I have a Histogram statistics bar chart with below data.
Count, HistogramBin
0, -1615.25
0, -1056.42
0, -497.48
1, 61.25
1, 620.05
1, 1178.92
0, 1737.76
0, 2296.59
I need to form Gauss curve based on above values. Could anyone guide me how to achieve the same.
I have written a function based on Wikipedia link: https://en.wikipedia.org/wiki/Gaussian_function
Our average is : 340.67
SD: Standard deviation: 488.98001098632812
private DataTable GenerateGaussTable1(DataTable histogramDataTable,
HistogramValueItem histogramValueDBItem)
{
double amplitude = (Average + 3 * Sigma) / 2;
double mean = Average;
double sd = Sigma;
DataTable dt = new DataTable();
dt.Columns.Add("x", typeof(float));
dt.Columns.Add("Y", typeof(float));
foreach (DataRow row in histogramDataTable.Rows)// top provided data
{
double x = Convert.ToDouble(row[1]) / 2;
double var1 = 1 / sd * Math.Sqrt(2 * 3.14);
double var2 = -0.5 * Math.Pow((x - mean)/sd, 2);
double var4= Math.Exp(var2);
double var5 = var1 * var4;
// Y = Amplitude * exp(-0.5 * ((X - Mean) / SD) ^ 2)
double y = var5;
dt.Rows.Add((float)x, (float)y);
}
return dt;
}
Here is my code:
double gauss(double x, double a, double b, double c)
{
var v1 = ( x - b) / (2d * c * c);
var v2 = -v1 * v1 / 2d;
var v3 = a * Math.Exp(v2);
return v3;
}
and:
private void button_Click(object sender, EventArgs e)
{
Series s1 = chart2.Series[0];
s1.ChartType = SeriesChartType.Line;
s1.Name = "Line";
Series s2 = chart2.Series.Add("Spline");
s2.ChartType = SeriesChartType.Spline;
double avg = 1.8;
double amp = 3;
double sd = 0.53;
List<double> xes = new List<double>
{ 0, 0, 0.05, 0.1, 0.4, 0.9, 1.3, 1.6, 2, 2.4, 2.8, 3.2, 4 };
foreach (var x in xes)
{
s1.Points.AddXY(x, gauss(x, amp, avg, sd));
s2.Points.AddXY(x, gauss(x, amp, avg, sd));
}
}
The math was taken from wikipedia
I think your SD is way too large to create a bell curve; try dividing by 10-100..! - Of course your SD actually is very large and so you really won't get a meaningful bell curve for those data..
I've tried your function, but it gives wrong curves,
The gauss function is wrong, why do you use "2d"?
Here the function :
so first, v1 = (x-b). Then v2 = (x-b)² / 2 c²
And finaly v3 = a exp (v2)
double gauss(double x, double a, double b, double c)
{
var v1 = (x - b);
var v2 = (v1 * v1) / (2 * (c*c));
var v3 = a * Math.Exp(-v2);
return v3;
}
After this fix, the curves are much better.
Related
I'm looking for a high precision solution to find the center point of a circle from 3 data points on a canvas (x,y). I found this example in the attached screenshot above, now I'm using the Math.NET package to solve the equation and I'm comparing the results against this online tool: https://planetcalc.com/8116/.
However, when I calculate the radius its completely off and often a negative number???
