public List<Correlation> FindCorrelationsViaLinearRegression(MultivariateSample sample, int columns)
{
var fitResult = sample.LinearRegression(0);
var correlations = new List<Correlation>();
// The two loops are for going across every column:column combination
for (var i = 0; i < columns; i++)
{
for (var j = i + 1; j < columns; j++)
{
var coefficient = fitResult.CorrelationCoefficient(i, j);
// REVISIT: Can pass in correlation thresholds through configuration
if (coefficient >= 0.55 || coefficient <= -0.55)
{
correlations.Add(new Correlation
{
Coefficient = coefficient,
ColumnA = i,
ColumnB = j,
CorrelationType = coefficient >= 0.8 || coefficient <= -0.8
? CorrelationType.Significant
: CorrelationType.Borderline
});
}
}
}
return correlations;
}
/// <summary>
/// Korrelatsiooni arvutus valitud näitajate jaoks (Total Assets, Total Liabilities, Total Current Assets, Total Current Liabilities: vs Reveneue)
/// </summary>
/// <param name="finDataAdapter">Adapter kõigi finantsandmete kättesaamise jaoks</param>
/// <param name="dcfInput">DCF arvutuste eelduste hoidja</param>
public static void CalculateCorrelation(FinDataAdapter finDataAdapter, DcfInput dcfInput)
{
MultivariateSample mvTA = new MultivariateSample(2);
MultivariateSample mvTL = new MultivariateSample(2);
MultivariateSample mvCA = new MultivariateSample(2);
MultivariateSample mvCL = new MultivariateSample(2);
int k = 0;
List<FinData> finDatas = finDataAdapter.FinDataDao.FinDatas;
for (int i = finDataAdapter.FinDataDao.FinDatas.Count - 1; i >= 0; i--)
{
if (k < 20)
{
double revChange = 0;
try
{
//revChange = (double) (finDatas[i].IsRevenue/finDatas[i - 5].IsRevenue);
revChange = (double)finDatas[i].IsRevenue;
}
catch (InvalidOperationException) { }
double caChange = 0;
try
{
//secChange = (double)(finDatas[i].BsTotalCurrentAssets / finDatas[i - 5].BsTotalCurrentAssets);
caChange = (double)finDatas[i].BsTotalCurrentAssets;
}
catch (InvalidOperationException) { }
double clChange = 0;
try
{
//secChange = (double)(finDatas[i].BsTotalCurrentAssets / finDatas[i - 5].BsTotalCurrentAssets);
clChange = (double)finDatas[i].BsTotalCurrentLiabilities;
}
catch (InvalidOperationException) { }
double taChange = 0;
try
{
//secChange = (double)(finDatas[i].BsTotalCurrentAssets / finDatas[i - 5].BsTotalCurrentAssets);
taChange = (double)finDatas[i].BsTotalAssets;
}
catch (InvalidOperationException) { }
double tlChange = 0;
try
{
//secChange = (double)(finDatas[i].BsTotalCurrentAssets / finDatas[i - 5].BsTotalCurrentAssets);
tlChange = (double)finDatas[i].BsTotalLiabilities;
}
catch (InvalidOperationException) { }
//MessageBox.Show("s:" + ((double)(prevPrice / curPrice) - 1));
//MessageBox.Show("i:" + ((double)(prevIndex / curIndex) - 1));
////bivariate.Add((double) (prevPrice/curPrice)-1,(double) (prevIndex/curIndex)-1);
double[] db = new double[2];
db[0] = caChange;
db[1] = revChange;
if (db[0] != 0 || db[1] != 0)
mvCA.Add(db);
db = new double[2];
db[0] = clChange;
db[1] = revChange;
if (db[0] != 0 || db[1] != 0)
mvCL.Add(db);
db = new double[2];
db[0] = taChange;
db[1] = revChange;
if (db[0] != 0 || db[1] != 0)
mvTA.Add(db);
db = new double[2];
db[0] = tlChange;
db[1] = revChange;
if (db[0] != 0 || db[1] != 0)
