public async Task <Tuple <double, double> > AlphaFromRawData(List <RawLJVDatum> data)
{
return(await Task.Run(() =>
{
Tuple <double, double> alphaAndR2 = new Tuple <double, double>(-1, 0.001);
List <double> pdBCData = new List <double>();
List <double> camData = new List <double>();
foreach (RawLJVDatum raw in data)
{
if (raw.CameraLuminance != null)
{
//interpolate readings to account for device instability
pdBCData.Add(Convert.ToDouble((raw.PhotoCurrentB + raw.PhotoCurrentC)) / 2.0f);
camData.Add(Convert.ToDouble(raw.CameraLuminance));
}
}
if (camData.Count > 2)
{
double[] xdata = pdBCData.ToArray();
double[] ydata = camData.ToArray();
Tuple <double, double> p = Fit.Line(xdata, ydata);
Debug.WriteLine("Measured Alpha = " + p.Item2);
double rsquared = GoodnessOfFit.RSquared(xdata.Select(x => p.Item1 + p.Item2 *x), ydata);
alphaAndR2 = new Tuple <double, double>(p.Item2, rsquared);
Debug.WriteLine("R^2 was: " + rsquared);
}
//take the ratio from a single measurement if not enough data for linear regression
else if (camData.Count <= 2 && camData.Count >= 1)
{
double ratioAlpha = camData.Last() / pdBCData.Last();
alphaAndR2 = new Tuple <double, double>(ratioAlpha, 0);
}
return alphaAndR2;
}).ConfigureAwait(false));
}
public bool Test(double start_wl, double end_wl, double max_slope, double min_slope, double max_error,
out bool noisyFit, out double slope)
{
noisyFit = false;
//normalize
var curve = _spectrum.SpectrumData;
var x = curve.Select(p => p.X).ToArray();
var y = curve.Select(p => p.Y).ToArray();
var minY = y.Min();
var maxY = y.Max();
y = y.Select(p => (p - minY) / (maxY - minY)).ToArray();
curve = x.Zip(y, (xp, yp) => new System.Windows.Point(xp, yp)).ToList();
var roi = curve.Where(p => p.X >= start_wl && p.X <= end_wl).ToList();
x = roi.Select(p => p.X).ToArray();
y = roi.Select(p => p.Y).ToArray();
var linear = Fit.Line(x, y);
double intercept = linear.Item1;
double s = linear.Item2;
var standardError = GoodnessOfFit.PopulationStandardError(x.Select(d => s * d + intercept), y);
if (Math.Round(standardError, 3) > max_error)
{
noisyFit = true;
}
slope = s;
bool res = (!noisyFit) && (slope >= min_slope) && (slope <= max_slope);
return(res);
}
private static async Task <(double R2, double Beta)> RollingRegression(string fundCode, string index, DateTime end)
{
var fundExcessReturn = await GetFundExcessReturn(fundCode, end.AddDays(-13 * 7), end);
if (!fundExcessReturn.Any())
{
return(double.NaN, 1);
}
var styleExcessReturn = GetStyleExcessReturn(index, end.AddDays(-13 * 7), end);
var y = new List <double>();
var x = new List <double>();
foreach (var item in styleExcessReturn)
{
var fundItem = fundExcessReturn.FirstOrDefault(it => it.Begin == item.Begin);
if (fundItem == null)
{
continue;
}
y.Add((double)fundItem.ExcessReturn);
x.Add((double)item.ExcessReturn);
}
if (x.Count < 2)
{
return(double.NaN, 1);
}
var fitResult = Fit.Line(x.ToArray(), y.ToArray());
var y2 = x.Select(item => fitResult.Item1 + fitResult.Item2 * item).ToArray();
return(GoodnessOfFit.RSquared(y2, y), fitResult.Item2);
}
public double GetR2(List <EDFSample> samples)
{
if (samples.Count <= 1)
{
return(0);
}
double[] Time = new double[samples.Count];
double[] Amount = new double[samples.Count];
int counter = 0;
foreach (EDFSample item in samples)
{
Time[counter] = int.Parse(item.DATE);
Amount[counter] = double.Parse(item.RESULT);
counter++;
}
Tuple <double, double> t = SimpleRegression.Fit(Time, Amount);
double a = t.Item2;
double b = t.Item1;
double[] model = new double[Time.Length];
for (int x = 0; x < Time.Count(); x++)
{
model[x] = (Time[x] * a) + b;
}
return(GoodnessOfFit.RSquared(model, Amount));
}
private static void TestMath()
{
var observed = new double[] { 1, 2, 3, 4, 5 };
var modelled = new double[] { 1.1, 2.1, 3.1, 4.1, 5.1 };
var a = GoodnessOfFit.CoefficientOfDetermination(observed, modelled);
var b = GoodnessOfFit.RSquared(observed, modelled);
}
public IDataQualityReport <double> GetReport(IList <double> expected, IList <double> actual)
{
return(new RegressionQualityReport(
expected,
actual,
expected.Count,
GoodnessOfFit.RSquared(expected, actual),
CalculateError(expected, actual)));
}
CalculateRSquaredValue(IModelledFunction modelledFunction,
IEnumerable <double> observedValues)
{
double rSquaredValue = GoodnessOfFit.RSquared(
observedValues, modelledFunction.Calculate(observedValues)
);
return(modelledFunction, rSquaredValue);
}
CalculateCoefficientOfDetermination(IModelledFunction modelledFunction,
IEnumerable <double> observedValues)
{
double coefficientOfDetermination = GoodnessOfFit.CoefficientOfDetermination(
observedValues, modelledFunction.Calculate(observedValues)
);
return(modelledFunction, coefficientOfDetermination);
}
private void btnCompare_Click(object sender, RoutedEventArgs e)
{
OpenFileDialog dlg = new OpenFileDialog();
dlg.Multiselect = false;
dlg.Filter = "csv Files (*.csv)|*.csv|All Files (*.*)|*.*";
if (!(dlg.ShowDialog() ?? false))
{
return;
}
var fs = dlg.File.OpenRead();
StreamReader sr = new StreamReader(fs);
var line = sr.ReadLine();
var splitor = new char[] { ',' };
var strs = line.Split(splitor);
var nts = strs.Count() - 1;
var legends = new string[nts];
DoubleTimeSeries[] ts = new DoubleTimeSeries[nts];
GoodnessOfFit[] fits = new GoodnessOfFit[nts - 1];
for (int i = 0; i < nts; i++)
{
ts[i] = new DoubleTimeSeries();
ts[i].DateTimes = new System.Collections.ObjectModel.ObservableCollection <DateTime>();
ts[i].Values = new System.Collections.ObjectModel.ObservableCollection <double>();
legends[i] = strs[i + 1];
}
for (int i = 1; i < nts; i++)
{
fits[i - 1] = new GoodnessOfFit()
{
Name = strs[i + 1]
};
}
double[] vec = new double[nts];
while (!sr.EndOfStream)
{
line = sr.ReadLine();
if (line != "" && line != null)
{
strs = line.Split(splitor);
DateTime date = DateTime.Parse(strs[0]);
for (int i = 0; i < nts; i++)
{
ts[i].DateTimes.Add(date);
ts[i].Values.Add(double.Parse(strs[i + 1]));
}
}
}
sr.Close();
for (int i = 0; i < nts; i++)
{
chart.PlotTimeSeries(ts[i], legends[i], colors[i], linetypes[i]);
}
datagrid.ItemsSource = fits;
}
public (double RSquaredX, double RSquaredY) Train(IList <Record> data)
{
Samples = data.ToArray();
var predict = data.Select(r => Predict(new HeadPoseAndGaze(r.HeadPose, r.Gaze))).ToArray();
var rSquaredX = GoodnessOfFit.RSquared(predict.Select(p => p.CoordinateX), data.Select(d => d.Display.X));
var rSquaredY = GoodnessOfFit.RSquared(predict.Select(p => p.CoordinateY), data.Select(d => d.Display.Y));
return(rSquaredX, rSquaredY);
}
public Vector2 Train(IList <GazeToDisplayCoordinateMappingRecord> data)
{
Samples = data.ToArray();
var predict = data.Select(r => Predict(new PoseAndEyeAndFace(r.HeadPose, r.Gaze, r.Face))).ToArray();
var rSquaredX = GoodnessOfFit.RSquared(predict.Select(p => (double)p.X), data.Select(d => d.Display.X).Select(d => (double)d));
var rSquaredY = GoodnessOfFit.RSquared(predict.Select(p => (double)p.Y), data.Select(d => d.Display.Y).Select(d => (double)d));
return(new Vector2((float)rSquaredX, (float)rSquaredY));
}
/// <summary>
/// Initializes a new instance of the <see cref="GoodnessOfFitViewModel"/> class.
