public void ComputeTest1()
{
double[][] inputs = training.Submatrix(null, 0, 3);
double[] outputs = training.GetColumn(4);
var regression = new LogisticRegressionAnalysis(inputs, outputs);
bool converged = regression.Compute();
Assert.IsTrue(converged);
double[] actual = regression.Result;
double[] expected =
{
0.000012, 0.892611, 0.991369, 0.001513, 0.904055,
0.001446, 0.998673, 0.001260, 0.629312, 0.004475,
0.505362, 0.999791, 0.000050, 1.000000, 0.990362,
0.985265, 1.000000, 1.000000, 0.001319, 0.000001,
0.000001, 0.000050, 0.702488, 0.003049, 0.000046,
0.000419, 0.026276, 0.036813, 0.000713, 0.001484,
0.000008, 0.000009, 0.278950, 0.001402, 0.025764,
0.002464, 0.000219, 0.007328, 0.000106, 0.002619,
0.002913, 0.000002,
};
for (int i = 0; i < expected.Length; i++)
{
Assert.AreEqual(expected[i], actual[i], 1e-6);
}
}
public void ComputeTest1()
{
double[][] inputs = training.Submatrix(null, 0, 3);
double[] outputs = training.GetColumn(4);
var regression = new LogisticRegressionAnalysis(inputs, outputs);
bool converged = regression.Compute();
Assert.IsTrue(converged);
double[] actual = regression.Result;
double[] expected =
{
0.000012, 0.892611, 0.991369, 0.001513, 0.904055,
0.001446, 0.998673, 0.001260, 0.629312, 0.004475,
0.505362, 0.999791, 0.000050, 1.000000, 0.990362,
0.985265, 1.000000, 1.000000, 0.001319, 0.000001,
0.000001, 0.000050, 0.702488, 0.003049, 0.000046,
0.000419, 0.026276, 0.036813, 0.000713, 0.001484,
0.000008, 0.000009, 0.278950, 0.001402, 0.025764,
0.002464, 0.000219, 0.007328, 0.000106, 0.002619,
0.002913, 0.000002,
};
for (int i = 0; i < expected.Length; i++)
Assert.AreEqual(expected[i], actual[i], 1e-6);
}
public void ComputeTest2()
{
// Test instance 01
double[][] trainInput =
{
new double[] { 1, 1 },
new double[] { 0, 0 },
};
double[] trainOutput = { 1, 0 };
double[] testInput = { 0, 0.2 };
var target = new LogisticRegressionAnalysis(trainInput, trainOutput);
target.Regularization = 1e-10;
target.Compute();
double[] coef = target.Coefficients.Apply(x => x.Value);
Assert.AreEqual(coef[0], -19.360661491141897);
Assert.AreEqual(coef[1], 19.702873967721807);
Assert.AreEqual(coef[2], 19.702873967721807);
double output = target.Regression.Compute(testInput);
Assert.AreEqual(0, output, 1e-6);
// Test instance 02
trainInput = new double[][]
{
new double[] { 1, 0, 1, 1, 0, 1, 1, 0, 1, 0 },
new double[] { 0, 1, 0, 1, 1, 0, 1, 1, 0, 1 },
new double[] { 1, 1, 0, 0, 1, 1, 0, 1, 1, 1 },
new double[] { 1, 0, 1, 1, 0, 1, 1, 0, 1, 0 },
new double[] { 0, 1, 0, 1, 1, 0, 1, 1, 0, 1 },
new double[] { 1, 1, 0, 0, 1, 1, 0, 1, 1, 1 },
};
trainOutput = new double[6] {
1, 1, 0, 0, 1, 1
};
target = new LogisticRegressionAnalysis(trainInput, trainOutput);
Assert.IsTrue(target.Compute());
double[] actual = target.Regression.Compute(trainInput);
//string str = actual.ToCSharp();
double[] expected = { 0.500000000158903, 0.999999998410966, 0.500000000913694, 0.500000000158903, 0.999999998410966, 0.500000000913694 };
Assert.IsTrue(actual.IsEqual(expected, 1e-6));
coef = target.Coefficients.Apply(x => x.Value);
//string str = coef.ToCSharp();
expected = new double[] { 1.86680346470929, -3.87720719574071, 2.44120453079343, -0.574401066088034, 5.16960959435804, 2.44120453079343, -3.87720719574087, 5.16960959435804, 2.44120453079343, -3.87720719574087, 2.44120453079343 };
Assert.IsTrue(coef.IsEqual(expected, 1e-6));
}
public void ComputeTest2()
{
// Test instance 01
double[][] trainInput =
{
new double[] { 1, 1 },
new double[] { 0, 0 },
};
double[] trainOutput = { 1, 0 };
double[] testInput = { 0, 0.2 };
LogisticRegressionAnalysis target = new LogisticRegressionAnalysis(trainInput, trainOutput);
target.Regularization = 0;
target.Compute();
foreach (var coefficient in target.Coefficients)
{
Assert.IsFalse(double.IsNaN(coefficient.Value));
}
double output = target.Regression.Compute(testInput);
Assert.AreEqual(0, output, 1e-10);
Assert.IsFalse(double.IsNaN(output));
// Test instance 02
trainInput = new double[][]
{
new double[] { 1, 0, 1, 1, 0, 1, 1, 0, 1, 0 },
new double[] { 0, 1, 0, 1, 1, 0, 1, 1, 0, 1 },
new double[] { 1, 1, 0, 0, 1, 1, 0, 1, 1, 1 },
