hMh(*dZddlZddlmZddlZddlZddlZddl Z ddl m Z  ddlZesJdZn #e$rdZYnwxYwddlmZddlmZdd lmZmZgd ZGd d ZGd deZedCideddeddeddeddeddeddeddedded d!ed"d#ed$d%ed&d'ed(d)ed*d+ed,d-ed.d/ed0d1ed2d3ed4d5ed6Zeedddddddd7dd8ddddddddddddd9d:dddddddddddddddd;'d<Zed=jdCiee_ dDdddddddd9d:dddddddddddddddd8dddd>d?Z ed@jdCiee _ dDddddddddddddddA dBZ!dS)Ez9Plotting functions for linear models (broadly construed).N)dedentTF)utils) algorithms) FacetGrid _facet_docs)lmplotregplot residplotc$eZdZdZdZdZdZdS)_LinearPlotterzBase class for plotting relational data in tidy format. To get anything useful done you'll have to inherit from this, but setup code that can be abstracted out should be put here. c ||_td|D}|r|td|D]\}}t |t r ||}n,t |trtj |}n|}||j dkrtj |}tj |dkrd}t|t|||dS)z,Extract variables from data or use directly.c8g|]}t|tS) isinstancestr.0vs R/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/seaborn/regression.py z6_LinearPlotter.establish_variables..%s"DDD!:a--DDDNz*Must pass `data` if using named variables.)rrzregplot inputs must be 1d)dataanyvalues ValueErroritemsrrlistnpasarrayshapesqueezendimsetattr)selfrkws any_stringsvarvalvectorerrs restablish_variablesz"_LinearPlotter.establish_variables s DDszz||DDDEE  K4<IJJ J ' 'HC#s## cC&& C!fld&:&:F++wv""1 oo% D#v & & & & ' 'rcfd|D}d|D}tjtjd|Dd}|D]+}t|}|t |||,dS)z&Remove observations with missing data.c0g|]}t|Sr)getattr)rr(r%s rrz)_LinearPlotter.dropna..:s#333sc""333rcg|]}||SNrrs rrz)_LinearPlotter.dropna..;s111a1====rc6g|]}tj|Sr)pdnotnullrs rrz)_LinearPlotter.dropna..<s (E(E(E1A(E(E(ErraxisN)rall column_stackr/r$)r%varsvalsnot_nar(r)s` rdropnaz_LinearPlotter.dropna8s3333d333114111(E(E(E(E(EFFQOOO 0 0C$$$Cc3v;/// 0 0rctr1)NotImplementedError)r%axs rplotz_LinearPlotter.plotBs!!rN)__name__ __module__ __qualname____doc__r,r<r@rrrr r sK '''0000"""""rr ceZdZdZ dd Zed Zed Zd Zdd Z dZ dZ dZ dZ dZdZdZdZdZdZdS)_RegressionPlotterzPlotter for numeric independent variables with regression model. This does the computations and drawing for the `regplot` function, and is thus also used indirectly by `lmplot`. NciT_rFc||_| |_|dkr| n||_| |_| |_||_||_| |_||_||_ ||_ ||_ ||_ ||_ ||_||_||_t#| dk||||fdkrt%d||||| |||r|ddddd |j%||j|j|_|j%||j|j|_|5| t4jn||_||\}}||_n |j|_t=|jdkrd |_|jr9|j|j f|_!dSdS) NrGrz&Mutually exclusive regression options.)xyunits x_partial y_partialrKrLrMrNrOF)" x_estimatorrGx_cin_bootseedscatterfit_regorderlogisticlowessrobustlogxtruncatex_jittery_jittercolorlabelsumrr,r<rN regress_outrKrOrLrmean bin_predictor x_discretelenminmaxx_range)r%rKrLrrPx_binsrQrTrUrGrRrMrSrVrWrXrYrZrNrOr[r<r\r]r^r_rds r__init__z_RegressionPlotter.__init__Ls'$,,BBD                     8VVT: ; ;a ? ?EFF F   au+4  ! K K K  E KKS'; D D D > %%%dfdn==DF > %%%dfdn==DF  *5*=rww;D !%!3!3F!;!; J(DOO"fDO tv;;!   DL < 66::<<5DLLL 6 6rc>|j}||j}n<|jtj| |t |jz}|j}||j}n<|jtj| |t |jz}||fS)z'Data where each observation is a point.)r\rKrrandomuniformrer]rL)r%x_jrKy_jrLs r scatter_dataz_RegressionPlotter.scatter_datasm ;AA**C4c$&kkBBBAm ;AA**C4c$&kkBBBA!t rcX|j|j}}ttj|}gg}}|D]}|||k}||}|||j|dUd} |jdkrtj|} || z || zf} nZ|j |j ||k} tj ||j|j | |j } tj| |j} || |||fS)z>#}}T4:>> D** ] 3 G G G G G G < < < < < <#33D#;C8:: 4 G G D** [ 3B**JD$$ [ 3 B B B B B B#33D#>> D** Y 3#}}T22 D**#}}T22 D* :IIRa888IT9$$rcd}tjtjt|j|jf|j}}tjtjt||f}||||}|j|dfStj ||||j |j |j j }||j }||fS)z9Low-level regression and prediction using linear algebra.cftj||Sr1)rlinalgpinvdot_xr}s rreg_funcz-_RegressionPlotter.fit_fast..reg_funcs$9>>"%%))"-- -rNrs)rc_onesrerKrLrrGryrzrRrMrST)r%rrXrLr beta_bootsrs rrz_RegressionPlotter.fit_fasts . . .uRWS[[))4612DF1uRWSYY''-.xxA'' 7?: ^Aq)1+/;*.