass);
dgvScatterWithin.DataSource = new ArrayDataView(kda.ScatterWithinClass);
dgvScatterTotal.DataSource = new ArrayDataView(kda.ScatterMatrix);
dgvPrincipalComponents.DataSource = kda.Discriminants;
distributionView.DataSource = kda.Discriminants;
cumulativeView.DataSource = kda.Discriminants;
// Populates classes information
dgvClasses.DataSource = kda.Classes;
lbStatus.Text = "Good! Feel free to browse the other tabs to see what has been found.";
}
/// <summary>
/// Launched when the user clicks the "Run analysis" button.
/// </summary>
///
private void btnCompute_Click(object sender, EventArgs e)
{
// Save any pending changes
dgvAnalysisSource.EndEdit();
if (dgvAnalysisSource.DataSource == null)
{
MessageBox.Show("Please load some data using File > Open!");
return;
}
// Create a matrix from the source data table
double[,] sourceMatrix = (dgvAnalysisSource.DataSource as DataTable).ToMatrix(out columnNames);
int rows = sourceMatrix.GetLength(0);
int cols = sourceMatrix.GetLength(1);
// Create and compute a new Simple Descriptive Analysis
sda = new DescriptiveAnalysis(sourceMatrix, columnNames);
sda.Compute();
// Show the descriptive analysis on the screen
dgvDistributionMeasures.DataSource = sda.Measures;
// Create the kernel function
IKernel kernel = createKernel();
// Get the input values (the two first columns)
double[,] inputs = sourceMatrix.GetColumns(0, 1);
// Get only the associated labels (last column)
int[] outputs = sourceMatrix.GetColumn(2).ToInt32();
AnalysisMethod method = (AnalysisMethod)cbMethod.SelectedValue;
// Creates the Kernel Principal Component Analysis of the given source
kpca = new KernelPrincipalComponentAnalysis(inputs, kernel, method);
// Whether to center in space
kpca.Center = cbCenter.Checked;
kpca.Compute(); // Finally, compute the analysis!
double[,] result;
if (kpca.Components.Count >= 2)
{
// Perform the transformation of the data using two components
result = kpca.Transform(inputs, 2);
}
else
{
result = kpca.Transform(inputs, 1);
result = result.InsertColumn(Matrix.Vector(result.GetLength(0), 0.0));
}
// Create a new plot with the original Z column
double[,] points = result.InsertColumn(sourceMatrix.GetColumn(2));
// Create output scatter plot
outputScatterplot.DataSource = points;
CreateScatterplot(graphMapFeature, points);
// Create output table
dgvProjectionResult.DataSource = new ArrayDataView(points, columnNames);
dgvReversionSource.DataSource = new ArrayDataView(kpca.Result);
// Populates components overview with analysis data
dgvFeatureVectors.DataSource = new ArrayDataView(kpca.ComponentMatrix);
dgvPrincipalComponents.DataSource = kpca.Components;
dgvProjectionComponents.DataSource = kpca.Components;
dgvReversionComponents.DataSource = kpca.Components;
cumulativeView.DataSource = kpca.Components;
distributionView.DataSource = kpca.Components;
numComponents.Maximum = kpca.Components.Count;
numNeighbor.Maximum = kpca.Result.GetLength(0);
numNeighbor.Value = System.Math.Min(10, numNeighbor.Maximum);
lbStatus.Text = "Good! Feel free to browse the other tabs to see what has been found.";
}
/// <summary>
/// Launched when the user clicks the "Run analysis" button.
/// </summary>
///
private void btnCompute_Click(object sender, EventArgs e)
{
// Save any pending changes
dgvAnalysisSource.EndEdit();
if (dgvAnalysisSource.DataSource == null)
{
MessageBox.Show("Please load some data using File > Open!");
return;
}
// Create a matrix from the source data table
double[][] sourceMatrix = (dgvAnalysisSource.DataSource as DataTable).ToJagged(out columnNames);
// Create and compute a new Simple Descriptive Analysis
sda = new DescriptiveAnalysis()
{
ColumnNames = columnNames
};
sda.Learn(sourceMatrix);
// Show the descriptive analysis on the screen
dgvDistributionMeasures.DataSource = sda.Measures;
// Create the kernel function
IKernel kernel = createKernel();
// Get the input values (the two first columns)
this.inputs = sourceMatrix.GetColumns(0, 1);
// Get only the associated labels (last column)
this.outputs = sourceMatrix.GetColumn(2).ToMulticlass();
var method = (PrincipalComponentMethod)cbMethod.SelectedValue;
// Creates the Kernel Principal Component Analysis of the given source
kpca = new KernelPrincipalComponentAnalysis()
{
Kernel = kernel,
Method = method
};
// Whether to center in space
kpca.Center = cbCenter.Checked;
var classifier = kpca.Learn(inputs); // Finally, compute the analysis!
