alglib 0.1.1

data/ext/alglib/nsevd.h

@@ -0,0 +1,140 @@
+/*************************************************************************
+Copyright (c) 1992-2007 The University of Tennessee.  All rights reserved.
+
+Contributors:
+    * Sergey Bochkanov (ALGLIB project). Translation from FORTRAN to
+      pseudocode.
+
+See subroutines comments for additional copyrights.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are
+met:
+
+- Redistributions of source code must retain the above copyright
+  notice, this list of conditions and the following disclaimer.
+
+- Redistributions in binary form must reproduce the above copyright
+  notice, this list of conditions and the following disclaimer listed
+  in this license in the documentation and/or other materials
+  provided with the distribution.
+
+- Neither the name of the copyright holders nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*************************************************************************/
+
+#ifndef _nsevd_h
+#define _nsevd_h
+
+#include "ap.h"
+#include "ialglib.h"
+
+#include "blas.h"
+#include "reflections.h"
+#include "rotations.h"
+#include "hsschur.h"
+#include "hessenberg.h"
+
+
+/*************************************************************************
+Finding eigenvalues and eigenvectors of a general matrix
+
+The algorithm finds eigenvalues and eigenvectors of a general matrix by
+using the QR algorithm with multiple shifts. The algorithm can find
+eigenvalues and both left and right eigenvectors.
+
+The right eigenvector is a vector x such that A*x = w*x, and the left
+eigenvector is a vector y such that y'*A = w*y' (here y' implies a complex
+conjugate transposition of vector y).
+
+Input parameters:
+    A       -   matrix. Array whose indexes range within [0..N-1, 0..N-1].
+    N       -   size of matrix A.
+    VNeeded -   flag controlling whether eigenvectors are needed or not.
+                If VNeeded is equal to:
+                 * 0, eigenvectors are not returned;
+                 * 1, right eigenvectors are returned;
+                 * 2, left eigenvectors are returned;
+                 * 3, both left and right eigenvectors are returned.
+
+Output parameters:
+    WR      -   real parts of eigenvalues.
+                Array whose index ranges within [0..N-1].
+    WR      -   imaginary parts of eigenvalues.
+                Array whose index ranges within [0..N-1].
+    VL, VR  -   arrays of left and right eigenvectors (if they are needed).
+                If WI[i]=0, the respective eigenvalue is a real number,
+                and it corresponds to the column number I of matrices VL/VR.
+                If WI[i]>0, we have a pair of complex conjugate numbers with
+                positive and negative imaginary parts:
+                    the first eigenvalue WR[i] + sqrt(-1)*WI[i];
+                    the second eigenvalue WR[i+1] + sqrt(-1)*WI[i+1];
+                    WI[i]>0
+                    WI[i+1] = -WI[i] < 0
+                In that case, the eigenvector  corresponding to the first
+                eigenvalue is located in i and i+1 columns of matrices
+                VL/VR (the column number i contains the real part, and the
+                column number i+1 contains the imaginary part), and the vector
+                corresponding to the second eigenvalue is a complex conjugate to
+                the first vector.
+                Arrays whose indexes range within [0..N-1, 0..N-1].
+
+Result:
+    True, if the algorithm has converged.
+    False, if the algorithm has not converged.
+
+Note 1:
+    Some users may ask the following question: what if WI[N-1]>0?
+    WI[N] must contain an eigenvalue which is complex conjugate to the
+    N-th eigenvalue, but the array has only size N?
+    The answer is as follows: such a situation cannot occur because the
+    algorithm finds a pairs of eigenvalues, therefore, if WI[i]>0, I is
+    strictly less than N-1.
+
+Note 2:
+    The algorithm performance depends on the value of the internal parameter
+    NS of the InternalSchurDecomposition subroutine which defines the number
+    of shifts in the QR algorithm (similarly to the block width in block-matrix
+    algorithms of linear algebra). If you require maximum performance
+    on your machine, it is recommended to adjust this parameter manually.
+
+
+See also the InternalTREVC subroutine.
+
+The algorithm is based on the LAPACK 3.0 library.
+*************************************************************************/
+bool rmatrixevd(ap::real_2d_array a,
+     int n,
+     int vneeded,
+     ap::real_1d_array& wr,
+     ap::real_1d_array& wi,
+     ap::real_2d_array& vl,
+     ap::real_2d_array& vr);
+
+
+/*************************************************************************
+Obsolete 1-based subroutine
+*************************************************************************/
+bool nonsymmetricevd(ap::real_2d_array a,
+     int n,
+     int vneeded,
+     ap::real_1d_array& wr,
+     ap::real_1d_array& wi,
+     ap::real_2d_array& vl,
+     ap::real_2d_array& vr);
+
+
+#endif