using MathNet.Numerics.LinearAlgebra.Double.Solvers;
using MathNet.Numerics.LinearAlgebra.Double;
using System;
namespace ConsoleAppTestBed
{
class Program
{
static void Main(string[] args)
{
var dataPoints = new double[,]
{
{ 5, 80 },
{ 20, 100 },
{ 40, 140 }
};
var fitter = new CircleFitter();
var result = fitter.Fit(dataPoints);
var x = -result[0];
var y = -result[1];
var c = result[2];
Console.WriteLine("Center Point:");
Console.WriteLine(x);
Console.WriteLine(y);
Console.WriteLine(c);
//// (x^2 + y^2 - c^2)
var radius = Math.Pow(x, 2) + Math.Pow(y, 2) - Math.Pow(c, 2);
//// sqrt((x^2 + y^2 - c^2))
radius = Math.Sqrt(radius);
Console.WriteLine("Radius:");
Console.WriteLine(radius);
Console.ReadLine();
}
public class CircleFitter
{
public double[] Fit(double[,] v)
{
var xy1 = new double[] { v[0,0], v[0,1] };
var xy2= new double[] { v[1, 0], v[1, 1] };
var xy3 = new double[] { v[2, 0], v[2, 1] };
// Create Left Side Matrix of Equation
var a = CreateLeftSide_(xy1);
var b = CreateLeftSide_(xy2);
var c = CreateLeftSide_(xy3);
var matrixA = DenseMatrix.OfArray(new[,]
{
{ a[0], a[1], a[2] },
{ b[0], b[1], b[2] },
{ c[0], c[1], c[2] }
});
// Create Right Side Vector of Equation
var d = CreateRightSide_(xy1);
var e = CreateRightSide_(xy2);
var f = CreateRightSide_(xy3);
double[] vector = { d, e, f };
var vectorB = Vector<double>.Build.Dense(vector);
// Solve Equation
var r = matrixA.Solve(vectorB);
var result = r.ToArray();
return result;
}
//2x, 2y, 1
public double[] CreateLeftSide_(double[] d)
{
return new double[] { (2 * d[0]), (2 * d[1]) , 1};
}
// -(x^2 + y^2)
public double CreateRightSide_(double[] d)
{
return -(Math.Pow(d[0], 2) + Math.Pow(d[1], 2));
}
}
}
}
Any ideas?
Thanks in advance.
The solution to your problem is here: The NumberDecimalDigits property
Code:
using System;
using System.Globalization;
namespace ConsoleApp1
{
class Program
{
static void Main()
{
double x1 = 1, y1 = 1;
double x2 = 2, y2 = 4;
double x3 = 5, y3 = -3;
findCircle(x1, y1, x2, y2, x3, y3);
Console.ReadKey();
}
static void findCircle(double x1, double y1,
double x2, double y2,
double x3, double y3)
{
NumberFormatInfo setPrecision = new NumberFormatInfo();
setPrecision.NumberDecimalDigits = 3; // 3 digits after the double point
double x12 = x1 - x2;
double x13 = x1 - x3;
double y12 = y1 - y2;
double y13 = y1 - y3;
double y31 = y3 - y1;
double y21 = y2 - y1;
double x31 = x3 - x1;
double x21 = x2 - x1;
double sx13 = (double)(Math.Pow(x1, 2) -
Math.Pow(x3, 2));
double sy13 = (double)(Math.Pow(y1, 2) -
Math.Pow(y3, 2));
double sx21 = (double)(Math.Pow(x2, 2) -
Math.Pow(x1, 2));
double sy21 = (double)(Math.Pow(y2, 2) -
Math.Pow(y1, 2));
double f = ((sx13) * (x12)
+ (sy13) * (x12)
+ (sx21) * (x13)
+ (sy21) * (x13))
/ (2 * ((y31) * (x12) - (y21) * (x13)));
double g = ((sx13) * (y12)
+ (sy13) * (y12)
+ (sx21) * (y13)
+ (sy21) * (y13))
/ (2 * ((x31) * (y12) - (x21) * (y13)));
double c = -(double)Math.Pow(x1, 2) - (double)Math.Pow(y1, 2) -
2 * g * x1 - 2 * f * y1;
double h = -g;
double k = -f;
double sqr_of_r = h * h + k * k - c;
// r is the radius
double r = Math.Round(Math.Sqrt(sqr_of_r), 5);
Console.WriteLine("Center of a circle: x = " + h.ToString("N", setPrecision) +
", y = " + k.ToString("N", setPrecision));
Console.WriteLine("Radius: " + r.ToString("N", setPrecision));
}
}
}
I have just converted William Li's answer to Swift 5 for
those who like to cmd+C and cmd+V like me :)
func calculateCircle(){
let x1:Float = 0
let y1:Float = 0
let x2:Float = 0.5
let y2:Float = 0.5
let x3:Float = 1
let y3:Float = 0
let x12 = x1 - x2
let x13 = x1 - x3
let y12 = y1 - y2
let y13 = y1 - y3
let y31 = y3 - y1
let y21 = y2 - y1
let x31 = x3 - x1
let x21 = x2 - x1
let sx13 = pow(x1, 2) - pow(x3, 2)
let sy13 = pow(y1, 2) - pow(y3, 2)
let sx21 = pow(x2, 2) - pow(x1, 2)
let sy21 = pow(y2, 2) - pow(y1, 2)
let f = ((sx13) * (x12)
+ (sy13) * (x12)
+ (sx21) * (x13)
+ (sy21) * (x13))
/ (2 * ((y31) * (x12) - (y21) * (x13)))
let g = ((sx13) * (y12)
+ (sy13) * (y12)
+ (sx21) * (y13)
+ (sy21) * (y13))
/ (2 * ((x31) * (y12) - (x21) * (y13)))
let c = -pow(x1, 2) - pow(y1, 2) - 2 * g * x1 - 2 * f * y1
let h = -g
let k = -f
let r = sqrt(h * h + k * k - c)
print("center x = \(h)")
print("center y = \(k)")
print("r = \(r)")
}
Updated Answer
The equation for radius is incorrect; it should be (not c squared):
which is why you get incorrect values for the radius.