double[][] result = kpca.Transform(inputs);
double[][] reduced;
if (kpca.Components.Count >= 2)
{
// Perform the transformation of the data using two components
kpca.NumberOfOutputs = 2;
reduced = kpca.Transform(inputs);
}
else
{
kpca.NumberOfOutputs = 1;
reduced = kpca.Transform(inputs);
reduced = reduced.InsertColumn(Vector.Zeros(reduced.GetLength(0)));
}
// Create a new plot with the original Z column
double[][] points = reduced.InsertColumn(sourceMatrix.GetColumn(2));
// Create output scatter plot
outputScatterplot.DataSource = points;
CreateScatterplot(graphMapFeature, points);
// Create output table
dgvProjectionResult.DataSource = new ArrayDataView(points, columnNames);
dgvReversionSource.DataSource = new ArrayDataView(result);
// Populates components overview with analysis data
dgvFeatureVectors.DataSource = new ArrayDataView(kpca.ComponentVectors);
dgvPrincipalComponents.DataSource = kpca.Components;
cumulativeView.DataSource = kpca.Components;
distributionView.DataSource = kpca.Components;
numNeighbor.Maximum = result.Rows();
numNeighbor.Value = System.Math.Min(10, numNeighbor.Maximum);
lbStatus.Text = "Good! Feel free to browse the other tabs to see what has been found.";
}
private void button1_Click(object sender, EventArgs e)
{
// Finishes and save any pending changes to the given data
dgvAnalysisSource.EndEdit();
if (dgvAnalysisSource.DataSource == null) return;
// Creates a matrix from the source data table
double[,] sourceMatrix = (dgvAnalysisSource.DataSource as DataTable).ToMatrix(out sourceColumns);
int rows = sourceMatrix.GetLength(0);
int cols = sourceMatrix.GetLength(1);
// Creates a new Simple Descriptive Analysis
sda = new DescriptiveAnalysis(sourceMatrix, sourceColumns);
sda.Compute();
// Populates statistics overview tab with analysis data
dgvDistributionMeasures.DataSource = sda.Measures;
IKernel kernel;
if (rbGaussian.Checked)
{
kernel = new Gaussian((double)numSigma.Value);
}
else
{
kernel = new Polynomial((int)numDegree.Value, (double)numConstant.Value);
}
// Get only the input values (exclude the class label indicator column)
double[,] data = sourceMatrix.Submatrix(null, startColumn: 0, endColumn: 1);
// Get only the associated labels
int[] labels = sourceMatrix.GetColumn(2).ToInt32();
// Creates the Kernel Principal Component Analysis of the given source
kpca = new KernelPrincipalComponentAnalysis(data, kernel,
(AnalysisMethod)cbMethod.SelectedValue);
kpca.Center = cbCenter.Checked;
// Compute the analysis
kpca.Compute();
double[,] result;
if (kpca.Components.Count >= 2)
{
// Perform the transformation of the data using two components
result = kpca.Transform(data, 2);
}
else
{
result = kpca.Transform(data, 1);
result = result.InsertColumn(Matrix.Vector(result.GetLength(0), 0.0));
}
// Create a new plot with the original Z column
double[,] points = result.InsertColumn(sourceMatrix.GetColumn(2));
// Create output scatter plot
outputScatterplot.DataSource = points;
CreateScatterplot(graphMapFeature, points);
// Create output table
dgvProjectionResult.DataSource = new ArrayDataView(points, sourceColumns);
dgvReversionSource.DataSource = new ArrayDataView(kpca.Result);
// Populates components overview with analysis data
dgvFeatureVectors.DataSource = new ArrayDataView(kpca.ComponentMatrix);
dgvPrincipalComponents.DataSource = kpca.Components;
dgvProjectionComponents.DataSource = kpca.Components;
dgvReversionComponents.DataSource = kpca.Components;
numComponents.Maximum = kpca.Components.Count;
numNeighbor.Maximum = kpca.Result.GetLength(0);
numNeighbor.Value = System.Math.Min(10, numNeighbor.Maximum);
CreateComponentCumulativeDistributionGraph(graphCurve);
CreateComponentDistributionGraph(graphShare);
}
private static void test(DescriptiveAnalysis analysis)
{
var columnNames = analysis.ColumnNames;
var correlation = analysis.CorrelationMatrix;
var covariance = analysis.CovarianceMatrix;
var deviationScores = analysis.DeviationScores;
var distinct = analysis.Distinct;
var kurtosis = analysis.Kurtosis;
var means = analysis.Means;
var medians = analysis.Medians;
var modes = analysis.Modes;
var ranges = analysis.Ranges;
var samples = analysis.Samples;
var skewness = analysis.Skewness;
var source = analysis.Source;
var standardDeviation = analysis.StandardDeviations;
var standardErrors = analysis.StandardErrors;
var standardScores = analysis.StandardScores;
var sums = analysis.Sums;
var variables = analysis.Variables;
