8f91ec929f
Distributions: StudentT.InvCDF
13 years ago
ccf4340ce0
Build: update supported platforms in NuGet nuspec descriptions
13 years ago
776cdfe080
Distributions: drop redundant xmldoc remarks. Closes #183 .
13 years ago
4f2560bb22
Generate: new variants with fast RandomUniform
13 years ago
28fcd8acb6
Tests: adapt tests to different data from new RNG (system instead of MT)
13 years ago
b7384c697b
LA, Statistics, Generate: switch default RNG from MersenneTwister to SystemRandomSource
13 years ago
6e004968c6
Distributions: switch default RNG from MersenneTwister to SystemRandomSource
13 years ago
b4592acd02
Distributions: static PDF/CDF functions for StudentT, Stable, Weibull #188
13 years ago
f29fa0c40a
Update release notes, contributors
13 years ago
dc5597c6d9
Build: include .Net 3.5 build in NuGet package
13 years ago
849f3bff0d
Update contributing.md with more details about primary and secondary project files
13 years ago
9482a7518c
Statistics: s/InverseCDF/EmpiricalInvCDF/
13 years ago
9ea8aebf7e
Statistics: quantile rank, empirical CDF, Excel percentrank
13 years ago
0b5f954739
Statistics: Ranks
13 years ago
a7c7b67647
Categorical dist: Tests for Var, SD, and Median
Added unit tests to validate the following properties of the
Categorical distribution:
- Variance,
- StdDev, and
- Median.
TODO: Find out the expected behaviour of Median in ambiguous cases
(e.g. where P(X=1)=0.5, and P(X=2)=0.5), then add appropriate unit
tests.
TODO: Research how to calculate entropy, then add unit tests for the
Entropy property.
13 years ago
978824c050
Fix to Categorical.Mean property.
Categorical.Mean was being calculated as _pmfNormalized.Mean(), which
is actually the mean probability across all possible values, rather
than the mean value of the distribution.
I've replaced it with a loop which performs the following standard
calculation for mean value:
mean = Sum(x * f(x), x=0..N)
where f(x) is the probability mass function, and N is the maximum
value.
An alternate method of calculation is:
Mean = Sum( 1 - F(x), x=0..N) or similar[1].
That might be preferable if it results in less computational error,
but it's a bit obscure, so for clarity I decided to go with the
standard calculation for mean value.
[1]: https://en.wikipedia.org/w/index.php?title=Expected_value&oldid=585750484#Discrete_distribution_taking_only_non-negative_integer_values
13 years ago
7c0d009b46
ValidateMean unit test for Categorical dist
Unit tests to validate Categorical.Mean. Currently they fail, indicating
that Categorical.Mean is not correctly implemented.
Unit tests for StdDev, Variance, Entropy, and Median properties are
still required.
13 years ago
ed97cc7575
Fixed comment in TriangularDistribution example
The <summary> tag of the TriangularDistribution class read "ContinuousUniform distribution example". It now reads "Triangular distribution example".
13 years ago
3aca1f4bf7
Interpolation: api cleanup
13 years ago
3e1665787d
Interpolation: upgrade remaining algorithms accordingly
13 years ago
160f872b91
Tests: move Excel tests to correct namespace
13 years ago
5edca01da9
ExcelFunctions
13 years ago
9d0787dc4d
Distributions: Gamma.InvCDF
13 years ago
ec22686f8a
Tests: typo in test class name ModifiedBesselTests
13 years ago
ad208ae9c7
Special Functions: inverse of Gamma lower regularized
13 years ago
a24a52634c
Update contributing.md to clarify it is ok not to use real names
13 years ago
2ecd8aa110
Distributions: cosmetics
13 years ago
566ec8d695
Merge pull request #184 from Superbest/triangular-distribution
Triangular distribution
13 years ago
eb537256b9
Added triangular distribution example (this time for real)
Signed-off-by: Superbest <arpharazon0@gmail.com>
13 years ago
cf1530d8ee
Added Triangular distribution.
Signed-off-by: Superbest <arpharazon0@gmail.com>
13 years ago
5e63d1c889
Added example for Triangular distribution.
Signed-off-by: Superbest <arpharazon0@gmail.com>
13 years ago
2164c799f0
Initial commit
Signed-off-by: Superbest <arpharazon0@gmail.com>
13 years ago
99d104b752
Interpolation: add missing algorithms to Interpolate facade
13 years ago
cf5bd78dca
Interpolation: drop old redundant barycentric interpolation classes
13 years ago
54a63dc0d5
Interpolation: migrate rational floater hormann to Barycentric class
13 years ago
be60421844
Interpolation: Barycentric class, migrate equidistant polynomial to it
13 years ago
c2e948fc3d
Interpolation: implement IInterpolation.Supports explicitly
13 years ago
749fc5709b
Interpolation: use more common terms in Interpolate facade
13 years ago
27866408af
Drop old redundant spline interpolation classes
13 years ago
94b5c448e6
Interpolation: migrate cubic spline to CubicSpline class
13 years ago
fb35625def
Interpolation: migrate akima and hermite cubic spline to CubicSpline class
13 years ago
8f0195dd5b
Interpolation: CubicSpline class (intended to replace old model)
13 years ago
01ed5cf41f
Interpolation: add QuadraticSpline (without solver yet)
13 years ago
aebb93a04a
Interpolation: Differentiate2 instead of DifferentiateAll; definite integral; cleanup
13 years ago
5d9b0143e3
Interpolation: more reasonable LinearSpline implementation
13 years ago
acd0eb623d
SpecialFunctions: increase iteration limit of BetaRegularized from 100 to 120
13 years ago
40bad6b301
Random: api cleanup
13 years ago
11519beb84
Random: tweak sampling (based on a lot of benchmarks), new robust seeds
13 years ago
57ea773354
Random: extend F# extensions with XSamples and XSampleSeq
13 years ago
21842ca4c6
Inline doc, cls compliance
13 years ago
Christoph Ruegg
David Prince
Superbest