ó áp7]c@s-dZddlmZddlmZddlZddlmZddl j Z ddl j ZddlmZmZddlmZmZmZddlmZmZdd lmZd d gZd d gZd ZeeedƒZeeƒd ZeeeƒZdd„Z!dd„Z"d„Z#d„Z$d„Z%d„Z&d„Z'd„Z(d„Z)d dgZ*d dgZ+d d gZ,d d dgZ-d dgZ.e/de)fde(fde'fd e'fgƒZ0de+e,ffde+e-ffde*e,ffd e*e.ffgZ1xÞe1D]Ö\Z2Z3e3\ZZe4d ƒe4e2eeƒeeed!dƒZ5eeed!dƒZ6e2d" d#kr•e0e2eƒZ7ne0e2eeƒZ7e4e5d$ ƒe4e7d$ ƒee5e7dƒee6e7e7ddƒqWd%d d&„Z8dd'„Z9d(d)„Z:d*„Z;e<e$e<dd+„Z=e8ƒZ>ee>dƒZ?e?j@d3ƒZAe4eAdƒee>dƒZBee>dd-eCƒZDe9e>dƒZEe9e>de>djFƒƒZGe4eBd ƒe4eDd ƒe4eEd ƒe4eGd ƒed dgd gd.ƒZe4eeƒd/ ƒe4ejHjIedƒƒe jJeƒe jKƒe=e eeƒe jKƒe=e eed0eCƒe jKƒee eBd/ ejLeMeBd/ ƒƒd0e<ƒe jKƒe jNd1ƒZOeeOeBd/ d0e<ƒe jNd2ƒZOeeOeBd/ ejLeMeBd/ ƒƒd0eCƒdS(4sštrying to verify theoretical acf of arma explicit functions for autocovariance functions of ARIMA(1,1), MA(1), MA(2) plus 3 functions from nitime.utils iÿÿÿÿ(tprint_function(trangeN(tassert_array_almost_equal(tarma_generate_sampletarma_impulse_response(t arma_acovftarma_acftARIMA(tacftacovf(tplotacfgð?g333333ã¿gš™™™™™Ù?tiˆi cCs<|dks|dkr"t|ƒS|dkr8t|ƒSdS(Ntconstanttlinear(tNonet detrend_meantdetrend_linear(txtkey((sClib/python2.7/site-packages/statsmodels/sandbox/tsa/example_arma.pytdetrend&s  icCs^tj|ƒ}|rMtdƒg|}|jtjƒ||j|ƒ|S||j|ƒS(s0Return x minus its mean along the specified axisN(tnptasarraytsliceRtappendtnewaxistmean(Rtaxistind((sClib/python2.7/site-packages/statsmodels/sandbox/tsa/example_arma.pytdemean,s cCs||jƒS(sReturn x minus the mean(x)(R(R((sClib/python2.7/site-packages/statsmodels/sandbox/tsa/example_arma.pyR5scCs|S(sReturn x: no detrending((R((sClib/python2.7/site-packages/statsmodels/sandbox/tsa/example_arma.pyt detrend_none9scCsrtjt|ƒdtjƒ}tj||ddƒ}|d|d}|jƒ||jƒ}||||S(s2Return y minus best fit line; 'linear' detrending tdtypetbiasii(ii(ii(Rtarangetlentfloat_tcovR(tyRtCtbta((sClib/python2.7/site-packages/statsmodels/sandbox/tsa/example_arma.pyR=s cCsMt||ƒ}gtdƒD]'}tj||| |||!ƒ^q}|S(s6add correlation of MA representation explicitely i (RRRtdot(tartmatnobstirttt acovfexpl((sClib/python2.7/site-packages/statsmodels/sandbox/tsa/example_arma.pytacovf_explicitFs:cCs¦|d }|d}d|dd||d|dg}|jd||||d|dƒx/tdƒD]!}|d}|j||ƒqtWtj|ƒS(Nigð?iiiÿÿÿÿ(RRRtarray(R)R*R'R&trhot_tlast((sClib/python2.7/site-packages/statsmodels/sandbox/tsa/example_arma.pyt acovf_arma11Ns  )) cCsa|d }|d }tjdƒ}d|d|d|d<| |||d<| |d<|S(Niii i(Rtzeros(R*tb1tb2R1((sClib/python2.7/site-packages/statsmodels/sandbox/tsa/example_arma.pyt acovf_ma2as   cCs;|d }tjdƒ}d|d|d<| |d<|S(Nii ii(RR5(R*R&R1((sClib/python2.7/site-packages/statsmodels/sandbox/tsa/example_arma.pyt acovf_ma1ps   gš™™™™™é¿gg333333ã?tma1tma2tarma11tar1R+iR*iicCsütjddddgƒ}tjjd|d|dƒ}tj|ƒ}t|ƒ}xGt|ƒD]9}||tj|| ddd…|| ƒ|||j