var variances = analysis.Variances;
var quartiles = analysis.Quartiles;
var inner = analysis.InnerFences;
var outer = analysis.OuterFences;
Assert.IsTrue(columnNames.IsEqual(new string[]
{
"Column 0",
"Column 1",
"Column 2",
}));
Assert.IsTrue(correlation.IsEqual(new double[, ]
{
{ 1.00000000000000000, -0.24074447786944278, 0 },
{ -0.24074447786944278, 1.00000000000000000, 0 },
{ 0.00000000000000000, 0.00000000000000000, 0 }
}));
Assert.IsTrue(covariance.IsEqual(new double[, ]
{
{ 0.3, -3.1, 0.0 },
{ -3.1, 552.7, 0.0 },
{ 0.0, 0.0, 0.0 }
}));
Assert.IsTrue(deviationScores.IsEqual(new double[, ]
{
{ -0.39999999999999991, 8.7999999999999972, 0.0 },
{ 0.60000000000000009, -31.200000000000003, 0.0 },
{ -0.39999999999999991, 21.799999999999997, 0.0 },
{ -0.39999999999999991, -18.200000000000003, 0.0 },
{ 0.60000000000000009, 18.799999999999997, 0.0 }
}));
Assert.IsTrue(distinct.IsEqual(new int[] { 2, 5, 1 }));
Assert.IsTrue(kurtosis.IsEqual(new double[] { -3.3333333333333321, -2.213664721197441, double.NaN }));
Assert.IsTrue(means.IsEqual(new double[] { 1.4, 43.2, 5.0 }));
Assert.IsTrue(medians.IsEqual(new double[] { 1.0, 52.0, 5.0 }));
Assert.IsTrue(modes.IsEqual(new double[] { 1.0, 12.0, 5.0 }));
Assert.IsTrue(ranges.Apply(p => p.Min).IsEqual(new double[] { 1, 12, 5 }));
Assert.IsTrue(ranges.Apply(p => p.Max).IsEqual(new double[] { 2, 65, 5 }));
Assert.IsTrue(samples == 5);
Assert.IsTrue(skewness.IsEqual(new double[] { 0.60858061945018527, -0.60008123614710385, double.NaN }));
Assert.IsTrue(source.IsEqual(new double[, ]
{
{ 1, 52, 5 },
{ 2, 12, 5 },
{ 1, 65, 5 },
{ 1, 25, 5 },
{ 2, 62, 5 },
}));
Assert.IsTrue(standardDeviation.IsEqual(new double[] { 0.54772255750516607, 23.509572518444482, 0.0 }));
Assert.IsTrue(standardErrors.IsEqual(new double[] { 0.24494897427831777, 10.513800454640558, 0.0 }));
Assert.IsTrue(standardScores.IsEqual(new double[, ]
{
{ -0.73029674334022132, 0.37431561093235277, 0.0 },
{ 1.0954451150103324, -1.3271189842147058, 0.0 },
{ -0.73029674334022132, 0.92728185435514676, 0.0 },
{ -0.73029674334022132, -0.77415274079191176, 0.0 },
{ 1.0954451150103324, 0.79967425971911732, 0.0 },
}));
Assert.IsTrue(sums.IsEqual(new double[] { 7, 216.0, 25 }));
Assert.IsTrue(variables == 3);
Assert.IsTrue(variances.IsEqual(new double[] { 0.3, 552.7, 0.0 }));
Assert.AreEqual(3, quartiles.Length);
Assert.AreEqual(1, quartiles[0].Min);
Assert.AreEqual(2, quartiles[0].Max);
Assert.AreEqual(18.5, quartiles[1].Min);
Assert.AreEqual(63.5, quartiles[1].Max);
Assert.AreEqual(18.5 - 1.5 * (63.5 - 18.5), inner[1].Min);
Assert.AreEqual(63.5 + 1.5 * (63.5 - 18.5), inner[1].Max);
Assert.AreEqual(18.5 - 3 * (63.5 - 18.5), outer[1].Min);
Assert.AreEqual(63.5 + 3 * (63.5 - 18.5), outer[1].Max);
Assert.AreEqual(5, quartiles[2].Min);
Assert.AreEqual(5, quartiles[2].Max);
}
private void button1_Click(object sender, EventArgs e)
{
// Finishes and save any pending changes to the given data
dgvAnalysisSource.EndEdit();
if (dgvAnalysisSource.DataSource == null) return;
// Creates a matrix from the source data table
double[,] sourceMatrix = (dgvAnalysisSource.DataSource as DataTable).ToMatrix(out sourceColumns);
// Creates a new Simple Descriptive Analysis
sda = new DescriptiveAnalysis(sourceMatrix, sourceColumns);
sda.Compute();
dgvDistributionMeasures.DataSource = sda.Measures;
// Populates statistics overview tab with analysis data
dgvDistributionMeasures.DataSource = sda.Measures;
IKernel kernel;
if (rbGaussian.Checked)
{
kernel = new Gaussian((double)numSigma.Value);
}
else
{
kernel = new Polynomial((int)numDegree.Value, (double)numConstant.Value);
}
// Get only the input values (exclude the class label indicator column)
double[,] data = sourceMatrix.Submatrix(null, startColumn: 0, endColumn: 1);
// Get only the associated labels
int[] labels = sourceMatrix.GetColumn(2).ToInt32();
// Creates the Kernel Discriminant Analysis of the given source
kda = new KernelDiscriminantAnalysis(data, labels, kernel);
// Keep all components
kda.Threshold = (double)numThreshold.Value;
// Computes the analysis
kda.Compute();
// Perform the transformation of the data using two components
double[,] result = kda.Transform(data, 2);
// Create a new plot with the original Z column
double[,] points = result.InsertColumn(sourceMatrix.GetColumn(2));
// Create output scatter plot
outputScatterplot.DataSource = points;
CreateScatterplot(graphMapFeature, points);
// Create output table
