I would like to generate numbers into an array that has normal distribution. Is there any function in objective-c or c that can help to get the result easily without any math?
Use the the Box-Muller-Transformation:
1.) you need two uniform distributed random numbers u and v as doubles in the interval (0,1] (0 needs to be excluded):
double u =(double)(random() %100000 + 1)/100000; //for precision
double v =(double)(random() %100000 + 1)/100000; //for precision
2.) calculate the uniform distributed value with average of 0 and the standard deviation sigma of 1:
double x = sqrt(-2*log(u))*cos(2*pi*v); //or sin(2*pi*v)
3.) if needed add sigma and average for your target distribution like this:
double y = x * sigmaValue + averageValue;
4.) put it in an array
[randomNumberArray addObject:[NSNumber numberWithDouble:y]]
There is no function norminv for objc. So, math is needed here.
Edit: I like using random() to be able to seed the random value generator
Let me preface this by saying, please, correct me if I'm wrong!
It's my understanding that the Box-Muller Transformation relies on the source numbers being them selves uniformly distributed, thus using random() or rand() as the source data-set for Box-Muller will NOT necessarily produce a uniform distribution.
It is instead intended to take a generic set of uniformly distributed random numbers, and produce independent pairs of random numbers uniformly distributed in a 2D coordinate system.
Wikipedia: Box-Muller Transform
There is however another way:
On most Unix systems (and thus Objective C on iOS or OSX) using the rand48 library of functions:
Reference: drand
double drand48(void);
void srand48(long int seedval);
srand48() seeds the generator, and drand48() produces random numbers uniformly distributed over the interval [0.0 - 1.0]
Related
I was wondering if it would be possible to poll the AnalyzerNode from the WebAudio API and use it to construct a PeriodicWave that is synthesized via an OscillatorNode?
My intuition is that something about the difference in amplitudes between analyzer frames can help calculate the right phase for a PeriodicWave, but I'm not sure how to go about implementing it. Any help on the right algorithm to use would be appreciated!
As luck would have it, I was working on a similar project just a few weeks ago. I put together a JSFiddle to explore the idea of reconstructing a phase-randomized version of a waveform using frequency data from an AnalyserNode. You can find that experiment here:
https://jsfiddle.net/mattdiamond/w4u7x8zk/
Here's the code that takes in the frequency data output from an AnalyserNode and generates a PeriodicWave:
function generatePeriodicWave(freqData) {
const real = [];
const imag = [];
freqData.forEach((x, i) => {
const amp = fromDecibels(x);
const phase = getRandomPhase();
real.push(amp * Math.cos(phase));
imag.push(amp * Math.sin(phase));
});
return context.createPeriodicWave(real, imag);
}
function fromDecibels(x) {
return 10 ** (x / 20);
}
function getRandomPhase() {
return Math.random() * 2 * Math.PI - Math.PI;
}
Since the AnalyserNode converts the FFT amplitude values to decibels, we need to recover those original values first (which we do by simply using the inverse of the formula that was used to convert them to decibels). We also need to provide a phase for each frequency, which we select at random from the range -π to π.
Now that we have an amplitude and phase, we construct a complex number by multiplying the amplitude by the cosine and sine of the phase. This is because the amplitude and phase correspond to a polar coordinate, and createPeriodicWave expects a list of real and imaginary numbers corresponding to Cartesian coordinates in the complex plane. (See here for more information on the mathematics behind this conversion.)
Once we've generated the PeriodicWave, all that's left to do is load it into an OscillatorNode, set the desired frequency, and start the oscillator. You'll notice that the default frequency is set to context.sampleRate / FFT_SIZE (you can ignore the toFixed, that was just for the sake of the UI). This causes the oscillator to play the wave at the same rate as the original samples. Increasing or decreasing the frequency from this value will pitch-shift the audio up or down, respectively.
You'll also notice that I chose 2^15 as the FFT size, which is the maximum size that the AnalyserNode allows. For my purposes -- creating interesting looped drones -- a larger FFT results in a more interesting and less "loopy" drone. (A while back I created a webpage that allowed users to generate drones from much larger FFTs... that experiment utilized a third-party FFT library instead of the AnalyserNode.) I'm not sure if this is the right FFT size for your purposes, but it's something to consider.
Anyway, I think that covers the core of the algorithm. Hope this helps! (And feel free to ask more questions in the comments if anything's unclear.)
I have a data set with 20 non-overlapping different swap rates (spot1y, 1y1y, 2y1y, 3y1y, 4y1y, 5y2y, 7y3y, 10y2y, 12y3y...) over the past year.
I want to use PCA / multiregression and look at residuals in order to determine which sectors on the curve are cheap/rich. Has anyone had experience with this? I've done PCA but not for time series. I'd ideally like to model something similar to the first figure here but in USD.
https://plus.credit-suisse.com/rpc4/ravDocView?docid=kv66a7
Thanks!
