ParaMonte Fortran 2.0.0
Parallel Monte Carlo and Machine Learning Library
See the latest version documentation.
pm_distMultiNorm::getMultiNormRand Interface Reference

Generate and return a (collection) of random vector(s) of size ndim from the ndim-dimensional MultiVariate Normal (MVN) distribution, optionally with the specified input mean(1:ndim) and the specified subset of the Cholesky Factorization of the Covariance matrix of the MVN distribution. More...

Detailed Description

Generate and return a (collection) of random vector(s) of size ndim from the ndim-dimensional MultiVariate Normal (MVN) distribution, optionally with the specified input mean(1:ndim) and the specified subset of the Cholesky Factorization of the Covariance matrix of the MVN distribution.

The procedures of this generic interface are merely wrappers around the subroutine interface setMultiNormRand.

Parameters
[in,out]rng: The input/output scalar that can be an object of,
  1. type rngf_type, implying the use of intrinsic Fortran uniform RNG.
  2. type xoshiro256ssw_type, implying the use of xoshiro256** uniform RNG.
(optional, default = rngf_type.)
[in]mean: The input contiguous vector of shape (1:ndim), of the same type and kind as the output rand, representing the mean of the Multivariate Normal distribution.
(optional, default = [(0., i = 1, size(rand))]. It must be present if the input argument chol is missing.)
[in]chol: The input contiguous matrix of shape (ndim, ndim) whose specified triangular subset contains the Cholesky Factorization of the covariance matrix of the MVN distribution.
(optional, the default is the Identity matrix of rank ndim. It must be present if and only if the input argument subset is also present.)
[in]subset: The input scalar constant that can be any of the following:
  1. the constant uppDia or an object of type uppDia_type implying that the upper-diagonal triangular block of the input chol must be used while the lower subset is not referenced.
  2. the constant lowDia or an object of type lowDia_type implying that the lower-diagonal triangular block of the input chol must be used while the upper subset is not referenced.
This argument is merely a convenience to differentiate the different procedure functionalities within this generic interface.
(optional. It must be present if and only if the input argument chol is present.)
[in]nsam: The input scalar integer of default kind IK containing the number of random MVN vectors to generate.
(optional. If present, the output rand is of rank 2, otherwise is of rank 1.)
Returns
rand : The output vector of
  1. type real of kind any supported by the processor (e.g., RK, RK32, RK64, or RK128),
containing the MVN distributed random output vector(s):
  1. If the input argument nsam is missing, then rand shall be of shape (1:ndim).
  2. If the input argument nsam is present, then rand shall be of shape (1:ndim, 1:nsam).


Possible calling interfaces

! single vector, using default rng
rand(1:ndim) = getMultiNormRand(mean(1:ndim))
rand(1:ndim) = getMultiNormRand(chol(1:ndim, 1:ndim), subset)
rand(1:ndim) = getMultiNormRand(mean(1:ndim), chol(1:ndim, 1:ndim), subset)
! single vector, using custom rng
rand(1:ndim) = getMultiNormRand(rng, mean(1:ndim))
rand(1:ndim) = getMultiNormRand(rng, chol(1:ndim, 1:ndim), subset)
rand(1:ndim) = getMultiNormRand(rng, mean(1:ndim), chol(1:ndim, 1:ndim), subset)
! collection of `nsam` vectors, using default rng
rand(1:ndim, 1:nsam) = getMultiNormRand(mean(1:ndim), nsam)
rand(1:ndim, 1:nsam) = getMultiNormRand(chol(1:ndim, 1:ndim), subset, nsam)
rand(1:ndim, 1:nsam) = getMultiNormRand(mean(1:ndim), chol(1:ndim, 1:ndim), subset, nsam)
! collection of `nsam` vectors, using custom rng
rand(1:ndim, 1:nsam) = getMultiNormRand(rng, mean(1:ndim), nsam)
rand(1:ndim, 1:nsam) = getMultiNormRand(rng, chol(1:ndim, 1:ndim), subset, nsam)
rand(1:ndim, 1:nsam) = getMultiNormRand(rng, mean(1:ndim), chol(1:ndim, 1:ndim), subset, nsam)
Generate and return a (collection) of random vector(s) of size ndim from the ndim-dimensional MultiVa...
This module contains classes and procedures for computing various statistical quantities related to t...
Remarks
The procedures under discussion are impure.
See also
getNormRand
setNormRand
getUnifRand
setUnifRand
getNormLogPDF


