Can someone please help me vectorize a moving slope calculation. I trying to eliminate the for loop but I am not sure how to do so.
>> pv = [18 19 20 20.5 20.75 21 21.05 21.07 21.07]'; %% price vector
>> slen = 3; %% slope length
function [slope] = slope(pv , slen)
svec = (1:1:slen)';
coef = [];
slope = zeros(size(pv));
for i = slen+1 : size(pv,1)
X = [ones(slen,1) svec];
y = pv( (i - (slen-1)) : i );
a = X\y;
slope(i,1) = a(2);
end
>> slp = slope(pv,3)
slp =
0
0
0
0.75
0.375
0.25
0.15
0.035
0.01
Thanks
EDIT: completely changing answer to make it scalable
function [slope] = calculate_slope(pv , slen) %% Note: bad practice to give a function and variable the same name
svec = (1:1:slen)';
X = [ones(slen,1) svec];
%% the following two lines basically create the all the sliding windows of length slen (as a submatrix of a larger matrix)
c = repmat ( flipud(pv), 1, length(pv))
d = flipud(reshape(c(1:end-1), length(pv)-1, length(pv) + 1));
%% then run MATLAB solver with all windows simultaneously
least_sq_result = X\d( end - slen + 1:end, (slen+1):end);
slope = [zeros(slen-1, 1); least_sq_result(2,:)']; %% padding with zeros is optional
EDIT: fixed swapped indices
Finding the slope in a sliding window using least-squares regression is equivalent to first-order Savitzy-Golay filtering (using a differentiating filter). The concept of SG filtering is to perform local polynomial fits in a sliding window, then use the local model to smooth the signal or compute its derivative. When the data points are spaced equally in time (as they are here), the computation can be run very efficiently by pre-computing a set of filter coefficients, then convolving them with the data. This should be much faster than constructing a giant matrix and doing regression on it.
This is a pretty standard technique, and there's definitely existing matlab code floating around. Search for something like 'Savitzky-Golay differentiation'. Note that SG filters can also perform smoothing (the matlab builtin SG filtering functions do this), but you want the version that does differentiation.
Savitzky and Golay (1964). Smoothing and Differentiation of Data by Simplified Least Squares Procedures
Related
I was asked to do circular convolution between two functions by sampling them, using the functions cconv. A known result of this sort of convolution is: CCONV( sin(x), sin(x) ) == -pi*cos(x)
To test the above I did:
w = linspace(0,2*pi,1000);
l = linspace(0,2*pi,1999);
stem(l,cconv(sin(w),sin(w))
but the result I got was:
which is absolutely not -pi*cos(x).
Can anybody please explain what is wrong with my code and how to fix it?
In the documentation of cconv it says that:
c = cconv(a,b,n) circularly convolves vectors a and b. n is the length of the resulting vector. If you omit n, it defaults to length(a)+length(b)-1. When n = length(a)+length(b)-1, the circular convolution is equivalent to the linear convolution computed with conv.
I believe that the reason for your problem is that you do not specify the 3rd input to cconv, which then selects the default value, which is not the right one for you. I have made an animation showing what happens when different values of n are chosen.
If you compare my result for n=200 to your plot you will see that the amplitude of your data is 10 times larger whereas the length of your linspace is 10 times bigger. This means that some normalization is needed, likely a multiplication by the linspace step.
Indeed, after proper scaling and choice of n we get the right result:
res = 100; % resolution
w = linspace(0,2*pi,res);
dx = diff(w(1:2)); % grid step
stem( linspace(0,2*pi,res), dx * cconv(sin(w),sin(w),res) );
This is the code I used for the animation:
hF = figure();
subplot(1,2,1); hS(1) = stem(1,cconv(1,1,1)); title('Autoscaling');
subplot(1,2,2); hS(2) = stem(1,cconv(1,1,1)); xlim([0,7]); ylim(50*[-1,1]); title('Constant limits');
w = linspace(0,2*pi,100);
for ind1 = 1:200
set(hS,'XData',linspace(0,2*pi,ind1));
set(hS,'YData',cconv(sin(w),sin(w),ind1));
suptitle("n = " + ind1);
drawnow
% export_fig(char("D:\BLABLA\F" + ind1 + ".png"),'-nocrop');
end
I have a set of frequency data with peaks to which I need to fit a Gaussian curve and then get the full width half maximum from. The FWHM part I can do, I already have a code for that but I'm having trouble writing code to fit the Gaussian.
Does anyone know of any functions that'll do this for me or would be able to point me in the right direction? (I can do least squares fitting for lines and polynomials but I can't get it to work for gaussians)
Also it would be helpful if it was compatible with both Octave and Matlab as I have Octave at the moment but don't get access to Matlab until next week.
Any help would be greatly appreciated!
Fitting a single 1D Gaussian directly is a non-linear fitting problem. You'll find ready-made implementations here, or here, or here for 2D, or here (if you have the statistics toolbox) (have you heard of Google? :)
Anyway, there might be a simpler solution. If you know for sure your data y will be well-described by a Gaussian, and is reasonably well-distributed over your entire x-range, you can linearize the problem (these are equations, not statements):
y = 1/(σ·√(2π)) · exp( -½ ( (x-μ)/σ )² )
ln y = ln( 1/(σ·√(2π)) ) - ½ ( (x-μ)/σ )²
= Px² + Qx + R
where the substitutions
P = -1/(2σ²)
Q = +2μ/(2σ²)
R = ln( 1/(σ·√(2π)) ) - ½(μ/σ)²
have been made. Now, solve for the linear system Ax=b with (these are Matlab statements):
% design matrix for least squares fit
xdata = xdata(:);
A = [xdata.^2, xdata, ones(size(xdata))];
% log of your data
b = log(y(:));
% least-squares solution for x
x = A\b;
The vector x you found this way will equal
x == [P Q R]
which you then have to reverse-engineer to find the mean μ and the standard-deviation σ:
mu = -x(2)/x(1)/2;
sigma = sqrt( -1/2/x(1) );
Which you can cross-check with x(3) == R (there should only be small differences).
Perhaps this has the thing you are looking for? Not sure about compatability:
http://www.mathworks.com/matlabcentral/fileexchange/11733-gaussian-curve-fit
From its documentation:
[sigma,mu,A]=mygaussfit(x,y)
[sigma,mu,A]=mygaussfit(x,y,h)
this function is doing fit to the function
y=A * exp( -(x-mu)^2 / (2*sigma^2) )
the fitting is been done by a polyfit
the lan of the data.
h is the threshold which is the fraction
from the maximum y height that the data
is been taken from.
h should be a number between 0-1.
if h have not been taken it is set to be 0.2
as default.
i had similar problem.
this was the first result on google, and some of the scripts linked here made my matlab crash.
finally i found here that matlab has built in fit function, that can fit Gaussians too.
it look like that:
>> v=-30:30;
>> fit(v', exp(-v.^2)', 'gauss1')
ans =
General model Gauss1:
ans(x) = a1*exp(-((x-b1)/c1)^2)
Coefficients (with 95% confidence bounds):
a1 = 1 (1, 1)
b1 = -8.489e-17 (-3.638e-12, 3.638e-12)
c1 = 1 (1, 1)
I found that the MATLAB "fit" function was slow, and used "lsqcurvefit" with an inline Gaussian function. This is for fitting a Gaussian FUNCTION, if you just want to fit data to a Normal distribution, use "normfit."
Check it
% % Generate synthetic data (for example) % % %
nPoints = 200; binSize = 1/nPoints ;
fauxMean = 47 ;fauxStd = 8;
faux = fauxStd.*randn(1,nPoints) + fauxMean; % REPLACE WITH YOUR ACTUAL DATA
xaxis = 1:length(faux) ;fauxData = histc(faux,xaxis);
yourData = fauxData; % replace with your actual distribution
xAxis = 1:length(yourData) ;
gausFun = #(hms,x) hms(1) .* exp (-(x-hms(2)).^2 ./ (2*hms(3)^2)) ; % Gaussian FUNCTION
% % Provide estimates for initial conditions (for lsqcurvefit) % %
height_est = max(fauxData)*rand ; mean_est = fauxMean*rand; std_est=fauxStd*rand;
x0 = [height_est;mean_est; std_est]; % parameters need to be in a single variable
options=optimset('Display','off'); % avoid pesky messages from lsqcurvefit (optional)
[params]=lsqcurvefit(gausFun,x0,xAxis,yourData,[],[],options); % meat and potatoes
lsq_mean = params(2); lsq_std = params(3) ; % what you want
% % % Plot data with fit % % %
myFit = gausFun(params,xAxis);
figure;hold on;plot(xAxis,yourData./sum(yourData),'k');
plot(xAxis,myFit./sum(myFit),'r','linewidth',3) % normalization optional
xlabel('Value');ylabel('Probability');legend('Data','Fit')
I have several Gaussian distributions and I want to draw different values from all of them at the same time. Since this is basically what a GMM does, I have looked into Matlab GMM implementation (gmrnd) and I have seen that it performs a simple loop over all the components.
I would like to implement it in a faster way, but the problem is that 3d matrices are involved. A simple code (with loop) would be
n = 10; % number of Gaussians
d = 2; % dimension of each Gaussian
mu = rand(d,n); % init some means
U = rand(d,d,n); % init some covariances with their Cholesky decomposition (Cov = U'*U)
I = repmat(triu(true(d,d)),1,1,n);
U(~I) = 0;
r = randn(d,n); % random values for drawing samples
samples = zeros(d,n);
for i = 1 : n
samples(:,i) = U(:,:,i)' * r(:,i) + mu(:,i);
end
Is it possible to speed it up? I do not know how to deal with the 3d covariances matrix (without using cellfun, which is much slower).
Few improvements (hopefully are improvements) could be suggested here.
PARTE #1 You can replace the following piece of code -
I = repmat(triu(true(d,d)),[1,1,n]);
U(~I) = 0;
with bsxfun(#times,..) one-liner -
U = bsxfun(#times,triu(true(d,d)),U)
PARTE #2 You can kill the loopy portion of the code again with bsxfun(#times,..) like so -
samples = squeeze(sum(bsxfun(#times,U,permute(r,[1 3 2])),2)) + mu
I'm not fully convinced this is faster, but it gets rid of the loop. It would be interesting to see benchmarking results if you can do that. I also think this code makes is rather ugly and it's a bit hard to deduce what's going on, but I'll let you decide between readability and performance.
Anyway, I decided to define a big n*d dimensional Gaussian where each block d of variates are independent of each other (as in the original). This allows defining the covariance as a block diagonal matrix, for which I use blkdiag. From there, it is a matter of applying bsxfun to remove the need for looping.
Using the same random seed, I can recover the same samples as your code:
%// sampling with block diagonal covariance matrix
rng(1) %// set random seed
Ub = mat2cell(U, d, d, ones(n,1)); %// 1-by-1-by-10 cell of 2-by-2 matrices
C = blkdiag(Ub{:});
Ns = 1; %// number of samples
joint_samples = bsxfun(#plus, C'*randn(d*n, Ns), mu(:));
new_samples = reshape(joint_samples, [d n]); %// or [d n Ns] if Ns > 1
%//Compare to original
rng(1) %// set same seed for repeatability
r = randn(d,n); % random values for drawing samples
samples = zeros(d,n);
for i = 1 : n
samples(:,i) = U(:,:,i)' * r(:,i) + mu(:,i);
end
isequal(samples, new_samples) %// true
I'm attempting to use scale space implementation to fit n Gaussian curves to peaks in a noisy time series digital signal (measuring voltage).