dgvProjectionResult.DataSource = new ArrayDataView(points, sourceColumns);
// Populates components overview with analysis data
dgvFeatureVectors.DataSource = new ArrayDataView(kda.DiscriminantMatrix);
dgvPrincipalComponents.DataSource = kda.Discriminants;
dgvScatterBetween.DataSource = new ArrayDataView(kda.ScatterBetweenClass);
dgvScatterWithin.DataSource = new ArrayDataView(kda.ScatterWithinClass);
dgvScatterTotal.DataSource = new ArrayDataView(kda.ScatterMatrix);
// Populates classes information
dgvClasses.DataSource = kda.Classes;
CreateComponentCumulativeDistributionGraph(graphCurve);
CreateComponentDistributionGraph(graphShare);
}
public void DescriptiveAnalysisTwoSampleTest()
{
double[][] data =
{
new [] { 52.0 },
new [] { 42.0 }
};
// Create the analysis
DescriptiveAnalysis analysis = new DescriptiveAnalysis(data);
// Compute
analysis.Compute();
var columnNames = analysis.ColumnNames;
var correlation = analysis.CorrelationMatrix;
var covariance = analysis.CovarianceMatrix;
var deviationScores = analysis.DeviationScores;
var distinct = analysis.Distinct;
var kurtosis = analysis.Kurtosis;
var means = analysis.Means;
var medians = analysis.Medians;
var modes = analysis.Modes;
var ranges = analysis.Ranges;
var samples = analysis.Samples;
var skewness = analysis.Skewness;
var source = analysis.Source;
var standardDeviation = analysis.StandardDeviations;
var standardErrors = analysis.StandardErrors;
var standardScores = analysis.StandardScores;
var sums = analysis.Sums;
var variables = analysis.Variables;
var variances = analysis.Variances;
var confidence = analysis.Confidence;
var quartiles = analysis.Quartiles;
var innerFence = analysis.InnerFences;
var outerFence = analysis.OuterFences;
Assert.IsTrue(columnNames.IsEqual(new string[]
{
"Column 0"
}));
Assert.IsTrue(correlation.IsEqual(Matrix.Create(1, 1, 0.99999999999999978)));
Assert.IsTrue(covariance.IsEqual(Matrix.Create(1, 1, 50.0)));
Assert.IsTrue(deviationScores.IsEqual(new double[, ] {
{ 5 }, { -5 }
}));
Assert.IsTrue(distinct.IsEqual(new int[] { 2 }));
Assert.IsTrue(kurtosis.IsEqual(new double[] { Double.NaN }));
Assert.IsTrue(means.IsEqual(new double[] { 47 }));
Assert.IsTrue(medians.IsEqual(new double[] { 94 }));
Assert.IsTrue(modes.IsEqual(new double[] { 52.0 }) ||
modes.IsEqual(new double[] { 42.0 }));
Assert.IsTrue(samples == 2);
Assert.IsTrue(skewness.IsEqual(new double[] { Double.NaN }));
Assert.IsTrue(source.IsEqual(new double[, ]
{
{ 52 },
{ 42 },
}));
Assert.IsTrue(standardDeviation.IsEqual(new double[] { 7.0710678118654755 }));
Assert.IsTrue(standardErrors.IsEqual(new double[] { 5.0 }));
Assert.IsTrue(standardScores.IsEqual(new double[, ]
{
{ 0.70710678118654746 }, { -0.70710678118654746 },
}));
Assert.IsTrue(sums.IsEqual(new double[] { 94 }));
Assert.IsTrue(variables == 1);
Assert.IsTrue(variances.IsEqual(new double[] { 50 }));
Assert.AreEqual(1, ranges.Length);
Assert.AreEqual(42, ranges[0].Min);
Assert.AreEqual(52, ranges[0].Max);
Assert.AreEqual(1, confidence.Length);
Assert.AreEqual(37.200180077299734, confidence[0].Min);
Assert.AreEqual(56.799819922700266, confidence[0].Max);
Assert.AreEqual(1, quartiles.Length);
Assert.AreEqual(73, quartiles[0].Min);
Assert.AreEqual(68, quartiles[0].Max);
Assert.AreEqual(1, innerFence.Length);
Assert.AreEqual(80.5, innerFence[0].Min);
Assert.AreEqual(60.5, innerFence[0].Max);
Assert.AreEqual(1, outerFence.Length);
Assert.AreEqual(88, outerFence[0].Min);
Assert.AreEqual(53, outerFence[0].Max);
}
public void DescriptiveAnalysisConstructorTest()
{
double[,] data = Matrix.Magic(3);
string[] columnNames = { "x", "y", "z" };
DescriptiveAnalysis target = new DescriptiveAnalysis(data, columnNames);
target.Compute();
Assert.AreEqual("x", target.ColumnNames[0]);
Assert.AreEqual("y", target.ColumnNames[1]);
Assert.AreEqual("z", target.ColumnNames[2]);
Assert.IsTrue(target.CorrelationMatrix.IsEqual(new double[,]
{
{ 1.0000, -0.7559, 0.1429 },
{ -0.7559, 1.0000, -0.7559 },
{ 0.1429, -0.7559, 1.0000 },
}, 0.0001));
Assert.IsTrue(target.CovarianceMatrix.IsEqual(new double[,]
{
{ 7, -8, 1 },
{ -8, 16, -8 },
{ 1, -8, 7 },
}, 0.00000001));
Assert.IsTrue(target.StandardScores.IsEqual(new double[,]
{
{ 1.1339, -1.0000, 0.3780 },
{ -0.7559, 0, 0.7559 },
{ -0.3780, 1.0000, -1.1339 },
}, 0.001));
Assert.IsTrue(target.Means.IsEqual(new double[] { 5, 5, 5 }));
Assert.IsTrue(target.StandardDeviations.IsEqual(new double[] { 2.6458, 4.0000, 2.6458 }, 0.001));