Example usage

1program example
2
3 use pm_kind, only: SK
4 use pm_kind, only: IK, LK, RKG => RKS ! all real kinds are supported.
5 use pm_io, only: display_type
6 use pm_matrixChol, only: getMatChol, uppDia
8 use pm_distCov, only: getCovRand
9
10 implicit none
11
12 real(RKG), allocatable :: mean(:), chol(:,:), rand(:)
13
14 type(display_type) :: disp
15 disp = display_type(file = "main.out.F90")
16
17
18 call disp%skip()
19 call disp%show("!%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%")
20 call disp%show("!%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%")
21 call disp%show("! Generate random numbers from the (Standard) Multivariate Normal distribution.")
22 call disp%show("!%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%")
23 call disp%show("!%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%")
24 call disp%skip()
25
26 call disp%skip()
27 call disp%show("!%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%")
28 call disp%show("! Multivariate Normal random vector with a particular mean and Identity covariance matrix.")
29 call disp%show("!%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%")
30 call disp%skip()
31
32 call disp%skip()
33 call disp%show("mean = [-5., -5.]")
34 mean = [-5., -5.]
35 call disp%show("rand = getMultiNormRand(mean)")
36 rand = getMultiNormRand(mean)
37 call disp%show("rand")
38 call disp%show( rand )
39 call disp%skip()
40
41 call disp%skip()
42 call disp%show("!%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%")
43 call disp%show("! Multivariate Normal random vector with zero mean and Covariance matrix specified via the Cholesky Lower Triangle.")
44 call disp%show("!%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%")
45 call disp%skip()
46
47 call disp%skip()
48 call disp%show("chol = getMatChol(getCovRand(mold = 1._RKG, scale = [real(RKG) :: 1, 2]), uppDia)")
49 chol = getMatChol(getCovRand(mold = 1._RKG, scale = [real(RKG) :: 1, 2]), uppDia)
50 call disp%show("chol")
51 call disp%show( chol )
52 call disp%show("rand = getMultiNormRand(chol, uppDia)")
53 rand = getMultiNormRand(chol, uppDia)
54 call disp%show("rand")
55 call disp%show( rand )
56 call disp%skip()
57
58 call disp%skip()
59 call disp%show("!%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%")
60 call disp%show("! Multivariate Normal random vector with given mean and Covariance matrix specified via the Cholesky Lower Triangle.")
61 call disp%show("!%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%")
62 call disp%skip()
63
64 call disp%skip()
65 call disp%show("mean")
66 call disp%show( mean )
67 call disp%show("chol")
68 call disp%show( chol )
69 call disp%show("rand = getMultiNormRand(mean, chol, uppDia)")
70 rand = getMultiNormRand(mean, chol, uppDia)
71 call disp%show("rand")
72 call disp%show( rand )
73 call disp%skip()
74
75 !%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
76 ! Output an example rand array for visualization.
77 !%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
78
79 block
80
81 use pm_io, only: getErrTableWrite, trans
82 real(RKG) :: rand(2, 5000)
83
84 rand = getMultiNormRand(mean, size(rand, 2, IK))
85 if (0 /= getErrTableWrite("getMultiNormRandMean.RK.txt", rand, trans)) error stop 'table write failed.'
86
87 rand = getMultiNormRand(chol, uppDia, size(rand, 2, IK))
88 if (0 /= getErrTableWrite("getMultiNormRandChol.RK.txt", rand, trans)) error stop 'table write failed.'
89
90 rand = getMultiNormRand(chol, uppDia, size(rand, 2, IK))
91 if (0 /= getErrTableWrite("getMultiNormRandMeanChol.RK.txt", rand, trans)) error stop 'table write failed.'
92
93 end block
94
95end program example
Generate and return a random positive-definite (correlation or covariance) matrix using the Gram meth...
Definition: pm_distCov.F90:394
Generate and return the iostat code resulting from writing the input table of rank 1 or 2 to the spec...
Definition: pm_io.F90:5940
This is a generic method of the derived type display_type with pass attribute.
Definition: pm_io.F90:11726
This is a generic method of the derived type display_type with pass attribute.
Definition: pm_io.F90:11508
Generate and return the upper or the lower Cholesky factorization of the input symmetric positive-def...
This module contains classes and procedures for generating random matrices distributed on the space o...
Definition: pm_distCov.F90:72
This module contains classes and procedures for input/output (IO) or generic display operations on st...
Definition: pm_io.F90:252
type(display_type) disp
This is a scalar module variable an object of type display_type for general display.
Definition: pm_io.F90:11393
This module defines the relevant Fortran kind type-parameters frequently used in the ParaMonte librar...
Definition: pm_kind.F90:268
integer, parameter LK
The default logical kind in the ParaMonte library: kind(.true.) in Fortran, kind(....
Definition: pm_kind.F90:541
integer, parameter IK
The default integer kind in the ParaMonte library: int32 in Fortran, c_int32_t in C-Fortran Interoper...
Definition: pm_kind.F90:540
integer, parameter SK
The default character kind in the ParaMonte library: kind("a") in Fortran, c_char in C-Fortran Intero...
Definition: pm_kind.F90:539
integer, parameter RKS
The single-precision real kind in Fortran mode. On most platforms, this is an 32-bit real kind.
Definition: pm_kind.F90:567
This module contains procedures and generic interfaces for computing the Cholesky factorization of po...
Generate and return an object of type display_type.
Definition: pm_io.F90:10282