*)- 44456  XXj))+ Zrcfd}|j|j}}|||}|j|dfStj||||j|j|j}||fS)z7Regression using numpy polyfit for higher-order trends.cVtjtj||Sr1)rpolyvalpolyfit)rr}rrVs rrz-_RegressionPlotter.fit_poly..reg_funcs#:bjR77>> >rNrs)rKrLrGryrzrRrMrS)r%rrVrrKrLrrs `` rrz_RegressionPlotter.fit_polys ? ? ? ? ? ?vtv1x1~~ 7?: ^Aq)1+/;*.*)- 444 Zrc  ddlmcm tjtjt |j|jf|j}}tjtjt f fd}|||}|j |dfStj ||||j |j |j}||fS)z;More general regression function using statsmodels objects.rNcjf} tj5tdr&tjdjg|jR}||fi}dddn #1swxYwYnK#|$rCtj t}| tj YnwxYw|S)NPerfectSeparationWarningerror) PerfectSeparationErrorwarningscatch_warningshasattr simplefilterrfitpredictremptyrefillnan)rr} err_classesrrkwargsmodelsmes rrz4_RegressionPlotter.fit_statsmodels..reg_funcsN57K ",..GGs$>??S -gs7STTT&R &RS5Q&R&R  5R226226688@@FFD GGGGGGGGGGGGGGG  " " "xD ** "&!!!!! "Ks6BA&B BBBBBAC$#C$rs)statsmodels.tools.sm_exceptionstools sm_exceptionsrrrrerKrLrGryrzrRrMrS) r%rrrrrLrrrrs ``` @rrz"_RegressionPlotter.fit_statsmodelss555555555uRWS[[))4612DF1uRWSYY''-.        x1~~ 7?: ^Aq)1+/;*.*)- 444 ZrcRddlm}||j|jj\}}||fS)z>Fit a locally-weighted regression, which returns its own grid.r)rX)*statsmodels.nonparametric.smoothers_lowessrXrLrKr)r%rXrrs rrz_RegressionPlotter.fit_lowess2s:EEEEEEVDFDF++- dTzrctjtjt|j|jf|j}}tjtjt|tj|f}d}||||}|j|dfStj ||||j |j |j j}||j}||fS)zFit the model in log-space.ctj|dddftj|dddff}tj||S)Nrr)rrlogrrrrs rrz-_RegressionPlotter.fit_logx..reg_func=sWr!!!Q$x111a4!1!112B9>>"%%))"-- -rNrs)rrrrerKrLrrrGryrzrRrMrSr)r%rrrLrrrrs rrz_RegressionPlotter.fit_logx8suRWS[[))4612DF1uRWSYY''56 . . .xxA'' 7?: ^Aq)1+/;*.*)- 44456  XXj))+ Zrctj|j}tj|r7tjdd|dzdd}tj||}ntj|}tjtj ||}|tj |d}||fS)z9Discretize a predictor by assigning value to closest bin.rrrr5) rr rKisscalarr percentileravelabssubtractouterargmin)r%binsrK percentilesdistx_binneds rrcz _RegressionPlotter.bin_predictorMs Jtv   ;t   "+adQh77"=K=K00DD8D>>Dvbk''40011 $Q///06688~rct|}||z }||z }tj|}||tj||z }tj||z|jS)z+Regress b from a keeping a's original mean.) rbrrrrrr reshaper!)r%aba_meana_primes rraz_RegressionPlotter.regress_out[s J L E!HaeeBINN1--11!44555z'F*++33AG<<.s333rBNNNNr) rPrrcParamsrrr!rprTrzipr@) r%r?r& line_markerslwrKrLci_kwsxsysr|rGs rrz_RegressionPlotter.scatterplots@??   #33x=L#@#@\"34\"9: NN< , , ,3w<11 ,S\5G5JQ5N5Nw+++$DAq BJq! # #s # # # # #s7|,F#~~"%g,w"%,/@"AD"HF;  NN3 # # #,KBC33S333 2 S\\22EArBGQFB11&1111 BJr2 % % % % % % %rcd||\}}}|d|df}|d}|dtjddz}|d||j||fi|\} |js|| jjdd<||j |g|R|d d dSdS) zDraw the model.rrr^rrg?rNg333333?) facecolorr) rpoprrrr@r[ sticky_edgesrK fill_between) r%r?r&rrredges fill_colorrlines rrz_RegressionPlotter.lineplots!% 3 3B 7 7dIQb!