p7]c@s$dZddlmZmZmZmZddlZddlZ ddl m Z ddl m Z mZmZddlmZddlmZddlmZdd lmZdd lmZdd lmZd d lmZmZmZm Z m!Z!dddddddddddddddddgZ"dZ#dd d!Z$ddd"Z&dd#Z'd$Z(die)ide*d%Z+dddd&Z,dd'Z-dddd(Z.ddddddd)Z/e)d*d+d,d-dd.Z0e j1id/d06e0_e)d*d+d,d-dd1Z2e j1id2d06e2_d*dd3Z3e!j1id/d06e3_d*dd4Z4e!j1id2d06e4_de)ddd5Z5eid6d06e5_dd7Z6eid6d06e6_d8ddd9Z7eid6d06e7_d8dd:Z8d;Z9de)dd<Z:dS(=sPartial Regression plot and residual plots to find misspecification Author: Josef Perktold License: BSD-3 Created: 2011-01-23 update 2011-06-05 : start to convert example to usable functions 2011-10-27 : docstrings i(tlranget string_typestlziptrangeN(tdmatrix(tOLStGLStWLS(tGLM(tGEE(twls_prediction_std(tutils(tlowess(tmaybe_unwrap_resultsi(t_plot_added_variable_doct_plot_partial_residuals_doct_plot_ceres_residuals_doct_plot_influence_doct_plot_leverage_resid2_doctplot_fittplot_regress_exogtplot_partregresst plot_ccprtplot_partregress_gridtplot_ccpr_gridt add_lowesst abline_plottinfluence_plottplot_leverage_resid2tadded_variable_residstpartial_residst ceres_residstplot_added_variabletplot_partial_residualstplot_ceres_residualscCsd|jd|jS(Ng@i(tdf_modeltnobs(tresults((sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyt_high_leverage)sig?cKs~|j|j}|j|j}t||d||}|j|dddf|dddfddd|jS(s Add Lowess line to a plot. Parameters ---------- ax : matplotlib Axes instance The Axes to which to add the plot lines_idx : int This is the line on the existing plot to which you want to add a smoothed lowess line. frac : float The fraction of the points to use when doing the lowess fit. lowess_kwargs Additional keyword arguments are passes to lowess. Returns ------- fig : matplotlib Figure instance The figure that holds the instance. tfracNiitrtlwg?(t get_linest_yt_xR tplottfigure(taxt lines_idxR't lowess_kwargsty0tx0tlres((sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyR.s 9c Kstj|\}}tj||j\}}t|}|jj}|jjdd|f}tj|} || }|| }|j ||dd|jj |dk r|j ||| dddnd|} t |\} } } |j ||j | ddd dd ||j|| | | | d d dd dd|j| |j||j|jj |jdddd |S(sPlot fit against one regressor. This creates one graph with the scatterplot of observed values compared to fitted values. Parameters ---------- results : result instance result instance with resid, model.endog and model.exog as attributes x_var : int or str Name or index of regressor in exog matrix. y_true : array_like (optional) If this is not None, then the array is added to the plot ax : Matplotlib AxesSubplot instance, optional If given, this subplot is used to plot in instead of a new figure being created. kwargs The keyword arguments are passed to the plot command for the fitted values points. Returns ------- fig : Matplotlib figure instance If `ax` is None, the created figure. Otherwise the figure to which `ax` is connected. Examples -------- Load the Statewide Crime data set and perform linear regression with `poverty` and `hs_grad` as variables and `murder` as the response >>> import statsmodels.api as sm >>> import matplotlib.pyplot as plt >>> data = sm.datasets.statecrime.load_pandas().data >>> murder = data['murder'] >>> X = data[['poverty', 'hs_grad']] >>> X["constant"] = 1 >>> y = murder >>> model = sm.OLS(y, X) >>> results = model.fit() Create a plot just for the variable 'Poverty': >>> fig, ax = plt.subplots() >>> fig = sm.graphics.plot_fit(results, 0, ax=ax) >>> ax.set_ylabel("Murder Rate") >>> ax.set_xlabel("Poverty Level") >>> ax.set_title("Linear Regression") >>> plt.show() .. plot:: plots/graphics_plot_fit_ex.py Ntbotlabelsb-s True valuessFitted values versus %stDtcolorR(tfittedt linewidthitktalphagffffff?tloctbestt numpoints(R t create_mpl_axtmaybe_name_or_idxtmodelR tendogtexogtnptargsortR-t endog_namestNoneR t fittedvaluestvlinest set_titlet set_xlabelt set_ylabeltlegend(R%texog_idxty_trueR/tkwargstfigt exog_nametytx1t x1_argsortttitletprstdtiv_ltiv_u((sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyRJs,:        &  c Cstj|}tj||j\}}t|}|jj}|jjdd|f}t|\}}}|jddd} | j ||jj dddddd || j ||j d dd d d dd | j |||dddddd| j ddd| j|| j|| jdd|jddd} | j ||jd| jdddd| j d|dd| j|| jd|jddd} tj|jjjdt} t| |<|jjdd| f} ddlm} t|jjj| |d|d|jjj| d td!