mvTL.Add(db);
//DateTime dt = finDataAdapter.PriceDataDao.PriceDatas[i].PriceDate;
//MessageBox.Show(finDataAdapter.PriceDataDao.PriceDatas[i].AdjClose + " " +
// dt.ToShortDateString());
//MessageBox.Show(finDataAdapter.PriceDataDao.GetClosePrice(dt, finDataAdapter.PriceDataDao.IndexDatas)[0].ToString());
}
k++;
}
// peab vähemalt olema 3 vaatlust
if (mvCA.Count > 2)
{
//FitResult fitResult = bivariate.LinearRegression();
FitResult fitResult = mvCA.LinearRegression(0);
dcfInput.TotalCurrentAssetsBeta = fitResult.Parameter(1).Value;
dcfInput.TotalCurrentAssetsAlpha = fitResult.Parameter(0).Value;
fitResult = mvCL.LinearRegression(0);
dcfInput.TotalCurrentLiabilitiesBeta = fitResult.Parameter(1).Value;
dcfInput.TotalCurrentLiabilitiesAlpha = fitResult.Parameter(0).Value;
fitResult = mvTA.LinearRegression(0);
dcfInput.TotalAssetsBeta = fitResult.Parameter(1).Value;
dcfInput.TotalAssetsAlpha = fitResult.Parameter(0).Value;
fitResult = mvTL.LinearRegression(0);
dcfInput.TotalLiabilitiesBeta = fitResult.Parameter(1).Value;
dcfInput.TotalLiabilitiesAlpha = fitResult.Parameter(0).Value;
//MessageBox.Show("alfa: " + fitResult.Parameter(0).Value.ToString());
//MessageBox.Show("beta: "+fitResult.Parameter(1).Value.ToString());
//double[] pars = fitResult.Parameters();
//foreach (var par in pars)
//{
// MessageBox.Show(par.ToString());
//}
//MessageBox.Show(fitResult.CorrelationCoefficient(0,1).ToString());
//double[] gfit = fitResult.
//MessageBox.Show(fitResult.);
//MessageBox.Show(fitResult.Parameter(2).ToString());
}
}
/// <summary>
/// Beta arvutus
/// </summary>
/// <param name="finDataAdapter">Adapter kõigi finantsandmete kättesaamise jaoks</param>
/// <param name="dcfInput">DCF arvutuste eelduste hoidja</param>
public static void CalculateBeta(FinDataAdapter finDataAdapter, DcfInput dcfInput)
{
BivariateSample bivariate = new BivariateSample();
MultivariateSample mv = new MultivariateSample(2);
decimal prevPrice = 0;
double? prevIndex = null;
decimal curPrice = 0;
double? curIndex = null;
int k = 0;
for (int i = 0; i < finDataAdapter.PriceDataDao.PriceDatas.Count; i = i + 22)
{
if (k < 36)
{
PriceData pd = finDataAdapter.PriceDataDao.PriceDatas[i];
curPrice = pd.AdjClose;
curIndex = finDataAdapter.PriceDataDao.GetClosePrice(pd.PriceDate, finDataAdapter.PriceDataDao.IndexDatas)[0];
if (curPrice != 0 && curIndex != null && prevPrice != 0 && prevIndex != null)
{
//MessageBox.Show("s:" + ((double)(prevPrice / curPrice) - 1));
//MessageBox.Show("i:" + ((double)(prevIndex / curIndex) - 1));
////bivariate.Add((double) (prevPrice/curPrice)-1,(double) (prevIndex/curIndex)-1);
double[] db = new double[2];
db[0] = ((double)(prevPrice / curPrice) - 1);
db[1] = ((double)(prevIndex / curIndex) - 1);
mv.Add(db);
}
prevPrice = curPrice;
prevIndex = curIndex;
//DateTime dt = finDataAdapter.PriceDataDao.PriceDatas[i].PriceDate;
//MessageBox.Show(finDataAdapter.PriceDataDao.PriceDatas[i].AdjClose + " " +
// dt.ToShortDateString());
//MessageBox.Show(finDataAdapter.PriceDataDao.GetClosePrice(dt, finDataAdapter.PriceDataDao.IndexDatas)[0].ToString());
}
k++;
}
if (mv.Count > 10)
{
//FitResult fitResult = bivariate.LinearRegression();