/// </summary>
///
/// <param name="gof">The goodness-of-fits results against a particular distribution.</param>
///
public GoodnessOfFitViewModel(GoodnessOfFit gof)
{
this.Name = DistributionManager.Normalize(gof.Distribution.GetType().Name);
// Transform the rank to ordinal positions
// i.e. 0 to "1st", 1 to "2nd", 2 to "3rd"
this.Rank = suffix(gof.ChiSquareRank + 1);
this.ChiSquare = gof.ChiSquare;
this.KolmogorovSmirnov = gof.KolmogorovSmirnov;
}
/// <summary>
/// Initializes a new instance of the <see cref="GoodnessOfFitViewModel"/> class.
/// </summary>
///
/// <param name="gof">The goodness-of-fits results against a particular distribution.</param>
///
public GoodnessOfFitViewModel(GoodnessOfFit gof)
{
this.Name = DistributionManager.Normalize(gof.Distribution.GetType().Name);
// Transform the rank to ordinal positions
// i.e. 0 to "1st", 1 to "2nd", 2 to "3rd"
this.Rank = suffix(gof.ChiSquareRank + 1);
this.ChiSquare = gof.ChiSquare;
this.KolmogorovSmirnov = gof.KolmogorovSmirnov;
}
internal static (double b0, double b1, double r2) LinealRegression(int[] xdata, int[] ydata)
{
var x = xdata.Select(c => (double)c).ToArray();
var y = ydata.Select(c => (double)c).ToArray();
Tuple <double, double> p = Fit.Line(x, y);
double a = Math.Round(p.Item1, 5);
double b = Math.Round(p.Item2, 5);
var r2 = GoodnessOfFit.RSquared(xdata.Select(x => a + b * x), y);
return(a, b, Math.Round(r2, 4));
}
/// <summary>
/// Calculates adjusted coefficient of determination value for a fitted model.
/// </summary>
/// <param name="y">List containing the response values.</param>
/// <param name="x">List containing lists for all explanatory variables.</param>
/// <returns>Coefficient of determination adjusted with number of explanatory variables
/// and observations.</returns>
/// <exception cref="MathError">Thrown when parameter lists are of different length.</exception>
/// <exception cref="ArgumentException">Thrown when matrix created from parameters is not valid.</exception>
public static double AdjustedR2(List <double> y, List <List <double> > x)
{
List <double> fitted;
int n = y.Count;
int k = x.Count;
fitted = FittedValues(y, x);
double R2 = GoodnessOfFit.CoefficientOfDetermination(fitted, y);
return(1 - (((1 - R2) * (n - 1)) / (n - k - 1)));
}
private void ComputeMomentum(HistoricPrice historicPrice, out double momentum, out double volatility)
{
var closingPrices = historicPrice.Candles.Select(r => Math.Log((double)r.Close)).ToArray();
var seqNumbers = Enumerable.Range(0, closingPrices.Count()).Select <int, double>(i => i).ToArray();
var leastSquaresFitting = Fit.Line(seqNumbers, closingPrices);
var correlationCoff = GoodnessOfFit.R(seqNumbers, closingPrices);
var annualizedSlope = (Math.Pow(Math.Exp(leastSquaresFitting.Item2), 252) - 1) * 100;
var score = annualizedSlope * correlationCoff * correlationCoff;
momentum = score;
var r = Math.Exp(leastSquaresFitting.Item2) * correlationCoff * correlationCoff * 100;
volatility = r;
}
public ModelScore(int nParams, Func<double, double> predictor, double[] x, double[] observed) : this()
{
int k = nParams, n = x.Length;
var predicted = x.Select(predictor).ToArray();
Rss = predicted.Zip(observed, (p, o) => Square(p - o)).Sum();
Mse = Rss / n;
Rmse = Math.Sqrt(Mse);
var observedMean = observed.Average();
var tss = Math.Sqrt(observed.Select(d => Square(d - observedMean)).Sum());
R2 = GoodnessOfFit.CoefficientOfDetermination(predicted, observed);
Aic = CalcAic(k, n, Rss);
AicC = CalcAicC(k, n, Aic);
// Note that AIC tells nothing about the absolute quality of a model, only the quality relative to other models.