| }| j d"dd|jddd#} t||d!| }| j d$dd|jd%|dd|j |j!d&d|S('ssPlot regression results against one regressor. This plots four graphs in a 2 by 2 figure: 'endog versus exog', 'residuals versus exog', 'fitted versus exog' and 'fitted plus residual versus exog' Parameters ---------- results : result instance result instance with resid, model.endog and model.exog as attributes exog_idx : int or str Name or index of regressor in exog matrix fig : Matplotlib figure instance, optional If given, this figure is simply returned. Otherwise a new figure is created. Returns ------- fig : matplotlib figure instance Examples -------- Load the Statewide Crime data set and build a model with regressors including the rate of high school graduation (hs_grad), population in urban areas (urban), households below poverty line (poverty), and single person households (single). Outcome variable is the muder rate (murder). Build a 2 by 2 figure based on poverty showing fitted versus actual murder rate, residuals versus the poverty rate, partial regression plot of poverty, and CCPR plot for poverty rate. >>> import statsmodels.api as sm >>> import matplotlib.pyplot as plot >>> import statsmodels.formula.api as smf >>> fig = plt.figure(figsize=(8, 6)) >>> crime_data = sm.datasets.statecrime.load_pandas() >>> results = smf.ols('murder ~ hs_grad + urban + poverty + single', ... data=crime_data.data).fit() >>> sm.graphics.plot_regress_exog(results, 'poverty', fig=fig) >>> plt.show() .. plot:: plots/graphics_regression_regress_exog.py NiitoR8tbR<g?R6R7R(R9g?R:R;gffffff?sY and Fitted vs. XtfontsizetlargeR=R>RTitblacksResiduals versus %stresidii(tSeriestnametindext obs_labelsR/sPartial regression plotis CCPR PlotsRegression Plots for %sttop("R tcreate_mpl_figRARBR RGRDR t add_subplotR-RCRIRJRKRLRMRNR`taxhlineREtonestshapetbooltFalsetpandasRaRtdatat orig_endogt row_labelsRtsuptitlet tight_layouttsubplots_adjust( R%RORRRSty_nameRURXRYRZR/t exog_notit exog_othersRa((sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyRsL/  +!%      cCsUt||j}t||j}t|j|jj}|||ffS(sPartial regression. regress endog on exog_i conditional on exog_others uses OLS Parameters ---------- endog : array_like exog : array_like exog_others : array_like Returns ------- res1c : OLS results instance (res1a, res1b) : tuple of OLS results instances results from regression of endog on exog_others and of exog_i on exog_others (RtfitR`(RCtexog_iRvtres1atres1btres1c((sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyt_partial_regression sc  Kstj|\} }t|tr:t|d|}nt|tr[t||} n6t|trdj|} t| |} n|} t} t| tj r| j dkrt } n$t| t j r| jrt } nt|tr t|d|}n| r|j||d| t||j} t|tj rSdn|j}t|tj rtdn |jjd}nt|| j}t|| j}|j}|j}|jj}|jj}|j||d| t||j} td| jdddd |} |dkr=d}n|jd ||jd ||jd ||t kr|dk r|j}n*t|d r|j}n|jj j!