new double[] { 1, 0, 1, 1, 0, 1, 1, 0, 1, 0 },
new double[] { 0, 1, 0, 1, 1, 0, 1, 1, 0, 1 },
new double[] { 1, 1, 0, 0, 1, 1, 0, 1, 1, 1 },
};
trainOutput = new double[6] {
1, 1, 0, 0, 1, 1
};
target = new LogisticRegressionAnalysis(trainInput, trainOutput);
bool expected = true;
bool actual = target.Compute();
foreach (LogisticCoefficient coefficient in target.Coefficients)
{
Assert.IsFalse(double.IsNaN(coefficient.Value));
}
Assert.AreEqual(expected, actual);
}
public void ComputeTest3()
{
double[][] inputs = training.Submatrix(null, 0, 3);
double[] outputs = training.GetColumn(4);
LogisticRegressionAnalysis regression = new LogisticRegressionAnalysis(inputs, outputs);
bool expected = false;
bool actual = regression.Compute(1e-5, 3);
Assert.AreEqual(expected, actual);
}
public void ComputeTest2()
{
// Test instance 01
double[][] trainInput =
{
new double[] { 1, 1 },
new double[] { 0, 0 },
};
double[] trainOutput = { 1, 0 };
double[] testInput = { 0, 0.2 };
LogisticRegressionAnalysis target = new LogisticRegressionAnalysis(trainInput, trainOutput);
target.Regularization = 0;
target.Compute();
foreach (var coefficient in target.Coefficients)
Assert.IsFalse(double.IsNaN(coefficient.Value));
double output = target.Regression.Compute(testInput);
Assert.AreEqual(0, output, 1e-10);
Assert.IsFalse(double.IsNaN(output));
// Test instance 02
trainInput = new double[][]
{
new double[] { 1, 0, 1, 1, 0, 1, 1, 0, 1, 0 },
new double[] { 0, 1, 0, 1, 1, 0, 1, 1, 0, 1 },
new double[] { 1, 1, 0, 0, 1, 1, 0, 1, 1, 1 },
new double[] { 1, 0, 1, 1, 0, 1, 1, 0, 1, 0 },
new double[] { 0, 1, 0, 1, 1, 0, 1, 1, 0, 1 },
new double[] { 1, 1, 0, 0, 1, 1, 0, 1, 1, 1 },
};
trainOutput = new double[6] { 1, 1, 0, 0, 1, 1 };
target = new LogisticRegressionAnalysis(trainInput, trainOutput);
bool expected = true;
bool actual = target.Compute();
foreach (LogisticCoefficient coefficient in target.Coefficients)
Assert.IsFalse(double.IsNaN(coefficient.Value));
Assert.AreEqual(expected, actual);
}
public void DoStepTest()
{
double[][] inputs = Matrix.Expand(
new double[][] {
new double[] { 0, 0, 0 },
new double[] { 1, 0, 0 },
new double[] { 0, 1, 0 },
new double[] { 1, 1, 0 },
new double[] { 0, 0, 1 },
new double[] { 1, 0, 1 },
new double[] { 0, 1, 1 },
new double[] { 1, 1, 1 },
}, new int[] { 60, 17, 8, 2, 187, 85, 51, 23 });
double[] outputs = Matrix.Expand(
new double[] { 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0 },
new int[] { 5, 60 - 5, 2, 17 - 2, 1, 8 - 1, 0, 2 - 0, 35, 187 - 35, 13, 85 - 13, 15, 51 - 15, 8, 23 - 8 });
var target2 = new LogisticRegressionAnalysis(inputs, outputs);
target2.Compute();
Assert.AreEqual(target2.CoefficientValues[0], -2.377661, 0.0001);
Assert.AreEqual(target2.CoefficientValues[1], -0.067775, 0.0001);
Assert.AreEqual(target2.CoefficientValues[2], 0.69531, 0.0001);
Assert.AreEqual(target2.CoefficientValues[3], 0.871939, 0.0001);
var target = new StepwiseLogisticRegressionAnalysis(
inputs, outputs,
new string[] { "x1", "x2", "x3" }, "Y"
);
target.Threshold = 0.15;
int actual;
actual = target.DoStep();
Assert.AreEqual(0, actual);
actual = target.DoStep();
Assert.AreEqual(-1, actual);
}
public void Learn(out double misclassificationError)
{
var inputs = trainingExamples.Select(e => e.Features.Values).ToArray();
var outputs = trainingExamples.Select(e => (double)e.Expected).ToArray();
regression = new LogisticRegressionAnalysis(inputs, outputs);
regression.Compute();
misclassificationError = 0.0;
foreach (var example in trainingExamples)
{
var expected = example.Expected;
var actual = Classify(example.Features);
if (Math.Abs(actual - expected) > 1e-5)
{
misclassificationError += 1.0;
}
}
misclassificationError /= trainingExamples.Count;
}
public void FromSummaryTest1()
{
// Suppose we have a (fictitious) data set about patients who
// underwent cardiac surgery. The first column gives the number
// of arterial bypasses performed during the surgery. The second
// column gives the number of patients whose surgery went well,
// while the third column gives the number of patients who had
// at least one complication during the surgery.