// Lets compare the rss to original values to approve only good accuracy
}
public void testRegression()
{
Console.WriteLine("---------------------------");
var ans = Fit.Line(X, Y);
var a = ans.Item1;
var b = ans.Item2;
Console.WriteLine("intercept:{0}, slope:{1}", ans.Item1, ans.Item2);
Console.WriteLine("r^2:" + GoodnessOfFit.RSquared(X.Select(x => a + b * x), Y));
Console.WriteLine("-------------------------");
var p = Fit.Polynomial(X, Y, 3);
Console.WriteLine("p:" + string.Join(",", p));
Console.WriteLine("r^2:" + GoodnessOfFit.RSquared(X.Select(x => p[0] + p[1] * x + p[2] * x * x + p[3] * x * x * x), Y));
Assert.True(true);
}
/// <summary>
/// Polynominal 커브피팅
/// </summary>
/// <param name="x">x축 값 배열</param>
/// <param name="y">y축 값 배열</param>
/// <param name="order">커브피팅하고자 하는 다항식 차수</param>
/// <returns></returns>
//다항 커브피팅 6차 다항식까지 지원
public static double[] polynominalRegression(double[] x, double[] y, int order) // x: x 배열, y: y: 배열, order :차수
{
double[] p = Fit.Polynomial(x, y, order); //curve fitting 하여 반환
double R2 = 0;
switch (order)
{
case 2:
R2 = GoodnessOfFit.RSquared(x.Select(d => p[0] + p[1] * d + p[2] * Math.Pow(d, 2)), y);
break;
case 3:
R2 = GoodnessOfFit.RSquared(x.Select(d => p[0] + p[1] * d + p[2] * Math.Pow(d, 2) + p[3] * Math.Pow(d, 3)), y);
break;
case 4:
R2 = GoodnessOfFit.RSquared(x.Select(d => p[0] + p[1] * d + p[2] * Math.Pow(d, 2) + p[3] * Math.Pow(d, 3) + p[4] * Math.Pow(d, 4)), y);
break;
case 5:
R2 = GoodnessOfFit.RSquared(x.Select(d => p[0] + p[1] * d + p[2] * Math.Pow(d, 2) + p[3] * Math.Pow(d, 3) + p[4] * Math.Pow(d, 4) + p[5] * Math.Pow(d, 5)), y);
break;
case 6:
R2 = GoodnessOfFit.RSquared(x.Select(d => p[0] + p[1] * d + p[2] * Math.Pow(d, 2) + p[3] * Math.Pow(d, 3) + p[4] * Math.Pow(d, 4) + p[5] * Math.Pow(d, 5) + p[6] * Math.Pow(d, 6)), y);
break;
case 7:
R2 = GoodnessOfFit.RSquared(x.Select(d => p[0] + p[1] * d + p[2] * Math.Pow(d, 2) + p[3] * Math.Pow(d, 3) + p[4] * Math.Pow(d, 4) + p[5] * Math.Pow(d, 5) + p[6] * Math.Pow(d, 6)), y);
break;
case 8:
R2 = GoodnessOfFit.RSquared(x.Select(d => p[0] + p[1] * d + p[2] * Math.Pow(d, 2) + p[3] * Math.Pow(d, 3) + p[4] * Math.Pow(d, 4) + p[5] * Math.Pow(d, 5) + p[6] * Math.Pow(d, 6)), y);
break;
}
double[] result = new double[order + 2];
result[0] = R2;
for (var i = 0; i <= order; i++)
{
result[i + 1] = p[i];
}
return(result);
}
public static SKUPrediction GenerateSkuPreduction(SKU sku, DateTime PredictionDate)
{
int Id = sku.Id;
double[] YValues = sku.MonthlyTotals.ToArray();
double[] NormalizedYs = RemoveSeasonality(sku.Months.Select(o => o.Month).ToArray(), YValues);
double[] ScalarDates = sku.Months.Select(o => o.ToOADate()).ToArray();
Tuple <double, double> p = Fit.Line(ScalarDates, NormalizedYs);
double Slope = p.Item2;
double Intercept = p.Item1;
double PredictedTotal = Slope * PredictionDate.ToOADate() + Intercept;
double SeasonallyPredictedTotal = AddSeasonality(PredictionDate.Month, PredictedTotal);
int SeasonallyPredictedTotalRounded;
if (Slope > 0)
{
SeasonallyPredictedTotalRounded = (int)Math.Ceiling(SeasonallyPredictedTotal);
}
else
{
SeasonallyPredictedTotalRounded = (int)Math.Floor(SeasonallyPredictedTotal);
}
string SkuClass = GetSkuClass(sku.MonthlyTotals.ToArray());
double GoodnessOfFitVar = GoodnessOfFit.RSquared(ScalarDates.Select(x => Intercept + Slope * x), NormalizedYs); // == 1.0
double StdDev = Statistics.PopulationStandardDeviation(YValues);
double Zscore = (SeasonallyPredictedTotalRounded - YValues.Average()) / StdDev;
return(new SKUPrediction()
{
Id = Id,
GoodnessOfFitRSquare = GoodnessOfFitVar,
Intercept = Intercept,
PredictedTotal = PredictedTotal,
PredictionDate = PredictionDate,
SeasonallyPredictedTotal = SeasonallyPredictedTotal,
SeasonallyPredictedTotalRounded = SeasonallyPredictedTotalRounded,
SkuClass = SkuClass,
Slope = Slope,
StandardDeviation = StdDev,
ZScore = Zscore
});
}
List <double> UpdateLinRegEquation(double[] KG, double[] MV)
{
List <double> linregTemp = new List <double>();
if (KG.Count() > 2)
{
double[] p = Fit.Polynomial(MV, KG, 1);
double rSqr = GoodnessOfFit.RSquared(MV.Select(x => p[1] * x + p[0]), KG);
linregTemp.Add(p[1]);
linregTemp.Add(p[0]);
linregTemp.Add(rSqr);
this.BeginInvoke(new Action(() =>
{
if (tipoSelected == "1D - 500x500")
{
EquationBox.Text = "Fy: " + Math.Round(linregTemp[0], 5) + "x + (" + Math.Round(linregTemp[1], 5) + ") [Kg] --> " + "R2: " + Math.Round(linregTemp[2], 5);
}
//EquationBox.Text = "Fy: " + Math.Round(SLOPE, 5) + "x + (" + Math.Round(INTERCEPT, 5) + ") [Kg] --> " + "R2: " + Math.Round(RSQR, 5);
else if (tipoSelected == "3D - 500x500")
{
if (FyCheckBox.Checked)
{
EquationBox.Text = "Fy: " + Math.Round(linregTemp[0], 5) + "x + (" + Math.Round(linregTemp[1], 5) + ") [Kg] --> " + "R2: " + Math.Round(linregTemp[2], 5);
}
if (MxCheckBox.Checked)
{
EquationBox.Text = "Mx: " + Math.Round(linregTemp[0], 5) + "x + (" + Math.Round(linregTemp[1], 5) + ") [Kg] --> " + "R2: " + Math.Round(linregTemp[2], 5);
}
if (MzCheckBox.Checked)
{
EquationBox.Text = "Mz: " + Math.Round(linregTemp[0], 5) + "x + (" + Math.Round(linregTemp[1], 5) + ") [Kg] --> " + "R2: " + Math.Round(linregTemp[2], 5);
}
}
}));
}
else
{
this.BeginInvoke(new Action(() =>
{
EquationBox.Text = "São necessários pelo menos 3 medidas.";
}));
}
return(linregTemp);
}
public static double[] powerRegression(double[] x, double[] y)
{
var convert_log = y.Select(d => Math.Log(d)).ToArray();
double[] p = Fit.LinearCombination(x, convert_log,
d => 1.0,
d => Math.Log(d)
);
p[0] = Math.Exp(p[0]);
var R2 = GoodnessOfFit.RSquared(x.Select(d => p[0] * Math.Pow(d, p[1])), y);
double[] result = new double[3];
result[0] = R2;
result[1] = p[0];
result[2] = p[1];
return(result);
}
void LinRegRaw()
{
try
{
LinRegChart.Series.Clear();