}|dkrt"t#|}qn|tk rt#|t#|krt$d n|j%t&ddddtj't"t#||t(|j|jdgt#|dd ||}n|r| |j|jffS| SdS(s Plot partial regression for a single regressor. Parameters ---------- endog : ndarray or string endogenous or response variable. If string is given, you can use a arbitrary translations as with a formula. exog_i : ndarray or string exogenous, explanatory variable. If string is given, you can use a arbitrary translations as with a formula. exog_others : ndarray or list of strings other exogenous, explanatory variables. If a list of strings is given, each item is a term in formula. You can use a arbitrary translations as with a formula. The effect of these variables will be removed by OLS regression. data : DataFrame, dict, or recarray Some kind of data structure with names if the other variables are given as strings. title_kwargs : dict Keyword arguments to pass on for the title. The key to control the fonts is fontdict. obs_labels : bool or array-like Whether or not to annotate the plot points with their observation labels. If obs_labels is a boolean, the point labels will try to do the right thing. First it will try to use the index of data, then fall back to the index of exog_i. Alternatively, you may give an array-like object corresponding to the obseveration numbers. labels_kwargs : dict Keyword arguments that control annotate for the observation labels. ax : Matplotlib AxesSubplot instance, optional If given, this subplot is used to plot in instead of a new figure being created. ret_coords : bool If True will return the coordinates of the points in the plot. You can use this to add your own annotations. kwargs The keyword arguments passed to plot for the points. Returns ------- fig : Matplotlib figure instance If `ax` is None, the created figure. Otherwise the figure to which `ax` is connected. coords : list, optional If ret_coords is True, return a tuple of arrays (x_coords, y_coords). Notes ----- The slope of the fitted line is the that of `exog_i` in the full multiple regression. The individual points can be used to assess the influence of points on the estimated coefficient. See Also -------- plot_partregress_grid : Plot partial regression for a set of regressors. Examples -------- Load the Statewide Crime data set and plot partial regression of the rate of high school graduation (hs_grad) on the murder rate(murder). The effects of the percent of the population living in urban areas (urban), below the poverty line (poverty) , and in a single person household (single) are removed by OLS regression. >>> import statsmodels.api as sm >>> import matplotlib.pyplot as plt >>> crime_data = sm.datasets.statecrime.load_pandas() >>> sm.graphics.plot_partregress(endog='murder', exog_i='hs_grad', ... exog_others=['urban', 'poverty', 'single'], ... data=crime_data.data, obs_labels=False) >>> plt.show() .. plot:: plots/graphics_regression_partregress.py More detailed examples can be found in the Regression Plots notebook on the examples page. s-1t+iR[txRTR8R;R/s e(%s | X)sPartial Regression PlotRcs*obs_labels does not match length of exog_ithatcentertvatbottomisx-largeN(ii()R R@t isinstanceRRtlisttjoinRlREtndarraytsizetTruetpdt DataFrametemptyR-RRwRbt design_infot column_namesR`RBRGRtparamsRLRMRKRHRcthasattrRnRpRtlent ValueErrortupdatetdictt annotate_axesR(RCRxRvRnt title_kwargsRdt label_kwargsR/t ret_coordsRQRRtRHSt RHS_isemtpyt fitted_linetx_axis_endog_namety_axis_endog_namet res_yaxist res_xaxist xaxis_residt yaxis_resid((sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyR'slU!  !+    "         c Csddl}tj|}tj||j\}}|j|jjd|jj}|jj}|j d}t |dd} | t |krdnd} |dk r|\} } n| dkriidd6d6} nt j |jj} xt|D]\} }t|}|j||j|dd|fd | |}|j| | | d}t||j|dd|fd| ||d |d | d t|jd qW|jddd|j|jdd|S(sPlot partial regression for a set of regressors. Parameters ---------- results : results instance A regression model results instance exog_idx : None, list of ints, list of strings (column) indices of the exog used in the plot, default is all. grid : None or tuple of int (nrows, ncols) If grid is given, then it is used for the arrangement of the subplots. If grid is None, then ncol is one, if there are only 2 subplots, and the number of columns is two otherwise. fig : Matplotlib figure instance, optional If given, this figure is simply returned. Otherwise a new figure is created. Returns ------- fig : Matplotlib figure instance If `fig` is None, the created figure. Otherwise `fig` itself. Notes ----- A subplot is created for each explanatory variable given by exog_idx. The partial regression plot shows the relationship between the response and the given explanatory variable after removing the effect of all other explanatory variables in exog. See Also -------- plot_partregress : Plot partial regression for a single regressor. plot_ccpr : Plot CCPR against one regressor Examples -------- Using the state crime dataset seperately plot the effect of the each variable on the on the outcome, murder rate while accounting for the effect of all other variables in the model visualized with a grid of partial regression plots. >>> from statsmodels.graphics.regressionplots import plot_partregress_grid >>> import statsmodels.api as sm >>> import matplotlib.pyplot as plt >>> import statsmodels.formula.api as smf >>> fig = plt.figure(figsize=(8, 6)) >>> crime_data = sm.datasets.statecrime.load_pandas() >>> results = smf.ols('murder ~ hs_grad + urban + poverty + single', ... data=crime_data.data).fit() >>> plot_partregress_grid(results, fig=fig) >>> plt.show() .. plot:: plots/graphics_regression_partregress_grid.py References ---------- See http://www.itl.nist.gov/div898/software/dataplot/refman1/auxillar/partregr.htm iNRbiitsmallR]tfontdicttcolumnsR/RRdtsPartial Regression PlotR^Regffffff?(RmR RfRARBRaRCRGRDRjRRHREtarrayt exog_namest enumerateRtpopRRgRRlRKRqRrRs(R%ROtgridRRRmRSRTRDtk_varstnrowstncolsRt other_namestitidxtothersRvR/((sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyRs8< !       "  c Cstj|\}}tj||j\}}t|}|jjdd|f}||j|}|j|||jdddl m }t |||j }|j} t | td|}|jd|jd||f|jd||S( sPlot CCPR against one regressor. Generates a CCPR (component and component-plus-residual) plot. Parameters ---------- results : result instance A regression results instance. exog_idx : int or string Exogenous, explanatory variable. If string is given, it should be the variable name that you want to use, and you can use arbitrary translations as with a formula. ax : Matplotlib AxesSubplot instance, optional If given, it is used to plot in instead of a new figure being created. Returns ------- fig : Matplotlib figure instance If `ax` is None, the created figure. Otherwise the figure to which `ax` is connected. See Also -------- plot_ccpr_grid : Creates CCPR plot for multiple regressors in a plot grid. Notes ----- The CCPR plot provides a way to judge the effect of one regressor on the response variable by taking into account the effects of the other independent variables. The partial residuals plot is defined as Residuals + B_i*X_i versus X_i. The component adds the B_i*X_i versus X_i to show where the fitted line would lie. Care should be taken if X_i is highly correlated with any of the other independent variables. If this is the case, the variance evident in the plot will be an underestimate of the true variance. Examples -------- Using the state crime dataset plot the effect of the rate of single households ('single') on the murder rate while accounting for high school graduation rate ('hs_grad'), percentage of people in an urban area, and rate of poverty ('poverty'). >>> import statsmodels.api as sm >>> import matplotlib.pyplot as