Re: [Numpy-discussion] simulate AR

2011-10-14 Thread josef . pktd
On Fri, Oct 14, 2011 at 2:59 PM, wrote: > On Fri, Oct 14, 2011 at 2:29 PM,   wrote: >> On Fri, Oct 14, 2011 at 2:18 PM, Alan G Isaac wrote: >>> On 10/14/2011 1:42 PM, josef.p...@gmail.com wrote: If I remember correctly, signal.lfilter doesn't require stationarity, but handling of the s

Re: [Numpy-discussion] simulate AR

2011-10-14 Thread josef . pktd
On Fri, Oct 14, 2011 at 2:29 PM, wrote: > On Fri, Oct 14, 2011 at 2:18 PM, Alan G Isaac wrote: >> On 10/14/2011 1:42 PM, josef.p...@gmail.com wrote: >>> If I remember correctly, signal.lfilter doesn't require stationarity, >>> but handling of the starting values is a bit difficult. >> >> >> Hmm.

Re: [Numpy-discussion] simulate AR

2011-10-14 Thread josef . pktd
On Fri, Oct 14, 2011 at 2:39 PM, Skipper Seabold wrote: > On Fri, Oct 14, 2011 at 2:18 PM, Alan G Isaac wrote: >> >> On 10/14/2011 1:42 PM, josef.p...@gmail.com wrote: >> > If I remember correctly, signal.lfilter doesn't require stationarity, >> > but handling of the starting values is a bit diff

Re: [Numpy-discussion] simulate AR

2011-10-14 Thread Skipper Seabold
On Fri, Oct 14, 2011 at 2:18 PM, Alan G Isaac wrote: > > On 10/14/2011 1:42 PM, josef.p...@gmail.com wrote: > > If I remember correctly, signal.lfilter doesn't require stationarity, > > but handling of the starting values is a bit difficult. > > > Hmm.  Yes. > AR(1) is trivial, but how do you hand

Re: [Numpy-discussion] simulate AR

2011-10-14 Thread josef . pktd
On Fri, Oct 14, 2011 at 2:18 PM, Alan G Isaac wrote: > On 10/14/2011 1:42 PM, josef.p...@gmail.com wrote: >> If I remember correctly, signal.lfilter doesn't require stationarity, >> but handling of the starting values is a bit difficult. > > > Hmm.  Yes. > AR(1) is trivial, but how do you handle h

Re: [Numpy-discussion] simulate AR

2011-10-14 Thread Alan G Isaac
On 10/14/2011 1:42 PM, josef.p...@gmail.com wrote: > If I remember correctly, signal.lfilter doesn't require stationarity, > but handling of the starting values is a bit difficult. Hmm. Yes. AR(1) is trivial, but how do you handle higher orders? Thanks, Alan ___

Re: [Numpy-discussion] simulate AR

2011-10-14 Thread josef . pktd
On Fri, Oct 14, 2011 at 1:26 PM, Alan G Isaac wrote: >>> Assuming stationarity ... > > On 10/14/2011 1:22 PM, josef.p...@gmail.com wrote: >> maybe ? > > I just meant that the MA approximation is > not reliable for a non-stationary AR. > E.g., http://www.jstor.org/stable/2348631 section 5: simulat

Re: [Numpy-discussion] simulate AR

2011-10-14 Thread Alan G Isaac
>> Assuming stationarity ... On 10/14/2011 1:22 PM, josef.p...@gmail.com wrote: > maybe ? I just meant that the MA approximation is not reliable for a non-stationary AR. E.g., http://www.jstor.org/stable/2348631 Cheers, Alan ___ NumPy-Discussion maili

Re: [Numpy-discussion] simulate AR

2011-10-14 Thread josef . pktd
On Fri, Oct 14, 2011 at 12:49 PM, Alan G Isaac wrote: > On 10/14/2011 12:21 PM, josef.p...@gmail.com wrote: >> One other way to simulate the AR is to get the (truncated) >> MA-representation, and then convolve can be used > > > Assuming stationarity ... maybe ? If it's integrated, then you need a

Re: [Numpy-discussion] simulate AR

2011-10-14 Thread Alan G Isaac
On 10/14/2011 12:21 PM, josef.p...@gmail.com wrote: > One other way to simulate the AR is to get the (truncated) > MA-representation, and then convolve can be used Assuming stationarity ... Alan ___ NumPy-Discussion mailing list NumPy-Discussion@scipy

Re: [Numpy-discussion] simulate AR

2011-10-14 Thread josef . pktd
On Fri, Oct 14, 2011 at 11:56 AM, Fabrice Silva wrote: > Le vendredi 14 octobre 2011 à 10:49 -0400, josef.p...@gmail.com a > écrit : >> On Fri, Oct 14, 2011 at 10:24 AM, Alan G Isaac wrote: >> > As a simple example, if I have y0 and a white noise series e, >> > what is the best way to produces a

[Numpy-discussion] statistics in python

2011-10-14 Thread Radim
Hi Rense (cross-posting to the numpy mailing list because these guys are awesome), On Oct 13, 10:01 pm, Rense Lange wrote: > I have potentially millions of tuples and > I want to create frequency distributions conditional on the values of > discrete variables v1, v2, ... (e.g. the sums for boys

Re: [Numpy-discussion] simulate AR

2011-10-14 Thread Fabrice Silva
Le vendredi 14 octobre 2011 à 10:49 -0400, josef.p...@gmail.com a écrit : > On Fri, Oct 14, 2011 at 10:24 AM, Alan G Isaac wrote: > > As a simple example, if I have y0 and a white noise series e, > > what is the best way to produces a series y such that y[t] = 0.9*y[t-1] + > > e[t] > > for t=1,2,