LinRegChart.ChartAreas[0].CursorX.IsUserEnabled = false;
LinRegChart.ChartAreas[0].CursorY.IsUserEnabled = false;
LinRegChart.ChartAreas[0].AxisX.ScaleView.Zoomable = false;
LinRegChart.ChartAreas[0].AxisY.ScaleView.Zoomable = false;
LinRegChart.ChartAreas[0].CursorX.AutoScroll = false;
LinRegChart.ChartAreas[0].CursorY.AutoScroll = false;
LinRegChart.ChartAreas[0].CursorX.IsUserSelectionEnabled = false;
LinRegChart.ChartAreas[0].CursorY.IsUserSelectionEnabled = false;
double[] KGinit = { 0, 10, 20, 30, 40, 50, 60 };
double[] MVinit = { 0, 5, 10, 15, 20, 25, 30 };
double[] p = Fit.Polynomial(MVinit, KGinit, 2);
double rSqr = GoodnessOfFit.RSquared(MVinit.Select(x => p[1] * x + p[2]), KGinit);
EquationBox.Text = "Fy: " + Math.Round(p[1], 5) + "x + (" + Math.Round(p[2], 5) + ") [Kg] --> " + "R2: " + Math.Round(rSqr, 5);
Series s = new Series();
for (int i = 0; i < KGinit.Count(); i++)
{
s.Points.AddXY(KGinit[i], MVinit[i]);
}
LinRegChart.Series.Add(s);
LinRegChart.Series[0].ChartType = SeriesChartType.Point;
LinRegChart.Series[0].Color = Color.Blue;
LinRegChart.Series[0].BorderWidth = 3;
LinRegChart.ChartAreas[0].AxisX.Title = "Carga Vertical (KG)";
LinRegChart.ChartAreas[0].AxisY.Title = "Tensão (mV)";
LinRegChart.ChartAreas[0].AxisX.Maximum = 60;
LinRegChart.ChartAreas[0].AxisX.Minimum = 0;
LinRegChart.ChartAreas[0].AxisX.Interval = 10;
LinRegChart.ChartAreas[0].AxisY.Maximum = 30;
LinRegChart.ChartAreas[0].AxisY.Minimum = 0;
LinRegChart.ChartAreas[0].AxisY.Interval = 5;
}
catch (Exception ex) { MessageBox.Show("Erro: " + ex.Message); }
}
/// <summary>
/// Get the regression parameter (slope, interception and r).
/// </summary>
/// <param name="xData">X data.</param>
/// <param name="yData">Y data.</param>
/// <returns>A DTOLineFitParameters object containing the regression parameters.</returns>
public DTOLineFitParameters getRegressionParameters(double[] xData, double[] yData)
{
if (xData.Count() < 2 || yData.Count() < 2)
{
return(new DTOLineFitParameters());
}
// Fit the data to a line
Tuple <double, double> p = Fit.Line(xData, yData);
// Get parameters
var slope = p.Item2;
var interception = p.Item1;
var ret = new DTOLineFitParameters
{
Slope = slope,
Interception = interception,
R = GoodnessOfFit.RSquared(xData.Select(x => slope + interception * x), yData)
};
return(ret);
}
public void FindLowestIndexReverse(List <ChartData> data)
{
// Find the lowest value in the list
int storeIndex = data.Count - 1;
int storedata = data[storeIndex].Value;
for (int i = data.Count - 2; i >= 0; i--)
{
if (storedata > data[i].Value)
{
storeIndex = i;
storedata = data[i].Value;
}
else
{
break;
}
}
// Convert the list from the lowest value index to the last value
// to a array of double
List <double> xlist = new List <double>();
List <double> ylist = new List <double>();
for (int i = storeIndex; i < data.Count; i++)
{
xlist.Add(i - storeIndex);
ylist.Add(Convert.ToDouble(data[i].Value));
}
xdata = xlist.ToArray <double>();
ydata = ylist.ToArray <double>();
// Linear regression
if (xdata.Count() >= 2 && ydata.Count() >= 2)
{
f = Fit.Line(xdata, ydata);
goodnessFit = GoodnessOfFit.RSquared(xdata.Select(x => f.Item1 + f.Item2 * x), ydata); // == 1.0
}
}
static async Task Main(string[] args)
{
var savegameFile = args.FirstOrDefault();
if (savegameFile == null)
{
Console.Error.WriteLine("Usage: MapCalibrator.exe <savegame>");
Environment.Exit(1);
}
var arkDataFile = Path.Combine(Path.Combine(Environment.GetFolderPath(Environment.SpecialFolder.LocalApplicationData), "Larkator"), "ark-data.json");
var arkData = ArkDataReader.ReadFromFile(arkDataFile);
(GameObjectContainer gameObjects, float gameTime) = await ReadSavegameFile(savegameFile);
// Find any objects that have a relevant BoxName
var items = gameObjects
.Where(o => o.Parent == null && o.GetPropertyValue <string>("BoxName", defaultValue: "").StartsWith("Calibration:"))
.ToList();
// Extract XYZ location and calibration lat/lon
var inputs = items.Select(o => (o.Location, LatLon: LatLongFromName(o.GetPropertyValue <string>("BoxName")))).ToArray();
// Perform linear regression on the values for best fit, separately for X and Y
double[] xValues = inputs.Select(i => (double)i.Location.X).ToArray();
double[] yValues = inputs.Select(i => (double)i.Location.Y).ToArray();
double[] lonValues = inputs.Select(i => i.LatLon.Lon).ToArray();
double[] latValues = inputs.Select(i => i.LatLon.Lat).ToArray();
var(xOffset, xMult) = Fit.Line(xValues, lonValues);
var(yOffset, yMult) = Fit.Line(yValues, latValues);
var xCorr = GoodnessOfFit.RSquared(xValues.Select(x => xOffset + xMult * x), lonValues);
var yCorr = GoodnessOfFit.RSquared(yValues.Select(y => yOffset + yMult * y), latValues);
Console.WriteLine($"X: {xOffset} + X/{1 / xMult} (corr {xCorr})");
Console.WriteLine($"Y: {yOffset} + X/{1 / yMult} (corr {yCorr})");
Console.ReadLine();
}
public bool Exists()
{
try
{
//normalize
var curve = _spectrum.SpectrumData.Where(p => p.X >= 560 && p.X <= 740).ToList();
var x = curve.Select(p => p.X).ToArray();
var y = curve.Select(p => p.Y).ToArray();
var minY = y.Min();
var maxY = y.Max();
y = y.Select(p => (p - minY) / (maxY - minY)).ToArray();
curve = x.Zip(y, (xp, yp) => new System.Windows.Point(xp, yp)).ToList();
//fit linear function
var curve1 = curve.Where(p => p.X >= 650 && p.X <= 740).ToList();
var xData = curve1.Select(p => p.X).ToArray();
var yData = curve1.Select(p => p.Y).ToArray();
var linear = Fit.Line(xData, yData);
var intercept = linear.Item1;
var slope = linear.Item2;
var goodnessOfFit = GoodnessOfFit.RSquared(xData.Select(d => slope * d + intercept), yData);
bool rule1 = (slope > 0.004) && (goodnessOfFit > 0.95);
if (!rule1)
{
return(false);
}
return(true);
}
catch
{
}
return(true);
}
/// <summary>
/// Shows a new chart in a default form.