The original answer was incorrect, but it is still 'interesting'.
(Incorrect) Original Answer
The cause of the problematic calculation is not solely due to the precision of the numbers, but more because problem is ill-conditioned. If you look at the three points and where they are located on the circle, you'll see that they are bunched on a small segment of the circumference. When the points are so close to each other, it is a tough ask to find the circle's centre and radius accurately.
So the intermediate calculations, which will have small rounding errors, result in hugely exaggerated errors.
You can see the ill-conditioned nature of the problem by adding the ConditionNumber() method.
// Solve Equation
Console.WriteLine(matrixA.ConditionNumber()); // <<< Returns 5800 -> Big!
var r = matrixA.Solve(vectorB); // Existing code
A large result indicates an ill-conditioned problem. In this case a value of 5800 is returned, which is large. You might get better results using Gaussian Elimination with partial pivoting, but it still does not address the fact that the basic problem is ill-conditioned, which is why you get wildly incorrect answers.
I am doing 2D trilateration using the MathNet for the matrices and vectors. This i my code:
public static double[] trilaterate2DLinear(double[] pA, double[] pB, double[] pC, double rA, double rB, double rC) {
//Convert doubles to vectors for processing
Vector<double> vA = Vector<double>.Build.Dense(pA);
Vector<double> vB = Vector<double>.Build.Dense(pB);
Vector<double> vC = Vector<double>.Build.Dense(pC);
//Declare elements of b vector
//bBA = 1/2 * (rA^2 - rB^2 + dBA^2)
double[] b = {0, 0};
b[0] = 0.5 * (Math.Pow(rA, 2) - Math.Pow(rB, 2) + Math.Pow(getDistance(pB, pA), 2));
b[1] = 0.5 * (Math.Pow(rA, 2) - Math.Pow(rC, 2) + Math.Pow(getDistance(pC, pA), 2));
//Convert b array to vector form
Vector<double> vb = Vector<double>.Build.Dense(b);
//Build A array
//A = {x2 -x1, y2 - y1}
// {x3 - x1, y3 - y1}
double[,] A = { { pB[0] - pA[0], pB[1] - pA[1] }, { pC[0] - pA[0], pC[1] - pA[1] } };
//Convert A to Matrix form
Matrix<double> mA = Matrix<double>.Build.DenseOfArray(A);
//Declare Transpose of A matrix;
Matrix<double> mAT = mA.Transpose();
//Declare solution vector x to 0
Vector<double> x = Vector<double>.Build.Dense(2);
//Check if A*AT is non-singular (non 0 determinant)
if (mA.Multiply(mAT).Determinant() == 0)
{
//x = ((AT * A)^-1)*AT*b
x = (((mA.Multiply(mAT)).Inverse()).Multiply(mAT)).Multiply(vb);
}
else
{
//TODO case for A*AT to be singular
x = (((mA.Multiply(mAT)).Inverse()).Multiply(mAT)).Multiply(vb);
}
//final position is x + vA
//return as double so as not
return (x.Add(vA)).ToArray();
}
//Gets the Euclidean distance between two points
private static double getDistance(double[] p1, double[] p2)
{
//d^2 = (p1[0] - p2[0])^2 + (p1[1] - p2[1]);
double distSquared = Math.Pow((p1[0] - p2[0]),2) + Math.Pow((p1[1] - p2[1]),2);
return Math.Sqrt(distSquared);
}
pA, pB & pC are the coordinates of the the Beacons and rA, rB & rC are the distances from the each beacon to the user. Is there anything obvious I am doing wrong? Maybe the order of Matrix multiplications need to change but I am not familiar enough with the Linear Least Squares to be able to track the Matrices and tell.
