Related
For an experiment I need to pseudo randomize a vector of 100 trials of stimulus categories, 80% of which are category A, 10% B, and 10% C. The B trials have at least two non-B trials between each other, and the C trials must come after two A trials and have two A trials following them.
At first I tried building a script that randomized a vector and sort of "popped" out the trials that were not where they should be, and put them in a space in the vector where there was a long series of A trials. I'm worried though that this is overcomplicated and will create an endless series of unforeseen errors that will need to be debugged, as well as it not being random enough.
After that I tried building a script which simply shuffles the vector until it reaches the criteria, which seems to require less code. However now that I have spent several hours on it, I am wondering if these criteria aren't too strict for this to make sense, meaning that it would take forever for the vector to shuffle before it actually met the criteria.
What do you think is the simplest way to handle this problem? Additionally, which would be the best shuffle function to use, since Shuffle in psychtoolbox seems to not be working correctly?
The scope of this question moves much beyond language-specific constructs, and involves a good understanding of probability and permutation/combinations.
An approach to solving this question is:
Create blocks of vectors, such that each block is independent to be placed anywhere.
Randomly allocate these blocks to get a final random vector satisfying all constraints.
Part 0: Category A
Since category A has no constraints imposed on it, we will go to the next category.
Part 1: Make category C independent
The only constraint on category C is that it must have two A's before and after. Hence, we first create random groups of 5 vectors, of the pattern A A C A A.
At this point, we have an array of A vectors (excluding blocks), blocks of A A C A A vectors, and B vectors.
Part 2: Resolving placement of B
The constraint on B is that two consecutive Bs must have at-least 2 non-B vectors between them.
Visualize as follows: Let's pool A and A A C A A in one array, X. Let's place all Bs in a row (suppose there are 3 Bs):
s0 B s1 B s2 B s3
Where s is the number of vectors between each B. Hence, we require that s1, s2 be at least 2, and overall s0 + s1 + s2 + s3 equal to number of vectors in X.
The task is then to choose random vectors from X and assign them to each s. At the end, we finally have a random vector with all categories shuffled, satisfying the constraints.
P.S. This can be mapped to the classic problem of finding a set of random numbers that add up to a certain sum, with constraints.
It is easier to reduce the constrained sum problem to one with no constraints. This can be done as:
s0 B s1 t1 B s2 t2 B s3
Where t1 and t2 are chosen from X just enough to satisfy constraints on B, and s0 + s1 + s2 + s3 equal to number of vectors in X not in t.
Implementation
Implementing the same in MATLAB could benefit from using cell arrays, and this algorithm for the random numbers of constant sum.
You would also need to maintain separate pools for each category, and keep building blocks and piece them together.
Really, this is not trivial but also not impossible. This is the approach you could try, if you want to step aside from brute-force search like you have tried before.
I'm currently working on implementing a gradient check function in which it requires to get certain index values from the result matrix. Could someone tell me how to get a group of values from the matrix?
To be specific, for a result matrx res with size M x N, I'll need to get element res(3,1), res(4,2), res(1,3), res(2,4)...
In my case, M is dimension and N is batch size and there's a label array whose size is 1xbatch_size, [3 4 1 2...]. So the desired values are res(label(:),1:batch_size). Since I'm trying to practice vectorization programming and it's better not using loop. Could someone tell me how to get a group of value without a iteration?
Cheers.
--------------------------UPDATE----------------------------------------------
The only idea I found is firstly building a 'mask matrix' then use the original result matrix to do element wise multiplication (technically called 'Hadamard product', see in wiki). After that just get non-zero element out and do the sum operation, the code in matlab should look like:
temp=Mask.*res;
desired_res=temp(temp~=0); %Note: the temp(temp~=0) extract non-zero elements in a 'column' fashion: it searches temp matrix column by column then put the non-zero number into container 'desired_res'.
In my case, what I wanna do next is simply sum(desired_res) so I don't need to consider the order of those non-zero elements in 'desired_res'.
Based on this idea above, creating mask matrix is the key aim. There are two methods to do this job.
Codes are shown below. In my case, use accumarray function to add '1' in certain location (which are stored in matrix 'subs') and add '0' to other space. This will give you a mask matrix size [rwo column]. The usage of full(sparse()) is similar. I made some comparisons on those two methods (repeat around 10 times), turns out full(sparse) is faster and their time costs magnitude is 10^-4. So small difference but in a large scale experiments, this matters. One benefit of using accumarray is that it could define the matrix size while full(sparse()) cannot. The full(sparse(subs, 1)) would create matrix with size [max(subs(:,1)), max(subs(:,2))]. Since in my case, this is sufficient for my requirement and I only know few of their usage. If you find out more, please share with us. Thanks.
The detailed description of those two functions could be found on matlab's official website. accumarray and full, sparse.