Re: [Numpy-discussion] simulate AR

2011-10-14 Thread josef . pktd
On Fri, Oct 14, 2011 at 10:24 AM, Alan G Isaac wrote: > As a simple example, if I have y0 and a white noise series e, > what is the best way to produces a series y such that y[t] = 0.9*y[t-1] + e[t] > for t=1,2,...? > > 1. How can I best simulate an autoregressive process using NumPy? > > 2. With

Re: [Numpy-discussion] yet another indexing question

2011-10-14 Thread Neal Becker
Fabrice Silva wrote: > Le vendredi 14 octobre 2011 à 08:04 -0400, Neal Becker a écrit : >> suppose I have: >> >> In [10]: u >> Out[10]: >> array([[0, 1, 2, 3, 4], >>[5, 6, 7, 8, 9]]) >> >> And I have a vector v: >> v = np.array ((0,1,0,1,0)) >> >> I want to form an output vector which

[Numpy-discussion] simulate AR

2011-10-14 Thread Alan G Isaac
As a simple example, if I have y0 and a white noise series e, what is the best way to produces a series y such that y[t] = 0.9*y[t-1] + e[t] for t=1,2,...? 1. How can I best simulate an autoregressive process using NumPy? 2. With SciPy, it looks like I could do this as e[0] = y0 signal.lfilter((1

Re: [Numpy-discussion] yet another indexing question

2011-10-14 Thread Fabrice Silva
Le vendredi 14 octobre 2011 à 08:04 -0400, Neal Becker a écrit : > suppose I have: > > In [10]: u > Out[10]: > array([[0, 1, 2, 3, 4], >[5, 6, 7, 8, 9]]) > > And I have a vector v: > v = np.array ((0,1,0,1,0)) > > I want to form an output vector which selects items from u where v is th

Re: [Numpy-discussion] yet another indexing question

2011-10-14 Thread Jean-Luc Menut
What about a=arange(len(v)) w=u[v,a] ? ___ NumPy-Discussion mailing list NumPy-Discussion@scipy.org http://mail.scipy.org/mailman/listinfo/numpy-discussion

Re: [Numpy-discussion] yet another indexing question

2011-10-14 Thread Warren Weckesser
On Fri, Oct 14, 2011 at 7:04 AM, Neal Becker wrote: > suppose I have: > > In [10]: u > Out[10]: > array([[0, 1, 2, 3, 4], > [5, 6, 7, 8, 9]]) > > And I have a vector v: > v = np.array ((0,1,0,1,0)) > > I want to form an output vector which selects items from u where v is the > index > of t

[Numpy-discussion] yet another indexing question

2011-10-14 Thread Neal Becker
suppose I have: In [10]: u Out[10]: array([[0, 1, 2, 3, 4], [5, 6, 7, 8, 9]]) And I have a vector v: v = np.array ((0,1,0,1,0)) I want to form an output vector which selects items from u where v is the index of the row of u to be selected. In the above example, I want: w = [0,6,2,8,4

Re: [Numpy-discussion] the difference of np.nan, np.NaN, np.NAN?

2011-10-14 Thread David Cournapeau
On Fri, Oct 14, 2011 at 11:53 AM, Olivier Delalleau wrote: > 2011/10/14 Matthew Brett >> >> Hi, >> >> On Fri, Oct 14, 2011 at 4:33 AM, Chao YUE wrote: >> > Dear all, >> > >> > is there any difference between np.nan, np.NaN and np.NAN? they really >> > confuse me >> > they are all Not a Numbe

Re: [Numpy-discussion] the difference of np.nan, np.NaN, np.NAN?

2011-10-14 Thread Olivier Delalleau
2011/10/14 Matthew Brett > Hi, > > On Fri, Oct 14, 2011 at 4:33 AM, Chao YUE wrote: > > Dear all, > > > > is there any difference between np.nan, np.NaN and np.NAN? they really > > confuse me > > they are all Not a Number? > > > > In [75]: np.nan==np.NaN > > Out[75]: False > > > > In [77]: n

Re: [Numpy-discussion] the difference of np.nan, np.NaN, np.NAN?

2011-10-14 Thread Chao YUE
good answer 2011/10/14 Matthew Brett > Hi, > > On Fri, Oct 14, 2011 at 4:33 AM, Chao YUE wrote: > > Dear all, > > > > is there any difference between np.nan, np.NaN and np.NAN? they really > > confuse me > > they are all Not a Number? > > > > In [75]: np.nan==np.NaN > > Out[75]: False >

Re: [Numpy-discussion] the difference of np.nan, np.NaN, np.NAN?

2011-10-14 Thread Matthew Brett
Hi, On Fri, Oct 14, 2011 at 4:33 AM, Chao YUE wrote: > Dear all, > > is there any difference between np.nan, np.NaN and np.NAN? they really > confuse me > they are all Not a Number? > > In [75]: np.nan==np.NaN > Out[75]: False > > In [77]: np.NaN==np.NAN > Out[77]: False The nan value is not

[Numpy-discussion] the difference of np.nan, np.NaN, np.NAN?

2011-10-14 Thread Chao YUE
Dear all, is there any difference between np.nan, np.NaN and np.NAN? they really confuse me they are all Not a Number? In [75]: np.nan==np.NaN Out[75]: False In [77]: np.NaN==np.NAN Out[77]: False Thanks a lot, Chao -- *

Re: [Numpy-discussion] the axis parameter in the np.ma.concatenate is not working?

2011-10-14 Thread Chao YUE
Thanks Josef, you're right. Could you explain me what's the difference between In [4]: a=np.arange(10) In [5]: a.shape Out[5]: (10,) and In [6]: a=np.arange(10).reshape(10,1) In [7]: a.shape Out[7]: (10, 1) (10) means the first a is only a one-dimensional ndarray, but the (10,1) means the s