public void TimeSeriesFitAR1()
{
double alpha = 0.3;
double mu = 0.2;
double sigma = 0.4;
int n = 24;
// For our fit to AR(1), we have incorporated bias correction (at least
// for the most important parameter alpha), so we can do a small-n test.
FrameTable data = new FrameTable();
data.AddColumn <UncertainValue>("mu");
data.AddColumn <UncertainValue>("alpha");
data.AddColumn <UncertainValue>("sigma");
data.AddColumn <SymmetricMatrix>("covariance");
data.AddColumn <double>("p");
for (int i = 0; i < 128; i++)
{
TimeSeries series = GenerateAR1TimeSeries(alpha, mu, sigma, n, n * i + 271828);
AR1FitResult result = series.FitToAR1();
data.AddRow(
result.Mu, result.Alpha, result.Sigma,
result.Parameters.CovarianceMatrix, result.GoodnessOfFit.Probability
);
}
data.AddComputedColumn("alphaValue", r => ((UncertainValue)r["alpha"]).Value);
data.AddComputedColumn("muValue", r => ((UncertainValue)r["mu"]).Value);
// Check that fit parameters agree with inputs
Assert.IsTrue(data["mu"].As((UncertainValue v) => v.Value).PopulationMean().ConfidenceInterval(0.99).ClosedContains(mu));
Assert.IsTrue(data["alpha"].As((UncertainValue v) => v.Value).PopulationMean().ConfidenceInterval(0.99).ClosedContains(alpha));
Assert.IsTrue(data["sigma"].As((UncertainValue v) => v.Value).PopulationMean().ConfidenceInterval(0.99).ClosedContains(sigma));
// Check that reported variances agree with actual variances
Assert.IsTrue(data["mu"].As((UncertainValue v) => v.Value).PopulationStandardDeviation().ConfidenceInterval(0.99).ClosedContains(data["mu"].As((UncertainValue v) => v.Uncertainty).Median()));
Assert.IsTrue(data["alpha"].As((UncertainValue v) => v.Value).PopulationStandardDeviation().ConfidenceInterval(0.99).ClosedContains(data["alpha"].As((UncertainValue v) => v.Uncertainty).Median()));
Assert.IsTrue(data["sigma"].As((UncertainValue v) => v.Value).PopulationStandardDeviation().ConfidenceInterval(0.99).ClosedContains(data["sigma"].As((UncertainValue v) => v.Uncertainty).Median()));
// Check that reported co-variances agree with actual co-variances
Assert.IsTrue(data["mu"].As((UncertainValue v) => v.Value).PopulationCovariance(data["alpha"].As((UncertainValue v) => v.Value)).ConfidenceInterval(0.99).ClosedContains(data["covariance"].As((SymmetricMatrix c) => c[0, 1]).Median()));
// For small n, the fitted alpha can vary considerably, and the formula for var(m) varies
// quite strongly with alpha, so the computed var(m) have a very long tail. This pushes the
// mean computed var(m) quite a bit higher than a typical value, so we use medians instead
// of means for our best guess for the predicted variance.
TestResult ks = data["p"].As <double>().KolmogorovSmirnovTest(new UniformDistribution());
Assert.IsTrue(ks.Probability > 0.05);
// This is an onerous way to store values, but it does let us test how the data-frame machinery deals with
// non-trivial storage types.
}
private FrameTable GetTestFrame()
{
FrameTable frame = new FrameTable();
frame.AddColumn <string>("name");
frame.AddColumn <double>("height");
frame.AddColumn <double>("weight");
frame.AddColumn <bool?>("male");
frame.AddRow("a", 7.0, 10.0, false);
frame.AddRow(null, 6.5, 11.0, true);
frame.AddRow("c", 6.0, 12.0, false);
frame.AddRow("d", 5.5, 11.0, true);
frame.AddRow("e", 5.0, 12.0, null);
frame.AddRow("f", 4.5, 13.0, true);
frame.AddRow(null, 4.0, 12.0, false);
frame.AddComputedColumn("bmi", r => ((double)r["weight"]) / MoreMath.Sqr((double)r["height"]));
return(frame);
}
public void FrameTableManipulation()
{
FrameTable table = new FrameTable();
table.AddColumn <int>("Id");
table.AddColumn <DateTime?>("Birthdate");
table.AddColumns <string>("FirstName", "LastName");
Assert.IsTrue(table.Columns.Count == 4);
// Index lookup should work
Assert.IsTrue(table.GetColumnIndex("Birthdate") >= 0);
Assert.IsTrue(table.GetColumnIndex("None") < 0);
// Add rows
Assert.IsTrue(table.Rows.Count == 0);
table.AddRow(1, DateTime.Parse("1990-01-01"), "a", "p");
table.AddRow(2, DateTime.Parse("2000-02-02"), null, null);
table.AddRow(new Dictionary <string, object>()
{
{ "Id", 3 }, { "Birthdate", null }, { "FirstName", "c" }, { "LastName", "r" }
});
Assert.IsTrue(table.Rows.Count == 3);
// Adding rows with the wrong types and/or entries should fail
// Careful, some of these will leave the table in a bad state
//try {
// table.AddRow(4, DateTime.Parse("2010-04-04"), 1.0, "s");
// Assert.Fail();
//} catch (Exception) { }
try {
table.AddRow(4, DateTime.Parse("2010-04-04"));
Assert.Fail();
} catch (Exception) { }
//try {
// table.AddRow(new Dictionary<string, object>() {
// {"Id", 4}, { "FirstName", "d" }, { "LastName", "r" }
// });
// Assert.Fail();
//} catch (Exception) { }
//try {
// table.AddRow(new Dictionary<string, object>() {
// {"Id", 4}, { "Birthdate", null }, { "FirstName", "d" }, { "LastName", "r" }, { "MiddleName", "u" }
// });
// Assert.Fail();
//} catch (Exception) { }
// Adding a new column with the wrong length should fail
try {
table.AddColumn <double>("Score");
Assert.Fail();
} catch (Exception) { }
Assert.IsTrue(table.GetColumnIndex("Score") < 0);
// Adding a new column with the right length should work
List <double> scores = new List <double>()
{
1.1, 1.2, 1.3
};
table.AddColumn("Score", scores);
Assert.IsTrue(table.GetColumnIndex("Score") >= 0);
// Adding a new computed column should work
table.AddComputedColumn <TimeSpan?>("Age", r => {
DateTime?b = (DateTime?)r["Birthdate"];
if (b.HasValue)
{
return(DateTime.Now - b.Value);
}
else
{
return(null);
}
});
Assert.IsTrue(table.GetColumnIndex("Age") >= 0);
// Changing a value should change the result of the computed column that depends on it
int birthdateIndex = table.GetColumnIndex("Birthdate");
int ageIndex = table.GetColumnIndex("Age");
TimeSpan age1 = (TimeSpan)table[0, ageIndex];
table[0, birthdateIndex] = DateTime.Parse("2010-01-01");
TimeSpan age2 = (TimeSpan)table[0, ageIndex];
Assert.IsTrue(age2 != age1);
// Clearing a table should work
table.Clear();
Assert.IsTrue(table.Columns.Count > 0);
Assert.IsTrue(table.Rows.Count == 0);
}
