[SciPy-User] Strange behaviour from corrcoef when calculating correlation-matrix in SciPy/NumPy.
Wed Mar 2 13:36:18 CST 2011
On Wed, Mar 2, 2011 at 2:28 PM, Pauli Virtanen <email@example.com> wrote:
> On Wed, 02 Mar 2011 14:06:23 -0500, josef.pktd wrote:
>> I also found it a bit strange that corrcoef(x,y) creates the stacked
>> version. scipy.stats.spearmanr inherits this behavior since I rewrote
>> it. scipy.stats.pearsonr hasn't been rewritten yet.
>> It didn't bug me enough, to figure out whether there is a reason for
>> this stacking behavior or not.
> The Matlab convention
> corrcoef(x, y) == corrcoef(c_[x.ravel(), y.ravel()])
I don't remember matlab exactly, but I don't think there is a ravel,
and I think R also does
cov(x, y) = np.dot((x-x.mean()).T, y-y.mean())
and normalized for corrcoef.
just getting the off-diagonal block of the matrix, x'y, instead of
also x'x and y'y
> is actually also a bit peculiar if you haven't seen it before -- how come
> there are now two variables, if x had variables on the rows (why not bail
> out with an error?).
> I don't typically deal with stuff that requires these functions, so I
> don't have an opinion, but it would have been better to do the same thing
> even if there is no real reason for it...
> Pauli Virtanen
> SciPy-User mailing list
More information about the SciPy-User