Example Unix compile command via Intel ifort compiler
1#!/usr/bin/env sh
2rm main.exe
3ifort -fpp -standard-semantics -O3 -Wl,-rpath,../../../lib -I../../../inc main.F90 ../../../lib/libparamonte* -o main.exe
4./main.exe

Example Windows Batch compile command via Intel ifort compiler
1del main.exe
2set PATH=..\..\..\lib;%PATH%
3ifort /fpp /standard-semantics /O3 /I:..\..\..\include main.F90 ..\..\..\lib\libparamonte*.lib /exe:main.exe
4main.exe

Example Unix / MinGW compile command via GNU gfortran compiler
1#!/usr/bin/env sh
2rm main.exe
3gfortran -cpp -ffree-line-length-none -O3 -Wl,-rpath,../../../lib -I../../../inc main.F90 ../../../lib/libparamonte* -o main.exe
4./main.exe

Example output
1
2!%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
3!%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
4! Generate random numbers from the (Standard) Multivariate Normal distribution.
5!%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
6!%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
7
8
9!%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
10! Multivariate Normal random vector with a particular mean and Identity covariance matrix.
11!%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
12
13
14mean = [-5., -5.]
15rand = getMultiNormRand(mean)
16rand
17-4.46326160, -5.21471453
18
19
20!%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
21! Multivariate Normal random vector with zero mean and Covariance matrix specified via the Cholesky Lower Triangle.
22!%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
23
24
25chol = getMatChol(getCovRand(mold = 1._RKG, scale = [real(RKG) :: 1, 2]), uppDia)
26chol
27+1.00000000, +1.05574059
28+0.00000000, +1.69865000
29rand = getMultiNormRand(chol, uppDia)
30rand
31+1.65168142, +3.89830971
32
33
34!%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
35! Multivariate Normal random vector with given mean and Covariance matrix specified via the Cholesky Lower Triangle.
36!%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
37
38
39mean
40-5.00000000, -5.00000000
41chol
42+1.00000000, +1.05574059
43+0.00000000, +1.69865000
44rand = getMultiNormRand(mean, chol, uppDia)
45rand
46-5.87313795, -6.62356663
47
48