Here are some broad strokes that can help answer your question. Also, that's a neat analysis from CS :)
Let's be pythonistas and use NumPy. You can imagine your dataset as a 20x261 array of floats. The first place to start is creating the array. Suppose you have a CSV file storing the raw data persistently. Then a reasonable first step to load the data would be something as simple as:
import numpy
x = numpy.loadtxt("path/to/my/file")
The object x is our raw time series matrix, and we verify the truthness of x.shape == (20, 261). The next step is to transform this array into it's covariance matrix. Whether it has been done on the raw data already, or it still has to be done, the first step is centering each time series on it's mean, like this:
x_centered = x - x.mean(axis=1, keepdims=True)
The purpose of this step is to help simplify any necessary rescaling, and is a very good habit that usually shouldn't be skipped. The call to x.mean uses the parameters axis and keepdims to make sure each row (e.g. the time series for spot1yr, ...) is centered with it's mean value.
The next steps are to square and scale x to produce a swap rate covariance array. With 2-dimensional arrays like x, there are two ways to square it-- one that leads to a 261x261 array and another that leads to a 20x20 array. It's the second array we are interested in, and the squaring procedure that will work for our purposes is:
x_centered_squared = numpy.matmul(x_centered, x_centered.transpose())
Then, to scale one can chose between 1/261 or 1/(261-1) depending on the statistical context, which looks like this:
x_covariance = x_centered_squared * (1/261)
The array x_covariance has an entry for how each swap rate changes with itself, and changes with any one of the other swap rates. In linear-algebraic terms, it is a symmetric operator that characterizes the spread of each swap rate.
Linear algebra also tells us that this array can be decomposed into it's associated eigen-spectrum, with elements in this spectrum being scalar-vector pairs, or eigenvalue-eigenvector pairs. In the analysis you shared, x_covariance's eigenvalues are plotted in exhibit two as percent variance explained. To produce the data for a plot like exhibit two (which you will always want to furnish to the readers of your PCA), you simply divide each eigenvalue by the sum of all of them, then multiply each by 100.0. Due to the convenient properties of x_covariance, a suitable way to compute it's spectrum is like this:
vals, vects = numpy.linalg.eig(x_covariance)
We are now in a position to talk about residuals! Here is their definition (with our namespace): residuals_ij = x_ij − reconstructed_ij; i = 1:20; j = 1:261. Thus for every datum in x, there is a corresponding residual, and to find them, we need to recover the reconstructed_ij array. We can do this column-by-column, operating on each x_i with a change of basis operator to produce each reconstructed_i, each of which can be viewed as coordinates in a proper subspace of the original or raw basis. The analysis describes a modified Gram-Schmidt approach to compute the change of basis operator we need, which ensures this proper subspace's basis is an orthogonal set.
What we are going to do in the approach is take the eigenvectors corresponding to the three largest eigenvalues, and transform them into three mutually orthogonal vectors, x, y, z. Research the web for active discussions and questions geared toward developing the Gram-Schmidt process for all sorts of practical applications, but for simplicity let's follow the analysis by hand:
x = vects[0] - sum([])
xx = numpy.dot(x, x)
y = vects[1] - sum(
(numpy.dot(x, vects[1]) / xx) * x
)
yy = numpy.dot(y, y)
z = vects[2] - sum(
(numpy.dot(x, vects[2]) / xx) * x,
(numpy.dot(y, vects[2]) / yy) * y
)
It's reasonable to implement normalization before or after this step, which should be informed by the data of course.
Now with the raw data, we implicitly made the assumption that the basis is standard, we need a map between {e1, e2, ..., e20} and {x,y,z}, which is given by
ch_of_basis = numpy.array([x,y,z]).transpose()
This can be used to compute each reconstructed_i, like this:
reconstructed = []
for measurement in x.transpose().tolist():
reconstructed.append(numpy.dot(ch_of_basis, measurement))
reconstructed = numpy.array(reconstructed).transpose()
And then you get the residuals by subtraction:
residuals = x - reconstructed
This flow obviously might need further tuning, but it's the gist of how to do compute all the residuals. To get that periodic bar plot, take the average of each row in residuals.
I'm having trouble understanding a lecture slide in my school's machine learning course
why does the expected value of Y = f(X)? what does it mean
my understanding is that X, Y are vectors and f(X) outputs a vector of Y where each individual value (y_i) in the Y vector corresponds to a f(x_i) where x_i is the value in X at index i; But now it's taking the expected value of Y, which is going to be a single value, so how is that equal to f(X)?