To test it I created the following sample sum of three gaussians with noise (0.2*rand, sorry no picture, i'm new here)
amp = [2; 0.9; 1.3];
mu = [19; 23; 28];
sigma = [4.8; 1.3; 2.5];
x = linspace(1,50,1000);
for n=1:3, y(n,:) = A(n)*exp(-(x-B(n)).^2./(2*C(n)^2)); end
noisysignal = y(1,:) + y(2,:) + y(3,:) + 0.2*rand(1,numel(x))
I found this article http://www.engineering.wright.edu/~agoshtas/GMIP94.pdf posted by user355856 answer to thread "Peak decomposition"!
I believe my code generates the correct result for plotting the zero crossings as a function of the gaussian filter resolution sigma, but I have two issues. The first is that it seems yet another fitting routine would be needed to identify the approximate location of the arch intercepts for approximating the initial peak sigma and mu values. The second is that the edges of the scale space plot have substantial arches that definitely do not correspond to any peak. I'm not sure how to screen these out effectively. Last thing is that is used a spacing of 50 when calculating the second derivative central finite difference since too much more destroyed feature, and to much less results in a forest of zero crossings. Would there be a better way to filter that to control random zero crossings in the gaussian peak tails?
function [crossing] = scalespace(x, y, sigmalimit)
figure; hold on; ylim([0 sigmalimit]);
for sigma = 1:sigmalimit %
yconv = convkernel(sigma, y); %convolve with kernel
xconv = linspace(x(1), x(end), length(yconv));
yconvpp = d2centralfinite(xconv, yconv, 50); % 50 was empirically chosen
num = 0;
for i = 1 : length(yconvpp)-1
if sign(yconvpp(i)) ~= sign(yconvpp(i+1))
crossing(sigma, num+1) = xconv(i);
num = num+1;
end
end
plot(crossing(sigma, crossing(sigma, :) ~= 0),...
sigma*ones(1, numel(crossing(sigma, crossing(sigma, :) ~= 0))), '.');
end
function [yconv] = convkernel(sigma, y)
t = sigma^2;
C = 3; % for kernel truncation
M = C*round(sqrt(t))+1;
window = (-M) : (+M);
G = zeros(1, length(window));
G(:) = (1/(2*pi()*t))*exp(-(window.^2)./(2*t));
yconv = conv(G, y);
This is my first post and I apologize in advance for any issues in style. I'm fairly new to programming, so any advice regarding the programming style or information provided in this question would be much appreciated. I also read through Amro's answer about matlab's GMM function! if anyone feels that would be a more efficient approach to modeling multiple gaussians in a digital signal.
Thank you!
I have found several questions/answers for vectorizing and speeding up routines for multiplying a matrix and a vector in a single loop, but I am trying to do something a little more general, namely multiplying an arbitrary number of matrices together, and then performing that operation an arbitrary number of times.
I am writing a general routine for calculating thin-film reflection from an arbitrary number of layers vs optical frequency. For each optical frequency W each layer has an index of refraction N and an associated 2x2 transfer matrix L and 2x2 interface matrix I which depends on the index of refraction and the thickness of the layer. If n is the number of layers, and m is the number of frequencies, then I can vectorize the index into an n x m matrix, but then in order to calculate the reflection at each frequency, I have to do nested loops. Since I am ultimately using this as part of a fitting routine, anything I can do to speed it up would be greatly appreciated.
This should provide a minimum working example:
W = 1260:0.1:1400; %frequency in cm^-1
N = rand(4,numel(W))+1i*rand(4,numel(W)); %dummy complex index of refraction
D = [0 0.1 0.2 0]/1e4; %thicknesses in cm
[n,m] = size(N);
r = zeros(size(W));
for x = 1:m %loop over frequencies
C = eye(2); % first medium is air
for y = 2:n %loop over layers
na = N(y-1,x);
nb = N(y,x);
%I = InterfaceMatrix(na,nb); % calculate the 2x2 interface matrix
I = [1 na*nb;na*nb 1]; % dummy matrix
%L = TransferMatrix(nb) % calculate the 2x2 transfer matrix
L = [exp(-1i*nb*W(x)*D(y)) 0; 0 exp(+1i*nb*W(x)*D(y))]; % dummy matrix
C = C*I*L;
end
a = C(1,1);
c = C(2,1);
r(x) = c/a; % reflectivity, the answer I want.
end
Running this twice for two different polarizations for a three layer (air/stuff/substrate) problem with 2562 frequencies takes 0.952 seconds while solving the exact same problem with the explicit formula (vectorized) for a three layer system takes 0.0265 seconds. The problem is that beyond 3 layers, the explicit formula rapidly becomes intractable and I would have to have a different subroutine for each number of layers while the above is completely general.