Postprocessing of the example output
1#!/usr/bin/env python
2
3import matplotlib.pyplot as plt
4import pandas as pd
5import numpy as np
6import glob
7import sys
8
9linewidth = 2
10fontsize = 17
11
12for kind in ["RK"]:
13
14 pattern = "*." + kind + ".txt"
15 fileList = glob.glob(pattern)
16
17 for file in fileList:
18
19 df = pd.read_csv(file, delimiter = ",", header = None)
20
21 # definitions for the axes
22 left, width = 0.1, 0.65
23 bottom, height = 0.1, 0.65
24 spacing = 0.015
25
26 # start with a square Figure
27 fig = plt.figure(figsize = (8, 8))
28
29 plt.rcParams.update({'font.size': fontsize - 2})
30 ax = fig.add_axes([left, bottom, width, height]) # scatter plot
31 ax_histx = fig.add_axes([left, bottom + height + spacing, width, 0.2], sharex = ax) # histx
32 ax_histy = fig.add_axes([left + width + spacing, bottom, 0.2, height], sharey = ax) # histy
33
34 for axes in [ax, ax_histx, ax_histy]:
35 axes.grid(visible = True, which = "both", axis = "both", color = "0.85", linestyle = "-")
36 axes.tick_params(axis = "y", which = "minor")
37 axes.tick_params(axis = "x", which = "minor")
38
39 # no labels
40 ax_histy.tick_params(axis = "y", labelleft = False)
41 ax_histx.tick_params(axis = "x", labelbottom = False)
42
43 # the scatter plot:
44 ax.scatter ( df.values[:, 0]
45 , df.values[:, 1]
46 , s = 8
47 , zorder = 1000
48 )
49
50 ax_histx.hist(df.values[:, 0], bins = 50, zorder = 1000)
51 ax_histy.hist(df.values[:, 1], bins = 50, orientation = "horizontal", zorder = 1000)
52
53 ax.set_xlabel("X", fontsize = 17)
54 ax.set_ylabel("Y", fontsize = 17)
55
56 plt.savefig(file.replace(".txt",".png"))

Visualization of the example output
Test:
test_pm_distMultiNorm
Internal naming convention:
The following illustrates the internal naming convention used for the procedures within this generic interface.
getMNR_RNGD_DM_DC_XXX_D1_RK5()
|||| || || ||| || |||
|||| || || ||| || |||
|||| || || ||| || |||
|||| || || ||| || |The Kind of the output array.
|||| || || ||| || The type of the output array: R => Real.
|||| || || ||| The Dimension of the output array.
|||| || || The subset of the Cholesky factor: D/U/L => Default/Upper/Lower.
|||| || The Cholesky factor of the covariance matrix of the distribution: DC/AC => Default/Arbitrary Cholesky
|||| The mean of the distribution: DM/AM => Default/Arbitrary Mean
The random number generator: RNG D/F/X => Default/Fortran/Xoroshiro256++


Final Remarks


If you believe this algorithm or its documentation can be improved, we appreciate your contribution and help to edit this page's documentation and source file on GitHub.
For details on the naming abbreviations, see this page.
For details on the naming conventions, see this page.
This software is distributed under the MIT license with additional terms outlined below.

  1. If you use any parts or concepts from this library to any extent, please acknowledge the usage by citing the relevant publications of the ParaMonte library.
  2. If you regenerate any parts/ideas from this library in a programming environment other than those currently supported by this ParaMonte library (i.e., other than C, C++, Fortran, MATLAB, Python, R), please also ask the end users to cite this original ParaMonte library.

This software is available to the public under a highly permissive license.
Help us justify its continued development and maintenance by acknowledging its benefit to society, distributing it, and contributing to it.

Author:
Amir Shahmoradi, April 23, 2017, 12:36 AM, Institute for Computational Engineering and Sciences (ICES), University of Texas at Austin

Definition at line 1092 of file pm_distMultiNorm.F90.


The documentation for this interface was generated from the following file: