DjKTdZddlZddlmcmZddlmcmZ ddl mcm Z ddl mZmZddlZddlZddlZGddej&ZGddeZGdd eZGd d ej.ZGd d eZGdde j4Ze j8eey)zA Conditional logistic, Poisson, and multinomial logit regression N)MultinomialResultsMultinomialResultsWrappercneZdZdfd ZdZ dfd Z ddZe d fd ZxZ S) _ConditionalModelc d|vr td|d}|j|jk7r d}t||jd|jk7r d}t|t|||fd|i||j j d}t||j}|jd|_i}t|D]"\}} | |vrg|| <|| j|$tj|tj|}}|jd } g|_g|_g|_| tj| } g|_g|_g|_d|_ddg} |j+D]\} } || j,} tj.| dk(r$| dxxdz cc<| dxxt1| z cc<R|xj(t1| z c_|jj| | |j"j| | |j jt1| |jj|| ddf|j&jtj2| !| ddkDr#d t5| z}t7j8|| `g|_t|j"D]A\}}|j:jtj<|j||Ct1|j|_g|_ g|_!tE|j>D]} |j@jtj<|j| |j| |jBjtj2|j| y) Ngroups'groups' is a required argumentz4'endog' and 'groups' should have the same dimensionsrzBThe leading dimension of 'exog' should equal the length of 'endog'missingzDConditional models should not have an intercept in the design matrixoffsetzIDropped %d groups and %d observations for having no within-group variance)# ValueErrorsizeshapesuper__init__data const_idxexogk_params enumerateappendnpasarrayget _endog_grp _exog_grp _groupsize _offset_grp_offset_sumynobsitemsflatstdlensumtuplewarningswarn_endofsdot _n_groups_xy_n1range)selfendogrr kwargsrmsgrow_ixigr dropsixykofs __class__s kC:\Crop_Prediction\Backend\crop-ai-system\venv\Lib\site-packages\statsmodels/discrete/conditional_models.pyrz_ConditionalModel.__init__sh 6 !>? ?! ;;%** $HCS/ ! ::a=EJJ &VCS/ !  4 4!( 4,2 4 99   *"CS/ !yy 1  f% DAqq 1I  Q  jj'D)9tH%  ZZ'F!D    A\\^ )EArb AvvayA~aA aCF" IIQ I OO " "1 %!  ''r 3 OO " "3q6 * NN ! !$r1u+ . JJ  bffQi ( ) 8a<.16u>C MM#   DL#D$4$45 E3 ##BFF4??1+=s$CD ET__-t~~& 8A HHOOBFF4??1#5t~~a7HI J HHOOBFF4??1#56 7 8cbddlm}|||j}tj|}|S)Nr) approx_fprime)statsmodels.tools.numdiffr@scorer atleast_2d)r0paramsr@hesss r=hessianz_ConditionalModel.hessianbs(;VTZZ0}}T" r>c  t ||||||| } t|| j| j d} || _|j | _|j| _dt|jzdt|jzdtj|jzg| _t| } | S)N start_paramsmethodmaxiter full_outputdisp skip_hessianr z%dz%.1f)rfitConditionalResultsrD cov_paramsrJr!r,n_groupsminrmaxrmean _group_statsConditionalResultsWrapper)r0rIrJrKrLrMfargscallbackretallrNr2rsltcrsltr<s r=rOz_ConditionalModel.fitisw{%#% '#4doo6GK YY  3t' ' 3t' ' RWWT__- -  )/ r>c zddlm}|dk7r tdddddd}|j|||f||||d |S) a Return a regularized fit to a linear regression model. Parameters ---------- method : {'elastic_net'} Only the `elastic_net` approach is currently implemented. alpha : scalar or array_like The penalty weight. If a scalar, the same penalty weight applies to all variables in the model. If a vector, it must have the same length as `params`, and contains a penalty weight for each coefficient. start_params : array_like