Solved. The if statement condition and calculations inside the if statement where wrong.
Correction:
public static double[] trilaterate2DLinear(double[] pA, double[] pB, double[] pC, double rA, double rB, double rC) {
//Convert doubles to vectors for processing
Vector<double> vA = Vector<double>.Build.Dense(pA);
Vector<double> vB = Vector<double>.Build.Dense(pB);
Vector<double> vC = Vector<double>.Build.Dense(pC);
//Declare elements of b vector
//bBA = 1/2 * (rA^2 - rB^2 + dBA^2)
double[] b = {0, 0};
b[0] = 0.5 * (Math.Pow(rA, 2) - Math.Pow(rB, 2) + Math.Pow(getDistance(pB, pA), 2));
b[1] = 0.5 * (Math.Pow(rA, 2) - Math.Pow(rC, 2) + Math.Pow(getDistance(pC, pA), 2));
//Convert b array to vector form
Vector<double> vb = Vector<double>.Build.Dense(b);
//Build A array
//A = {x2 -x1, y2 - y1}
// {x3 - x1, y3 - y1}
double[,] A = { { pB[0] - pA[0], pB[1] - pA[1] }, { pC[0] - pA[0], pC[1] - pA[1] } };
//Convert A to Matrix form
Matrix<double> mA = Matrix<double>.Build.DenseOfArray(A);
//Declare Transpose of A matrix;
Matrix<double> mAT = mA.Transpose();
//Declare solution vector x to 0
Vector<double> x = Vector<double>.Build.Dense(2);
//Check if A*AT is non-singular (non 0 determinant)
double det = mA.Multiply(mAT).Determinant();
if (mA.Multiply(mAT).Determinant() > 0.1)
{
//x = ((AT * A)^-1)*AT*b
// x = (((mA.Multiply(mAT)).Inverse()).Multiply(mAT)).Multiply(vb);
x = (mA.Transpose() * mA).Inverse() * (mA.Transpose() * vb);
}
else
{
//TODO case for A*AT to be singular
x = (((mA.Multiply(mAT)).Inverse()).Multiply(mAT)).Multiply(vb);
}
//final position is x + vA
//return as double so as not
return (x.Add(vA)).ToArray();
}
You are not calculating the B vector correctly.
It should be:
//dBA = 0.5 * (rA^2 - rB^2 - length_vA^2 + length_vB^2)
b[0] = 0.5 * (Math.Pow(rA, 2) - Math.Pow(rB, 2) - Math.Pow(getDistance(pA,{0,0}), 2) + Math.Pow(getDistance(pB,{0,0}), 2));
b[1] = 0.5 * (Math.Pow(rA, 2) - Math.Pow(rC, 2) - Math.Pow(getDistance(pA,{0,0}), 2) + Math.Pow(getDistance(pC,{0,0}), 2));
I'm trying to calculate the slope of two data lists. You can easily calculate this in EXCEL using the SLOPE function. =SLOPE(A1:A100, B1:B100). I'm trying to mimic this function in C# WinForm. Here is my code, it can calculate something, but not the correct number that you would get from the Excel function. Please help me find the error here. Thanks so much!
private double Getslope(List<double> ProductGrossExcessReturnOverRFR, List<double> primaryIndexExcessReturnOverRFR, int months, int go_back = 0)
{
double slope = 0;
double sumx = 0, sumy = 0, sumxy = 0, sumx2 = 0;
for (int i = ProductGrossExcessReturnOverRFR.Count - 1 - go_back; i > ProductGrossExcessReturnOverRFR.Count - (1 + months + go_back); i--)
{
sumxy += ProductGrossExcessReturnOverRFR[i] * primaryIndexExcessReturnOverRFR[i];
sumx += ProductGrossExcessReturnOverRFR[i];
sumy += primaryIndexExcessReturnOverRFR[i];
sumx2 += ProductGrossExcessReturnOverRFR[i] * ProductGrossExcessReturnOverRFR[i];
}
return slope = 1 / (((sumxy - sumx * sumy / months) / (sumx2 - sumx * sumx / months)));
}
Test data:
{1.085231224, 2.335034309, 0.346667278} and
{3.185231224,3.705034309 , -0.883332722} should have slope of 0.3373 if you calculate in Excel using =SLOPE function. But my code produces 0.47 somehow...
