scientific-computing

I'm very new to scikit learn and machine learning in general. I am currently designing a SVM to predict if a specific amino acid sequence will be cut by a protease. So far the the SVM method seems to be working quite well: I'd like to visualize the distance between the two categories (cut and uncut), so I'm trying to use the linear discrimination analysis, which is similar to the principal component analysis, using the following code: from sklearn.discriminant_analysis import LinearDiscriminantAnalysis lda = LinearDiscriminantAnalysis(n_components=2) targs = np.array([1 if _ else 0 for _ in

The new Scipy v0.11 offers a package for spectral analysis. Unfortunately the documentation is sparse and there aren't many available examples. As a baby example, I'm trying to do period discovery of a sine wave. Unfortunately it predicts a period of 1 instead of the expected 2pi . Any ideas? # imports the numerical array and scientific computing packages import numpy as np import scipy as sp from scipy.signal import spectral # generates 100 evenly spaced points between 1 and 1000 time = np.linspace(1, 1000, 100) # computes the sine value of each of those points mags = np.sin(time) # scales

While I know (so I have been told) that Floating-point coprocessors work faster than any software implementation of floating-point arithmetic, I totally lack the gut feeling how large this difference is, in order of magnitudes. The answer probably depends on the application and where you work, between microprocessors and supercomputers. I am particularly interested in computer simulations. Can you point out articles or papers for this question? A general answer will obviously very vague, because performance depends on so many factors. However, based on my understanding, in processors that do

I'm writing a large number of small datasets to an HDF5 file, and the resulting filesize is about 10x what I would expect from a naive tabulation of the data I'm putting in. My data is organized hierarchically as follows: group 0 -> subgroup 0 -> dataset (dimensions: 100 x 4, datatype: float) -> dataset (dimensions: 100, datatype: float) -> subgroup 1 -> dataset (dimensions: 100 x 4, datatype: float) -> dataset (dimensions: 100, datatype: float) ... group 1 ... Each subgroup should take up 500 * 4 Bytes = 2000 Bytes, ignoring overhead. I don't store any attributes alongside the data. Yet, in

Is there a built-in function in scipy/numpy for getting the PMF of a Multinomial? I'm not sure if binom generalizes in the correct way, e.g. # Attempt to define multinomial with n = 10, p = [0.1, 0.1, 0.8] rv = scipy.stats.binom(10, [0.1, 0.1, 0.8]) # Score the outcome 4, 4, 2 rv.pmf([4, 4, 2]) What is the correct way to do this? thanks. There's no built-in function that I know of, and the binomial probabilities do not generalize (you need to normalise over a different set of possible outcomes, since the sum of all the counts must be n which won't be taken care of by independent binomials).

I have to do calculation on array of 1,2,3...9 dimensional vectors, and the number of those vectors varies significantly (say from 100 to up to couple of millions). Of course, it would be great if the data container can be easily decomposed to enable parallel algorithms. I came across blitz++(almost impossible to compile for me), but are there any other fast libs that manipulate array of vector data? Is boost::fusion worth a look? Furthermore, vtk's vtkDoubleArray seems nice, but vtk is lib used only for visualization. I must admit that having array of tuples is a tempting idea, but I didn't