//
int[,] data =
{
// # of stents success complications
{ 1, 140, 45 },
{ 2, 130, 60 },
{ 3, 150, 31 },
{ 4, 96, 65 }
};
double[][] inputs = data.GetColumn(0).ToDouble().ToJagged();
int[] positive = data.GetColumn(1);
int[] negative = data.GetColumn(2);
// Create a new Logistic Regression Analysis from the summary data
var regression = LogisticRegressionAnalysis.FromSummary(inputs, positive, negative);
regression.Compute(); // compute the analysis.
// Now we can show a summary of the analysis
// Accord.Controls.DataGridBox.Show(regression.Coefficients);
// We can also investigate all parameters individually. For
// example the coefficients values will be available at the
// vector
double[] coef = regression.CoefficientValues;
// The first value refers to the model's intercept term. We
// can also retrieve the odds ratios and standard errors:
double[] odds = regression.OddsRatios;
double[] stde = regression.StandardErrors;
// Finally, we can use it to estimate risk for a new patient
double y = regression.Regression.Compute(new double[] { 4 });
Assert.AreEqual(3.7586367581050162, odds[0], 1e-8);
Assert.AreEqual(0.85772731075090014, odds[1], 1e-8);
Assert.AreEqual(0.20884336554629004, stde[0], 1e-8);
Assert.AreEqual(0.075837785246620285, stde[1], 1e-8);
Assert.AreEqual(0.67044096045332713, y, 1e-8);
LogisticRegressionAnalysis expected;
{
int[] qtr = data.GetColumn(0);
var expanded = Accord.Statistics.Tools.Expand(qtr, positive, negative);
double[][] inp = expanded.GetColumn(0).ToDouble().ToJagged();
double[] outputs = expanded.GetColumn(1).ToDouble();
expected = new LogisticRegressionAnalysis(inp, outputs);
expected.Compute();
double slope = expected.Coefficients[1].Value; // should return -0.153
double inter = expected.Coefficients[0].Value;
double value = expected.ChiSquare.PValue; // should return 0.042
Assert.AreEqual(-0.15346904821339602, slope, 1e-8);
Assert.AreEqual(1.324056323049271, inter, 1e-8);
Assert.AreEqual(0.042491262992507946, value, 1e-8);
}
var actual = regression;
Assert.AreEqual(expected.Coefficients[0].Value, actual.Coefficients[0].Value, 1e-8);
Assert.AreEqual(expected.Coefficients[1].Value, actual.Coefficients[1].Value, 1e-8);
Assert.AreEqual(expected.ChiSquare.PValue, actual.ChiSquare.PValue, 1e-8);
Assert.AreEqual(expected.WaldTests[0].PValue, actual.WaldTests[0].PValue, 1e-8);
Assert.AreEqual(expected.WaldTests[1].PValue, actual.WaldTests[1].PValue, 1e-8);
Assert.AreEqual(expected.Confidences[0].Max, actual.Confidences[0].Max, 1e-6);
Assert.AreEqual(expected.Confidences[0].Min, actual.Confidences[0].Min, 1e-6);
Assert.AreEqual(expected.Confidences[1].Max, actual.Confidences[1].Max, 1e-6);
Assert.AreEqual(expected.Confidences[1].Min, actual.Confidences[1].Min, 1e-6);
}
public void ComputeTest4()
{
// Suppose we have the following data about some patients.