/// </summary>
/// <param name="gof">A goodness of fit object.</param>
/// <param name="alpha">A significance level.</param>
/// <remarks>
/// Equivalent to:
/// <code>
/// NMathStatsChart.Show( ToChart( gof, alpha ) );
/// </code>
/// </remarks>
public static void Show( GoodnessOfFit gof, double alpha )
{
Show( ToChart( gof, alpha ) );
}
public void PopulatePropertiesFromPath(string fp)
{
TheELSpectrum.FilePath = fp;
try
{
Debug.WriteLine("ELSpec filepath: " + fp);
//perform linear fits on both sides of the gaussian to approximate where the peak would be if the spectrophotometer had better resolution
LoadELSpecDataIntoList(fp);
var max = _ELSpecList.Max(x => x.Intensity);
var maxListIndex = _ELSpecList.FindIndex(x => x.Intensity == max);
Debug.WriteLine("Maximum ELSpec raw value is: " + max + " at list index: " + maxListIndex);
foreach (ELSpecDatum e in _ELSpecList)
{
e.Intensity = e.Intensity / max;
}
//find points between 0.42 and 0.9 on the high energy side of the peak and add to list
var leftList = new List <ELSpecDatum>();
for (int i = 0; i < maxListIndex; i++)
{
if (_ELSpecList[i].Intensity > 0.42 && _ELSpecList[i].Intensity < 0.9)
{
leftList.Add(_ELSpecList[i]);
}
}
//same for lower energy side but in reverse
var rightList = new List <ELSpecDatum>();
for (int i = _ELSpecList.Count() - 1; i > maxListIndex; i--)
{
if (_ELSpecList[i].Intensity > 0.42 && _ELSpecList[i].Intensity < 0.9)
{
rightList.Add(_ELSpecList[i]);
}
}
if (leftList.Count >= 2 && rightList.Count >= 2)
{
//perform linear fits on these data
double[] leftXData = leftList.Select(x => x.Wavelength).ToArray();
double[] leftYData = leftList.Select(x => x.Intensity).ToArray();
Tuple <double, double> leftVals = Fit.Line(leftXData, leftYData);
//Debug.WriteLine("Left side line: Intensity = " + leftVals.Item2 + "x + " + leftVals.Item1);
double rsquared = GoodnessOfFit.RSquared(leftXData.Select(x => leftVals.Item1 + leftVals.Item2 * x), leftYData);
//Debug.WriteLine("R^2 = " + rsquared);
double[] rightXData = rightList.Select(x => x.Wavelength).ToArray();
double[] rightYData = rightList.Select(x => x.Intensity).ToArray();
Tuple <double, double> rightVals = Fit.Line(rightXData, rightYData);
//Debug.WriteLine("Right side line: Intensity = " + rightVals.Item2 + "x + " + rightVals.Item1);
rsquared = GoodnessOfFit.RSquared(rightXData.Select(x => rightVals.Item1 + rightVals.Item2 * x), rightYData);
//Debug.WriteLine("R^2 = " + rsquared);
double calculatedPeakLambda = (leftVals.Item1 - rightVals.Item1) / (rightVals.Item2 - leftVals.Item2);
//Debug.WriteLine("Calculated peak lambda to be: " + calculatedPeakLambda + "nm");
TheELSpectrum.ELPeakLambda = Math.Round(Convert.ToDecimal(calculatedPeakLambda), 1);
double leftLambdaAtHalfMax = (0.5 - leftVals.Item1) / leftVals.Item2;
double rightLambdaAtHalfMax = (0.5 - rightVals.Item1) / rightVals.Item2;
var calculatedFWHM = Math.Round(Convert.ToDecimal(rightLambdaAtHalfMax - leftLambdaAtHalfMax), 1);
//Debug.WriteLine("Calculated FWHM to be: " + calculatedFWHM + "nm");
TheELSpectrum.ELFWHM = calculatedFWHM;
}
else
{
TheELSpectrum.ELPeakLambda = Convert.ToDecimal(_ELSpecList[maxListIndex].Wavelength);
//need to update ELSpectrum entity with nullables
}
var CIEcoords = CIE1931Calculator.CalculateCIE1931CoordsFromFilePath(fp);
TheELSpectrum.CIEx = Convert.ToDecimal(CIEcoords.Item1);
TheELSpectrum.CIEy = Convert.ToDecimal(CIEcoords.Item2);
}
catch (Exception e)
{
Debug.WriteLine(e);
MessageBox.Show(e.ToString());
}
}
public void LineFit(Tuple <List <double>, List <double> > edgeSegment, List <Tuple <double, double> > linesOfAnEdgeSegment)
{
List <double> xData = new List <double>();
xData = edgeSegment.Item1;
List <double> yData = new List <double>();
yData = edgeSegment.Item2;
double lineFitError = Double.MaxValue;
int numberOfPixels = xData.Count;
lineFitError = Double.MaxValue; // current line fit error
Tuple <double, double> line; // y = ax+b OR x = ay+b
double a = 0;
double b = 0;
while (numberOfPixels > MIN_LINE_LENGTH)
{
Tuple <double, double> line2 = Fit.Line(xData.ToArray(), yData.ToArray());
a = line2.Item1;
b = line2.Item2;
GoodnessOfFit.RSquared(xData.Select(x => a + b * x), yData.ToArray());
if (lineFitError <= 1.0)
{
break; // OK. An initial line segment detected
}
// Skip the first pixel & try with the remaining pixels
xData.RemoveAt(xData.Count - 1);
yData.RemoveAt(yData.Count - 1);
numberOfPixels--; // One less pixel
} // end-while
if (lineFitError > 1.0)
{
return; // no initial line segment. Done.
}
// An initial line segment detected. Try to extend this line segment
int lineLen = MIN_LINE_LENGTH;
List <double> xDataExtended = new List <double>();
List <double> yDataExtended = new List <double>();
for (int i = 0; i < MIN_LINE_LENGTH; i++)
{
xDataExtended[i] = xData[i];
yDataExtended[i] = yData[i];
}
while (lineLen < numberOfPixels)
{
double x = edgeSegment.Item1[lineLen];
double y = edgeSegment.Item2[lineLen];
double d = ComputePointDistance2Line(a, -1, b, (int)x, (int)y);
if (d > 1.0)
{
break;
}
lineLen++;
} //end-while
// End of the current line segment. Compute the final line equation & output it.
