J/Ph\$gdZddlZddlZddlmZddlmZddlm Z m Z dZ dZ dZ d ZGd d eZd ZdS) )balanced demo_data LookupFactorN) PatsyError)C) no_picklingassert_no_picklingc X|dd}g}t|}|D]<|}|fdtd|dzD=t t j|}i}t ||D]\}t||z|<|S)aTbalanced(factor_name=num_levels, [factor_name=num_levels, ..., repeat=1]) Create simple balanced factorial designs for testing. Given some factor names and the number of desired levels for each, generates a balanced factorial design in the form of a data dictionary. For example: .. ipython:: In [1]: balanced(a=2, b=3) Out[1]: {'a': ['a1', 'a1', 'a1', 'a2', 'a2', 'a2'], 'b': ['b1', 'b2', 'b3', 'b1', 'b2', 'b3']} By default it produces exactly one instance of each combination of levels, but if you want multiple replicates this can be accomplished via the `repeat` argument: .. ipython:: In [2]: balanced(a=2, b=2, repeat=2) Out[2]: {'a': ['a1', 'a1', 'a2', 'a2', 'a1', 'a1', 'a2', 'a2'], 'b': ['b1', 'b2', 'b1', 'b2', 'b1', 'b2', 'b1', 'b2']} repeatcg|]}| Sr).0inames O/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/patsy/user_util.py zbalanced..2s"MMMaqq)MMM)popsortedappendrangezip itertoolsproductlist) kwargsr levelsnames level_countvaluesdatavaluers @rrrs6ZZ! $ $F F 6NNEOOTl  MMMM5K!O3L3LMMMNNNN )#V, -F D5&))** e%[[6)T Krctdd}|dgdksJ|dgdksJtddd}|dgd ksJ|dgd ksJdS) N)abr')a1r)r)a2r*r*r()b1b2b3r+r,r-)r'r(r ) r)r)r)r*r*r*r)r)r)r*r*r*) r+r,r-r+r,r-r+r,r-r+r,r-)r)r"s r test_balancedr.;s a1   D 9<<< < < < < 9<<< < < < < a1Q ' ' 'D 9        9         rc|dd}|dd}|rtd|t}i}|D]C}|ddvr|||<|ddvr||2t d |t jt|t }tt j |d z|z }||z} tdd |i|} t j d} t|D]}| | | |<| S)a?demo_data(*names, nlevels=2, min_rows=5) Create simple categorical/numerical demo data. Pass in a set of variable names, and this function will return a simple data set using those variable names. Names whose first letter falls in the range "a" through "m" will be made categorical (with `nlevels` levels). Those that start with a "p" through "z" are numerical. We attempt to produce a balanced design on the categorical variables, repeating as necessary to generate at least `min_rows` data points. Categorical variables are returned as a list of strings. Numerical data is generated by sampling from a normal distribution. A fixed random seed is used, so that identical calls to demo_data() will produce identical results. Numerical data is returned in a numpy array. Example: .. ipython: In [1]: patsy.demo_data("a", "b", "x", "y") Out[1]: {'a': ['a1', 'a1', 'a2', 'a2', 'a1', 'a1', 'a2', 'a2'], 'b': ['b1', 'b2', 'b1', 'b2', 'b1', 'b2', 'b1', 'b2'], 'x': array([ 1.76405235, 0.40015721, 0.97873798, 2.2408932 , 1.86755799, -0.97727788, 0.95008842, -0.15135721]), 'y': array([-0.10321885, 0.4105985 , 0.14404357, 1.45427351, 0.76103773, 0.12167502, 0.44386323, 0.33367433])} nlevelsr%min_rowszunexpected keyword arguments rabcdefghijklmn pqrstuvwxyzz bad name )dtypeg?r )sizer)r TypeErrorsetaddrnpprodrr!intceilrrandom RandomStaternormal) rrr0r1 numerical categoricalrbalanced_design_sizer num_rowsr"rs rrr^ssBjjA&&Gzz*a((H GiVVEFFFIK66 7& & & 'K   !W % % MM$    *dd455 574 (:(:(<(<#=#=SIII C*>>?? @ @F,,H  1 16 1[ 1 1D a  Ay!!