ddƒ|j d d ƒ|j | | |\} d } | | | | fS( s call signature:: def xcorr(self, x, y, normed=True, detrend=detrend_none, usevlines=True, maxlags=10, **kwargs): Plot the cross correlation between *x* and *y*. If *normed* = *True*, normalize the data by the cross correlation at 0-th lag. *x* and y are detrended by the *detrend* callable (default no normalization). *x* and *y* must be equal length. Data are plotted as ``plot(lags, c, **kwargs)`` Return value is a tuple (*lags*, *c*, *line*) where: - *lags* are a length ``2*maxlags+1`` lag vector - *c* is the ``2*maxlags+1`` auto correlation vector - *line* is a :class:`~matplotlib.lines.Line2D` instance returned by :func:`~matplotlib.pyplot.plot`. The default *linestyle* is *None* and the default *marker* is 'o', though these can be overridden with keyword args. The cross correlation is performed with :func:`numpy.correlate` with *mode* = 2. If *usevlines* is *True*: :func:`~matplotlib.pyplot.vlines` rather than :func:`~matplotlib.pyplot.plot` is used to draw vertical lines from the origin to the xcorr. Otherwise the plotstyle is determined by the kwargs, which are :class:`~matplotlib.lines.Line2D` properties. The return value is a tuple (*lags*, *c*, *linecol*, *b*) where *linecol* is the :class:`matplotlib.collections.LineCollection` instance and *b* is the *x*-axis. *maxlags* is a positive integer detailing the number of lags to show. The default value of *None* will return all ``(2*len(x)-1)`` lags. **Example:** :func:`~matplotlib.pyplot.xcorr` above, and :func:`~matplotlib.pyplot.acorr` below. **Example:** .. plot:: mpl_examples/pylab_examples/xcorr_demo.py sx and y must be equal lengthRWiis.maxlags must be None or strictly positive < %ditmarkertot linestyleRN( R!t ValueErrorRRRUtsqrtR(RR tvlinestaxhlinet setdefaulttplot(RZRR$tnormedRt usevlinestmaxlagsR[tNxtctlagsR'R&td((sClib/python2.7/site-packages/statsmodels/sandbox/tsa/example_arma.pytpltxcorrs48 2  itunbiasediôiRgiÓiÔ(iii(Pt__doc__t __future__Rtstatsmodels.compat.pythonRtnumpyRt numpy.testingRtmatplotlib.pyplottpyplottplttstatsmodels.apitapitsmtstatsmodels.tsa.arima_processRRRRRtstatsmodels.tsa.stattoolsRR tstatsmodels.graphics.tsaplotsR R)R*tmodRtx_acftx_irRRRRRRR/R4R8R9R=tar0R:R;tma0tdictt comparefntcasesRjtargstprinttmyacovftmyacftothacovfRIRSRXR\tTrueRmtarrvstarmatfittrestacf1tFalsetacovf1btacf2Rtacf2mt regressiont yule_walkerRetfigureR R!tsubplottax(((sClib/python2.7/site-packages/statsmodels/sandbox/tsa/example_arma.pytsª                     >_     -