plot >>> import statsmodels.formula.api as smf >>> crime_data = sm.datasets.statecrime.load_pandas() >>> results = smf.ols('murder ~ hs_grad + urban + poverty + single', ... data=crime_data.data).fit() >>> sm.graphics.plot_ccpr(results, 'single') >>> plt.show() .. plot:: plots/graphics_regression_ccpr.py References ---------- http://www.itl.nist.gov/div898/software/dataplot/refman1/auxillar/ccpr.htm NR[i(t add_constantR/s*Component and component plus residual plotsResidual + %s*beta_%ds%s(R R@RARBR RDRR-R`tstatsmodels.tools.toolsRRRwRRRKRMRL( R%ROR/RRRSRUtx1betaRtmodR((sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyR.s?   c Cs[tj|}tj||j\}}|dk rE|\}}nLt|dkrttjt|d}d}nt|}d}d}xt |D]\}} |jj dd| fj dkrd}qn|j |||d|} t |d| d| }| jdqW|jd d d |j|jd d |S(sGenerate CCPR plots against a set of regressors, plot in a grid. Generates a grid of CCPR (component and component-plus-residual) plots. Parameters ---------- results : result instance uses exog and params of the result instance exog_idx : None or list of int (column) indices of the exog used in the plot grid : None or tuple of int (nrows, ncols) If grid is given, then it is used for the arrangement of the subplots. If grid is None, then ncol is one, if there are only 2 subplots, and the number of columns is two otherwise. fig : Matplotlib figure instance, optional If given, this figure is simply returned. Otherwise a new figure is created. Returns ------- fig : Matplotlib figure instance If `ax` is None, the created figure. Otherwise the figure to which `ax` is connected. Notes ----- Partial residual plots are formed as:: Res + Betahat(i)*Xi versus Xi and CCPR adds:: Betahat(i)*Xi versus Xi See Also -------- plot_ccpr : Creates CCPR plot for a single regressor. Examples -------- Using the state crime dataset seperately plot the effect of the each variable on the on the outcome, murder rate while accounting for the effect of all other variables in the model. >>> import statsmodels.api as sm >>> import matplotlib.pyplot as plt >>> import statsmodels.formula.api as smf >>> fig = plt.figure(figsize=(8, 8)) >>> crime_data = sm.datasets.statecrime.load_pandas() >>> results = smf.ols('murder ~ hs_grad + urban + poverty + single', ... data=crime_data.data).fit() >>> sm.graphics.plot_ccpr_grid(results, fig=fig) >>> plt.show() .. plot:: plots/graphics_regression_ccpr_grid.py References ---------- See http://www.itl.nist.gov/div898/software/dataplot/refman1/auxillar/ccpr.htm ig@iiNROR/Rs&Component-Component Plus Residual PlotR]R^Regffffff?(R RfRARBRHRtintREtceilRRDtvarRgRRKRqRrRs( R%RORRRRSRRt seen_constantRRR/((sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyRs*>   ( c  s|dk r|j}nd}tj|\}}|r|j\|dkr|jjdddfj|jjdddfjg}qnBdk odk st dn|dkr|j}n|d|dg} |j |ddl m } d| ffdY|| |} |j | |jjd | j| _|jjd | j| _|r|j|n|r|j|n|S( s Plots a line given an intercept and slope. intercept : float The intercept of the line slope : float The slope of the line horiz : float or array-like Data for horizontal lines on the y-axis vert : array-like Data for verterical lines on the x-axis model_results : statsmodels results instance Any object that has a two-value `params` attribute. Assumed that it is (intercept, slope) ax : axes, optional Matplotlib axes instance kwargs Options passed to matplotlib.pyplot.plt Returns ------- fig : Figure The figure given by `ax.figure` or a new instance. Examples -------- >>> import numpy as np >>> import statsmodels.api as sm >>> np.random.seed(12345) >>> X = sm.add_constant(np.random.normal(0, 20, size=30)) >>> y = np.dot(X, [25, 3.5]) + np.random.normal(0, 30, size=30) >>> mod = sm.OLS(y,X).fit() >>> fig = sm.graphics.abline_plot(model_results=mod) >>> ax = fig.axes[0] >>> ax.scatter(X[:,1], y) >>> ax.margins(.1) >>> import matplotlib.pyplot as plt >>> plt.show() .. plot:: plots/graphics_regression_abline.py Nis-specify slope and intercepty or model_resultsii(tLine2DtABLine2Dcs8eZfdZfdZfdZRS(cs/t|j||d|_d|_dS(N(tsupert__init__RHtid_xlim_callbacktid_ylim_callback(tselftargsRQ(R(sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyR&s cs^|j}|jr(|jj|jn|jrG|jj|jnt|jdS(N(taxesRt callbackst disconnectRRtremove(RR/(R(sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyR+s    cs|jt|j}g|D]}||kr |^q }|d}|j}|d|dg}|j|||jjjdS(Nii(tset_autoscale_onRlt get_childrentget_xlimtset_dataR.tcanvastdraw(RR/tchildrentchildtablinestablineR~RT(t intercepttslope(sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pytupdate_datalim3s  %  $(t__name__t __module__RRR((RRR(sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyR%st xlim_changedt ylim_changed(RHRR R@RRBRDtmintmaxRtset_xlimtmatplotlib.linesRtadd_lineRtconnectRRRthlinetvline( RRthoriztvertt model_resultsR/RQR~RRtdata_yRtline((RRRsClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyRs4-  + $ " g?tcooksi0g?cKs&|} tj|\} }|jjdr@| jd} n>|jjdrntj| jd} ntd|tj | } |dd} | | j | | d} | j }|r| j }n | j }ddlm}|jjd |d|j}tj||k}|t|k}tj||}|j||d | d ||jjj}|dkrtt|}ntjtj|d|t||t| dd  | dd d |}idd6dd6}|jd||j d||j!d|| S(NtcooitdffsCriterion %s not understoodiii(tstatsg?tsR<g?sx-largeiR]R_R8sStudentized Residualss H LeveragesInfluence Ploti@i@("R R@tlowert startswithtcooks_distanceREtabstdffitsRtptpRthat_matrix_diagtresid_studentized_externaltresid_studentizedtscipyRtttppftdf_residR&t logical_ortscatterRBRnRpRHRRRtwhereRRMRLRK(R%t influencetexternalR<t criterionRt plot_alphaR/RQtinflRRtpsizet old_ranget new_rangetleveragetresidsRtcutofft large_residtlarge_leveraget large_pointstlabelstfont((sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyt_influence_plotJs@        snresults: object Results for a fitted regression model influence: instance instance of Influence for modeltextra_params_docc KsF|j}t||d|d|d|d|d|d||} | S(NRR<RRRR/(t get_influenceR( R%RR<RRRR/RQRtres((sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyRs   s9results: object Results for a fitted regression modelc Ksxddlm}m}tj|\}}|}|j} ||j} |j| d| d||jd|j d|j d| t |k} |j d|d} t j| | k} |jjj}|dkrtt|j}nt jt j| | d }tj||t| d| dgt|jd d |d ddd}|jdd|S(Ni(tzscoretnormiR[sNormalized residuals**2tLeverages)Leverage vs. Normalized residuals squaredg?iiR^R/RRRRg333333?(ii(t scipy.statsR R R R@RR`R-RLRMRKR&RRERRBRnRpRHRRR$RRRRtmargins(R%RR<R/RQR R RRRRR`RRRRRc((sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyt_plot_leverage_resid2s*     cKs.|j}t||dddd|}|S(NR<g?R/(R RRH(R%R<R/RQRR ((sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyRs  c Cs|j}tj|\}}t||d|d|d|\}} |j| |ddd|jddd t|tkr|} n |j|} |j | d d |j |j d d d |S( Nt resid_typetuse_glm_weightst fit_kwargsR[R<g333333?sAdded variable plotR]R^Ris residuals( RBR R@RR-RKttypetstrRRLRMRG( R%t focus_exogRRRR/RBRRt endog_residtfocus_exog_residtxname((sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyR s    s6results: object Results for a fitted regression modelc Cs|j}tj||\}}t||}|jjdd|f}tj|\}}|j||ddd|jdddt|t kr|}n |j |}|j |dd|j d dd|S( NR[R<g333333?sPartial residuals plotR]R^RisComponent plus residual( RBR RARRDR@R-RKRRRRLRM( R%RR/RBt focus_coltprtfocus_exog_valsRRR((sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyR!s   gQ?c Cs|j}tj||\}}t||d|d|}|jdd|f}tj|\} }|j||ddd|jddd|j|d d |j d d d | S( NR't cond_meansR[R<g333333?sCERES residuals plotR]R^RisComponent plus residual( RBR