Starting values for `params`. refit : bool If True, the model is refit using only the variables that have non-zero coefficients in the regularized fit. The refitted model is not regularized. **kwargs Additional keyword argument that are used when fitting the model. Returns ------- Results A results instance. r)fit_elasticnet elastic_netz.method for fit_regularized must be elastic_net2r g|=)rKL1_wt cnvrg_tolzero_tol)rJalpharIrefit)statsmodels.base.elastic_netr^r update)r0rJrdrIrer2r^defaultss r=fit_regularizedz!_ConditionalModel.fit_regularizedscB @ ] "MN N!AE %'d*6$)+7$)*!) * *r>c |d}|d=t|tr||}d|j ddvrt j dt | |g|||d|}|S#t$r tdwxYw)Nrr z0+ z2Conditional models should not include an intercept)rr) KeyErrorr isinstancestrreplacer(r)r from_formula) clsformularsubset drop_colsargsr2rmodelr<s r=rqz_ConditionalModel.from_formulas @H%Fx  fc "&\F wsB/ / MMN O$ @04@v@8>@  @>? ? @s A!!A6none NBFGSdTFNFF)r_NF)NN) __name__ __module__ __qualname__rrFrOri classmethodrq __classcell__r<s@r=rrsbN8`B - %)# .*b!# r>rcLeZdZdZd fd ZdZdZd dZd dZdZ dZ xZ S) ConditionalLogita Fit a conditional logistic regression model to grouped data. Every group is implicitly given an intercept, but the model is fit using a conditional likelihood in which the intercepts are not present. Thus, intercept estimates are not given, but the other parameter estimates can be interpreted as being adjusted for any group-level confounders. Parameters ---------- endog : array_like The response variable, must contain only 0 and 1. exog : array_like The array of covariates. Do not include an intercept in this array. groups : array_like Codes defining the groups. This is a required keyword parameter. c t|||fd|i|tjtj|j tj dk7r d}t||jjd|_ y)Nr )rr zendog must be coded as 0, 1r ) rrranyuniquer1r_r rrK)r0r1rr r2r3r<s r=rzConditionalLogit.__init__sp  4 4!( 4,2 4 66"))DJJ'255;6 7/CS/ !#r>czd}tt|jD]}||j||z }|SNr)r/r%r loglike_grp)r0rDllr6s r=loglikezConditionalLogit.loglikesB s4??+, .A $""1f- -B . r>chd}t|jD]}||j||z }|Sr)r/r, score_grp)r0rDrBr6s r=rBzConditionalLogit.scores;t~~& /A T^^Av. .E / r>c|d}tjtj|j|||zifd|j||j |S)Nrc||kry|dk(ry ||fS#t$rYnwxYw|dz ||dz |dz |dz zz}|||f<|S)Nrr )rm)tr:vexbfmemos r=rz"ConditionalLogit._denom..fs1uAv QF|#  !a% aAq1uoAE ::AD!QLHs  "")rexpr+rrr.)r0grprDr;rrrs @@@r=_denomzConditionalLogit._denoms` ;CffRVVDNN3/83>?  %txx}55r>c|d}j|tjtj||zifdj|j |S)Nrc@||kr!dtjjfS|dk(ry ||fS#t$rYnwxYw |dz } |dz |\}} |dz |dz \}}||z |dz ddfz}|||zz||z||zz} }|| f ||f<|| fS)Nr)r rr )rzerosrrm)rr:habcedurexrrsr0s r=rz'ConditionalLogit._denom_grad..s.s1u"((4==111Av QF|#  AE AQUA;DAqQUAE?DAqA1q5!8 $Aq1u9a!ea!emqAq6D!QLa4Ks6 AA)rrrr+rr.)r0rrDr;rrrrs` @@@@r= _denom_gradzConditionalLogit._denom_grad"sj ;C ^^C ffRVVB'#-.  ,%txx}55r>cd}t|dr|j|}tj|j||}|||j |z }|tj |j|||z}|S)Nr )hasattrrrr+r-r*logr)r0rrDr;llgs r=rzConditionalLogit.loglike_grpFsv 4 """3'CffTXXc]F+ ? 4<<$ $C rvvdkk#vs344 r>cd}t|dr|j|}|j|||\}}|j|||z z S)Nrr )rrrr-)r0rrDr;rrs r=rzConditionalLogit.score_grpUsP 4 """3'CVS11xx}q1u$$r>rx)N) rrr__doc__rrrBrrrrrrs@r=rrs,& $6:"6H %r>rceZdZdZdZdZy)ConditionalPoissonaU Fit a conditional Poisson regression model to grouped data. Every group is implicitly given an intercept, but the model is fit using a conditional likelihood in which the intercepts are not present. Thus, intercept estimates are not given, but the other parameter estimates can be interpreted as being adjusted for any group-level confounders. Parameters ---------- endog : array_like The response variable exog : array_like The covariates groups : array_like Codes defining the groups. This is a required keyword parameter. cd}t|dr |j}d}tt|jD]}t j |j||}||||z }t j|}|j|}|t j ||z }|j}||j|t j|zz}|SNr r~) rrr/r%rrr+rrr&r r) r0rDr;rr5xbrr9rs r=rzConditionalPoisson.loglikers 4 """C s4??+, ,Aq)62Bc!f &&*C"A "&&B- B A $**Q-"&&)+ +B , r>cd}t|dr |j}d}tt|jD]}|j |}t j||}||||z }t j|}|j}|j|} |t j| |z }||j|t j||z|z z}|Sr) rrr/r%rrrr+rr&r ) r0rDr;rBr5xrrrr9s r=rBzConditionalPoisson.scores 4 """Cs4??+, 8Aq!A6"Bc!f &&*C A"A RVVAq\ !E TZZ]RVVC^3a7 7E 8 r>N)rrrrrrBr}r>r=rr_s$*r>rc&eZdZfdZddZxZS)rPc,t|||||y)N)normalized_cov_paramsscale)rr)r0rwrDrrr<s r=rzConditionalResults.__init__s!   "7  r>cHdddd|jgfddg}dd|jgfd |jd gfd |jd gfd |jdgfg}|d}d dlm}|}|j |||||||j |||||j|S)a< Summarize the fitted model. Parameters ---------- yname : str, optional Default is `y` xname : list[str], optional Names for the exogenous variables, default is "var_xx". Must match the number of parameters in the model title : str, optional Title for the top table. If not None, then this replaces the default title alpha : float Significance level for the confidence intervals Returns ------- smry : Summary instance This holds the summary tables and text, which can be printed or converted to various output formats. See Also -------- statsmodels.iolib.summary.Summary : class to hold summary results )zDep. Variable:N)zModel:N)zLog-Likelihood:NzMethod:)zDate:N)zTime:N)zNo. Observations:Nz No. groups:zMin group size:rzMax group size:r zMean group size:z*Conditional Logit Model Regression Results)Summary)gleftgrightynamexnametitle)rrrduse_t)rJrRrVstatsmodels.iolib.summaryradd_table_2colsadd_table_paramsr) r0rrrrdtop_left top_rightrsmrys r=summaryzConditionalResults.summarys< %  %  &     ( T]]O , !2!21!5 6 7 !2!21!5 6 7 $"3"3A"6!7 8   =@E 6y      U%tzz  K r>)NNNg?)rrrrrrrs@r=rPrPs >r>rPcJeZdZdZdfd Z ddZdZdZxZS)ConditionalMNLogita Fit a conditional multinomial logit model to grouped data. Parameters ---------- endog : array_like The dependent variable, must be integer-valued, coded 0, 1, ..., c-1, where c is the number of response categories. exog : array_like The independent variables. groups : array_like Codes defining the groups. This is a required keyword parameter. Notes ----- Equivalent to femlogit in Stata. References ---------- Gary Chamberlain (1980). Analysis of covariance with qualitative data. The Review of Economic Studies. Vol. 47, No. 1, pp. 225-238. c t |||fd|i||jjt|_|jj dz|_|j dz |jjdz|_ |j|jz |_ t|j Dcic]}|t|c}|_|j |_|jjd|_|jj#dkr d}t%|t'j(t*}t-|j.D]\}} || j1|t+|j3|_|j4j7|j4Dcgc]}|| c}|_ycc}wcc}w)Nr r rz%endog may not contain negative values)rrr1astypeintrTk_catrrdf_modelr!df_residr/ro _ynames_mapJrrSr collections defaultdictlistrrrkeys _group_labelssort_grp_ix) r0r1rr r2jr3grxr:rr<s r=rzConditionalMNLogit.__init__sv  4 4!( 4,2 4ZZ&&s+ ZZ^^%) a499??1+==  DMM1 /4TZZ/@A!As1vIA# ::>> a 9CS/ !%%d+dkk* DAq FMM!  !#((*- !(,(:(:;1A; BG Gc |K|jjd} |jdz } tjj | | z}t jj||||||| } | jj|jjddf| _ t|| } | jtjt| S)Nr )rrH)llnull)rrrrrandomnormalbaseLikelihoodModelrOrDreshaperset_null_optionsnanr)r0rIrJrKrLrMrXrYrZrNr2qrr[s r=rOzConditionalMNLogit.fits   "A QA99++Q+7L##'' %#%('kk))499??1+=r*BC !$- RVV,(..r>c|jjd}|jdz }|j||f}t j t j |df|fd}t j|j|}d}|jD]}||ddf}t j|jdt} |j|} d} tj| D]-} | t j|| | fjz } /||| | fjt j | z z }|S)Nr axisr~rdtype)rrrrr concatenaterr+rarangerr1 itertools permutationsrr&r) r0rDrrpmatlprriirjjr9denomps r=rzConditionalMNLogit.loglike?s! IIOOA  JJN~~q!f%~~rxxA/6Q?ffTYY% ,, 3BBE A1771:S1B 2AE++A. 22q'  011 2 !RG*.."RVVE]2 2B 3 r>c |jjd}|jdz }|j||f}t j t j |df|fd}t j|j|}t j ||f}|jD]0}||ddf}t j|jdt} |j|} d} t j ||f} tj| D]s} t j|| | fj}| |z } t!| D]6\}}|dk7s | dd|dz fxx||j||ddfzz cc<8ut!| D]3\}}|dk7s |dd|dz fxx|j||ddfz cc<5|| | z z}3|j#S)Nr rrrr~)rrrrrrrr+rrrr1rrrr&rflatten)r0rDrrrrgradrrrr9rdenomgrrr5rs r=rBzConditionalMNLogit.scoreUs IIOOA  JJN~~q!f%~~rxxA/6Q?ffTYY%xxA,, #BBE A1771:S1B 2AEXXq!f%F++A. DFF1b!W:>>+, %aLDDAqAvq!a%x(A "Q%(0C,CC(D D"!  :16AENdii1q&99N : FUN "D# #&||~r>rxrz) rrrrrrOrrBrrs@r=rrs:0<6#/J,r>rc eZdZy)rWN)rrrr}r>r=rWrWvsr>rW)rnumpyrstatsmodels.base.modelrrw#statsmodels.regression.linear_model regression linear_modellmstatsmodels.base.wrapperwrapperwrap#statsmodels.discrete.discrete_modelrrrr(rrrrrLikelihoodModelResultsrPrRegressionResultsWrapperrWpopulate_wrapperr}r>r=r s%%00''!B,,BJG%(G%T<*<~G44GRK*K^  ; ; /1CDr>