I think your formula is wrong
According to the Excel documentation the formula for SLOPE is
Note also that the first argument to the function is the the y values.
It's unclear how goback and months apply, but it looks like this might work:
private double Getslope(List<double> ProductGrossExcessReturnOverRFR,
List<double> primaryIndexExcessReturnOverRFR,
int months,
int go_back = 0)
{
// calc # of items to skip
int skip = ProductGrossExcessReturnOverRFR.Count - go_back - months;
// get list of x's and y's
var ys = ProductGrossExcessReturnOverRFR.Skip(skip).Take(months);
var xs = primaryIndexExcessReturnOverRFR.Skip(skip).Take(months);
// "zip" xs and ys to make the sum of products easier
var xys = Enumerable.Zip(xs,ys, (x, y) => new {x = x, y = y});
double xbar = xs.Average();
double ybar = ys.Average();
double slope = xys.Sum(xy => (xy.x - xbar) * (xy.y - ybar)) / xs.Sum(x => (x - xbar)*(x - xbar));
return slope;
}
I'm writing a small application in C# using MSChart control to do Scatter Plots of sets of X and Y data points. Some of these can be rather large (hundreds of data points).
Wanted to ask if there's a 'standard' algorith for plotting a best-fit line across the points. I'm thinking to divide the X data points to a predefined number of sets, say 10 or 20, and for each set take the average of the corresponding Y values and the middle X value, and so on to create the line. Is this a correct approach?
I've searched existing threads but they all seem to be about achieving the same using existing applications like Matlab.
Thanks,
using a Linear least squares algorithm
public class XYPoint
{
public int X;
public double Y;
}
class Program
{
public static List<XYPoint> GenerateLinearBestFit(List<XYPoint> points, out double a, out double b)
{
int numPoints = points.Count;
double meanX = points.Average(point => point.X);
double meanY = points.Average(point => point.Y);
double sumXSquared = points.Sum(point => point.X * point.X);
double sumXY = points.Sum(point => point.X * point.Y);
a = (sumXY / numPoints - meanX * meanY) / (sumXSquared / numPoints - meanX * meanX);
b = (a * meanX - meanY);
double a1 = a;
double b1 = b;
return points.Select(point => new XYPoint() { X = point.X, Y = a1 * point.X - b1 }).ToList();
}
static void Main(string[] args)
{
List<XYPoint> points = new List<XYPoint>()
{
new XYPoint() {X = 1, Y = 12},
new XYPoint() {X = 2, Y = 16},
new XYPoint() {X = 3, Y = 34},
new XYPoint() {X = 4, Y = 45},
new XYPoint() {X = 5, Y = 47}
};
double a, b;
List<XYPoint> bestFit = GenerateLinearBestFit(points, out a, out b);
Console.WriteLine("y = {0:#.####}x {1:+#.####;-#.####}", a, -b);
for(int index = 0; index < points.Count; index++)
{
Console.WriteLine("X = {0}, Y = {1}, Fit = {2:#.###}", points[index].X, points[index].Y, bestFit[index].Y);
}
}
}
Yes. You will want to use Linear Regression, specifically Simple Linear Regression.
The algorithm is essentially:
assume there exists a line of best fit, y = ax + b
for each of your points, you want to minimise their distance from this line
calculate the distance for each point from the line, and sum the distances (normally we use the square of the distance to more heavily penalise points further from the line)
find the values of a and b that minimise the resulting equation using basic calculus (there should be only one minimum)
The wikipedia page will give you everything you need.
