public void MultivariateLinearLogisticRegressionSimple() { // define model y = a + b0 * x0 + b1 * x1 + noise double a = 1.0; double b0 = -1.0 / 2.0; double b1 = 1.0 / 3.0; ContinuousDistribution x0distribution = new LaplaceDistribution(); ContinuousDistribution x1distribution = new NormalDistribution(); // draw a sample from the model Random rng = new Random(1); MultivariateSample old = new MultivariateSample("y", "x0", "x1"); FrameTable table = new FrameTable(); table.AddColumn <double>("x0"); table.AddColumn <double>("x1"); table.AddColumn <bool>("y"); for (int i = 0; i < 100; i++) { double x0 = x0distribution.GetRandomValue(rng); double x1 = x1distribution.GetRandomValue(rng); double t = a + b0 * x0 + b1 * x1; double p = 1.0 / (1.0 + Math.Exp(-t)); bool y = (rng.NextDouble() < p); old.Add(y ? 1.0 : 0.0, x0, x1); table.AddRow(x0, x1, y); } // do a linear regression fit on the model MultiLinearLogisticRegressionResult oldResult = old.LogisticLinearRegression(0); MultiLinearLogisticRegressionResult newResult = table["y"].As <bool>().MultiLinearLogisticRegression( table["x0"].As <double>(), table["x1"].As <double>() ); // the result should have the appropriate dimension Assert.IsTrue(newResult.Parameters.Count == 3); // The parameters should match the model Assert.IsTrue(newResult.CoefficientOf(0).ConfidenceInterval(0.99).ClosedContains(b0)); Assert.IsTrue(newResult.CoefficientOf("x1").ConfidenceInterval(0.99).ClosedContains(b1)); Assert.IsTrue(newResult.Intercept.ConfidenceInterval(0.99).ClosedContains(a)); // Our predictions should be better than chance. int correct = 0; for (int i = 0; i < table.Rows.Count; i++) { FrameRow row = table.Rows[i]; double x0 = (double)row["x0"]; double x1 = (double)row["x1"]; double p = newResult.Predict(x0, x1).Value; bool y = (bool)row["y"]; if ((y && p > 0.5) || (!y & p < 0.5)) { correct++; } } Assert.IsTrue(correct > 0.5 * table.Rows.Count); }
public void MultivariateLinearLogisticRegressionVariances() { // define model y = a + b0 * x0 + b1 * x1 + noise double a = -3.0; double b0 = 2.0; double b1 = 1.0; ContinuousDistribution x0distribution = new ExponentialDistribution(); ContinuousDistribution x1distribution = new LognormalDistribution(); FrameTable data = new FrameTable(); data.AddColumns <double>("a", "da", "b0", "db0", "b1", "db1", "p", "dp"); // draw a sample from the model Random rng = new Random(2); for (int j = 0; j < 32; j++) { List <double> x0s = new List <double>(); List <double> x1s = new List <double>(); List <bool> ys = new List <bool>(); FrameTable table = new FrameTable(); table.AddColumn <double>("x0"); table.AddColumn <double>("x1"); table.AddColumn <bool>("y"); for (int i = 0; i < 32; i++) { double x0 = x0distribution.GetRandomValue(rng); double x1 = x1distribution.GetRandomValue(rng); double t = a + b0 * x0 + b1 * x1; double p = 1.0 / (1.0 + Math.Exp(-t)); bool y = (rng.NextDouble() < p); x0s.Add(x0); x1s.Add(x1); ys.Add(y); } // do a linear regression fit on the model MultiLinearLogisticRegressionResult result = ys.MultiLinearLogisticRegression( new Dictionary <string, IReadOnlyList <double> > { { "x0", x0s }, { "x1", x1s } } ); UncertainValue pp = result.Predict(0.0, 1.0); data.AddRow( result.Intercept.Value, result.Intercept.Uncertainty, result.CoefficientOf("x0").Value, result.CoefficientOf("x0").Uncertainty, result.CoefficientOf("x1").Value, result.CoefficientOf("x1").Uncertainty, pp.Value, pp.Uncertainty ); } // The estimated parameters should agree with the model that generated the data. // The variances of the estimates should agree with the claimed variances Assert.IsTrue(data["a"].As <double>().PopulationStandardDeviation().ConfidenceInterval(0.99).ClosedContains(data["da"].As <double>().Mean())); Assert.IsTrue(data["b0"].As <double>().PopulationStandardDeviation().ConfidenceInterval(0.99).ClosedContains(data["db0"].As <double>().Mean())); Assert.IsTrue(data["b1"].As <double>().PopulationStandardDeviation().ConfidenceInterval(0.99).ClosedContains(data["db1"].As <double>().Mean())); Assert.IsTrue(data["p"].As <double>().PopulationStandardDeviation().ConfidenceInterval(0.99).ClosedContains(data["dp"].As <double>().Mean())); }