% assume we have a label vector
test_labels=ones(10000,1);
% method one, accumarray(subs,1,[row column])
tic
subs=zeros(10000,2);
subs(:,1)=test_labels;
subs(:,2)=1:10000;
k1=accumarray(subs,1,[10, 10000]);
t1=toc % to compare with method two to check which one is faster
%method two: full(sparse(),1)
tic
k2=full(sparse(test_labels,1:10000,1));
t2=toc
I have a small MATLAB script (included below) for handling data read from a CSV file with two columns and hundreds of thousands of rows. Each entry is a natural number, with zeros only occurring in the second column. This code is taking a truly incredible amount of time (hours) to run what should be achievable in at most some seconds. The profiler identifies that approximately 100% of the run time is spent writing a matrix of zeros, whose size varies depending on input, but in all usage is smaller than 1000x1000.
The code is as follows
function [data] = DataHandler(D)
n = size(D,1);
s = max(D,1);
data = zeros(s,s);
for i = 1:n
data(D(i,1),D(i,2)+1) = data(D(i,1),D(i,2)+1) + 1;
end
It's the data = zeros(s,s); line that takes around 100% of the runtime. I can make the code run quickly by just changing out the s's in this line for 1000, which is a sufficient upper bound to ensure it won't run into errors for any of the data I'm looking at.
Obviously there're better ways to do this, but being that I just bashed the code together to quickly format some data I wasn't too concerned. As I said, I fixed it by just replacing s with 1000 for my purposes, but I'm perplexed as to why writing that matrix would bog MATLAB down for several hours. New code runs instantaneously.
I'd be very interested if anyone has seen this kind of behaviour before, or knows why this would be happening. Its a little disconcerting, and it would be good to be able to be confident that I can initialize matrices freely without killing MATLAB.
Your call to zeros is incorrect. Looking at your code, D looks like a D x 2 array. However, your call of s = max(D,1) would actually generate another D x 2 array. By consulting the documentation for max, this is what happens when you call max in the way you used:
C = max(A,B) returns an array the same size as A and B with the largest elements taken from A or B. Either the dimensions of A and B are the same, or one can be a scalar.
Therefore, because you used max(D,1), you are essentially comparing every value in D with the value of 1, so what you're actually getting is just a copy of D in the end. Using this as input into zeros has rather undefined behaviour. What will actually happen is that for each row of s, it will allocate a temporary zeros matrix of that size and toss the temporary result. Only the dimensions of the last row of s is what is recorded. Because you have a very large matrix D, this is probably why the profiler hangs here at 100% utilization. Therefore, each parameter to zeros must be scalar, yet your call to produce s would produce a matrix.
What I believe you intended should have been:
s = max(D(:));
This finds the overall maximum of the matrix D by unrolling D into a single vector and finding the overall maximum. If you do this, your code should run faster.
As a side note, this post may interest you:
Faster way to initialize arrays via empty matrix multiplication? (Matlab)
It was shown in this post that doing zeros(n,n) is in fact slow and there are several neat tricks to initializing an array of zeros. One way is to accomplish this by empty matrix multiplication:
data = zeros(n,0)*zeros(0,n);
One of my personal favourites is that if you assume that data was not declared / initialized, you can do:
data(n,n) = 0;
If I can also comment, that for loop is quite inefficient. What you are doing is calculating a 2D histogram / accumulation of data. You can replace that for loop with a more efficient accumarray call. This also avoids allocating an array of zeros and accumarray will do that under the hood for you.
As such, your code would basically become this:
function [data] = DataHandler(D)
data = accumarray([D(:,1) D(:,2)+1], 1);
accumarray in this case will take all pairs of row and column coordinates, stored in D(i,1) and D(i,2) + 1 for i = 1, 2, ..., size(D,1) and place all that match the same row and column coordinates into a separate 2D bin, we then add up all of the occurrences and the output at this 2D bin gives you the total tally of how many values at this 2D bin which corresponds to the row and column coordinate of interest mapped to this location.
Let A and B be two matrices of the same size. For a matrix M, let ht(M,t) threshold all the entries of M by t. That is All entries whose absolute value is less than t are set to 0. Suppose I want to find the optimal threshold t such that norm(ht(A,t)-B,'fro')^2 is minimized.
The only way that I can see to do this is deficient: do a for loop over the unique values of A and threshold A and setting C=ht(A,t)-B, compute sum(sum(C.*C)).
This is just too slow when A is large. I have considered sorting the elements of A and finding some efficient way to set a few entries to zero at a time, but I'm not sure this can all be done without a for loop.
Is there a way to do it?