// The first variable is continuous and represent patient
// age. The second variable is dichotomic and give whether
// they smoke or not (this is completely fictional data).
double[][] inputs =
{
// Age Smoking
new double[] { 55, 0 },
new double[] { 28, 0 },
new double[] { 65, 1 },
new double[] { 46, 0 },
new double[] { 86, 1 },
new double[] { 56, 1 },
new double[] { 85, 0 },
new double[] { 33, 0 },
new double[] { 21, 1 },
new double[] { 42, 1 },
};
// Additionally, we also have information about whether
// or not they those patients had lung cancer. The array
// below gives 0 for those who did not, and 1 for those
// who did.
double[] output =
{
0, 0, 0, 1, 1, 1, 0, 0, 0, 1
};
// Create a Logistic Regression analysis
var regression = new LogisticRegressionAnalysis(inputs, output);
regression.Regularization = 0;
regression.Compute(); // compute the analysis.
// Now we can show a summary of the analysis
// Accord.Controls.DataGridBox.Show(regression.Coefficients);
// We can also investigate all parameters individually. For
// example the coefficients values will be available at the
// vector
double[] coef = regression.CoefficientValues;
// The first value refers to the model's intercept term. We
// can also retrieve the odds ratios and standard errors:
double[] odds = regression.OddsRatios;
double[] stde = regression.StandardErrors;
// Finally, we can also use the analysis to classify a new patient
double y = regression.Regression.Compute(new double[] { 87, 1 });
// For those inputs, the answer probability is approximately 75%.
Assert.AreEqual(0.085627701183146374, odds[0], 1e-8);
Assert.AreEqual(1.0208597029292648, odds[1], 1e-8);
Assert.AreEqual(5.8584748981777919, odds[2], 1e-8);
Assert.AreEqual(2.1590686019473897, stde[0], 1e-8);
Assert.AreEqual(0.033790422321041035, stde[1], 1e-8);
Assert.AreEqual(1.4729903935788211, stde[2], 1e-8);
Assert.AreEqual(0.75143272858389798, y, 1e-8);
}
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);
//}
}
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 RegressTest()
{
double[,] inputGrouped =
{
{ 1, 4, 5 }, // product 1 has four occurrences of class 1 and five of class 0
{ 2, 1, 3 }, // product 2 has one occurrence of class 1 and three of class 0
};
double[,] inputGroupProb =
{
{ 1, 4.0 / (4 + 5) }, // product 1 has 0.44 probability of belonging to class 1
{ 2, 1.0 / (1 + 3) }, // product 2 has 0.25 probability of belonging to class 1
};
double[,] inputExtended =
{
{ 1, 1 }, // observation of product 1 in class 1
{ 1, 1 }, // observation of product 1 in class 1
{ 1, 1 }, // observation of product 1 in class 1
{ 1, 1 }, // observation of product 1 in class 1
{ 1, 0 }, // observation of product 1 in class 0
{ 1, 0 }, // observation of product 1 in class 0
{ 1, 0 }, // observation of product 1 in class 0
{ 1, 0 }, // observation of product 1 in class 0
{ 1, 0 }, // observation of product 1 in class 0
{ 2, 1 }, // observation of product 2 in class 1
{ 2, 0 }, // observation of product 2 in class 0
{ 2, 0 }, // observation of product 2 in class 0
{ 2, 0 }, // observation of product 2 in class 0
};
// Fit using extended data
double[][] inputs = Matrix.ColumnVector(inputExtended.GetColumn(0)).ToArray();
double[] outputs = inputExtended.GetColumn(1);
LogisticRegression target = new LogisticRegression(1);
IterativeReweightedLeastSquares irls = new IterativeReweightedLeastSquares(target);
irls.Run(inputs, outputs);
// Fit using grouped data
double[][] inputs2 = Matrix.ColumnVector(inputGroupProb.GetColumn(0)).ToArray();
double[] outputs2 = inputGroupProb.GetColumn(1);
LogisticRegression target2 = new LogisticRegression(1);
IterativeReweightedLeastSquares irls2 = new IterativeReweightedLeastSquares(target2);
irls2.Run(inputs2, outputs2);
Assert.IsTrue(Matrix.IsEqual(target.Coefficients, target2.Coefficients, 0.000001));
double[,] data = new double[, ]
{
{ 1, 0 },
{ 2, 0 },
{ 3, 0 },
{ 4, 0 },
{ 5, 1 },
{ 6, 0 },
{ 7, 1 },
{ 8, 0 },
{ 9, 1 },
{ 10, 1 }
};
double[][] inputs3 = Matrix.ColumnVector(data.GetColumn(0)).ToArray();
