diff --git a/ChangeLog b/ChangeLog new file mode 100644 --- /dev/null +++ b/ChangeLog @@ -0,0 +1,110 @@ + Changes in 0.10.2.0 + + * Bugs in DCT and IDCT are fixed. + + * Accesors for uniform distribution are added. + + * ContGen instances for all continous distribtuions are added. + + * Beta distribution is added. + + * Constructor for improper gamma distribtuion is added. + + * Binomial distribution allows zero trials. + + * Poisson distribution now accept zero parameter. + + * Integer overflow in caculation of Wilcoxon-T test is fixed. + + * Bug in 'ContGen' instance for normal distribution is fixed. + +Changes in 0.10.1.0 + + * Kolmogorov-Smirnov nonparametric test added. + + * Pearson chi squared test added. + + * Type class for generating random variates for given distribution + is added. + + * Modules 'Statistics.Math' and 'Statistics.Constants' are moved to + the @math-functions@ package. They are still available but marked + as deprecated. + + +Changed in 0.10.0.1 + + * @dct@ and @idct@ now have type @Vector Double -> Vector Double@ + + +Changes in 0.10.0.0 + + * The type classes Mean and Variance are split in two. This is + required for distributions which do not have finite variance or + mean. + + * The S.Sample.KernelDensity module has been renamed, and + completely rewritten to be much more robust. The older module + oversmoothed multi-modal data. (The older module is still + available under the name S.Sample.KernelDensity.Simple). + + * Histogram computation is added, in S.Sample.Histogram. + + * Discrete Fourie transform is added, in S.Transform + + * Root finding is added, in S.Math.RootFinding. + + * The complCumulative function is added to the Distribution + class in order to accurately assess probalities P(X>x) which are + used in one-tailed tests. + + * A stdDev function is added to the Variance class for + distributions. + + * The constructor S.Distribution.normalDistr now takes standard + deviation instead of variance as its parameter. + + * A bug in S.Quantile.weightedAvg is fixed. It produced a wrong + answer if a sample contained only one element. + + * Bugs in quantile estimations for chi-square and gamma distribution + are fixed. + + * Integer overlow in mannWhitneyUCriticalValue is fixed. It + produced incorrect critical values for moderately large + samples. Something around 20 for 32-bit machines and 40 for 64-bit + ones. + + * A bug in mannWhitneyUSignificant is fixed. If either sample was + larger than 20, it produced a completely incorrect answer. + + * One- and two-tailed tests in S.Tests.NonParametric are selected + with sum types instead of Bool. + + * Test results returned as enumeration instead of @Bool@. + + * Performance improvements for Mann-Whitney U and Wilcoxon tests. + + * Module @S.Tests.NonParamtric@ is split into @S.Tests.MannWhitneyU@ + and @S.Tests.WilcoxonT@ + + * sortBy is added to S.Function. + + * Mean and variance for gamma distribution are fixed. + + * Much faster cumulative probablity functions for Poisson and + hypergeometric distributions. + + * Better density functions for gamma and Poisson distributions. + + * Student-T, Fisher-Snedecor F-distributions and Cauchy-Lorentz + distrbution are added. + + * The function S.Function.create is removed. Use generateM from + the vector package instead. + + * Function to perform approximate comparion of doubles is added to + S.Function.Comparison + + * Regularized incomplete beta function and its inverse are added to + S.Function diff --git a/Statistics/Distribution/Transform.hs b/Statistics/Distribution/Transform.hs --- a/Statistics/Distribution/Transform.hs +++ b/Statistics/Distribution/Transform.hs @@ -25,11 +25,11 @@ -- > x' = μ + σ·x data LinearTransform d = LinearTransform { linTransLocation :: {-# UNPACK #-} !Double - -- | Location parameter. + -- ^ Location parameter. , linTransScale :: {-# UNPACK #-} !Double - -- | Scale parameter. + -- ^ Scale parameter. , linTransDistr :: d - -- | Distribution being transformed. + -- ^ Distribution being transformed. } deriving (Eq,Show,Read,Typeable) -- | Apply linear transformation to distribution. diff --git a/benchmark/bench.hs b/benchmark/bench.hs new file mode 100644 --- /dev/null +++ b/benchmark/bench.hs @@ -0,0 +1,68 @@ +import Control.Monad.ST (runST) +import Data.Complex +import qualified Data.Vector.Unboxed as U + +import System.Random.MWC +import Criterion.Main + +import Statistics.Sample +import Statistics.Transform + + +-- Test sample +sample :: U.Vector Double +sample = runST $ flip uniformVector 10000 =<< create + +-- Weighted test sample +sampleW :: U.Vector (Double,Double) +sampleW = U.zip sample (U.reverse sample) + +-- Comlex vector for FFT tests +sampleC :: U.Vector (Complex Double) +sampleC = U.zipWith (:+) sample (U.reverse sample) + + +-- Simple benchmark for functions from Statistics.Sample +main :: IO () +main = + defaultMain + [ bgroup "sample" + [ bench "range" $ nf (\x -> range x) sample + -- Mean + , bench "mean" $ nf (\x -> mean x) sample + , bench "meanWeighted" $ nf (\x -> meanWeighted x) sampleW + , bench "harmonicMean" $ nf (\x -> harmonicMean x) sample + , bench "geometricMean" $ nf (\x -> geometricMean x) sample + -- Variance + , bench "variance" $ nf (\x -> variance x) sample + , bench "varianceUnbiased" $ nf (\x -> varianceUnbiased x) sample + , bench "varianceWeighted" $ nf (\x -> varianceWeighted x) sampleW + -- Other + , bench "stdDev" $ nf (\x -> stdDev x) sample + , bench "skewness" $ nf (\x -> skewness x) sample + , bench "kurtosis" $ nf (\x -> kurtosis x) sample + -- Central moments + , bench "C.M. 2" $ nf (\x -> centralMoment 2 x) sample + , bench "C.M. 3" $ nf (\x -> centralMoment 3 x) sample + , bench "C.M. 4" $ nf (\x -> centralMoment 4 x) sample + , bench "C.M. 5" $ nf (\x -> centralMoment 5 x) sample + ] + , bgroup "FFT" + [ bgroup "fft" + [ bench (show n) $ whnf fft (U.take n sampleC) | n <- fftSizes ] + , bgroup "ifft" + [ bench (show n) $ whnf ifft (U.take n sampleC) | n <- fftSizes ] + , bgroup "dct" + [ bench (show n) $ whnf dct (U.take n sample) | n <- fftSizes ] + , bgroup "dct_" + [ bench (show n) $ whnf dct_ (U.take n sampleC) | n <- fftSizes ] + , bgroup "idct" + [ bench (show n) $ whnf idct (U.take n sample) | n <- fftSizes ] + , bgroup "idct_" + [ bench (show n) $ whnf idct_ (U.take n sampleC) | n <- fftSizes ] + ] + ] + + +fftSizes :: [Int] +fftSizes = [32,128,512,2048] diff --git a/statistics.cabal b/statistics.cabal --- a/statistics.cabal +++ b/statistics.cabal @@ -1,5 +1,5 @@ name: statistics -version: 0.10.3.0 +version: 0.10.3.1 synopsis: A library of statistical types, data, and functions description: This library provides a number of common functions and types useful @@ -147,12 +147,17 @@ build-type: Simple cabal-version: >= 1.8 extra-source-files: + ChangeLog README.markdown + benchmark/bench.hs examples/kde/KDE.hs examples/kde/data/faithful.csv examples/kde/kde.html examples/kde/kde.tpl tests/Tests/Math/gen.py + tests/Tests/Math/Tables.hs + tests/utils/Makefile + tests/utils/fftw.c library exposed-modules: diff --git a/tests/Tests/Math/Tables.hs b/tests/Tests/Math/Tables.hs new file mode 100644 --- /dev/null +++ b/tests/Tests/Math/Tables.hs @@ -0,0 +1,47 @@ +module Tests.Math.Tables where + +tableLogGamma :: [(Double,Double)] +tableLogGamma = + [(0.000001250000000, 13.592366285131769033) + , (0.000068200000000, 9.5930266308318756785) + , (0.000246000000000, 8.3100370767447966358) + , (0.000880000000000, 7.03508133735248542) + , (0.003120000000000, 5.768129358365567505) + , (0.026700000000000, 3.6082588918892977148) + , (0.077700000000000, 2.5148371858768232556) + , (0.234000000000000, 1.3579557559432759994) + , (0.860000000000000, 0.098146578027685615897) + , (1.340000000000000, -0.11404757557207759189) + , (1.890000000000000, -0.0425116422978701336) + , (2.450000000000000, 0.25014296569217625565) + , (3.650000000000000, 1.3701041997380685178) + , (4.560000000000000, 2.5375143317949580002) + , (6.660000000000000, 5.9515377269550207018) + , (8.250000000000000, 9.0331869196051233217) + , (11.300000000000001, 15.814180681373947834) + , (25.600000000000001, 56.711261598328121636) + , (50.399999999999999, 146.12815158702164808) + , (123.299999999999997, 468.85500075897556371) + , (487.399999999999977, 2526.9846647543727158) + , (853.399999999999977, 4903.9359135978220365) + , (2923.300000000000182, 20402.93198938705973) + , (8764.299999999999272, 70798.268343590112636) + , (12630.000000000000000, 106641.77264982508495) + , (34500.000000000000000, 325976.34838781820145) + , (82340.000000000000000, 849629.79603036714252) + , (234800.000000000000000, 2668846.4390507959761) + , (834300.000000000000000, 10540830.912557534873) + , (1230000.000000000000000, 16017699.322315014899) + ] +tableIncompleteBeta :: [(Double,Double,Double,Double)] +tableIncompleteBeta = + [(2.000000000000000, 3.000000000000000, 0.030000000000000, 0.0051864299999999996862) + , (2.000000000000000, 3.000000000000000, 0.230000000000000, 0.22845923000000001313) + , (2.000000000000000, 3.000000000000000, 0.760000000000000, 0.95465728000000005249) + , (4.000000000000000, 2.300000000000000, 0.890000000000000, 0.93829812158347802864) + , (1.000000000000000, 1.000000000000000, 0.550000000000000, 0.55000000000000004441) + , (0.300000000000000, 12.199999999999999, 0.110000000000000, 0.95063000053947077639) + , (13.100000000000000, 9.800000000000001, 0.120000000000000, 1.3483109941962659385e-07) + , (13.100000000000000, 9.800000000000001, 0.420000000000000, 0.071321857831804780226) + , (13.100000000000000, 9.800000000000001, 0.920000000000000, 0.99999578339197081611) + ] diff --git a/tests/utils/Makefile b/tests/utils/Makefile new file mode 100644 --- /dev/null +++ b/tests/utils/Makefile @@ -0,0 +1,9 @@ +C = gcc +CFLAGS = -W -Wall -O2 -std=c99 +LDFLAGS = -lfftw3 + +.PHONY: all clean + +all : fftw +clean : + rm -rf fftw *.o diff --git a/tests/utils/fftw.c b/tests/utils/fftw.c new file mode 100644 --- /dev/null +++ b/tests/utils/fftw.c @@ -0,0 +1,46 @@ +/* Generate some test cases using fftw3 */ +#include +#include +#include + +void dump_vector(int n, double* vec) { + for(int i = 0; i < n; i++) + printf("%20.15f ", vec[i]); + printf("\n"); +} + +void dct(int flag, int n) { + double* in = malloc( n * sizeof(double)); + double* out = malloc( n * sizeof(double)); + // + fftw_plan plan = fftw_plan_r2r_1d(n, in, out, flag, FFTW_ESTIMATE); + for( int k = 0; k < n; k++) { + // Init input vector + for( int i = 0; i < n; i++) + in[i] = 0; + in[k] = 1; + // Perform DFT + fftw_execute(plan); + // Print results + dump_vector(n, in ); + dump_vector(n, out); + printf("\n"); + } + // + free(in); + free(out); + fftw_destroy_plan(plan); +} + +int main(void) +{ + printf("DCT II (the DCT)\n"); + dct( FFTW_REDFT10, 2); + dct( FFTW_REDFT10, 4); + + printf("DCT III (Inverse DCT)\n"); + dct( FFTW_REDFT01, 2); + dct( FFTW_REDFT01, 4); + + return 0; +}