\ WWT3<(9:S@ A A {B'''d**c**} +%*D   "  BOD N9 N N # N N N N N N ! r)NNNrGTTrHrINNrFFFFNNFTNNNN)NNN)rArBrCrDrjpropertyrprrrrrrrrrcrar@rrrrrrFrFFsA BFFJHMEIFJ#' :6:6:6:6xX  ! !X !D777)%)%)%)%V   &   "   >    *   ==="'"'"'H & & &DOOOOOrrF model_apiz There are a number of mutually exclusive options for estimating the regression model. See the :ref:`tutorial ` for more information. regplot_vs_lmplotz The :func:`regplot` and :func:`lmplot` functions are closely related, but the former is an axes-level function while the latter is a figure-level function that combines :func:`regplot` and :class:`FacetGrid`. rPaJ x_estimator : callable that maps vector -> scalar, optional Apply this function to each unique value of ``x`` and plot the resulting estimate. This is useful when ``x`` is a discrete variable. If ``x_ci`` is given, this estimate will be bootstrapped and a confidence interval will be drawn. ria x_bins : int or vector, optional Bin the ``x`` variable into discrete bins and then estimate the central tendency and a confidence interval. This binning only influences how the scatterplot is drawn; the regression is still fit to the original data. This parameter is interpreted either as the number of evenly-sized (not necessary spaced) bins or the positions of the bin centers. When this parameter is used, it implies that the default of ``x_estimator`` is ``numpy.mean``. rQaZ x_ci : "ci", "sd", int in [0, 100] or None, optional Size of the confidence interval used when plotting a central tendency for discrete values of ``x``. If ``"ci"``, defer to the value of the ``ci`` parameter. If ``"sd"``, skip bootstrapping and show the standard deviation of the observations in each bin. rTz scatter : bool, optional If ``True``, draw a scatterplot with the underlying observations (or the ``x_estimator`` values). rUz fit_reg : bool, optional If ``True``, estimate and plot a regression model relating the ``x`` and ``y`` variables. rGaw ci : int in [0, 100] or None, optional Size of the confidence interval for the regression estimate. This will be drawn using translucent bands around the regression line. The confidence interval is estimated using a bootstrap; for large datasets, it may be advisable to avoid that computation by setting this parameter to None. rRz n_boot : int, optional Number of bootstrap resamples used to estimate the ``ci``. The default value attempts to balance time and stability; you may want to increase this value for "final" versions of plots. rMa units : variable name in ``data``, optional If the ``x`` and ``y`` observations are nested within sampling units, those can be specified here. This will be taken into account when computing the confidence intervals by performing a multilevel bootstrap that resamples both units and observations (within unit). This does not otherwise influence how the regression is estimated or drawn. rSz seed : int, numpy.random.Generator, or numpy.random.RandomState, optional Seed or random number generator for reproducible bootstrapping. rVz order : int, optional If ``order`` is greater than 1, use ``numpy.polyfit`` to estimate a polynomial regression. rWaw logistic : bool, optional If ``True``, assume that ``y`` is a binary variable and use ``statsmodels`` to estimate a logistic regression model. Note that this is substantially more computationally intensive