double[] outputs3 = data.GetColumn(1);
LogisticRegressionAnalysis analysis = new LogisticRegressionAnalysis(inputs3, outputs3);
analysis.Compute();
Assert.IsFalse(double.IsNaN(analysis.Deviance));
Assert.IsFalse(double.IsNaN(analysis.ChiSquare.PValue));
Assert.AreEqual(analysis.Deviance, 8.6202, 0.0005);
Assert.AreEqual(analysis.ChiSquare.PValue, 0.0278, 0.0005);
// Check intercept
Assert.IsFalse(double.IsNaN(analysis.Coefficients[0].Value));
Assert.AreEqual(analysis.Coefficients[0].Value, -4.3578, 0.0005);
// Check coefficients
Assert.IsFalse(double.IsNaN(analysis.Coefficients[1].Value));
Assert.AreEqual(analysis.Coefficients[1].Value, 0.6622, 0.0005);
// Check statistics
Assert.AreEqual(analysis.Coefficients[1].StandardError, 0.4001, 0.0005);
Assert.AreEqual(analysis.Coefficients[1].Wald.PValue, 0.0979, 0.0005);
Assert.AreEqual(analysis.Coefficients[1].OddsRatio, 1.9391, 0.0005);
Assert.AreEqual(analysis.Coefficients[1].ConfidenceLower, 0.8852, 0.0005);
Assert.AreEqual(analysis.Coefficients[1].ConfidenceUpper, 4.2478, 0.0005);
Assert.IsFalse(double.IsNaN(analysis.Coefficients[1].Wald.PValue));
Assert.IsFalse(double.IsNaN(analysis.Coefficients[1].StandardError));
Assert.IsFalse(double.IsNaN(analysis.Coefficients[1].OddsRatio));
Assert.IsFalse(double.IsNaN(analysis.Coefficients[1].ConfidenceLower));
Assert.IsFalse(double.IsNaN(analysis.Coefficients[1].ConfidenceUpper));
}
public void RegressTest()
{
double[,] inputGrouped =
{
{ 1, 4, 5 }, // product 1 has four occurances of class 1 and five of class 0
{ 2, 1, 3 }, // product 2 has one occurance of class 1 and three of class 0
};
double[,] inputGroupProb =
{
{ 1, 4.0 / (4 + 5) }, // product 1 has 0.44 probability of belonging to class 1
{ 2, 1.0 / (1 + 3) }, // product 2 has 0.25 probability of belonging to class 1
};
double[,] inputExtended =
{
{ 1, 1 }, // observation of product 1 in class 1
{ 1, 1 }, // observation of product 1 in class 1
{ 1, 1 }, // observation of product 1 in class 1
{ 1, 1 }, // observation of product 1 in class 1
{ 1, 0 }, // observation of product 1 in class 0
{ 1, 0 }, // observation of product 1 in class 0
{ 1, 0 }, // observation of product 1 in class 0
{ 1, 0 }, // observation of product 1 in class 0
{ 1, 0 }, // observation of product 1 in class 0
{ 2, 1 }, // observation of product 2 in class 1
{ 2, 0 }, // observation of product 2 in class 0
{ 2, 0 }, // observation of product 2 in class 0
{ 2, 0 }, // observation of product 2 in class 0
};
// Fit using extended data
double[][] inputs = Matrix.ColumnVector(inputExtended.GetColumn(0)).ToArray();
double[] outputs = inputExtended.GetColumn(1);
LogisticRegression target = new LogisticRegression(1);
IterativeReweightedLeastSquares irls = new IterativeReweightedLeastSquares(target);
irls.Run(inputs, outputs);
// Fit using grouped data
double[][] inputs2 = Matrix.ColumnVector(inputGroupProb.GetColumn(0)).ToArray();
double[] outputs2 = inputGroupProb.GetColumn(1);
LogisticRegression target2 = new LogisticRegression(1);
IterativeReweightedLeastSquares irls2 = new IterativeReweightedLeastSquares(target2);
irls2.Run(inputs2, outputs2);
Assert.IsTrue(Matrix.IsEqual(target.Coefficients, target2.Coefficients, 0.000001));
double[,] data = new double[,]
{
{ 1, 0 },
{ 2, 0 },
{ 3, 0 },
{ 4, 0 },
{ 5, 1 },
{ 6, 0 },
{ 7, 1 },
{ 8, 0 },
{ 9, 1 },
{ 10, 1 }
};
double[][] inputs3 = Matrix.ColumnVector(data.GetColumn(0)).ToArray();
double[] outputs3 = data.GetColumn(1);
LogisticRegressionAnalysis analysis = new LogisticRegressionAnalysis(inputs3, outputs3);
analysis.Compute();
Assert.IsFalse(double.IsNaN(analysis.Deviance));
Assert.IsFalse(double.IsNaN(analysis.ChiSquare.PValue));
Assert.AreEqual(analysis.Deviance, 8.6202, 0.0005);
Assert.AreEqual(analysis.ChiSquare.PValue, 0.0278, 0.0005);
// Check intercept
Assert.IsFalse(double.IsNaN(analysis.Coefficients[0].Value));
Assert.AreEqual(analysis.Coefficients[0].Value, -4.3578, 0.0005);
// Check coefficients
Assert.IsFalse(double.IsNaN(analysis.Coefficients[1].Value));