FitResult fitResult = mv.LinearRegression(0);
dcfInput.Beta = fitResult.Parameter(1).Value;
List<FinData> finDatas = finDataAdapter.FinDataDao.FinDatas;
dcfInput.CostOfEquity = dcfInput.RiskFreeRate + dcfInput.Beta * dcfInput.MarketRiskPremium;
double debt = 0;
if (finDatas[finDatas.Count - 1].BsCurrentPortionOfLongTermDebt != null)
{
debt += (double)finDatas[finDatas.Count - 1].BsCurrentPortionOfLongTermDebt;
}
if (finDatas[finDatas.Count - 1].BsTotalLongTermDebt != null)
{
debt += (double)finDatas[finDatas.Count - 1].BsTotalLongTermDebt;
}
double total = 0.0;
if (finDatas[finDatas.Count - 1].BsShareholdersEquity1 != null)
{
total += (double)(finDatas[finDatas.Count - 1].BsShareholdersEquity1);
}
total += debt;
try
{
dcfInput.Wacc = dcfInput.CostOfEquity *
(double)(finDatas[finDatas.Count - 1].BsShareholdersEquity1 / total) +
dcfInput.CostOfDebt * (double)(debt / total) * (1 - dcfInput.TaxRate);
}
catch (InvalidOperationException) { }
//MessageBox.Show("beta: "+fitResult.Parameter(1).Value.ToString());
//double[] pars = fitResult.Parameters();
//foreach (var par in pars)
//{
// MessageBox.Show(par.ToString());
//}
//MessageBox.Show(fitResult.CorrelationCoefficient(0,1).ToString());
//double[] gfit = fitResult.
//MessageBox.Show(fitResult.);
//MessageBox.Show(fitResult.Parameter(2).ToString());
}
}
public void MultivariateLinearRegressionAgreement()
{
Random rng = new Random(1);
MultivariateSample SA = new MultivariateSample(2);
for (int i = 0; i < 10; i++) {
SA.Add(rng.NextDouble(), rng.NextDouble());
}
FitResult RA = SA.LinearRegression(0);
ColumnVector PA = RA.Parameters;
SymmetricMatrix CA = RA.CovarianceMatrix;
MultivariateSample SB = SA.Columns(1, 0);
FitResult RB = SB.LinearRegression(1);
ColumnVector PB = RB.Parameters;
SymmetricMatrix CB = RB.CovarianceMatrix;
Assert.IsTrue(TestUtilities.IsNearlyEqual(PA[0], PB[1])); Assert.IsTrue(TestUtilities.IsNearlyEqual(PA[1], PB[0]));
Assert.IsTrue(TestUtilities.IsNearlyEqual(CA[0, 0], CB[1, 1])); Assert.IsTrue(TestUtilities.IsNearlyEqual(CA[0, 1], CB[1, 0])); Assert.IsTrue(TestUtilities.IsNearlyEqual(CA[1, 1], CB[0, 0]));
Assert.IsTrue(TestUtilities.IsNearlyEqual(RA.GoodnessOfFit.Statistic, RB.GoodnessOfFit.Statistic));
BivariateSample SC = SA.TwoColumns(1, 0);
FitResult RC = SC.LinearRegression();
ColumnVector PC = RC.Parameters;
SymmetricMatrix CC = RC.CovarianceMatrix;
Assert.IsTrue(TestUtilities.IsNearlyEqual(PA, PC));
Assert.IsTrue(TestUtilities.IsNearlyEqual(CA, CC));
Assert.IsTrue(TestUtilities.IsNearlyEqual(RA.GoodnessOfFit.Statistic, RC.GoodnessOfFit.Statistic));
}
public void OldMultivariateLinearRegressionTest()
{
MultivariateSample sample = new MultivariateSample(3);
sample.Add(98322, 81449, 269465);
sample.Add(65060, 31749, 121900);
sample.Add(36052, 14631, 37004);
sample.Add(31829, 27732, 91400);
sample.Add(7101, 9693, 54900);
sample.Add(41294, 4268, 16160);
sample.Add(16614, 4697, 21500);
sample.Add(3449, 4233, 9306);
sample.Add(3386, 5293, 38300);
sample.Add(6242, 2039, 13369);
sample.Add(14036, 7893, 29901);
sample.Add(2636, 3345, 10930);
sample.Add(869, 1135, 5100);
sample.Add(452, 727, 7653);
/*
sample.Add(41.9, 29.1, 251.3);
sample.Add(43.4, 29.3, 251.3);
sample.Add(43.9, 29.5, 248.3);
