|
Thank you Alan,
I wrote a function in my program and it works perfect.
Groover,
0200 A9 23
0202 8D 01 80
0205 00
|
|
|
|
|
I have a group of points that I need to plot on a graph and calculate the line of best fit(Slope and Intercept) in a programming language.
for example
x 0 1 2 3 4
y 40 41 45 41 47
At the moment I am using and have implemented the Least Squares algorithm
here http://en.wikipedia.org/wiki/Least_squares[^]
I was wondering whether anyone knows of a computationally more efficient algorithm with close to the same accuracy and be able to explain how the algorithm works?
Thanks in advance 
|
|
|
|
|
A decent implementation of linear fitting by LSQ should run in O(n) time and O(1) space.
One pass over the data, accumulating sum(x), sum(y), sum(x*x) and sum(x*y) then crunch those four (and n) to get the answer.
If you're just doing a simple linear fit, DON'T get sucked into all the matrix stuff. Waaaaay overkill.
Cheers,
Peter
[edit]forgot sum(y)[/edit]
Software rusts. Simon Stephenson, ca 1994. So does this signature. me, 2012
modified 5-Sep-12 2:43am.
|
|
|
|
|
So, a quick maths check.
If I want to store the results of an iterative algorithm for every pixel in an image (fractals!) then I think it's a dumb thing to start with but want to check before I even start bothering to write the class that would store the results.
Assume image size is 1000 x 1000, so 1 million pixels
Algorithm is an iteration of Zn+1 = Zn^2 + Z0 up to a maximum of say 10,000 times
Each iteration results in a complex number
A complex number is a structure with 2 doubles (let's assume it occupies 128 bits for simplicty)
Theoretically this could result in 10,000 x 1,000,000 complex number instances
This is 1 x 10^10 instances, at 128 bits each that 1.28 x 10^12 bits
Which is:
1.6 x 10^11 bytes
1.56 x 10^8 K bytes
152,588 M bytes
149 G bytes
That would seem a dumb thing to do
But I'm assuming that my maths is correct and there aren't memory optimisations I know nothing about.
Mike
|
|
|
|
|
Does your algorithm depend on the pixel colour or pixel position?
What I'm thinking is that, if it depends on your pixel colour alone, then your iterations for two pixels with identical colour should yield the same results. If you come up with a way of storing the results in bulk for pixels with the same colours, then your memory consumption would most likely go way down.
Other than that, after a quick at your numbers as displayed above, they seem to be correct
Full-fledged Java/.NET lover, full-fledged PHP hater.
Full-fledged Google/Microsoft lover, full-fledged Apple hater.
Full-fledged Skype lover, full-fledged YM hater.
modified 3-Sep-12 15:22pm.
|
|
|
|
|
Pixel position, it's converted to a complex number which is then stuffed into the iterative equation and that results in a long (or short) list of complex numbers, Z0 to Zn, n could be anywhere from 0 to the limiting number - 10k in the example I gave, but could be much much lower (50) or much much higher.
The problem arises since the way I'm going through this 'rite of passage' (doing Mandelbrot images) is to try and create a pluggable set of classes that could be used to implement any fractal set (mandelbrot, julia, newton etc.) and use any of the many colourising methods (escape time, distance estimators etc.). Adding a new set (e.g. Burning Ship, Phoenix) or a new colourising method (e.g. escape angle) therefore simply entails creating a new class that does that specific job and implements the relevant interface.
The consequence of this is that the key class which manages and calls the FractalSet iterators and then calls the colouriser to get a colour for the complex number (pixel) under investigation has no way of knowing what data that colouriser needs, the classic escape time needs only the actual number of iterations, the distance estimators need things like the last 2 (or more) results of the iteration.
So the above question came from my first idea which was to store them all whilst the entire image was iterated pixel by pixel - bad idea!
I think my way of doing this will be to change the colouriser interface and have a method that takes the complete result set of results for a single iteration, processes it as appropriate (turning potentially thousands of complex numbers into something much smaller) and builds the data set it needs, plus a method to to manipulate them once all iterations have been completed and finally a method that spits out the image.
Thanks for the confirmation.
Mike
|
|
|
|
|
Mike-MadBadger wrote: I think my way of doing this will be to change the colouriser interface and have a method that takes the complete result set of results for a single iteration, processes it as appropriate and builds the data set it needs
Yeah, if you can do that (I thought storing all the values was a requirement or spec or mandatory), it definitely beats having to store tons of values.
Now, in terms of speed, I have no idea what the gain would be, but I'm also betting it would be faster than storing the calculations (which, come to think of it, in your particular case would only be a cache of some sort).
Mike-MadBadger wrote: Thanks for the confirmation.
I doubt I was of much help, but you're welcome
Full-fledged Java/.NET lover, full-fledged PHP hater.