Assert.AreEqual(analysis.Coefficients[1].Value, 0.6622, 0.0005);
// Check statistics
Assert.AreEqual(analysis.Coefficients[1].StandardError, 0.4001, 0.0005);
Assert.AreEqual(analysis.Coefficients[1].Wald.PValue, 0.0979, 0.0005);
Assert.AreEqual(analysis.Coefficients[1].OddsRatio, 1.9391, 0.0005);
Assert.AreEqual(analysis.Coefficients[1].ConfidenceLower, 0.8852, 0.0005);
Assert.AreEqual(analysis.Coefficients[1].ConfidenceUpper, 4.2478, 0.0005);
Assert.IsFalse(double.IsNaN(analysis.Coefficients[1].Wald.PValue));
Assert.IsFalse(double.IsNaN(analysis.Coefficients[1].StandardError));
Assert.IsFalse(double.IsNaN(analysis.Coefficients[1].OddsRatio));
Assert.IsFalse(double.IsNaN(analysis.Coefficients[1].ConfidenceLower));
Assert.IsFalse(double.IsNaN(analysis.Coefficients[1].ConfidenceUpper));
}
public void ComputeTest4()
{
// Suppose we have the following data about some patients.
// The first variable is continuous and represent patient
// age. The second variable is dichotomic and give whether
// they smoke or not (this is completely fictional data).
double[][] inputs = new double[][]
{
// Age Smoking
new double[] { 55, 0 },
new double[] { 28, 0 },
new double[] { 65, 1 },
new double[] { 46, 0 },
new double[] { 86, 1 },
new double[] { 56, 1 },
new double[] { 85, 0 },
new double[] { 33, 0 },
new double[] { 21, 1 },
new double[] { 42, 1 },
};
// Additionally, we also have information about whether
// or not they those patients had lung cancer. The array
// below gives 0 for those who did not, and 1 for those
// who did.
double[] output = new double[]
{
0, 0, 0, 1, 1, 1, 0, 0, 0, 1
};
// Create a Logistic Regression analysis
var regression = new LogisticRegressionAnalysis(inputs, output);
regression.Compute(); // compute the analysis.
// Now we can show a summary of the analysis
// DataGridBox.Show(regression.Coefficients);
// We can also investigate all parameters individually. For
// example the coefficients values will be available at the
// vector
double[] coef = regression.CoefficientValues;
// The first value refers to the model's intercept term. We
// can also retrieve the odds ratios and standard errors:
double[] odds = regression.OddsRatios;
double[] stde = regression.StandardErrors;
// Finally, we can also use the analysis to classify a new patient
double y = regression.Regression.Compute(new double[] { 87, 1 });
// For those inputs, the answer probability is approximately 75%.
Assert.AreEqual(0.085627701654393359, odds[0], 1e-10);
Assert.AreEqual(1.0208597028836701, odds[1], 1e-10);
Assert.AreEqual(5.8584748789881331, odds[2], 1e-10);
Assert.IsFalse(odds.HasNaN());
Assert.AreEqual(2.15901268940475, stde[0], 1e-10);
Assert.AreEqual(0.033789966967853677, stde[1], 1e-10);
Assert.AreEqual(1.4729620910282104, stde[2], 1e-10);
Assert.IsFalse(stde.HasNaN());
Assert.AreEqual(0.75143272827425545, y, 1e-10);
Assert.IsFalse(Double.IsNaN(y));
}
public void ComputeTest2()
{
// Test instance 01
double[][] trainInput =
{
new double[] { 1, 1 },
new double[] { 0, 0 },
};
double[] trainOutput = { 1, 0 };
double[] testInput = { 0, 0.2 };
var target = new LogisticRegressionAnalysis(trainInput, trainOutput);
target.Regularization = 1e-10;
target.Compute();
double[] coef = target.Coefficients.Apply(x => x.Value);
Assert.AreEqual(coef[0], -19.360661491141897);
Assert.AreEqual(coef[1], 19.702873967721807);
Assert.AreEqual(coef[2], 19.702873967721807);
double output = target.Regression.Compute(testInput);
Assert.AreEqual(0, output, 1e-6);
// Test instance 02
trainInput = new double[][]
{
new double[] { 1, 0, 1, 1, 0, 1, 1, 0, 1, 0 },
new double[] { 0, 1, 0, 1, 1, 0, 1, 1, 0, 1 },
new double[] { 1, 1, 0, 0, 1, 1, 0, 1, 1, 1 },
new double[] { 1, 0, 1, 1, 0, 1, 1, 0, 1, 0 },
new double[] { 0, 1, 0, 1, 1, 0, 1, 1, 0, 1 },
new double[] { 1, 1, 0, 0, 1, 1, 0, 1, 1, 1 },
};
trainOutput = new double[6] { 1, 1, 0, 0, 1, 1 };
target = new LogisticRegressionAnalysis(trainInput, trainOutput);
Assert.IsTrue(target.Compute());
double[] actual = target.Regression.Compute(trainInput);