Is there hope for vectorizing this code or otherwise speeding it up?
(edited to add that I've left several things out of the code to shorten it, so please don't try to use this to actually calculate reflectivity)
Edit: In order to clarify, I and L are different for each layer and for each frequency, so they change in each loop. Simply taking the exponent will not work. For a real world example, take the simplest case of a soap bubble in air. There are three layers (air/soap/air) and two interfaces. For a given frequency, the full transfer matrix C is:
C = L_air * I_air2soap * L_soap * I_soap2air * L_air;
and I_air2soap ~= I_soap2air. Thus, I start with L_air = eye(2) and then go down successive layers, computing I_(y-1,y) and L_y, multiplying them with the result from the previous loop, and going on until I get to the bottom of the stack. Then I grab the first and third values, take the ratio, and that is the reflectivity at that frequency. Then I move on to the next frequency and do it all again.
I suspect that the answer is going to somehow involve a block-diagonal matrix for each layer as mentioned below.
Not next to a matlab, so that's only a starter,
Instead of the double loop you can write na*nb as Nab=N(1:end-1,:).*N(2:end,:);
The term in the exponent nb*W(x)*D(y) can be written as e=N(2:end,:)*W'*D;
The result of I*L is a 2x2 block matrix that has this form:
M = [1, Nab; Nab, 1]*[e-, 0;0, e+] = [e- , Nab*e+ ; Nab*e- , e+]
with e- as exp(-1i*e), and e+ as exp(1i*e)'
see kron on how to get the block matrix form, to vectorize the propagation C=C*I*L just take M^n
#Lama put me on the right path by suggesting block matrices, but the ultimate answer ended up being more complicated, and so I put it here for posterity. Since the transfer and interface matrix is different for each layer, I leave in the loop over the layers, but construct a large sparse block matrix where each block represents a frequency.
W = 1260:0.1:1400; %frequency in cm^-1
N = rand(4,numel(W))+1i*rand(4,numel(W)); %dummy complex index of refraction
D = [0 0.1 0.2 0]/1e4; %thicknesses in cm
[n,m] = size(N);
r = zeros(size(W));
C = speye(2*m); % first medium is air
even = 2:2:2*m;
odd = 1:2:2*m-1;
for y = 2:n %loop over layers
na = N(y-1,:);
nb = N(y,:);
% get the reflection and transmission coefficients from subroutines as a vector
% of length m, one value for each frequency
%t = Tab(na, nb);
%r = Rab(na, nb);
t = rand(size(W)); % dummy vector for MWE
r = rand(size(W)); % dummy vector for MWE
% create diagonal and off-diagonal elements. each block is [1 r;r 1]/t
Id(even) = 1./t;
Id(odd) = Id(even);
Io(even) = 0;
Io(odd) = r./t;
It = [Io;Id/2].';
I = spdiags(It,[-1 0],2*m,2*m);
I = I + I.';
b = 1i.*(2*pi*D(n).*nb).*W;
B(even) = -b;
B(odd) = b;
L = spdiags(exp(B).',0,2*m,2*m);
C = C*I*L;
end
a = spdiags(C,0);
a = a(odd).';
c = spdiags(C,-1);
c = c(odd).';
r = c./a; % reflectivity, the answer I want.
With the 3 layer system mentioned above, it isn't quite as fast as the explicit formula, but it's close and probably can get a little faster after some profiling. The full version of the original code clocks at 0.97 seconds, the formula at 0.012 seconds and the sparse diagonal version here at 0.065 seconds.