data/ext/alglib/pca.cpp

@@ -0,0 +1,168 @@
+/*************************************************************************
+Copyright (c) 2008, Sergey Bochkanov (ALGLIB project).
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are
+met:
+
+- Redistributions of source code must retain the above copyright
+  notice, this list of conditions and the following disclaimer.
+
+- Redistributions in binary form must reproduce the above copyright
+  notice, this list of conditions and the following disclaimer listed
+  in this license in the documentation and/or other materials
+  provided with the distribution.
+
+- Neither the name of the copyright holders nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*************************************************************************/
+
+#include <stdafx.h>
+#include "pca.h"
+
+/*************************************************************************
+Principal components analysis
+
+Subroutine  builds  orthogonal  basis  where  first  axis  corresponds  to
+direction with maximum variance, second axis maximizes variance in subspace
+orthogonal to first axis and so on.
+
+It should be noted that, unlike LDA, PCA does not use class labels.
+
+INPUT PARAMETERS:
+    X           -   dataset, array[0..NPoints-1,0..NVars-1].
+                    matrix contains ONLY INDEPENDENT VARIABLES.
+    NPoints     -   dataset size, NPoints>=0
+    NVars       -   number of independent variables, NVars>=1
+
+�������� ���������:
+    Info        -   return code:
+                    * -4, if SVD subroutine haven't converged
+                    * -1, if wrong parameters has been passed (NPoints<0,
+                          NVars<1)
+                    *  1, if task is solved
+    S2          -   array[0..NVars-1]. variance values corresponding
+                    to basis vectors.
+    V           -   array[0..NVars-1,0..NVars-1]
+                    matrix, whose columns store basis vectors.
+
+  -- ALGLIB --
+     Copyright 25.08.2008 by Bochkanov Sergey
+*************************************************************************/
+void pcabuildbasis(const ap::real_2d_array& x,
+     int npoints,
+     int nvars,
+     int& info,
+     ap::real_1d_array& s2,
+     ap::real_2d_array& v)
+{
+    ap::real_2d_array a;
+    ap::real_2d_array u;
+    ap::real_2d_array vt;
+    ap::real_1d_array m;
+    ap::real_1d_array t;
+    int i;
+    int j;
+    double mean;
+    double variance;
+    double skewness;
+    double kurtosis;
+
+    
+    //
+    // Check input data
+    //
+    if( npoints<0||nvars<1 )
+    {
+        info = -1;
+        return;
+    }
+    info = 1;
+    
+    //
+    // Special case: NPoints=0
+    //
+    if( npoints==0 )
+    {
+        s2.setbounds(0, nvars-1);
+        v.setbounds(0, nvars-1, 0, nvars-1);
+        for(i = 0; i <= nvars-1; i++)
+        {
+            s2(i) = 0;
+        }
+        for(i = 0; i <= nvars-1; i++)
+        {
+            for(j = 0; j <= nvars-1; j++)
+            {
+                if( i==j )
+                {
+                    v(i,j) = 1;
+                }
+                else
+                {
+                    v(i,j) = 0;
+                }
+            }
+        }
+        return;
+    }
+    
+    //
+    // Calculate means
+    //
+    m.setbounds(0, nvars-1);
+    t.setbounds(0, npoints-1);
+    for(j = 0; j <= nvars-1; j++)
+    {
+        ap::vmove(t.getvector(0, npoints-1), x.getcolumn(j, 0, npoints-1));
+        calculatemoments(t, npoints, mean, variance, skewness, kurtosis);
+        m(j) = mean;
+    }
+    
+    //
+    // Center, apply SVD, prepare output
+    //
+    a.setbounds(0, ap::maxint(npoints, nvars)-1, 0, nvars-1);
+    for(i = 0; i <= npoints-1; i++)
+    {
+        ap::vmove(&a(i, 0), &x(i, 0), ap::vlen(0,nvars-1));
+        ap::vsub(&a(i, 0), &m(0), ap::vlen(0,nvars-1));
+    }
+    for(i = npoints; i <= nvars-1; i++)
+    {
+        for(j = 0; j <= nvars-1; j++)
+        {
+            a(i,j) = 0;
+        }
+    }
+    if( !rmatrixsvd(a, ap::maxint(npoints, nvars), nvars, 0, 1, 2, s2, u, vt) )
+    {
+        info = -4;
+        return;
+    }
+    if( npoints!=1 )
+    {
+        for(i = 0; i <= nvars-1; i++)
+        {
+            s2(i) = ap::sqr(s2(i))/(npoints-1);
+        }
+    }
+    v.setbounds(0, nvars-1, 0, nvars-1);
+    copyandtranspose(vt, 0, nvars-1, 0, nvars-1, v, 0, nvars-1, 0, nvars-1);
+}
+
+
+