Assert.IsTrue(target.Medians.IsEqual(new double[] { 4, 5, 6 }));
Assert.AreEqual(3, target.Ranges[0].Min);
Assert.AreEqual(8, target.Ranges[0].Max);
Assert.AreEqual(1, target.Ranges[1].Min);
Assert.AreEqual(9, target.Ranges[1].Max);
Assert.AreEqual(2, target.Ranges[2].Min);
Assert.AreEqual(7, target.Ranges[2].Max);
Assert.AreEqual(3, target.Samples);
Assert.AreEqual(3, target.Variables);
Assert.IsTrue(target.Source.IsEqual(Matrix.Magic(3)));
Assert.IsTrue(target.Sums.IsEqual(new double[] { 15, 15, 15 }));
Assert.IsTrue(target.Variances.IsEqual(new double[] { 7, 16, 7 }));
}
public void DescriptiveAnalysisNSampleTest()
{
for (int i = 1; i < 100; i++)
{
double[] data = Matrix.Random(i, 0.0, 1.0);
// Create the analysis
DescriptiveAnalysis analysis = new DescriptiveAnalysis(data);
// Compute
analysis.Compute();
var columnNames = analysis.ColumnNames;
var correlation = analysis.CorrelationMatrix;
var covariance = analysis.CovarianceMatrix;
var deviationScores = analysis.DeviationScores;
var distinct = analysis.Distinct;
var kurtosis = analysis.Kurtosis;
var means = analysis.Means;
var medians = analysis.Medians;
var modes = analysis.Modes;
var ranges = analysis.Ranges;
var samples = analysis.Samples;
var skewness = analysis.Skewness;
var source = analysis.Source;
var standardDeviation = analysis.StandardDeviations;
var standardErrors = analysis.StandardErrors;
var standardScores = analysis.StandardScores;
var sums = analysis.Sums;
var variables = analysis.Variables;
var variances = analysis.Variances;
var confidence = analysis.Confidence;
var quartiles = analysis.Quartiles;
var innerFence = analysis.InnerFences;
var outerFence = analysis.OuterFences;
Assert.AreEqual(1, columnNames.Length);
Assert.AreEqual(1, correlation.Length);
Assert.AreEqual(1, covariance.Length);
Assert.AreEqual(i, deviationScores.Length);
Assert.AreEqual(1, distinct.Length);
Assert.AreEqual(1, kurtosis.Length);
Assert.AreEqual(1, means.Length);
Assert.AreEqual(1, medians.Length);
Assert.AreEqual(1, modes.Length);
Assert.AreEqual(1, ranges.Length);
Assert.AreEqual(i, samples);
Assert.AreEqual(1, skewness.Length);
Assert.AreEqual(i, source.Length);
Assert.AreEqual(1, standardDeviation.Length);
Assert.AreEqual(1, standardErrors.Length);
Assert.AreEqual(i, standardScores.Length);
Assert.AreEqual(1, sums.Length);
Assert.AreEqual(1, variables);
Assert.AreEqual(1, variances.Length);
Assert.AreEqual(1, confidence.Length);
Assert.AreEqual(1, innerFence.Length);
Assert.AreEqual(1, outerFence.Length);
Assert.AreEqual(1, quartiles.Length);
}
}
private void btnRunAnalysis_Click(object sender, EventArgs e)
{
if (dgvAnalysisSource.DataSource == null)
{
MessageBox.Show("Please load some data first.");
return;
}
// Finishes and save any pending changes to the given data
dgvAnalysisSource.EndEdit();
// Creates a matrix from the source data table
double[,] sourceMatrix = (dgvAnalysisSource.DataSource as DataTable).ToMatrix(out sourceColumnNames);
// Creates the Simple Descriptive Analysis of the given source
sda = new DescriptiveAnalysis(sourceMatrix, sourceColumnNames);
sda.Compute();
// Populates statistics overview tab with analysis data
dgvStatisticCenter.DataSource = new ArrayDataView(sda.DeviationScores, sourceColumnNames);
dgvStatisticStandard.DataSource = new ArrayDataView(sda.StandardScores, sourceColumnNames);
dgvStatisticCovariance.DataSource = new ArrayDataView(sda.CovarianceMatrix, sourceColumnNames);
dgvStatisticCorrelation.DataSource = new ArrayDataView(sda.CorrelationMatrix, sourceColumnNames);
dgvDistributionMeasures.DataSource = sda.Measures;
// Creates the Principal Component Analysis of the given source
pca = new PrincipalComponentAnalysis(sda.Source,
(AnalysisMethod)cbMethod.SelectedValue);
// Compute the Principal Component Analysis
pca.Compute();
// Populates components overview with analysis data
dgvFeatureVectors.DataSource = new ArrayDataView(pca.ComponentMatrix);
dgvPrincipalComponents.DataSource = pca.Components;
dgvProjectionComponents.DataSource = pca.Components;
numComponents.Maximum = pca.Components.Count;
numComponents.Value = 1;
numThreshold.Value = (decimal)pca.Components[0].CumulativeProportion * 100;
CreateComponentCumulativeDistributionGraph(graphCurve);
CreateComponentDistributionGraph(graphShare);
}
public DistributionAnalysis(DescriptiveAnalysis descriptiveAnalysis)
{
}
/// <summary>
/// Launched when the user clicks the "Run analysis" button.