Tuple <double, double> line3 = Fit.Line(xDataExtended.ToArray(), yDataExtended.ToArray());
linesOfAnEdgeSegment.Add(line3);
// Extract line segments from the remaining pixels
for (int i = lineLen; i < edgeSegment.Item1.Count; i++)
{
xData[i - lineLen] = edgeSegment.Item1[i];
yData[i - lineLen] = edgeSegment.Item2[i];
}
for (int i = 0; i < lineLen; i++)
{
edgeSegment.Item1.RemoveAt(i);
edgeSegment.Item2.RemoveAt(i);
}
LineFit(edgeSegment);
}
public static MetalTemperatureClass MultiMetalTemperatureCaculate(List <PValue> valueList, double LimitHH, double LimitH, double LimitRP, double LimitOO, double LimitRN, double LimitL, double LimitLL)
{
try
{
List <MetalTemperatureClass> returnClass = new List <MetalTemperatureClass>();
MetalTemperatureClass newClass = new MetalTemperatureClass();
int l = 1;
List <CurveClass> ccList = new List <CurveClass>();
foreach (PValue childItem in valueList)
{
CurveClass cc = new CurveClass();
cc.x = l;
cc.y = childItem.Value;
ccList.Add(cc);
l++;
}
double Min = ccList[0].y;
double MinN = 1;
double Max = ccList[0].y;
double MaxN = 1;
double Sum = 0;
double HHG = 0;
double HHHB = 0;
double HRPB = 0;
double RP0B = 0;
double RM0B = 0;
double RMLB = 0;
double LLLB = 0;
double LLL = 0;
double RPRMB = 0;
double HLB = 0;
double HHHLLLB = 0;
double HHLLGL = 0;
double HG = 0;
double LL = 0;
foreach (CurveClass childItem in ccList)
{
if (Min > childItem.y)
{
Min = childItem.y;
MinN = childItem.x;
}
if (Max < childItem.y)
{
Max = childItem.y;
MaxN = childItem.x;
}
Sum += childItem.y;
if (childItem.y > LimitHH)
{
HHG++;
}
if (childItem.y > LimitH)
{
HG++;
}
if (childItem.y <= LimitHH && childItem.y > LimitH)
{
HHHB++;
}
if (childItem.y <= LimitH && childItem.y > LimitRP)
{
HRPB++;
}
if (childItem.y <= LimitRP && childItem.y > LimitOO)
{
RP0B++;
}
if (childItem.y <= LimitOO && childItem.y > LimitRN)
{
RM0B++;
}
if (childItem.y <= LimitRN && childItem.y > LimitL)
{
RMLB++;
}
if (childItem.y <= LimitL && childItem.y > LimitLL)
{
LLLB++;
}
if (childItem.y <= LimitL)
{
LL++;
}
if (childItem.y <= LimitLL)
{
LLL++;
}
}
RPRMB = RP0B + RM0B;
HLB = HRPB + RP0B + RM0B + RMLB;
HHHLLLB = HHHB + LLLB;
HHLLGL = HHG + LLL;
newClass.Min = Min.ToString();
newClass.MinN = MinN.ToString();
newClass.Max = Max.ToString();
newClass.MaxN = MaxN.ToString();
double Avg = Math.Round(Sum / (double)(ccList.Count), 3);
newClass.Avg = Avg.ToString();
double xi = Math.Abs(Avg - ccList[0].y);
double AvgN = 1;
double[] xList = new double[ccList.Count];
double[] yList = new double[ccList.Count];
int n = 0;
foreach (CurveClass childItem in ccList)
{
xList[n] = childItem.x;
yList[n] = childItem.y;
if (xi > Math.Abs(Avg - childItem.y))
{
xi = Math.Abs(Avg - childItem.y);
AvgN = childItem.x;
}
n++;
}
double dMaxB = ccList[1].y - ccList[0].y;
double dMaxBN = 1;
for (int i = 1; i < ccList.Count - 1; i++)
{
if (dMaxB < ccList[i].y - ccList[i - 1].y)
{
dMaxB = ccList[i].y - ccList[i - 1].y;
dMaxBN = ccList[i - 1].x;
}
}
newClass.AvgN = AvgN.ToString();
newClass.dX = (Max - Min).ToString();
newClass.dXNR = Math.Round((MaxN - MinN) / (double)(ccList.Count), 3).ToString();
newClass.dMaxB = AvgN.ToString();
newClass.dMaxBN = AvgN.ToString();
newClass.sigma = AlgorithmHelper.StandardDeviationSolve(ccList).ToString();
double lk = 0;
double lb = 0;
AlgorithmHelper.LinearRegressionSolve(ccList, ref lk, ref lb);
newClass.lk = lk.ToString();
newClass.lb = lb.ToString();
List <double> lY = new List <double>();
List <double> lX = new List <double>();
foreach (CurveClass lcItem in ccList)
{
lY.Add(lcItem.y);
lX.Add(lcItem.x);
}
List <double> lYTest = new List <double>();
foreach (double fdItem in lX)
{
lYTest.Add(lk * fdItem + lb);
}
double lR = GoodnessOfFit.RSquared(lY, lYTest);
newClass.lr = lR.ToString();
double[] res = Fit.Polynomial(xList, yList, 2);
newClass.qa = Math.Round(res[2], 3).ToString();
newClass.qb = Math.Round(res[1], 3).ToString();
newClass.qc = Math.Round(res[0], 3).ToString();
List <double> qYTest = new List <double>();
foreach (double qdItem in xList)
{
qYTest.Add(res[2] * Math.Pow(qdItem, 2) + res[1] * qdItem + res[0]);
}
double qR = GoodnessOfFit.RSquared(yList, qYTest);
newClass.qr = qR.ToString();
double Bulge = (ccList[1].y - ccList[0].y) * 2;
double BulgeN = 1;
double Cave = (ccList[1].y - ccList[0].y) * 2;
double CaveN = 1;
for (int i = 1; i < ccList.Count - 1; i++)
{
double b = 0;
if (i == ccList.Count - 1)
{
b = (ccList[i].y - ccList[i - 1].y) * 2;
}
else
{
b = ccList[i].y * 2 - ccList[i - 1].y - ccList[i + 1].y;
}
if (Bulge < b)
{
Bulge = b;
BulgeN = ccList[i].x;
}
if (Cave > b)
{
Cave = b;
CaveN = ccList[i].x;
}
}
newClass.Bulge = Bulge.ToString();
newClass.BulgeN = BulgeN.ToString();
newClass.Cave = Cave.ToString();
newClass.CaveN = CaveN.ToString();
newClass.HHG = Math.Round(HHG / (double)(ccList.Count), 3).ToString();
newClass.HHHB = Math.Round(HHHB / (double)(ccList.Count), 3).ToString();
newClass.HRPB = Math.Round(HRPB / (double)(ccList.Count), 3).ToString();
newClass.RP0B = Math.Round(RP0B / (double)(ccList.Count), 3).ToString();
newClass.RM0B = Math.Round(RM0B / (double)(ccList.Count), 3).ToString();
newClass.RMLB = Math.Round(RMLB / (double)(ccList.Count), 3).ToString();
newClass.LLLB = Math.Round(LLLB / (double)(ccList.Count), 3).ToString();
newClass.LLL = Math.Round(LLL / (double)(ccList.Count), 3).ToString();
newClass.RPRMB = Math.Round(RPRMB / (double)(ccList.Count), 3).ToString();
newClass.HLB = Math.Round(HLB / (double)(ccList.Count), 3).ToString();
newClass.HHHLLLB = Math.Round(HHHLLLB / (double)(ccList.Count), 3).ToString();
newClass.HHLLGL = Math.Round(HHLLGL / (double)(ccList.Count), 3).ToString();
newClass.HG = Math.Round(HG / (double)(ccList.Count), 3).ToString();
newClass.LL = Math.Round(LL / (double)(ccList.Count), 3).ToString();
//returnClass.Add(newClass);
return(newClass);
}
catch (Exception ex)
{
throw ex;
}
}
/// <summary>
/// Updates the given chart with a bar chart plotting the model parameter values and <c>1 - alpha</c> confidence intervals.