data/ext/alglib/pca.h

@@ -0,0 +1,87 @@
+/*************************************************************************
+Copyright (c) 2008, Sergey Bochkanov (ALGLIB project).
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are
+met:
+
+- Redistributions of source code must retain the above copyright
+  notice, this list of conditions and the following disclaimer.
+
+- Redistributions in binary form must reproduce the above copyright
+  notice, this list of conditions and the following disclaimer listed
+  in this license in the documentation and/or other materials
+  provided with the distribution.
+
+- Neither the name of the copyright holders nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*************************************************************************/
+
+#ifndef _pca_h
+#define _pca_h
+
+#include "ap.h"
+#include "ialglib.h"
+
+#include "reflections.h"
+#include "bidiagonal.h"
+#include "qr.h"
+#include "lq.h"
+#include "blas.h"
+#include "rotations.h"
+#include "bdsvd.h"
+#include "svd.h"
+#include "descriptivestatistics.h"
+
+
+/*************************************************************************
+Principal components analysis
+
+Subroutine  builds  orthogonal  basis  where  first  axis  corresponds  to
+direction with maximum variance, second axis maximizes variance in subspace
+orthogonal to first axis and so on.
+
+It should be noted that, unlike LDA, PCA does not use class labels.
+
+INPUT PARAMETERS:
+    X           -   dataset, array[0..NPoints-1,0..NVars-1].
+                    matrix contains ONLY INDEPENDENT VARIABLES.
+    NPoints     -   dataset size, NPoints>=0
+    NVars       -   number of independent variables, NVars>=1
+
+�������� ���������:
+    Info        -   return code:
+                    * -4, if SVD subroutine haven't converged
+                    * -1, if wrong parameters has been passed (NPoints<0,
+                          NVars<1)
+                    *  1, if task is solved
+    S2          -   array[0..NVars-1]. variance values corresponding
+                    to basis vectors.
+    V           -   array[0..NVars-1,0..NVars-1]
+                    matrix, whose columns store basis vectors.
+
+  -- ALGLIB --
+     Copyright 25.08.2008 by Bochkanov Sergey
+*************************************************************************/
+void pcabuildbasis(const ap::real_2d_array& x,
+     int npoints,
+     int nvars,
+     int& info,
+     ap::real_1d_array& s2,
+     ap::real_2d_array& v);
+
+
+#endif

data/ext/alglib/poissondistr.cpp

@@ -0,0 +1,143 @@
+/*************************************************************************
+Cephes Math Library Release 2.8:  June, 2000
+Copyright 1984, 1987, 1995, 2000 by Stephen L. Moshier
+
+Contributors:
+    * Sergey Bochkanov (ALGLIB project). Translation from C to
+      pseudocode.
+
+See subroutines comments for additional copyrights.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are
+met:
+
+- Redistributions of source code must retain the above copyright
+  notice, this list of conditions and the following disclaimer.
+
+- Redistributions in binary form must reproduce the above copyright
+  notice, this list of conditions and the following disclaimer listed
+  in this license in the documentation and/or other materials
+  provided with the distribution.
+
+- Neither the name of the copyright holders nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*************************************************************************/
+
+#include <stdafx.h>
+#include "poissondistr.h"
+
+/*************************************************************************
+Poisson distribution
+
+Returns the sum of the first k+1 terms of the Poisson
+distribution:
+
+  k         j
+  --   -m  m
+  >   e    --
+  --       j!
+ j=0
+
+The terms are not summed directly; instead the incomplete
+gamma integral is employed, according to the relation
+
+y = pdtr( k, m ) = igamc( k+1, m ).
+
+The arguments must both be positive.
+ACCURACY:
+
+See incomplete gamma function
+
+Cephes Math Library Release 2.8:  June, 2000
+Copyright 1984, 1987, 1995, 2000 by Stephen L. Moshier
+*************************************************************************/
+double poissondistribution(int k, double m)
+{
+    double result;
+
+    ap::ap_error::make_assertion(k>=0&&m>0, "Domain error in PoissonDistribution");
+    result = incompletegammac(double(k+1), m);
+    return result;
+}
+
+
+/*************************************************************************
+Complemented Poisson distribution
+
+Returns the sum of the terms k+1 to infinity of the Poisson
+distribution:
+
+ inf.       j
+  --   -m  m
+  >   e    --
+  --       j!
+ j=k+1
+
+The terms are not summed directly; instead the incomplete
+gamma integral is employed, according to the formula
+
+y = pdtrc( k, m ) = igam( k+1, m ).
+
+The arguments must both be positive.
+
+ACCURACY:
+
+See incomplete gamma function
+
+Cephes Math Library Release 2.8:  June, 2000
+Copyright 1984, 1987, 1995, 2000 by Stephen L. Moshier
+*************************************************************************/
+double poissoncdistribution(int k, double m)
+{
+    double result;
+
+    ap::ap_error::make_assertion(k>=0&&m>0, "Domain error in PoissonDistributionC");
+    result = incompletegamma(double(k+1), m);
+    return result;
+}
+
+
+/*************************************************************************
+Inverse Poisson distribution
+
+Finds the Poisson variable x such that the integral
+from 0 to x of the Poisson density is equal to the
+given probability y.
+
+This is accomplished using the inverse gamma integral
+function and the relation
+
+   m = igami( k+1, y ).
+
+ACCURACY:
+
+See inverse incomplete gamma function
+
+Cephes Math Library Release 2.8:  June, 2000
+Copyright 1984, 1987, 1995, 2000 by Stephen L. Moshier
+*************************************************************************/
+double invpoissondistribution(int k, double y)
+{
+    double result;
+
+    ap::ap_error::make_assertion(k>=0&&y>=0&&y<1, "Domain error in InvPoissonDistribution");
+    result = invincompletegammac(double(k+1), y);
+    return result;
+}
+
+
+