sample.Add(44.5, 29.7, 267.5);
sample.Add(47.3, 29.9, 273.0);
sample.Add(47.5, 30.3, 276.5);
sample.Add(47.9, 30.5, 270.3);
sample.Add(50.2, 30.7, 274.9);
sample.Add(52.8, 30.8, 285.0);
sample.Add(53.2, 30.9, 290.0);
sample.Add(56.7, 31.5, 297.0);
sample.Add(57.0, 31.7, 302.5);
sample.Add(63.5, 31.9, 304.5);
sample.Add(65.3, 32.0, 309.3);
sample.Add(71.1, 32.1, 321.7);
sample.Add(77.0, 32.5, 330.7);
sample.Add(77.8, 32.9, 349.0);
*/
Console.WriteLine(sample.Count);
//sample.LinearRegression(0);
sample.LinearRegression(0);
}
public void MultivariateLinearRegressionTest()
{
// define model y = a + b0 * x0 + b1 * x1 + noise
double a = 1.0;
double b0 = -2.0;
double b1 = 3.0;
Distribution noise = new NormalDistribution(0.0, 10.0);
// draw a sample from the model
Random rng = new Random(1);
MultivariateSample sample = new MultivariateSample(3);
for (int i = 0; i < 100; i++) {
double x0 = -10.0 + 20.0 * rng.NextDouble();
double x1 = -10.0 + 20.0 * rng.NextDouble();
double eps = noise.InverseLeftProbability(rng.NextDouble());
double y = a + b0 * x0 + b1 * x1 + eps;
sample.Add(x0, x1, y);
}
// do a linear regression fit on the model
FitResult result = sample.LinearRegression(2);
// the result should have the appropriate dimension
Assert.IsTrue(result.Dimension == 3);
// the result should be significant
Console.WriteLine("{0} {1}", result.GoodnessOfFit.Statistic, result.GoodnessOfFit.LeftProbability);
Assert.IsTrue(result.GoodnessOfFit.LeftProbability > 0.95);
// the parameters should match the model
Console.WriteLine(result.Parameter(0));
Assert.IsTrue(result.Parameter(0).ConfidenceInterval(0.90).ClosedContains(b0));
Console.WriteLine(result.Parameter(1));
Assert.IsTrue(result.Parameter(1).ConfidenceInterval(0.90).ClosedContains(b1));
Console.WriteLine(result.Parameter(2));
Assert.IsTrue(result.Parameter(2).ConfidenceInterval(0.90).ClosedContains(a));
}
public void MultivariateLinearRegressionNullDistribution()
{
int d = 4;
Random rng = new Random(1);
NormalDistribution n = new NormalDistribution();
Sample fs = new Sample();
for (int i = 0; i < 64; i++) {
MultivariateSample ms = new MultivariateSample(d);
for (int j = 0; j < 8; j++) {
double[] x = new double[d];
for (int k = 0; k < d; k++) {
x[k] = n.GetRandomValue(rng);
}
ms.Add(x);
}
FitResult r = ms.LinearRegression(0);
fs.Add(r.GoodnessOfFit.Statistic);
}
// conduct a KS test to check that F follows the expected distribution
TestResult ks = fs.KolmogorovSmirnovTest(new FisherDistribution(3, 4));
Assert.IsTrue(ks.LeftProbability < 0.95);
}
public void MultivariateLinearRegressionBadInputTest()
{
// create a sample
MultivariateSample sample = new MultivariateSample(3);
sample.Add(1, 2, 3);
sample.Add(2, 3, 4);
// try to predict with too little data
try {
sample.LinearRegression(2);
Assert.IsTrue(false);
} catch (InvalidOperationException) {
Assert.IsTrue(true);
}
// add enough data
sample.Add(3, 4, 5);
sample.Add(4, 5, 6);
// try to predict a non-existent variable
try {
sample.LinearRegression(-1);
Assert.IsTrue(false);
} catch (ArgumentOutOfRangeException) {
Assert.IsTrue(true);
}
try {
sample.LinearRegression(3);
Assert.IsTrue(false);
} catch (ArgumentOutOfRangeException) {
Assert.IsTrue(true);
}
}