U md@stdZddlZddlmZddlmZddlmZddZ dd Z Gd d d eZ Gd d d eZ GdddeZ dS)a Created on Mon Jul 26 08:34:59 2010 Author: josef-pktd changes: added offset and zero-inflated version of Poisson - kind of ok, need better test cases, - a nan in ZIP bse, need to check hessian calculations - found error in ZIP loglike - all tests pass with Issues ------ * If true model is not zero-inflated then numerical Hessian for ZIP has zeros for the inflation probability and is not invertible. -> hessian inverts and bse look ok if row and column are dropped, pinv also works * GenericMLE: still get somewhere (where?) "CacheWriteWarning: The attribute 'bse' cannot be overwritten" * bfgs is too fragile, does not come back * `nm` is slow but seems to work * need good start_params and their use in genericmle needs to be checked for consistency, set as attribute or method (called as attribute) * numerical hessian needs better scaling * check taking parts out of the loop, e.g. factorial(endog) could be precalculated N)stats) factorial)GenericLikelihoodModelcCstt||S)NnpmaxabsZarr1Zarr2r U/home/sam/Atlas/atlas_env/lib/python3.8/site-packages/statsmodels/miscmodels/count.pymaxabs%sr cCstt||dS)Nrr r r r maxabsrel(src@s eZdZdZddZddZdS) PoissonGMLEafMaximum Likelihood Estimation of Poisson Model This is an example for generic MLE which has the same statistical model as discretemod.Poisson. Except for defining the negative log-likelihood method, all methods and results are generic. Gradients and Hessian and all resulting statistics are based on numerical differentiation. cCs4t|j|}|j}t|||tt|S| Loglikelihood of Poisson model Parameters ---------- params : array_like The parameters of the model. Returns ------- The log likelihood of the model evaluated at `params` Notes ----- .. math:: \ln L=\sum_{i=1}^{n}\left[-\lambda_{i}+y_{i}x_{i}^{\prime}\beta-\ln y_{i}!\right] )rdotexogendogexplogr)selfparamsXBrr r r nloglikeobs;szPoissonGMLE.nloglikeobscCs@t|dstn,|j}|j}tt||}tj|ddSdS)zOreturn frozen scipy.stats distribution with mu at estimated prediction resultr)locN) hasattr ValueErrorrrrrrrZpoisson)rrrrmur r r predict_distributionPs  z PoissonGMLE.predict_distributionN)__name__ __module__ __qualname____doc__rr r r r r r-s rcs*eZdZdZdfdd ZddZZS) PoissonOffsetGMLEauMaximum Likelihood Estimation of Poisson Model This is an example for generic MLE which has the same statistical model as discretemod.Poisson but adds offset Except for defining the negative log-likelihood method, all methods and results are generic. Gradients and Hessian and all resulting statistics are based on numerical differentiation. Nnonec sV|dk r.|jdkr"|dddf}||_nd|_tt|j||fd|i|dS)Nr missing)ndimraveloffsetsuperr%__init__rrrr+r(kwds __class__r r r-ms  zPoissonOffsetGMLE.__init__cCs>|jt|j|}|j}t|||tt|}|Sr)r+rrrrrrr)rrrrnloglikr r r r}s zPoissonOffsetGMLE.nloglikeobs)NNr&r!r"r#r$r-r __classcell__r r r0r r%`s r%cs*eZdZdZdfdd ZddZZS) PoissonZiGMLEaMaximum Likelihood Estimation of Poisson Model This is an example for generic MLE which has the same statistical model as discretemod.Poisson but adds offset and zero-inflation. Except for defining the negative log-likelihood method, all methods and results are generic. Gradients and Hessian and all resulting statistics are based on numerical differentiation. There are numerical problems if there is no zero-inflation. Nr&c sd|_tt|j||f|dgd||dk rV|jdkrJ|dddf}||_nd|_|dkrvt|j df|_ |j j d|_ t t|j df|_|j d7_ dg|_dS)Nr Zzi)r(Zextra_params_namesr'r start_params)Zk_extrar,r5r-r)r*r+rZonesZnobsrshapeZnparamsZhstackr6Z cloneattrr.r0r r r-s"  zPoissonZiGMLE.__init__cCs|dd}ddt|d}|jt|j|}|j}td| t|||tt|}t|t||dk  ||dk<|S)rNr r)rrr+rrrrr)rrbetaZgammrrr2r r r rs 0(zPoissonZiGMLE.nloglikeobs)NNr&r3r r r0r r5sr5)r$numpyrZscipyrZ scipy.specialrZstatsmodels.base.modelrr rrr%r5r r r r s   34