ó áp7]c@ s»ddlmZddlZddlmZddlmZd„Z dd„Z dd„Z ej d„Zie d 6e d 6ed 6Zd „Zejd jeejƒƒƒf;_dS(iÿÿÿÿ(tdivisionN(tscoreatpercentile(tkernelscC sKd}t|dƒt|dƒ|}tjtj|ddddƒ|ƒS(sŠ Returns the smaller of std(X, ddof=1) or normalized IQR(X) over axis 0. References ---------- Silverman (1986) p.47 g/Ý$•õ?iKitaxisitddofi(tsaptnptminimumtstd(tXt normalizetIQR((sClib/python2.7/site-packages/statsmodels/nonparametric/bandwidths.pyt _select_sigmas  cC s(t|ƒ}t|ƒ}d||dS(s* Scott's Rule of Thumb Parameters ---------- x : array-like Array for which to get the bandwidth kernel : CustomKernel object Unused Returns ------- bw : float The estimate of the bandwidth Notes ----- Returns 1.059 * A * n ** (-1/5.) where :: A = min(std(x, ddof=1), IQR/1.349) IQR = np.subtract.reduce(np.percentile(x, [75,25])) References ---------- Scott, D.W. (1992) Multivariate Density Estimation: Theory, Practice, and Visualization. g‹lçû©ñð?gš™™™™™É¿(R tlen(txtkerneltAtn((sClib/python2.7/site-packages/statsmodels/nonparametric/bandwidths.pytbw_scotts  cC s(t|ƒ}t|ƒ}d||dS(s÷ Silverman's Rule of Thumb Parameters ---------- x : array-like Array for which to get the bandwidth kernel : CustomKernel object Unused Returns ------- bw : float The estimate of the bandwidth Notes ----- Returns .9 * A * n ** (-1/5.) where :: A = min(std(x, ddof=1), IQR/1.349) IQR = np.subtract.reduce(np.percentile(x, [75,25])) References ---------- Silverman, B.W. (1986) `Density Estimation.` gÍÌÌÌÌÌì?gš™™™™™É¿(R R (RRRR((sClib/python2.7/site-packages/statsmodels/nonparametric/bandwidths.pyt bw_silverman9s  cC s1|j}t|ƒ}t|ƒ}|||dS(sQ Plug-in bandwidth with kernel specific constant based on normal reference. This bandwidth minimizes the mean integrated square error if the true distribution is the normal. This choice is an appropriate bandwidth for single peaked distributions that are similar to the normal distribution. Parameters ---------- x : array-like Array for which to get the bandwidth kernel : CustomKernel object Used to calculate the constant for the plug-in bandwidth. Returns ------- bw : float The estimate of the bandwidth Notes ----- Returns C * A * n ** (-1/5.) where :: A = min(std(x, ddof=1), IQR/1.349) IQR = np.subtract.reduce(np.percentile(x, [75,25])) C = constant from Hansen (2009) When using a Gaussian kernel this is equivalent to the 'scott' bandwidth up to two decimal places. This is the accuracy to which the 'scott' constant is specified. References ---------- Silverman, B.W. (1986) `Density Estimation.` Hansen, B.E. (2009) `Lecture Notes on Nonparametrics.` gš™™™™™É¿(tnormal_reference_constantR R (RRtCRR((sClib/python2.7/site-packages/statsmodels/nonparametric/bandwidths.pytbw_normal_referenceZs&   tscottt silvermantnormal_referencecC s<|jƒ}|tkr+td|ƒ‚nt|||ƒS(sš Selects bandwidth for a selection rule bw this is a wrapper around existing bandwidth selection rules Parameters ---------- x : array-like Array for which to get the bandwidth bw : string name of bandwidth selection rule, currently supported are: %s kernel : not used yet Returns ------- bw : float The estimate of the bandwidth sBandwidth %s not understood(tlowertbandwidth_funcst ValueError(RtbwR((sClib/python2.7/site-packages/statsmodels/nonparametric/bandwidths.pytselect_bandwidth’s  s, (t __future__RtnumpyRt scipy.statsRRt!statsmodels.sandbox.nonparametricRR tNoneRRtGaussianRRRt__doc__tjointsortedtkeys(((sClib/python2.7/site-packages/statsmodels/nonparametric/bandwidths.pyts   ! !1