/// </summary>
///
private void btnCompute_Click(object sender, EventArgs e)
{
// Save any pending changes
dgvAnalysisSource.EndEdit();
if (dgvAnalysisSource.DataSource == null)
{
MessageBox.Show("Please load some data using File > Open!");
return;
}
// Create a matrix from the source data table
double[][] sourceMatrix = (dgvAnalysisSource.DataSource as DataTable).ToArray(out columnNames);
// Create and compute a new Simple Descriptive Analysis
sda = new DescriptiveAnalysis(columnNames).Learn(sourceMatrix);
// Show the descriptive analysis on the screen
dgvDistributionMeasures.DataSource = sda.Measures;
// Populates statistics overview tab with analysis data
dgvStatisticCenter.DataSource = new ArrayDataView(sda.DeviationScores, columnNames);
dgvStatisticStandard.DataSource = new ArrayDataView(sda.StandardScores, columnNames);
dgvStatisticCovariance.DataSource = new ArrayDataView(sda.CovarianceMatrix, columnNames);
dgvStatisticCorrelation.DataSource = new ArrayDataView(sda.CorrelationMatrix, columnNames);
var method = (PrincipalComponentMethod)cbMethod.SelectedValue;
// Create the Principal Component Analysis of the data
pca = new PrincipalComponentAnalysis(method);
pca.Learn(sourceMatrix); // Finally, compute the analysis!
// Populate components overview with analysis data
dgvFeatureVectors.DataSource = new ArrayDataView(pca.ComponentVectors);
dgvPrincipalComponents.DataSource = pca.Components;
dgvProjectionComponents.DataSource = pca.Components;
distributionView.DataSource = pca.Components;
cumulativeView.DataSource = pca.Components;
numComponents.Maximum = pca.Components.Count;
numComponents.Value = 1;
numThreshold.Value = (decimal)pca.Components[0].CumulativeProportion * 100;
}
private void btnRunAnalysis_Click(object sender, EventArgs e)
{
if (dgvAnalysisSource.DataSource == null)
{
MessageBox.Show("Please load some data first.");
return;
}
// Finishes and save any pending changes to the given data
dgvAnalysisSource.EndEdit();
DataTable table = dgvAnalysisSource.DataSource as DataTable;
// Creates a matrix from the source data table
double[,] sourceMatrix = table.ToMatrix(out inputColumnNames);
// Creates the Simple Descriptive Analysis of the given source
sda = new DescriptiveAnalysis(sourceMatrix, inputColumnNames);
sda.Compute();
// Populates statistics overview tab with analysis data
dgvDistributionMeasures.DataSource = sda.Measures;
// Extract variables
List<string> inputNames = new List<string>();
foreach (string name in clbInput.CheckedItems)
inputNames.Add(name);
this.inputColumnNames = inputNames.ToArray();
List<string> outputNames = new List<string>();
foreach (string name in clbOutput.CheckedItems)
outputNames.Add(name);
this.outputColumnNames = outputNames.ToArray();
DataTable inputTable = table.DefaultView.ToTable(false, inputColumnNames);
DataTable outputTable = table.DefaultView.ToTable(false, outputColumnNames);
double[,] inputs = inputTable.ToMatrix();
double[,] outputs = outputTable.ToMatrix();
// Creates the Partial Least Squares of the given source
pls = new PartialLeastSquaresAnalysis(inputs, outputs,
(AnalysisMethod)cbMethod.SelectedValue,
(PartialLeastSquaresAlgorithm)cbAlgorithm.SelectedValue);
// Computes the Partial Least Squares
pls.Compute();
// Populates components overview with analysis data
dgvWeightMatrix.DataSource = new ArrayDataView(pls.Weights);
dgvFactors.DataSource = pls.Factors;
dgvAnalysisLoadingsInput.DataSource = new ArrayDataView(pls.Predictors.FactorMatrix);
dgvAnalysisLoadingsOutput.DataSource = new ArrayDataView(pls.Dependents.FactorMatrix);
this.regression = pls.CreateRegression();
dgvRegressionCoefficients.DataSource = new ArrayDataView(regression.Coefficients, outputColumnNames);
dgvRegressionIntercept.DataSource = new ArrayDataView(regression.Intercepts, outputColumnNames);
dgvProjectionComponents.DataSource = pls.Factors;
numComponents.Maximum = pls.Factors.Count;
numComponents.Value = 1;
dgvRegressionComponents.DataSource = pls.Factors;