than linear regression, so you may wish to decrease the number of bootstrap resamples (``n_boot``) or set ``ci`` to None. rXz lowess : bool, optional If ``True``, use ``statsmodels`` to estimate a nonparametric lowess model (locally weighted linear regression). Note that confidence intervals cannot currently be drawn for this kind of model. rYai robust : bool, optional If ``True``, use ``statsmodels`` to estimate a robust regression. This will de-weight outliers. Note that this is substantially more computationally intensive than standard linear regression, so you may wish to decrease the number of bootstrap resamples (``n_boot``) or set ``ci`` to None. rZz logx : bool, optional If ``True``, estimate a linear regression of the form y ~ log(x), but plot the scatterplot and regression model in the input space. Note that ``x`` must be positive for this to work. xy_partialz {x,y}_partial : strings in ``data`` or matrices Confounding variables to regress out of the ``x`` or ``y`` variables before plotting. r[z truncate : bool, optional If ``True``, the regression line is bounded by the data limits. If ``False``, it extends to the ``x`` axis limits. xy_jitteraT {x,y}_jitter : floats, optional Add uniform random noise of this size to either the ``x`` or ``y`` variables. The noise is added to a copy of the data after fitting the regression, and only influences the look of the scatterplot. This can be helpful when plotting variables that take discrete values. scatter_line_kwsz {scatter,line}_kws : dictionaries Additional keyword arguments to pass to ``plt.scatter`` and ``plt.plot``. orHrI)'rKrLhuecolrowpalettecol_wrapheightaspectmarkerssharexsharey hue_order col_order row_orderlegend legend_outrPrirQrTrUrGrRrMrSrVrWrXrYrZrNrOr[r\r]rr facet_kwsc'\''i''fd}(|(d| |(d| |(d||td||||||| |!g})tjd|)D}*||*}t |f||||||| || |d '}+|+jd},nt |+j},t| ts| g|,z} t | |,krtd d | i|+_ d }-|+ |-|| td"id |d|d|d|d|d|d|d|d|d|d|d|d|d|d| d|!d|"d|#d|$d |%d!|&}.|+j tf||d |.|+|||r||||fvr|+|+S)#NcX|d}|!tj|t||<dSdS)Nzj is deprecated from the `lmplot` function signature. Please update your code to pass it using `facet_kws`.)rwarn UserWarning)keyr)msgr's rfacet_kw_deprecationz$lmplot..facet_kw_deprecationPsJ D D D  ? M#{ + + + IcNNN ?rr r!r&z)Missing required keyword argument `data`.cg|]}||Sr1r)rrs rrzlmplot..bs<<.update_datalim{s_Aq6l##%%,,U33 #u--- '''''r)rKrLrPrirQrTrUrGrRrMrSrVrWrXrYrZrNrOr[r\r]rrr) TypeErrorrrvtolistr hue_namesrerrrhue_kws map_dataframedictr set_axis_labels add_legend)/rrKrLrrrrrrrrr r!r"r#r$r%r&rPrirQrTrUrGrRrMrSrVrWrXrYrZrNrOr[r\r]rrr'r. need_colscolsfacets n_markersr6 regplot_kwss/ ` rr r @s !!!!!6***6***z222 |CDDDAsCeY BI 9<<<<< = = D D F FD :D 3CyIfx   F ()) gt $ $()i' 7||y  >?? ?(FN(((  1222K(.59T!