X, Y (uppercase) are vectors
x_i,y_i (lowercase with subscript) are scalars at index i in X,Y
There is a lot of confusion here. First let's start with definitions
Definitions
Expectation operator E[.]: Takes a random variable as an input and gives a scalar/vector as an output. Let's say Y is a normally distributed random variable with mean Mu and Variance Sigma^{2} (usually stated as:
Y ~ N( Mu , Sigma^{2} ), then E[Y] = Mu
Function f(.): Takes a scalar/vector (not a random variable) and gives a scalar/vector. In this context it is an affine function, that is f(X) = a*X + b where a and b are fixed constants.
What's Going On
Now you can view linear regression from two angles.
Stats View
One angle assumes that your response variable-Y- is a normally distributed random variable because:
Y ~ a*X + b + epsilon
where
epsilon ~ N( 0 , sigma^sq )
and X is some other distribution. We don't really care how X is distributed and treat it as given. In that case the conditional distribution is
Y|X ~ N( a*X + b , sigma^sq )
Notice here that a,b and also X is a number, there is no randomness associated with them.
Maths View
The other view is the math view where I assume that there is a function f(.) that governs the real life process, that if in real life I observe X, then f(X) should be the output. Of course this is not the case and the deviations are assumed to be due to various reasons such as gauge error etc. The claim is that this function is linear:
f(X) = a*X + b
Synthesis
Now how do we combine these? Well, as follows:
E[Y|X] = a*X + b = f(X)
About your question, I first would like to challenge that it should be Y|X and not Y by itself.
Second, there are tons of possible ontological discussions over what each term here represents in real life. X,Y (uppercase) could be vectors. X,Y (uppercase) could also be random variables. A sample of these random variables might be stored in vectors and both would be represented with uppercase letters (the best way is to use different fonts for each). In this case, your sample will become your data. Discussions about the general view of the model and its relevance to real life should be made at random variable level. The way to infer the parameters, how linear regression algorithms works should be made at matrix and vectors levels. There could be other discussion where you should care about both.
I hope this overly unorganized answer helps you. In general if you want to learn such stuff, be sure you know what kind of math objects and operators you are dealing with , what do they take as input and what are their relevance to real life.
I would like to implement an embedding table with float inputs instead of int32 or 64b.
The reason is that instead of words like in a simple RNN, I would like to use percentages.
For example in case of a recipe; I may have 1000 or 3000 ingredients; but in every recipe I may have a maximum of 80.
The ingredients will be represented in percentage for example: ingredient1=0.2 ingredient2=0.8... etc
my problem is that tensorflow forces me to use integers for my embedding table:
TypeError: Value passed to parameter ‘indices’ has DataType float32 not in list of allowed values: int32, int64
any suggestion?
I appreciate your feedback,
example of embedding look up:
inputs = tf.placeholder(tf.float32, shape=[None, ninp], name=“x”)
n_vocab = len(int_to_vocab)
n_embedding = 200 # Number of embedding features
with train_graph.as_default():
embedding = tf.Variable(tf.random_uniform((n_vocab, n_embedding), -1, 1))
embed = tf.nn.embedding_lookup(embedding, inputs)
the error is caused by
inputs = tf.placeholder(**tf.float32,** shape=[None, ninp], name=“x”)
I have thought of an algorithm that could work using loops. But, I was wondering if there is a more direct solution.
Thanks!
tf.nn.embedding_lookup can't allow float input, because the point of this function is to select the embeddings at the specified rows.
Example:
Here there are 5 words and 5 embedding 3D vectors, and the operation returns the 3-rd row (with 0-indexing). This is equivalent to this line in tensorflow:
embed = tf.nn.embedding_lookup(embed_matrix, [3])
You can't possibly look up a floating point index, such as 0.2 or 0.8, because there is no 0.2 and 0.8 row index in the matrix. Highly recommend this post by Chris McCormick about word2vec.
What you describe sounds more like a softmax loss function, which outputs a probability distribution over the target classes.
This question already has an answer here:
Closed 10 years ago.
Possible Duplicate:
Generating a random Gaussian double in Objective-C/C
Is there any way of getting a random number not from a uniform distribution, but from a Gaussian (Normal, Bell Curve) distribution in iOS? All the random number generators I have found are basically uniform and I want to make the numbers cluster around a certain point. Thanks!
Just use a uniform distribution generator and apply the Box-Muller Transform:
double u1 = (double)arc4random() / UINT32_MAX; // uniform distribution
double u2 = (double)arc4random() / UINT32_MAX; // uniform distribution
double f1 = sqrt(-2 * log(u1));
double f2 = 2 * M_PI * u2;
double g1 = f1 * cos(f2); // gaussian distribution
double g2 = f1 * sin(f2); // gaussian distribution
One simple option is to add several numbers from a uniform distribution together. Many dice based games use this approach to generate roughly normal distributions of results.
via wikipedia
If you can be more specific about what distribution you want there may be more precise solutions but combining several rolls is an easy and fairly flexible solution.