//string str = actual.ToCSharp();
double[] expected = { 0.500000000158903, 0.999999998410966, 0.500000000913694, 0.500000000158903, 0.999999998410966, 0.500000000913694 };
Assert.IsTrue(actual.IsEqual(expected, 1e-6));
coef = target.Coefficients.Apply(x => x.Value);
//string str = coef.ToCSharp();
expected = new double[] { 1.86680346470929, -3.87720719574071, 2.44120453079343, -0.574401066088034, 5.16960959435804, 2.44120453079343, -3.87720719574087, 5.16960959435804, 2.44120453079343, -3.87720719574087, 2.44120453079343 };
Assert.IsTrue(coef.IsEqual(expected, 1e-6));
}
public override void Train(double[][] predictors, double[] results)
{
regression = new LogisticRegressionAnalysis(predictors, results);
regression.Compute();
}
public void FromSummaryTest1()
{
// Suppose we have a (fictitious) data set about patients who
// underwent cardiac surgery. The first column gives the number
// of arterial bypasses performed during the surgery. The second
// column gives the number of patients whose surgery went well,
// while the third column gives the number of patients who had
// at least one complication during the surgery.
//
int[,] data =
{
// # of stents success complications
{ 1, 140, 45 },
{ 2, 130, 60 },
{ 3, 150, 31 },
{ 4, 96, 65 }
};
double[][] inputs = data.GetColumn(0).ToDouble().ToArray();
int[] positive = data.GetColumn(1);
int[] negative = data.GetColumn(2);
// Create a new Logistic Regression Analysis from the summary data
var regression = LogisticRegressionAnalysis.FromSummary(inputs, positive, negative);
regression.Compute(); // compute the analysis.
// Now we can show a summary of the analysis
// Accord.Controls.DataGridBox.Show(regression.Coefficients);
// We can also investigate all parameters individually. For
// example the coefficients values will be available at the
// vector
double[] coef = regression.CoefficientValues;
// The first value refers to the model's intercept term. We
// can also retrieve the odds ratios and standard errors:
double[] odds = regression.OddsRatios;
double[] stde = regression.StandardErrors;
// Finally, we can use it to estimate risk for a new patient
double y = regression.Regression.Compute(new double[] { 4 });
Assert.AreEqual(3.7586367581050162, odds[0], 1e-8);
Assert.AreEqual(0.85772731075090014, odds[1], 1e-8);
Assert.IsFalse(odds.HasNaN());
Assert.AreEqual(0.20884336554629004, stde[0], 1e-8);
Assert.AreEqual(0.075837785246620285, stde[1], 1e-8);
Assert.IsFalse(stde.HasNaN());
Assert.AreEqual(0.67044096045332713, y, 1e-8);
Assert.IsFalse(Double.IsNaN(y));
LogisticRegressionAnalysis expected;
{
int[] qtr = data.GetColumn(0);
var expanded = Accord.Statistics.Tools.Expand(qtr, positive, negative);
double[][] inp = expanded.GetColumn(0).ToDouble().ToArray();
double[] outputs = expanded.GetColumn(1).ToDouble();
expected = new LogisticRegressionAnalysis(inp, outputs);
expected.Compute();
double slope = expected.Coefficients[1].Value; // should return -0.153
double inter = expected.Coefficients[0].Value;
double value = expected.ChiSquare.PValue; // should return 0.042
Assert.AreEqual(-0.15346904821339602, slope);
Assert.AreEqual(1.324056323049271, inter);
Assert.AreEqual(0.042491262992507946, value);
}
var actual = regression;
Assert.AreEqual(expected.Coefficients[0].Value, actual.Coefficients[0].Value, 1e-8);
Assert.AreEqual(expected.Coefficients[1].Value, actual.Coefficients[1].Value, 1e-8);
Assert.AreEqual(expected.ChiSquare.PValue, actual.ChiSquare.PValue, 1e-8);
Assert.AreEqual(expected.WaldTests[0].PValue, actual.WaldTests[0].PValue, 1e-8);
Assert.AreEqual(expected.WaldTests[1].PValue, actual.WaldTests[1].PValue, 1e-8);
Assert.AreEqual(expected.Confidences[0].Max, actual.Confidences[0].Max, 1e-6);
Assert.AreEqual(expected.Confidences[0].Min, actual.Confidences[0].Min, 1e-6);
Assert.AreEqual(expected.Confidences[1].Max, actual.Confidences[1].Max, 1e-6);
Assert.AreEqual(expected.Confidences[1].Min, actual.Confidences[1].Min, 1e-6);
}
public void ComputeTest4()
{
// Suppose we have the following data about some patients.