Here's a very simple example (so simple a for loop works easily in this case):
B =
0.101508820368332 0
0 0.301996943246957
Set
A=B+.1*ones(2)
A =
0.201508820368332 0.1
0.1 0.401996943246957
Simple inspection shows that if we zero out the off-diagonal entries of A we minimize the difference between A and B. There are 3 possible threshold values, given by unique(A)=[.1,.2015,.402]. Given a potential threshold value t, we can hard threshold A by:
function [A_thresholded] = ht(A,t)
%
A_thresholded = A .* (abs(A)>t);
The form of the data in a matrix is irrelevant. You can convert them to vectors and simply compute the square-norm. In fact, you can sort the contents of A in increasing order (and permute B to preserve pairing). When you increase the threshold to include one more value in A, the norm only changes by that one increment. Therefore, you can find your solution in O(n log n). Hope this helps.
I currently implementing an optimization algorithm that requires me to sample without replacement from several sets. Although I am coding in MATLAB, this is essentially a CS question.
The situation is as follows:
I have a finite number of sets (A, B, C) each with a finite but possibly different number of elements (a1,a2...a8, b1,b2...b10, c1, c2...c25). I also have a vector of probabilities for each set which lists a probability for each element in that set (i.e. for set A, P_A = [p_a1 p_a2... p_a8] where sum(P_A) = 1). I normally use these to create a probability generating function for each set, which given a uniform number between 0 to 1, can spit out one of the elements from that set (i.e. a function P_A(u), which given u = 0.25, will select a2).
I am looking to sample without replacement from the sets A, B, and C. Each "full sample" is a sequence of elements from each of the different sets i.e. (a1, b3, c2). Note that the space of full samples is the set of all permutations of the elements in A, B, and C. In the example above, this space is (a1,a2...a8) x (b1,b2...b10) x (c1, c2...c25) and there are 8*10*25 = 2000 unique "full samples" in my space.
The annoying part of sampling without replacement with this setup is that if my first sample is (a1, b3, c2) then that does not mean I cannot sample the element a1 again - it just means that I cannot sample the full sequence (a1, b3, c2) again. Another annoying part is that the algorithm I am working with requires me do a function evaluation for all permutations of elements that I have not sampled.
The best method at my disposal right now is to keep track the sampled cases. This is a little inefficient since my sampler is forced to reject any case that has been sampled before (since I'm sampling without replacement). I then do the function evaluations for the unsampled cases, by going through each permutation (ax, by, cz) using nested for loops and only doing the function evaluation if that combination of (ax, by, cz) is not included in the sampled cases. Again, this is a little inefficient since I have to "check" whether each permutation (ax, by, cz) has already been sampled.
I would appreciate any advice in regards to this problem. In particular, I am looking a method to sample without replacement and keep track of unsampled cases that does not explicity list out the full sample space (I usually work with 10 sets with 10 elements each so listing out the full sample space would require a 10^10 x 10 matrix). I realize that this may be impossible, though finding efficient way to do it will allow me to demonstrate the true limits of the algorithm.
Do you really need to keep track of all of the unsampled cases? Even if you had a 1-by-1010 vector that stored a logical value of true or false indicating if that permutation had been sampled or not, that would still require about 10 GB of storage, and MATLAB is likely to either throw an "Out of Memory" error or bring your entire machine to a screeching halt if you try to create a variable of that size.
An alternative to consider is storing a sparse vector of indicators for the permutations you've already sampled. Let's consider your smaller example:
A = 1:8;
B = 1:10;
C = 1:25;
nA = numel(A);
nB = numel(B);
nC = numel(C);
beenSampled = sparse(1,nA*nB*nC);
The 1-by-2000 sparse matrix beenSampled is empty to start (i.e. it contains all zeroes) and we will add a one at a given index for each sampled permutation. We can get a new sample permutation using the function RANDI to give us indices into A, B, and C for the new set of values:
indexA = randi(nA);
indexB = randi(nB);
indexC = randi(nC);
We can then convert these three indices into a single unique linear index into beenSampled using the function SUB2IND:
index = sub2ind([nA nB nC],indexA,indexB,indexC);
Now we can test the indexed element in beenSampled to see if it has a value of 1 (i.e. we sampled it already) or 0 (i.e. it is a new sample). If it has been sampled already, we repeat the process of finding a new set of indices above. Once we have a permutation we haven't sampled yet, we can process it:
while beenSampled(index)
indexA = randi(nA);
indexB = randi(nB);
indexC = randi(nC);
index = sub2ind([nA nB nC],indexA,indexB,indexC);
end
beenSampled(index) = 1;
newSample = [A(indexA) B(indexB) C(indexC)];
%# ...do your subsequent processing...
The use of a sparse array will save you a lot of space if you're only going to end up sampling a small portion of all of the possible permutations. For smaller total numbers of permutations, like in the above example, I would probably just use a logical vector instead of a sparse vector.
Check the matlab documentation for the randi function; you'll just want to use that in conjunction with the length function to choose random entries from each vector. Keeping track of each sampled vector should be as simple as just concatenating it to a matrix;
current_values = [5 89 45]; % lets say this is your current sample set
used_values = [used_values; current_values];
% wash, rinse, repeat