I want to use a random number generator that creates random numbers in a gaussian range where I can define the median by myself. I already asked a similar question here and now I'm using this code:
class RandomGaussian
{
private static Random random = new Random();
private static bool haveNextNextGaussian;
private static double nextNextGaussian;
public static double gaussianInRange(double from, double mean, double to)
{
if (!(from < mean && mean < to))
throw new ArgumentOutOfRangeException();
int p = Convert.ToInt32(random.NextDouble() * 100);
double retval;
if (p < (mean * Math.Abs(from - to)))
{
double interval1 = (NextGaussian() * (mean - from));
retval = from + (float)(interval1);
}
else
{
double interval2 = (NextGaussian() * (to - mean));
retval = mean + (float)(interval2);
}
while (retval < from || retval > to)
{
if (retval < from)
retval = (from - retval) + from;
if (retval > to)
retval = to - (retval - to);
}
return retval;
}
private static double NextGaussian()
{
if (haveNextNextGaussian)
{
haveNextNextGaussian = false;
return nextNextGaussian;
}
else
{
double v1, v2, s;
do
{
v1 = 2 * random.NextDouble() - 1;
v2 = 2 * random.NextDouble() - 1;
s = v1 * v1 + v2 * v2;
} while (s >= 1 || s == 0);
double multiplier = Math.Sqrt(-2 * Math.Log(s) / s);
nextNextGaussian = v2 * multiplier;
haveNextNextGaussian = true;
return v1 * multiplier;
}
}
}
Then to verify the results I plotted them with gaussianInRange(0, 0.5, 1) for n=100000000
As one can see the median is really at 0.5 but there isn't really a curve visible. So what I'm doing wrong?
EDIT
What i want is something like this where I can set the highest probability by myself by passing a value.
The simplest way to draw normal deviates conditional on them being in a particular range is with rejection sampling:
do {
retval = NextGaussian() * stdev + mean;
} while (retval < from || to < retval);
The same sort of thing is used when you draw coordinates (v1, v2) in a circle in your unconditional normal generator.
Simply folding in values outside the range doesn't produce the same distribution.
Also, if you have a good implementation of the error function and its inverse, you can calculate the values directly using an inverse CDF. The CDF of a normal distribution is
F(retval) = (1 + erf((retval-mean) / (stdev*sqrt(2)))) / 2
The CDF of a censored distribution is
C(retval) = (F(retval) - F(from)) / (F(to) - F(from)), from ≤ x < to
To draw a random number using a CDF, you draw v from a uniform distribution on [0, 1] and solve C(retval) = v. This gives
double v = random.NextDouble();
double t1 = erf((from - mean) / (stdev*sqrt(2)));
t2 = erf((to - mean) / (stdev*sqrt(2)));
double retval = mean + stdev * sqrt(2) * erf_inv(t1*(1-v) + t2*v);
You can precalculate t1 and t2 for specific parameters. The advantage of this approach is that there is no rejection sampling, so you only need a single NextDouble() per draw. If the [from, to] interval is small this will be faster.
However, it sounds like you might want the binomial distribution instead.
I have similar methods in my Graph generator (had to modify it a bit):
Returns a random floating-point number using a generator function with a specific range:
private double NextFunctional(Func<double, double> func, double from, double to, double height, out double x)
{
double halfWidth = (to - from) / 2;
double distance = halfWidth + from;
x = this.rand.NextDouble() * 2 - 1;// -1 .. 1
double y = func(x);
x = halfWidth * x + distance;
y *= height;
return y;
}
Gaussian function:
private double Gauss(double x)
{
// Graph should look better with double-x scale.
x *= 2;
double σ = 1 / Math.Sqrt(2 * Math.PI);
double variance = Math.Pow(σ, 2);
double exp = -0.5 * Math.Pow(x, 2) / variance;
double y = 1 / Math.Sqrt(2 * Math.PI * variance) * Math.Pow(Math.E, exp);
return y;
}
A method that generates a graph using the random numbers:
private void PlotGraph(Graphics g, Pen p, double from, double to, double height)
{
for (int i = 0; i < 1000; i++)
{
double x;
double y = this.NextFunctional(this.Gauss, from, to, height, out x);
this.DrawPoint(g, p, x, y);
}
}
I would rather used a cosine function - it is much faster and pretty close to the gaussian function for your needs:
double x;
double y = this.NextFunctional(a => Math.Cos(a * Math.PI), from, to, height, out x);
The out double x parameter in the NextFunctional() method is there so you can easily test it on your graphs (I use an iterator in my method).