--XX8X,,T Krc tddd}t|gdksJ|dgdksJ|dgdksJ|djt jt ksJ|djdksJtdd}t|ddgksJt|dt|dcxkrd ksnJttdd dd ksJttdddd dd ksJttdddd d ddksJddl}| ttddd| ttddddS)Nr'r(x)r'r(rG)r)r)r*r*r)r)r*r*)r+r,r+r,r+r,r+r,)yr2 )r1 r&)r1r0r__123{)asdfasdf) rrkeysr5r:floatshapelenpytestraisesrr7)d1d2rTs rtest_demo_datarXs 3S ! !B "''))   / / / / c7FFF F F F F c7FFF F F F F c7=BHUOO + + + + c7=D 3  B "''))  c * * * * r#w<<3r#w<< , , , ,1 , , , , , , yr***3/ 0 0B 6 6 6 6 yc3444S9 : :b @ @ @ @ yc3Q???D E E K K K KMMM MM*ic7;;; MM)YS3M?????rcVeZdZdZ ddZdZdZdZdZd Z d Z d Z d Z d Z eZdS)ra8A simple factor class that simply looks up a named entry in the given data. Useful for programatically constructing formulas, and as a simple example of the factor protocol. For details see :ref:`expert-model-specification`. Example:: dmatrix(ModelDesc([], [Term([LookupFactor("x")])]), {"x": [1, 2, 3]}) :arg varname: The name of this variable; used as a lookup key in the passed in data dictionary/DataFrame/whatever. :arg force_categorical: If True, then treat this factor as categorical. (Equivalent to using :func:`C` in a regular formula, but of course you can't do that with a :class:`LookupFactor`. :arg contrast: If given, the contrast to use; see :func:`C`. (Requires ``force_categorical=True``.) :arg levels: If given, the categorical levels; see :func:`C`. (Requires ``force_categorical=True``.) :arg origin: Either ``None``, or the :class:`Origin` of this factor for use in error reporting. .. versionadded:: 0.2.0 The ``force_categorical`` and related arguments. FNc||_||_||_||_||_|js"|t d|t ddSdS)Nz)contrast= requires force_categorical=Truez'levels= requires force_categorical=True)_varname_force_categorical _contrast_levelsorigin ValueError)selfvarnameforce_categoricalcontrastrr_s r__init__zLookupFactor.__init__sr  "3!  & L# !LMMM! !JKKK  L L"!rc|jSN)r[ras rrzLookupFactor.names }rc0|jjd|jdS)N()) __class____name__r[rhs r__repr__zLookupFactor.__repr__s>222DMMMBBrct|to?|j|jko/|j|jko|j|jko|j|jkSrg) isinstancerr[r\r]r^raothers r__eq__zLookupFactor.__eq__s^ ul + + . / .'5+CC .%/1 .  -  rc||k Srgrrqs r__ne__zLookupFactor.__ne__s5=  rc\tt|j|j|j|jfSrg)hashrr[r\r]r^rhs r__hash__zLookupFactor.__hash__s1 '     rcdS)Nrr)rastateeval_envs rmemorize_passes_neededz#LookupFactor.memorize_passes_neededsqrcJrgr)rarz which_passr"s rmemorize_chunkzLookupFactor.memorize_chunk rcJrgr)rarzr~s rmemorize_finishzLookupFactor.memorize_finishrrcf||j}|jrt||j|j}|S)N)rdr)r[r\rr]r^)ramemorize_stater"r#s revalzLookupFactor.evals7T]#  " KednT\JJJE r)FNNN)rm __module__ __qualname____doc__rerrnrsrurxr|rrrr __getstate__rrrrrs8TX L L L LCCC   !!!     LLLrrctd}|dksJ|tdksJ|tdksJt|ttdksJt|ttdksJ|iddidksJ|iddidksJt |dksJ|jJtdd}|jdksJtdd d d }|idgd i}|jgd ksJ|jd ksJ|jd ksJddl }| ttdd | ttdd ttddS)Nr'r(r r%zLookupFactor('a')asdf)r_cTCONTRAST)r r%)rcrdr)r r r%rnc)rd)r) rrrwrreprr_r"rdrrTrUr`r )l_a l_with_originl_cboxrTs rtest_LookupFactorrs s  C 88::     ,s## # # # # ,s## # # # # 99\#..// / / / / 99\#..// / / / / 88Ba ! !Q & & & & 88Ba ! !Q & & & & 99+ + + + + :    V444M  6 ) ) ) ) sdZPV W W WC ((2YYY' ( (C 8yyy <: % % % % :    MMM MM*lD:MFFF MM*lDM@@@|C(()))))r)__all__rnumpyr:patsyrpatsy.categoricalr patsy.utilrr rr.rrXobjectrrrrrrs 4 3 366666666&&&R   F555p@@@,VVVVV6VVVr*****r