/// </summary>
/// <param name="chart">A chart.</param>
/// <param name="gof">A goodness of fit object.</param>
/// <param name="alpha">A significance level.</param>
/// <remarks>
/// Titles are added only if chart does not currently contain any titles.
/// <br/>
/// The first two data series are replaced, or added if necessary.
/// </remarks>
public static void Update( ref ChartControl chart, GoodnessOfFit gof, double alpha )
{
List<string> titles = new List<string>()
{
"GoodnessOfFit",
string.Format( "R2: {0}; adjusted R2: {1}", gof.RSquared, gof.AdjustedRsquared ),
string.Format( "F-statistic: {0} on {1} and {2} DF, p-value: {3}", gof.FStatistic, gof.ModelDegreesOfFreedom, gof.ErrorDegreesOfFreedom, gof.FStatisticPValue ),
};
string xTitle = "Parameter";
string yTitle = "Value";
ChartSeries series = new ChartSeries()
{
Type = ChartSeriesType.Column
};
series.ConfigItems.ErrorBars.Enabled = true;
series.ConfigItems.ErrorBars.SymbolShape = ChartSymbolShape.None;
for( int i = 0; i < gof.Parameters.Length; i++ )
{
GoodnessOfFitParameter param = gof.Parameters[i];
Interval ci = param.ConfidenceInterval( alpha );
series.Points.Add( new ChartPoint( i, new double[] { param.Value, param.Value - ci.Min, ci.Max - param.Value } ) );
}
Update( ref chart, series, titles, xTitle, yTitle );
}
//this is asych for the calling Task.WhenAll
//but does not necessarily need internal asych awaits
public async Task RunAlgorithmAsync(List <List <double> > data)
{
try
{
//minimal data requirement is first five cols
if (_colNames.Count() < 5 ||
_mathTerms.Count() == 0)
{
ErrorMessage = "Regression requires at least one dependent variable and one independent variable.";
return;
}
if (data.Count() < 5)
{
//185 same as other analysis
ErrorMessage = "Regression requires at least 2 rows of observed data and 3 rows of scoring data.";
return;
}
//convert data to a Math.Net Matrix
//v185 uses same ci technique as algos 2,3 and 4 -last 3 rows are used to generate ci
List <List <double> > dataci = data.Skip(data.Count - _scoreRows).ToList();
data.Reverse();
List <List <double> > dataobs = data.Skip(_scoreRows).ToList();
dataobs.Reverse();
//actual observed values
Vector <double> y = Shared.GetYData(dataobs);
Matrix <double> x = Shared.GetDoubleMatrix(dataobs, _colNames, _depColNames);
Matrix <double> ci = Shared.GetDoubleMatrix(dataci, _colNames, _depColNames);
//model expected values - get the coefficents
//use normal equations regression
Vector <double> p = MultipleRegression.NormalEquations(x, y);
//but note that this runs without errors in more cases but still does not give good results
//Vector<double> p = MultipleRegression.QR(x, y);
if (p.Count() != ci.Row(_scoreRows - 1).Count())
{
//185 same as other analysis
ErrorMessage = "The scoring and training datasets have different numbers of columns.";
return;
}
//get the predicted yhats
Vector <double> yhat = GetYHatandSetQTPred(y.Count, x, p, ci.Row(_scoreRows - 1).ToArray());
//get the durbin-watson d statistic
double d = GetDurbinWatson(y, yhat);
double SSE = 0;
//sum of the square of the error (between the predicted, p, and observed, y);
SSE = Distance.SSD(yhat, y);
double rSquared = GoodnessOfFit.RSquared(yhat, y);
//sum of the square of the regression (between the predicted, p, and observed mean, statsY.Mean);
double SSR = 0;
for (int i = 0; i < yhat.Count(); i++)
{
SSR += Math.Pow((yhat[i] - y.Mean()), 2);
}
//set joint vars properties
//degrees freedom
double dfR = x.ColumnCount - 1;
double dfE = x.RowCount - x.ColumnCount;
int idfR = x.ColumnCount - 1;
int idfE = x.RowCount - x.ColumnCount;
double s2 = SSE / dfE;
double s = Math.Sqrt(s2);
double MSR = SSR / dfR;
double MSE = SSE / dfE;
double FValue = MSR / MSE;
double adjRSquared = 1 - ((x.RowCount - 1) * (MSE / (SSE + SSR)));
double pValue = Shared.GetPValueForFDist(idfR, idfE, FValue);
//correct 2 tailed t test
//double TCritialValue = ExcelFunctions.TInv(0.05, idfE);
//so do this
double dbCI = CalculatorHelpers.GetConfidenceIntervalProb(_confidenceInt);
double tCriticalValue = ExcelFunctions.TInv(dbCI, idfE);
//set each coeff properties
//coeffs st error
//use matrix math to get the standard error of coefficients
Matrix <double> xt = x.Transpose();
//matrix x'x
Matrix <double> xx = xt.Multiply(x);
Matrix <double> xxminus1 = xx.Inverse();
double sxx = 0;
double[] xiSE = new double[x.ColumnCount];
//coeff tstats
double[] xiT = new double[x.ColumnCount];
//lower value for pvalue
double[] xiP = new double[x.ColumnCount];
for (int i = 0; i < x.ColumnCount; i++)
{
//use the matrix techniques shown on p 717 of Mendenhall and Sincich
sxx = s * Math.Sqrt(xxminus1.Column(i)[i]);
xiSE[i] = sxx;
xiT[i] = p[i] / sxx;
xiP[i] = Shared.GetPValueForTDist(idfE, xiT[i], 0, 1);
}
double FCriticalValue = 0;
string FGreaterFCritical = string.Empty;
if (_subalgorithm == Calculator1.MATH_SUBTYPES.subalgorithm8.ToString())
{
//anova regression
//anova critical fvalue test
//FCriticalValue = ExcelFunctions.FInv(1 - _confidenceInt, idfR, idfE);
FCriticalValue = ExcelFunctions.FInv(dbCI, idfR, idfE);
FGreaterFCritical = (FValue > FCriticalValue) ? "true" : "false";
SetAnovaIntervals(0, p, xiSE, tCriticalValue);
SetAnovaIntervals(1, p, xiSE, tCriticalValue);
SetAnovaIntervals(2, p, xiSE, tCriticalValue);
}
else
{