RARRDR@R-RKRLRM( R%RR'RR/RBRtpresidRRR((sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyR"s  cCs|j}t|tttfs:td|jjntj ||\}}t t |j }t |}|j|t |}|dkr|jdd|f}||jd8}tjj|d\} } } tj| dk} | dd| f}|jdd|f} tjt | |jdf}xet |jdD]M}|dd|f}t|| d|dt}||dd|fiR't return_sortedtaxis(#RBRRR RRt __class__RR RARRRRRRHRDtmeanREtlinalgtsvdt flatnonzeroRRjR Rlt concatenatet_get_init_kwdsRCRwRItfamilytlinktderivtdot(R%RR'RRBRtix_nftnnftpexogtuRtvttiitfcoltjR2tcftnew_exogtklasst init_kwargst new_modelt new_resultR((sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyRs@"     ".   6cCs|j}|j|j}t|ttfrP||jjj|j 9}n1t|t t t frknt dt|t|tkr|jj|}n|}|j||jdd|f}||S(s: Returns partial residuals for a fitted model with respect to a 'focus predictor'. Parameters ---------- results : results instance A fitted regression model. focus col : int The column index of model.exog with respect to which the partial residuals are calculated. Returns ------- An array of partial residuals. References ---------- RD Cook and R Croos-Dabrera (1998). Partial residual plots in generalized linear models. Journal of the American Statistical Association, 93:442. s+Partial residuals for '%s' not implemented.N(RBRCtpredictRRR R)R*R+RIRRRRRRRRcRRD(R%RRBR`Rt focus_val((sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyRks $cCsT|j}t|tttfs:td|jjn|j}|j }t j ||\}}|dd|f} |dkrt|ttfrd}qd}nt |jd} t| } | j||dd| f} |j| } |j} |j}| || |}i| d6}|dk rL|j|n|j|}|jsstdnyt||}Wn!tk rtd|nXd dljj}t|ttfr)|r)|jj|j}t|d r ||j}n|j | | |j}n|j| | j}|j!}||fS( sY Residualize the endog variable and a 'focus' exog variable in a regression model with respect to the other exog variables. Parameters ---------- results : regression results instance A fitted model including the focus exog and all other predictors of interest. focus_exog : integer or string The column of results.model.exog or a variable name that is to be residualized against the other predictors. resid_type : string The type of residuals to use for the dependent variable. If None, uses `resid_deviance` for GLM/GEE and `resid` otherwise. use_glm_weights : bool Only used if the model is a GLM or GEE. If True, the residuals for the focus predictor are computed using WLS, with the weights obtained from the IRLS calculations for fitting the GLM. If False, unweighted regression is used. fit_kwargs : dict, optional Keyword arguments to be passed to fit when refitting the model. Returns ------- endog_resid : array-like The residuals for the original exog focus_exog_resid : array-like The residuals for the focus predictor Notes ----- The 'focus variable' residuals are always obtained using linear regression. Currently only GLM, GEE, and OLS models are supported. s8model type %s not supported for added variable residualsNtresid_devianceR`it start_paramss>fit did not converge when calculating added variable residualss '%s' residual type not availableit data_weights("RBRR RRRR"RRDRCR RARHRRjRRRR(RRwt convergedtgetattrtAttributeErrort#statsmodels.regression.linear_modelt regressiont linear_modelR)tweightsRIRR?RR`(R%RRRRRBRDRCRRR2t reduced_exogR>R7RQR9RR:RtlmRFt lm_resultsR((sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyRsN)                (;t__doc__tstatsmodels.compat.pythonRRRRtnumpyRERmRtpatsyRRCRRRt+statsmodels.genmod.generalized_linear_modelRt3statsmodels.genmod.generalized_estimating_equationsR t&statsmodels.sandbox.regression.predstdR tstatsmodels.graphicsR t*statsmodels.nonparametric.smoothers_lowessR RR t_regressionplots_docRRRRRt__all__R&RRHRRR|RRlRRRRRRtformatRRRR R!R"RRR(((sClib/python2.7/site-packages/statsmodels/graphics/regressionplots.pyt sx"  (      Z e  d T^ i4       Y 0