Full-fledged Google/Microsoft lover, full-fledged Apple hater.
Full-fledged Skype lover, full-fledged YM hater.
|
|
|
|
|
Andrei Straut wrote: I thought storing all the values was a requirement or spec or mandatory
The closest I have to a spec. is the jumbled nonsense in my head and its many and frequent lurches from bad to poor design (an improvement of sorts!).
Thanks again.
Mike
|
|
|
|
|
Even if you wanted the results of all iterations, why would you need the results of all iterations for all pixels at the same time? Surely the pixels are independent?
|
|
|
|
|
Absolutely correct, I don't need them all at the same time.
That was my gut reaction to the problem of using pluggable colourisers, i.e. the Imager class, that does the looping through the pixels, asks a FractalSet to iterate its equation and send back the results, it would then manipulate them and finally send the manipuplated data to the colouriser. However, the Imager doesn't know what data the colouriser needs, it could be as simple as the iteraton count and the max iterations, it could be the average of all iterations, the escape angle etc.
The conclusion is that I need to send the results of each iteration to the colouriser immediately after each iteration has finished. The colouriser can then do whatever manipulations it wants to and store only the data it needs rather than the Imager storing everything and only invoking the colouriser once all iterations have finished.
I think that'll work, we'll soon see...
Mike
|
|
|
|
|
Noooo 
This question is on the news page. Really! Must be a slow news day.
Ah well, my dumb question for the world to peruse and giggle quietly to itself.
|
|
|
|
|
What use could it be to keep all iterates for all pixels ? The main reason I can think of is to render an animation showing the evolution of convergence, and be able to play it forwards but also backwards. (If only forwards, your machine will be fast enough to recompute the iterates on the fly; if just the final result matters, there is no reason to stroe all iterates.)
If your purpose is that kind of animation, a solution can be to MPEG compress the rendered images, achieving decent storage amounts even for large frame numbers.
|
|
|
|
|
See my answer to harold atropot, hopefully that answers your question - essentially I don't need to store them all, that was just a really poor way of solving a problem (so poor it wouldn't have worked).
Creating animations is a much later (if ever) addition to this project, right now it's just about me learning how to use interfaces, design patterns etc.
Thanks,
Mike
|
|
|
|
|
Mike,
Do you need to keep all 10,000 iterations leading up to your final image? I thought the idea with fractals was to loop back through the formula until you either settle on a value of not, and then paint the pixel (or not). Wouldn't you just need the final iteration, or maybe an array with your decision (paint/don't paint) for each pixel? Would reduce the size of your data by 10k.
Paul
|
|
|
|
|
The colouriser needs all the iterations for a given pixel (= a complex) since there are n ways to colourise a fractal, some of which manipulate all the values of Zn achieved during an iterative cycle.
However, the colouriser doesn't need all iterations for all pixels at the same time, so I am now sending all iterations for one pixel to the colouriser, it can then do whatever it needs, store its necessary data (number of iterations, escape angle, whatever) and then the cycle starts again for the next pixel. I think this is quite close to your suggestion?
Mostly the colourisers store their data in List(Of T) objects since they can cope better than arrays with changing dimensions.
Mike
|
|
|
|
|
Mike-MadBadger wrote: I am now sending all iterations for one pixel to the colouriser, it can then do whatever it needs, store its necessary data (number of iterations, escape angle, whatever) and then the cycle starts again for the next pixel. I think this is quite close to your suggestion?
Yes, I was thinking in terms of storing only what is absolutely necessary for each pixel.
Good luck.
Paul
|
|
|
|
|
You may want to check out www.FractalForums.com.
The people that wrote mandelbulb (mandelbox?) hang out there and may be a source of programming knowhow.
I'm user panzerboy there, I've written a few plugins for FractalExtreme. I use that to make zoom movies which I post on YouTube as CommandLineCowboy.
FractalExtreme is somewhat limited in its colouring, its strictly iteration count indexing into a 228 element palette table. I often do multiple renders with different palettes and mappings layering the results. If you check out my latest videos you'll see that you can still accomplish quite a lot with simple iteration count colouring.
Your 'average of all iterations' comment intrigues me. In Fractal Extreme you can hold Shift and Ctrl and click on the initial mandelbrot set to see the 'iteration paths'. Values in the M-set spiral inwards around a central point which would be your average value. The values outside the set with high iteration counts buzz around a point before going outside the window. Again that average would the central point only slightly altered by the last few iterations. So I'm thinking you may not need all the iterations to find the axis of the spirals.
|
|
|
|
|
Jeremy David Thomson wrote: Your 'average of all iterations' comment intrigues me
Then I was probably a little misleading, I was just trying to pick an example as to why you might want anything other than than the classic 'IterationCount / MaxIterations' which is what most folk doing this 'rite of passage' project would recognise. More practical examples might have been standard deviation or other more complex statistical analysis - many (all?) of which have been done by someone at some point to varying degrees of success and aesthetic value.