numComponentsRegression.Maximum = pls.Factors.Count;
numComponentsRegression.Value = 1;
CreateComponentCumulativeDistributionGraph(graphCurve);
CreateComponentDistributionGraph(graphShare);
dgvProjectionSourceX.DataSource = inputTable;
dgvProjectionSourceY.DataSource = outputTable;
dgvRegressionInput.DataSource = table.DefaultView.ToTable(false, inputColumnNames.Concatenate(outputColumnNames));
}
public void DescriptiveAnalysisConstructorTest3()
{
// Suppose we would like to compute descriptive
// statistics from the following data samples:
double[] data = { 52, 12, 65, 25, 62, 12 };
// Create the analysis
DescriptiveAnalysis analysis = new DescriptiveAnalysis(data);
// Compute
analysis.Compute();
var columnNames = analysis.ColumnNames;
var correlation = analysis.CorrelationMatrix;
var covariance = analysis.CovarianceMatrix;
var deviationScores = analysis.DeviationScores;
var distinct = analysis.Distinct;
var kurtosis = analysis.Kurtosis;
var means = analysis.Means;
var medians = analysis.Medians;
var modes = analysis.Modes;
var ranges = analysis.Ranges;
var samples = analysis.Samples;
var skewness = analysis.Skewness;
var source = analysis.Source;
var standardDeviation = analysis.StandardDeviations;
var standardErrors = analysis.StandardErrors;
var standardScores = analysis.StandardScores;
var sums = analysis.Sums;
var variables = analysis.Variables;
var variances = analysis.Variances;
var confidence = analysis.Confidence;
var quartiles = analysis.Quartiles;
Assert.IsTrue(columnNames.IsEqual(new string[]
{
"Column 0",
}));
Assert.IsTrue(correlation.IsEqual(new double[,] { { 1 } }));
Assert.IsTrue(covariance.IsEqual(new double[,] { { 604.39999999999998 } }));
Assert.IsTrue(deviationScores.IsEqual(new double[,]
{
{ 14.0 },
{ -26.0 },
{ 27.0 },
{ -13.0 },
{ 24.0 },
{ -26.0 }
}));
Assert.IsTrue(distinct.IsEqual(new int[] { 5 }));
Assert.IsTrue(kurtosis.IsEqual(new double[] { -2.7161799571726601 }));
Assert.IsTrue(means.IsEqual(new double[] { 38.0 }));
Assert.IsTrue(medians.IsEqual(new double[] { 38.5 }));
Assert.IsTrue(modes.IsEqual(new double[] { 12.0 }));
Assert.IsTrue(ranges.Apply(p => p.Min).IsEqual(new double[] { 12 }));
Assert.IsTrue(ranges.Apply(p => p.Max).IsEqual(new double[] { 65 }));
Assert.IsTrue(samples == 6);
Assert.IsTrue(skewness.IsEqual(new double[] { -0.022168530787350427 }));
Assert.IsTrue(source.IsEqual(new double[,]
{
{ 52 },
{ 12 },
{ 65 },
{ 25 },
{ 62 },
{ 12 },
}));
Assert.IsTrue(standardDeviation.IsEqual(new double[] { 24.584547992590792 }));
Assert.IsTrue(standardErrors.IsEqual(new double[] { 10.036599689801987 }));
Assert.IsTrue(standardScores.IsEqual(new double[,]
{
{ 0.5694633883128245 },
{ -1.0575748640095313 },
{ 1.09825082031759 },
{ -0.52878743200476563 },
{ 0.97622295139341342 },
{ -1.0575748640095313 },
}));
Assert.IsTrue(sums.IsEqual(new double[] { 228.0 }));
Assert.IsTrue(variables == 1);
Assert.IsTrue(variances.IsEqual(new double[] { 604.39999999999998 }));
Assert.AreEqual(1, confidence.Length);
Assert.AreEqual(18.328626080742229, confidence[0].Min);
Assert.AreEqual(57.671373919257775, confidence[0].Max);
DoubleRange q;
double q2 = Accord.Statistics.Tools.Quartiles(data, out q, alreadySorted: false);
Assert.AreEqual(1, quartiles.Length);
Assert.AreEqual(q.Min, quartiles[0].Min);
Assert.AreEqual(q.Max, quartiles[0].Max);
Assert.AreEqual(12, quartiles[0].Min);
Assert.AreEqual(62, quartiles[0].Max);
}
private void btnSampleRunAnalysis_Click(object sender, EventArgs e)
{
// Check requirements
if (sourceTable == null)
{
MessageBox.Show("A sample spreadsheet can be found in the " +
"Resources folder in the same directory as this application.",
"Please load some data before attempting an analysis");
return;
}
if (checkedListBox1.CheckedItems.Count == 0)
{
MessageBox.Show("Please select the dependent input variables to be used in the regression model.",
"Please choose at least one input variable");
}
// Finishes and save any pending changes to the given data
dgvAnalysisSource.EndEdit();