//set QTM ci and pi intervals
SetQTIntervals(0, s, xxminus1, ci.Row(_scoreRows - 1).ToArray(), p, tCriticalValue);
SetQTIntervals(1, s, xxminus1, ci.Row(_scoreRows - 2).ToArray(), p, tCriticalValue);
SetQTIntervals(2, s, xxminus1, ci.Row(_scoreRows - 3).ToArray(), p, tCriticalValue);
}
//add the data to a string builder
StringBuilder sb = new StringBuilder();
sb.AppendLine("regression results");
//dep var has to be in the 4 column always
string sLine = string.Concat("dependent variable: ", _colNames[3]);
sb.AppendLine(sLine);
string[] cols = new string[] { "source", "df", "SS", "MS" };
sb.AppendLine(Shared.GetLine(cols, true));
cols = new string[] { "model", dfR.ToString("F0"), SSR.ToString("F4"), MSR.ToString("F4") };
sb.AppendLine(Shared.GetLine(cols, false));
cols = new string[] { "error ", dfE.ToString("F0"), SSE.ToString("F4"), MSE.ToString("F4") };
sb.AppendLine(Shared.GetLine(cols, false));
cols = new string[] { "total ", (dfR + dfE).ToString("F0"), (SSR + SSE).ToString("F4") };
sb.AppendLine(Shared.GetLine(cols, false));
sb.AppendLine(string.Empty);
cols = new string[] { "R-squared", rSquared.ToString("F4"), "Adj R-squared", adjRSquared.ToString("F4") };
sb.AppendLine(Shared.GetLine(cols, false));
cols = new string[] { "F value", FValue.ToString("F4"), "prob > F", pValue.ToString("F4") };
sb.AppendLine(Shared.GetLine(cols, false));
sb.AppendLine(string.Empty);
cols = new string[] { GetName("variable"), "coefficient", "stand error", "T-ratio", "prob > T" };
sb.AppendLine(Shared.GetLine(cols, true));
for (int i = 0; i < p.Count(); i++)
{
if (i == 0)
{
cols = new string[] { GetName(_depColNames[i]), p[i].ToString("F5"), xiSE[i].ToString("F4"), xiT[i].ToString("F4"), xiP[i].ToString("F4") };
sb.AppendLine(Shared.GetLine(cols, false));
}
else
{
cols = new string[] { GetName(_depColNames[i]), p[i].ToString("F5"), xiSE[i].ToString("F4"), xiT[i].ToString("F4"), xiP[i].ToString("F4") };
sb.AppendLine(Shared.GetLine(cols, false));
}
}
cols = new string[] { "durbin-watson: ", d.ToString("F4") };
sb.AppendLine(Shared.GetLine(cols, false));
if (_subalgorithm == Calculator1.MATH_SUBTYPES.subalgorithm8.ToString())
{
cols = new string[] { "F Critical Value", FCriticalValue.ToString("F5"), "F > F Critical", FGreaterFCritical };
sb.AppendLine(Shared.GetLine(cols, true));
cols = new string[] { "estimate", "predicted", string.Concat("lower ", _confidenceInt.ToString(), "%"), string.Concat("upper ", _confidenceInt.ToString(), "%") };
sb.AppendLine(Shared.GetLine(cols, true));
cols = new string[] { "Col 0 Mean CI ", QTPredicted.ToString("F4"), QTL.ToString("F4"), QTU.ToString("F4") };
sb.AppendLine(Shared.GetLine(cols, false));
cols = new string[] { "Col 1 - 0 Mean CI ", QTPredicted10.ToString("F4"), QTL10.ToString("F4"), QTU10.ToString("F4") };
sb.AppendLine(Shared.GetLine(cols, false));
cols = new string[] { "Col 2 - 0 Mean CI ", QTPredicted20.ToString("F4"), QTL20.ToString("F4"), QTU20.ToString("F4") };
sb.AppendLine(Shared.GetLine(cols, false));
}
else
{
cols = new string[] { "estimate", "predicted", string.Concat("lower ", _confidenceInt.ToString(), "%"), string.Concat("upper ", _confidenceInt.ToString(), "%") };
sb.AppendLine(Shared.GetLine(cols, true));
cols = new string[] { "QTM CI ", QTPredicted.ToString("F4"), QTL.ToString("F4"), QTU.ToString("F4") };
sb.AppendLine(Shared.GetLine(cols, false));
cols = new string[] { "QTM PI ", QTPredicted.ToString("F4"), (QTPredicted - QTPI).ToString("F4"), (QTPredicted + QTPI).ToString("F4") };
sb.AppendLine(Shared.GetLine(cols, false));
string sRow = string.Concat("row ", data.Count - 2);
cols = new string[] { sRow };
sb.AppendLine(Shared.GetLine(cols, true));
cols = new string[] { "CI ", QTPredicted10.ToString("F4"), QTL10.ToString("F4"), QTU10.ToString("F4") };
sb.AppendLine(Shared.GetLine(cols, false));
cols = new string[] { "PI ", QTPredicted10.ToString("F4"), (QTPredicted10 - QTPI10).ToString("F4"), (QTPredicted10 + QTPI10).ToString("F4") };
sb.AppendLine(Shared.GetLine(cols, false));
sRow = string.Concat("row ", data.Count - 1);
cols = new string[] { sRow };
sb.AppendLine(Shared.GetLine(cols, true));
cols = new string[] { "CI ", QTPredicted20.ToString("F4"), QTL20.ToString("F4"), QTU20.ToString("F4") };
sb.AppendLine(Shared.GetLine(cols, false));
cols = new string[] { "PI ", QTPredicted20.ToString("F4"), (QTPredicted20 - QTPI20).ToString("F4"), (QTPredicted20 + QTPI20).ToString("F4") };
sb.AppendLine(Shared.GetLine(cols, false));
}
if (this.MathResult.ToLower().StartsWith("http"))
{
string sError = string.Empty;
bool bHasSaved = CalculatorHelpers.SaveTextInURI(
_params.ExtensionDocToCalcURI, sb.ToString(), this.MathResult, out sError);
if (!string.IsNullOrEmpty(sError))
{
this.MathResult += sError;
}
}
else
{
this.MathResult = sb.ToString();
}
}
catch (Exception ex)
{
this.ErrorMessage = ex.Message;
}
}
/// <summary>
/// Returns a bar chart plotting the model parameter values and <c>1 - alpha</c> confidence intervals.
/// </summary>
/// <param name="gof">A goodness of fit object.</param>
/// <param name="alpha">A significance level.</param>
/// <returns>A new chart.</returns>
public static ChartControl ToChart( GoodnessOfFit gof, double alpha )
{
ChartControl chart = GetDefaultChart();
Update( ref chart, gof, alpha );
return chart;
}