(-/R8>FKeT*2;A&v !D -6I BK    %-H  8@x   K  +3( KF:A::k::: 1a   3?S#J)>)> Mraa Plot data and regression model fits across a FacetGrid. This function combines :func:`regplot` and :class:`FacetGrid`. It is intended as a convenient interface to fit regression models across conditional subsets of a dataset. When thinking about how to assign variables to different facets, a general rule is that it makes sense to use ``hue`` for the most important comparison, followed by ``col`` and ``row``. However, always think about your particular dataset and the goals of the visualization you are creating. {model_api} The parameters to this function span most of the options in :class:`FacetGrid`, although there may be occasional cases where you will want to use that class and :func:`regplot` directly. Parameters ---------- {data} x, y : strings, optional Input variables; these should be column names in ``data``. hue, col, row : strings Variables that define subsets of the data, which will be drawn on separate facets in the grid. See the ``*_order`` parameters to control the order of levels of this variable. {palette} {col_wrap} {height} {aspect} markers : matplotlib marker code or list of marker codes, optional Markers for the scatterplot. If a list, each marker in the list will be used for each level of the ``hue`` variable. {share_xy} .. deprecated:: 0.12.0 Pass using the `facet_kws` dictionary. {{hue,col,row}}_order : lists, optional Order for the levels of the faceting variables. By default, this will be the order that the levels appear in ``data`` or, if the variables are pandas categoricals, the category order. legend : bool, optional If ``True`` and there is a ``hue`` variable, add a legend. {legend_out} .. deprecated:: 0.12.0 Pass using the `facet_kws` dictionary. {x_estimator} {x_bins} {x_ci} {scatter} {fit_reg} {ci} {n_boot} {units} {seed} {order} {logistic} {lowess} {robust} {logx} {xy_partial} {truncate} {xy_jitter} {scatter_line_kws} facet_kws : dict Dictionary of keyword arguments for :class:`FacetGrid`. See Also -------- regplot : Plot data and a conditional model fit. FacetGrid : Subplot grid for plotting conditional relationships. pairplot : Combine :func:`regplot` and :class:`PairGrid` (when used with ``kind="reg"``). Notes ----- {regplot_vs_lmplot} Examples -------- .. include:: ../docstrings/lmplot.rst )rKrLrPrirQrTrUrGrRrMrSrVrWrXrYrZrNrOr[r<r\r]r_r^rrrr?ct|||||||||| | | | | |||||||||||}|tj}|intj|}||d<|intj|}|||||S)Nr)rFpltgcacopyr@)rrKrLrPrirQrTrUrGrRrMrSrVrWrXrYrZrNrOr[r<r\r]r_r^rrrr?plotters rr r s!At[&$!('2vud!&&&$!*Ix!)8UE CCG  z WYY#+"";1G1GK"K%rr49X+>+>H LL[(+++ Ira Plot data and a linear regression model fit. {model_api} Parameters ---------- x, y: string, series, or vector array Input variables. If strings, these should correspond with column names in ``data``. When pandas objects are used, axes will be labeled with the series name. {data} {x_estimator} {x_bins} {x_ci} {scatter} {fit_reg} {ci} {n_boot} {units} {seed} {order} {logistic} {lowess} {robust} {logx} {xy_partial} {truncate} {xy_jitter} label : string Label to apply to either the scatterplot or regression line (if ``scatter`` is ``False``) for use in a legend. color : matplotlib color Color to apply to all plot elements; will be superseded by colors passed in ``scatter_kws`` or ``line_kws``. marker : matplotlib marker code Marker to use for the scatterplot glyphs. {scatter_line_kws} ax : matplotlib Axes, optional Axes object to draw the plot onto, otherwise uses the current Axes. Returns ------- ax : matplotlib Axes The Axes object containing the plot. See Also -------- lmplot : Combine :func:`regplot` and :class:`FacetGrid` to plot multiple linear relationships in a dataset. jointplot : Combine :func:`regplot` and :class:`JointGrid` (when used with ``kind="reg"``). pairplot : Combine :func:`regplot` and :class:`PairGrid` (when used with ``kind="reg"``). residplot : Plot the residuals of a linear regression model. Notes ----- {regplot_vs_lmplot} It's also easy to combine :func:`regplot` and :class:`JointGrid` or :class:`PairGrid` through the :func:`jointplot` and :func:`pairplot` functions, although these do not directly accept all of :func:`regplot`'s parameters. Examples -------- .. include:: ../docstrings/regplot.rst ) rKrLrNrOrXrVrYr<r_r^rrr?c t|||d|||||| |  }| tj} ||j\}}}|j|z |_|rd|_nd|_| ddd | in| } | in| } | | | | | S) a Plot the residuals of a linear regression. This function will regress y on x (possibly as a robust or polynomial regression) and then draw a scatterplot of the residuals. You can optionally fit a lowess smoother to the residual plot, which can help in determining if there is structure to the residuals. Parameters ---------- data : DataFrame, optional DataFrame to use if `x` and `y` are column names. x : vector or string Data or column name in `data` for the predictor variable. y : vector or string Data or column name in `data` for the response variable. {x, y}_partial : vectors or string(s) , optional These variables are treated as confounding and are removed from the `x` or `y` variables before plotting. lowess : boolean, optional Fit a lowess smoother to the residual scatterplot. order : int, optional Order of the polynomial to fit when calculating the residuals. robust : boolean, optional Fit a robust linear regression when calculating the residuals. dropna : boolean, optional If True, ignore observations with missing data when fitting and plotting. label : string, optional Label that will be used in any plot legends. color : matplotlib color, optional Color to use for all elements of the plot. {scatter, line}_kws : dictionaries, optional Additional keyword arguments passed to scatter() and plot() for drawing the components of the plot. ax : matplotlib axis, optional Plot into this axis, otherwise grab the current axis or make a new one if not existing. Returns ------- ax: matplotlib axes Axes with the regression plot. See Also -------- regplot : Plot a simple linear regression model. jointplot : Draw a :func:`residplot` with univariate marginal distributions (when used with ``kind="resid"``). Examples -------- .. include:: ../docstrings/residplot.rst N)rGrVrYrNrOr<r^r_)rTFr:z.2)lsc) rFrGrHrrKrLrXrUaxhlinerIr@)rrKrLrNrOrXrVrYr<r_r^rrr?rJrrs rr r Vsz!At',V+4 (.e5JJJG  z WYY''WY'77JAtQ D GI JJqSDJ!!!$+""1A1A1C1CK%rr8==??H LL[(+++ Irrr1)"rDrItextwraprrnumpyrpandasr3 matplotlibrmatplotlib.pyplotpyplotrG statsmodelsr ImportErrorrrryaxisgridrr__all__r rFr>_regression_docsupdater rr r rrrr]s??   ,,,,,,,, - , ,*"*"*"*"*"*"*"*"ZtOtOtOtOtOtOtOtOn 4f   f      & 6  ':    ;H F   IR F   S\v   ]l 6   mx &   yH    IP &   QZV   [j 6   kv 6   wF    GRv   S\V   ]ff   gtV   u@ $$$  d$D 4!S  Dd4 tTb TU5 u D4T TQQQQQhYYY Y r sY$Y$r#sY$Y$z DT $2d$ QuU $$ $ d3t6H&&HH H P QH$H$P#QH$H$X VDd5 E$d$t VVVVVVVs /99