public static void AnalyzingData() { FrameTable table; Uri url = new Uri("https://raw.githubusercontent.com/dcwuser/metanumerics/master/Examples/Data/example.csv"); WebRequest request = WebRequest.Create(url); using (WebResponse response = request.GetResponse()) { using (StreamReader reader = new StreamReader(response.GetResponseStream())) { table = FrameTable.FromCsv(reader); } } FrameView view = table.WhereNotNull(); // Get the column with (zero-based) index 4. FrameColumn column4 = view.Columns[4]; // Get the column named "Height". FrameColumn heightsColumn = view.Columns["Height"]; // Even easier way to get the column named "Height". FrameColumn alsoHeightsColumn = view["Height"]; IReadOnlyList <double> heights = view["Height"].As <double>(); SummaryStatistics summary = new SummaryStatistics(view["Height"].As <double>()); Console.WriteLine($"Count = {summary.Count}"); Console.WriteLine($"Mean = {summary.Mean}"); Console.WriteLine($"Standard Deviation = {summary.StandardDeviation}"); Console.WriteLine($"Skewness = {summary.Skewness}"); Console.WriteLine($"Estimated population mean = {summary.PopulationMean}"); Console.WriteLine($"Estimated population standard deviation = {summary.PopulationStandardDeviation}"); IReadOnlyList <double> maleHeights = view.Where <string>("Sex", s => s == "M").Columns["Height"].As <double>(); IReadOnlyList <double> femaleHeights = view.Where <string>("Sex", s => s == "F").Columns["Height"].As <double>(); TestResult test = Univariate.StudentTTest(maleHeights, femaleHeights); Console.WriteLine($"{test.Statistic.Name} = {test.Statistic.Value}"); Console.WriteLine($"P = {test.Probability}"); TestResult maleHeightNormality = maleHeights.ShapiroFranciaTest(); TestResult totalHeightNormality = view["Height"].As <double>().ShapiroFranciaTest(); TestResult heightCompatibility = Univariate.KolmogorovSmirnovTest(maleHeights, femaleHeights); LinearRegressionResult fit = view["Weight"].As <double>().LinearRegression(view["Height"].As <double>()); Console.WriteLine($"Model weight = ({fit.Slope}) * height + ({fit.Intercept})."); Console.WriteLine($"Model explains {fit.RSquared * 100.0}% of variation."); ContingencyTable <string, bool> contingency = Bivariate.Crosstabs(view["Sex"].As <string>(), view["Result"].As <bool>()); Console.WriteLine($"Male incidence: {contingency.ProbabilityOfColumnConditionalOnRow(true, "M")}"); Console.WriteLine($"Female incidence: {contingency.ProbabilityOfColumnConditionalOnRow(true, "F")}"); Console.WriteLine($"Log odds ratio = {contingency.Binary.LogOddsRatio}"); view.AddComputedColumn("Bmi", r => ((double)r["Weight"]) / MoreMath.Sqr((double)r["Height"] / 100.0)); view.AddComputedColumn("Age", r => (DateTime.Now - (DateTime)r["Birthdate"]).TotalDays / 365.24); MultiLinearLogisticRegressionResult result = view["Result"].As <bool>().MultiLinearLogisticRegression( view["Bmi"].As <double>(), view["Sex"].As <string, double>(s => s == "M" ? 1.0 : 0.0) ); foreach (Parameter parameter in result.Parameters) { Console.WriteLine($"{parameter.Name} = {parameter.Estimate}"); } TestResult spearman = Bivariate.SpearmanRhoTest(view["Age"].As <double>(), view["Result"].As <double>()); Console.WriteLine($"{spearman.Statistic.Name} = {spearman.Statistic.Value} P = {spearman.Probability}"); }