// The first variable is continuous and represent patient
// age. The second variable is dichotomic and give whether
// they smoke or not (this is completely fictional data).
double[][] inputs =
{
// Age Smoking
new double[] { 55, 0 },
new double[] { 28, 0 },
new double[] { 65, 1 },
new double[] { 46, 0 },
new double[] { 86, 1 },
new double[] { 56, 1 },
new double[] { 85, 0 },
new double[] { 33, 0 },
new double[] { 21, 1 },
new double[] { 42, 1 },
};
// Additionally, we also have information about whether
// or not they those patients had lung cancer. The array
// below gives 0 for those who did not, and 1 for those
// who did.
double[] output =
{
0, 0, 0, 1, 1, 1, 0, 0, 0, 1
};
// Create a Logistic Regression analysis
var regression = new LogisticRegressionAnalysis(inputs, output);
regression.Regularization = 0;
regression.Compute(); // compute the analysis.
// Now we can show a summary of the analysis
// Accord.Controls.DataGridBox.Show(regression.Coefficients);
// We can also investigate all parameters individually. For
// example the coefficients values will be available at the
// vector
double[] coef = regression.CoefficientValues;
// The first value refers to the model's intercept term. We
// can also retrieve the odds ratios and standard errors:
double[] odds = regression.OddsRatios;
double[] stde = regression.StandardErrors;
// Finally, we can also use the analysis to classify a new patient
double y = regression.Regression.Compute(new double[] { 87, 1 });
// For those inputs, the answer probability is approximately 75%.
Assert.AreEqual(0.085627701183146374, odds[0], 1e-8);
Assert.AreEqual(1.0208597029292648, odds[1], 1e-8);
Assert.AreEqual(5.8584748981777919, odds[2], 1e-8);
Assert.IsFalse(odds.HasNaN());
Assert.AreEqual(2.1590686019473897, stde[0], 1e-8);
Assert.AreEqual(0.033790422321041035, stde[1], 1e-8);
Assert.AreEqual(1.4729903935788211, stde[2], 1e-8);
Assert.IsFalse(stde.HasNaN());
Assert.AreEqual(0.75143272858389798, y, 1e-8);
Assert.IsFalse(Double.IsNaN(y));
}
public void ComputeTest3()
{
double[][] inputs = training.Submatrix(null, 0, 3);
double[] outputs = training.GetColumn(4);
LogisticRegressionAnalysis regression = new LogisticRegressionAnalysis(inputs, outputs);
bool expected = false;
regression.Iterations = 3;
bool actual = regression.Compute();
Assert.AreEqual(expected, actual);
}
public void DoStepTest()
{
double[][] inputs = Matrix.Expand(
new double[][] {
new double[] {0, 0, 0},
new double[] {1, 0, 0},
new double[] {0, 1, 0},
new double[] {1, 1, 0},
new double[] {0, 0, 1},
new double[] {1, 0, 1},
new double[] {0, 1, 1},
new double[] {1, 1, 1},
}, new int[] { 60, 17, 8, 2, 187, 85, 51, 23 });
double[] outputs = Matrix.Expand(
new double[] { 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0 },
new int[] { 5, 60 - 5, 2, 17 - 2, 1, 8 - 1, 0, 2 - 0, 35, 187 - 35, 13, 85 - 13, 15, 51 - 15, 8, 23 - 8 });
var target2 = new LogisticRegressionAnalysis(inputs, outputs);
target2.Compute();
Assert.AreEqual(target2.CoefficientValues[0], -2.377661, 0.0001);
Assert.AreEqual(target2.CoefficientValues[1], -0.067775, 0.0001);
Assert.AreEqual(target2.CoefficientValues[2], 0.69531, 0.0001);
Assert.AreEqual(target2.CoefficientValues[3], 0.871939, 0.0001);
var target = new StepwiseLogisticRegressionAnalysis(
inputs, outputs,
new string[] { "x1", "x2", "x3" }, "Y"
);
target.Threshold = 0.15;
int actual;
actual = target.DoStep();
Assert.AreEqual(0, actual);
actual = target.DoStep();
Assert.AreEqual(-1, actual);
}
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 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);
//}
}