sourceTable.AcceptChanges();
// Gets the column of the dependent variable
String dependentName = (string)comboBox1.SelectedItem;
DataTable dependent = sourceTable.DefaultView.ToTable(false, dependentName);
// Gets the columns of the independent variables
List<string> names = new List<string>();
foreach (string name in checkedListBox1.CheckedItems)
names.Add(name);
String[] independentNames = names.ToArray();
DataTable independent = sourceTable.DefaultView.ToTable(false, independentNames);
// Creates the input and output matrices from the source data table
double[][] input = independent.ToArray();
double[] output = dependent.Columns[dependentName].ToArray();
double[,] sourceMatrix = sourceTable.ToMatrix(independentNames);
// Creates the Simple Descriptive Analysis of the given source
DescriptiveAnalysis sda = new DescriptiveAnalysis(sourceMatrix, independentNames);
sda.Compute();
// Populates statistics overview tab with analysis data
dgvDistributionMeasures.DataSource = sda.Measures;
// Creates the Logistic Regression Analysis of the given source
lra = new LogisticRegressionAnalysis(input, output, independentNames, dependentName);
// Compute the Logistic Regression Analysis
lra.Compute();
// Populates coefficient overview with analysis data
dgvLogisticCoefficients.DataSource = lra.Coefficients;
// Populate details about the fitted model
tbChiSquare.Text = lra.ChiSquare.Statistic.ToString("N5");
tbPValue.Text = lra.ChiSquare.PValue.ToString("N5");
checkBox1.Checked = lra.ChiSquare.Significant;
tbDeviance.Text = lra.Deviance.ToString("N5");
tbLogLikelihood.Text = lra.LogLikelihood.ToString("N5");
// Create the Multiple Linear Regression Analysis of the given source
mlr = new MultipleLinearRegressionAnalysis(input, output, independentNames, dependentName, true);
// Compute the Linear Regression Analysis
mlr.Compute();
dgvLinearCoefficients.DataSource = mlr.Coefficients;
dgvRegressionAnova.DataSource = mlr.Table;
tbRSquared.Text = mlr.RSquared.ToString("N5");
tbRSquaredAdj.Text = mlr.RSquareAdjusted.ToString("N5");
tbChiPValue.Text = mlr.ChiSquareTest.PValue.ToString("N5");
tbFPValue.Text = mlr.FTest.PValue.ToString("N5");
tbZPValue.Text = mlr.ZTest.PValue.ToString("N5");
tbChiStatistic.Text = mlr.ChiSquareTest.Statistic.ToString("N5");
tbFStatistic.Text = mlr.FTest.Statistic.ToString("N5");
tbZStatistic.Text = mlr.ZTest.Statistic.ToString("N5");
cbChiSignificant.Checked = mlr.ChiSquareTest.Significant;
cbFSignificant.Checked = mlr.FTest.Significant;
cbZSignificant.Checked = mlr.ZTest.Significant;
// Populate projection source table
string[] cols = independentNames;
if (!independentNames.Contains(dependentName))
cols = independentNames.Concatenate(dependentName);
DataTable projSource = sourceTable.DefaultView.ToTable(false, cols);
dgvProjectionSource.DataSource = projSource;
}
private ArrayDataView AnalysisData(DataTable dataTable)
{
DescriptiveAnalysis analysis;
string[] columnNames;
double[,] arrayData = dataTable.ToMatrix(out columnNames);
// Analysis Data
analysis = new DescriptiveAnalysis(arrayData, columnNames);
analysis.Compute();
double[,] analysisData = new double[0, arrayData.GetLength(1)];
analysisData = analysisData.InsertRow<double>(analysis.Distinct.ToDouble(), analysisData.GetLength(0));
analysisData = analysisData.InsertRow<double>(analysis.Means, analysisData.GetLength(0));
analysisData = analysisData.InsertRow<double>(analysis.Medians, analysisData.GetLength(0));
analysisData = analysisData.InsertRow<double>(analysis.Modes, analysisData.GetLength(0));
analysisData = analysisData.InsertRow<double>(analysis.StandardDeviations, analysisData.GetLength(0));
analysisData = analysisData.InsertRow<double>(analysis.Variances, analysisData.GetLength(0));
analysisData = analysisData.InsertRow<double>(analysis.Sums, analysisData.GetLength(0));
string[] rowNames = { "Distinct", "Means", "Medians", "Modes", "StandardDeviations", "Variances", "Sums" };
return new ArrayDataView(analysisData, columnNames, rowNames);
}
