o #ez#@s|gdZddlZddlZddlmZddlmZddlm Z m Z ddZ dd Z d d Z d d ZGdddeZddZdS))balanced demo_data LookupFactorN) PatsyError)C) no_picklingassert_no_picklingc s|dd}g}t|}|D]|}|fddtd|dDqttj|}i}t||D] \}t|||<q4|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']} repeatcsg|]}d|fqS)z%s%s).0inamer /lib/python3.10/site-packages/patsy/user_util.py 1szbalanced..)popsortedappendrangezip itertoolsproductlist)kwargsr levelsnamesZ level_countvaluesdatavaluer rrrs $rcCsntddd}|dgdksJ|dgdksJtdddd}|dgd ks+J|dgd ks5JdS) N)abr")a1r$r$a2r%r%r#)b1b2b3r&r'r()r"r#r ) r$r$r$r%r%r%r$r$r$r%r%r%) r&r'r(r&r'r(r&r'r(r&r'r()r)rr r r test_balanced9s r)c Os|dd}|dd}|rtd|ft}i}|D]}|ddvr)|||<q|ddvr5||qtd |ftjt|t d }t t |d |}||} t dd |i|} tj d} t|D] }| j| d | |<qi| S)a?demo_data(*names, nlevels=2, min_rows=5) Create simple categorical/numerical demo data. Pass in a set of variable names, and this function will return a simple data set using those variable names. Names whose first letter falls in the range "a" through "m" will be made categorical (with `nlevels` levels). Those that start with a "p" through "z" are numerical. We attempt to produce a balanced design on the categorical variables, repeating as necessary to generate at least `min_rows` data points. Categorical variables are returned as a list of strings. Numerical data is generated by sampling from a normal distribution. A fixed random seed is used, so that identical calls to demo_data() will produce identical results. Numerical data is returned in a numpy array. Example: .. ipython: In [1]: patsy.demo_data("a", "b", "x", "y") Out[1]: {'a': ['a1', 'a1', 'a2', 'a2', 'a1', 'a1', 'a2', 'a2'], 'b': ['b1', 'b2', 'b1', 'b2', 'b1', 'b2', 'b1', 'b2'], 'x': array([ 1.76405235, 0.40015721, 0.97873798, 2.2408932 , 1.86755799, -0.97727788, 0.95008842, -0.15135721]), 'y': array([-0.10321885, 0.4105985 , 0.14404357, 1.45427351, 0.76103773, 0.12167502, 0.44386323, 0.33367433])} nlevelsr min_rowszunexpected keyword arguments %rrZabcdefghijklmnZ pqrstuvwxyzz bad name %r)dtypeg?r )sizeNr )r TypeErrorsetaddrnpZprodrrintZceilrZrandomZ RandomStaterZnormal) rrr*r+Z numericalZ categoricalrZbalanced_design_sizer Znum_rowsrrr r rrCs( !       rcCsTtddd}t|gdksJ|dgdksJ|dgdks&J|djttks2J|djdks;Jtdd}t|ddgksLJt|dt|dkr_d ksbJJttdd d dd kspJttdddd d dd ksJttdddd d dddksJddl}| t tddd|j t tdddddS)Nr"r#x)r"r#r5)r$r$r%r%r$r$r%r%)r&r'r&r'r&r'r&r')yr, )r+ r!)r+r*rZ__123{)Zasdfasdf) rrkeysr-r2floatshapelenpytestraisesrr/)Zd1Zd2r@r r rtest_demo_datazs  , "rBc@sjeZdZdZ  dddZddZdd Zd d Zd d ZddZ ddZ ddZ ddZ ddZ eZdS)ra8A simple factor class that simply looks up a named entry in the given data. Useful for programatically constructing formulas, and as a simple example of the factor protocol. For details see :ref:`expert-model-specification`. Example:: dmatrix(ModelDesc([], [Term([LookupFactor("x")])]), {"x": [1, 2, 3]}) :arg varname: The name of this variable; used as a lookup key in the passed in data dictionary/DataFrame/whatever. :arg force_categorical: If True, then treat this factor as categorical. (Equivalent to using :func:`C` in a regular formula, but of course you can't do that with a :class:`LookupFactor`. :arg contrast: If given, the contrast to use; see :func:`C`. (Requires ``force_categorical=True``.) :arg levels: If given, the categorical levels; see :func:`C`. (Requires ``force_categorical=True``.) :arg origin: Either ``None``, or the :class:`Origin` of this factor for use in error reporting. .. versionadded:: 0.2.0 The ``force_categorical`` and related arguments. FNcCsL||_||_||_||_||_|js"|durtd|dur$tddSdS)Nz)contrast= requires force_categorical=Truez'levels= requires force_categorical=True)_varname_force_categorical _contrast_levelsorigin ValueError)selfZvarnameforce_categoricalcontrastrrGr r r__init__szLookupFactor.__init__cCs|jSN)rCrIr r rrszLookupFactor.namecCsd|jj|jfS)Nz%s(%r)) __class____name__rCrNr r r__repr__szLookupFactor.__repr__cCs:t|to|j|jko|j|jko|j|jko|j|jkSrM) isinstancerrCrDrErFrIotherr r r__eq__s     zLookupFactor.__eq__cCs ||k SrMr rSr r r__ne__s zLookupFactor.__ne__cCstt|j|j|j|jfSrM)hashrrCrDrErFrNr r r__hash__s zLookupFactor.__hash__cCsdS)Nrr )rIstateZeval_envr r rmemorize_passes_neededz#LookupFactor.memorize_passes_neededcCJrMr )rIrY which_passrr r rmemorize_chunkr[zLookupFactor.memorize_chunkcCr\rMr )rIrYr]r r rmemorize_finishr[zLookupFactor.memorize_finishcCs&||j}|jrt||j|jd}|S)N)rKr)rCrDrrErF)rIZmemorize_staterrr r revals zLookupFactor.eval)FNNN)rP __module__ __qualname____doc__rLrrQrUrVrXrZr^r_r`r __getstate__r r r rrs rcCs^td}|dks J|tdksJ|tdksJt|ttdks(Jt|ttdks4J|iddidks@J|iddidksLJt|dksTJ|jdus[Jtddd}|jdkshJtdd d d d }|idgd i}|jgd ksJ|jd ksJ|jd ksJddl }|j t tdd d|j t tdd dt tddS)Nr"r#r r zLookupFactor('a')Zasdf)rGcTZCONTRAST)r r )rJrKr)r r r rZnc)rK)r) rrrWr`reprrGrrKrr@rArHr)Zl_aZ l_with_originZl_cZboxr@r r rtest_LookupFactors. rg)__all__rZnumpyr2ZpatsyrZpatsy.categoricalrZ patsy.utilrrrr)rrBobjectrrgr r r rs  ( 7 N