Jeremy David Thomson wrote: You may want to check out www.FractalForums.com
That I have discovered, though I have only scratched the surface at this point. It seems one of the better (or at least more broad ranging) places to go, though there are literally millions of places to get little bits and pieces of useful information.
Thanks for your time.
|
|
|
|
|
Howdy
Hmm, is double precision complex really needed, in your case e.q. storing all in int's could
reduce required space 4x.
also maybe the whole image could be 7zipped.
You could allocate each time 1M ints array and run 7zip through it, I assume a lot of compression could be achieved that way 
Dunno though
|
|
|
|
|
Zipping wouldn't work due to the very nature of fractals: they're all about chaos and unpredictability, whereas compression algorithms are all about detecting patterns and predictability of data sequences. The two don't mesh. Ever.
P.S: for the same reason restricting yourself to lower precision won't work either. In fact, with a precision of only about 55 bit (which I think is the usual length of the mantisse in a double), doing more than about 500 iterations will yield no meaningful data. It may still look nice when visualized (which is usually the point of fractal programs), but you are effectively looking at rounding errors. I would go so far as to say you need an arbitrary math library for more than 100 iterations.
|
|
|
|
|
I'm a bit in a hurry right now, but I'd like to point out that for 10000 iterations you need arbitrary precision math! The rounding errors from each iteration grow exponentially, and so will the size you need to store each resulting value in sufficient precision.
Unless of course you're fine that you're effectively looking at rounding errors after a few hundred iterations.
|
|
|
|
|
Stefan_Lang wrote: for 10000 iterations you need arbitrary precision math
Good point, well made. << Heads off to investigate >>
To be fair, at this point it's more proof of concept, can I design a set of classes that allow you to plug any fractal set into any colourising method (with any mapping technique to boot), it's not intended to be a finished product, why would the world need another fractal generator?
Thanks,
Mike
|
|
|
|
|
I had some time to get an estimate for the accumulation of the precision-based error, and found that it's upper limit is about machine_precision*4^iterations, and the average error would be around machine_precision*2^iterations. That means the maximum error approaches 1 after about 28 iterations for double values (55-56 bit mantisse), and the average error approaches 1 after about 56 iterations.
If you intend to store intermediate results, you might consider approaching this problem from the other side:
1. partition your intervals according to your machine precision, e. g. 2^16x2^16 points
2. for each point, store 1 if after one iteration the divergence criterium is met, or 0 if not. This is the iteration counter.
3. repeat for each point with a value of 0:
3.1 convert the result after one iteration to the resolution of your point array (i. e. check which pixel is closest)
3.2 check the iteration counter for the point corresponding to that value: if it is not 0, store this value+1. Else your counter is still 0.
3.3 when you're done with all points that still have a counter of 0, start all over again, for at most as many times as appropriate to your initial resolution (e. g. no more than 16 times if you started at 2^16x2^16)
This is a reversion of the actual algorithm, deliberately adding in the error (in step 3.1) that you would otherwise get when calculating at a given resolution (in this case 16 bit).
|
|
|
|
|
Thanks for spending time on this - I'm going to have to sit down with a large coffee (or 8) before I get my head around this. Separately I found GNU MP and some .Net wrappers. When I get there I'll have a decent look at both options
Thanks again,
Mik
|
|
|
|
|
From here: http://mrob.com/pub/muency/accuracy.html[^]
The commonly-seen views of the Mandelbrot Set have been challenged by arguments based on techniques like error-term analysis (see Propagation of uncertainty). They show that if you want to get an accurate view of a lemniscate ZN you need to use at least N digits in all your calculations. The result is that most views of the Mandelbrot Set that people see on computers are (in theory) completely inaccurate or even "fictitious".
However, except for certain specific purposes (notably using iteration to trace an external ray), the problem is much smaller. The overwhelming amount of experimental evidence shows that ordinary Mandelbrot images (plotting e.g. the dwell for each point on a pixel grid) are indistinguishable from equivalent results produced by exact calculation. The images look the same to the human eye regardless of how many digits you use, as long as the number of digits is sufficient to distinguish the coordinates of the parameter value C.
This is because the roundoff errors added by each step in the iteration tend to cancel out as they would if randomly distributed, rather than systematically biased in one certain direction. See Systematic error, "Systematic versus random error".
Not that this means the discussion about errors is without value, especially since the above explanation of why you might choose to ignore it relies on an assumed internal cancellation of errors through randomness. Indeed the above validates the discussion but perhaps helps put into context how much effort one might want to put into higher accuracy vs. say better functionality etc.
Mike
|
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
