/Dj\$xgdZddlZddlZddlmZddlmZddlm Z m Z dZ dZ dZ d ZGd d eZd Zy) )balanced demo_data LookupFactorN) PatsyError)C) no_picklingassert_no_picklingc D|jdd}g}t|}|D]7}||}|jtd|dzDcgc]}|| c}9t t j |}i}t ||D]\}} t| |z||<|Scc}w)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']} repeat)popsortedappendrangezip itertoolsproductlist) kwargsr levelsnamesname level_countivaluesdatavalues SC:\Crop_Prediction\Backend\crop-ai-system\venv\Lib\site-packages\patsy/user_util.pyrrs6ZZ! $F F 6NEOTl  5K!O3LMaq)MNO)##V, -F D5&)* e%[6)T * K Ns B ctdd}|dgdk(sJ|dgdk(sJtddd}|dgd k(sJ|dgd k(sJy) N)abr")a1r$r$a2r%r%r#)b1b2b3r&r'r()r"r#r ) r$r$r$r%r%r%r$r$r$r%r%r%) r&r'r(r&r'r(r&r'r(r&r'r()r)rs r test_balancedr);so a1 D 9< << 9< << a1Q 'D 9    9    cR|jdd}|jdd}|rtd|t}i}|D]5}|ddvr|||<|ddvr|j|)t d |t j t|jt }tt j|d z|z }||z} tdd |i|} t jjd} t|D]}| j| | |<| S)a?demo_data(*names, nlevels=2, min_rows=5) Create simple categorical/numerical demo data. Pass in a set of variable names, and this function will return a simple data set using those variable names. Names whose first letter falls in the range "a" through "m" will be made categorical (with `nlevels` levels). Those that start with a "p" through "z" are numerical. We attempt to produce a balanced design on the categorical variables, repeating as necessary to generate at least `min_rows` data points. Categorical variables are returned as a list of strings. Numerical data is generated by sampling from a normal distribution. A fixed random seed is used, so that identical calls to demo_data() will produce identical results. Numerical data is returned in a numpy array. Example: .. ipython: In [1]: patsy.demo_data("a", "b", "x", "y") Out[1]: {'a': ['a1', 'a1', 'a2', 'a2', 'a1', 'a1', 'a2', 'a2'], 'b': ['b1', 'b2', 'b1', 'b2', 'b1', 'b2', 'b1', 'b2'], 'x': array([ 1.76405235, 0.40015721, 0.97873798, 2.2408932 , 1.86755799, -0.97727788, 0.95008842, -0.15135721]), 'y': array([-0.10321885, 0.4105985 , 0.14404357, 1.45427351, 0.76103773, 0.12167502, 0.44386323, 0.33367433])} nlevelsr min_rowszunexpected keyword arguments rabcdefghijklmn pqrstuvwxyzz bad name )dtypeg?r )size)r TypeErrorsetaddrnpprodrrintceilrrandom RandomStaternormal) rrr,r- numerical categoricalrbalanced_design_sizer num_rowsrrs rrr^s*BjjA&Gzz*a(H VEFFIK6 7& & 'K  !W % MM$ d45 5 6774 (:(:(<#=SI C*>>? @F,,H  16 1[ 1D a Ay!-XX8X,T - Kr*c tddd}t|jgdk(sJ|dgdk(sJ|dgdk(sJ|djt jt k(sJ|dj dk(sJtdd}t|jddgk(sJt|dt|dcxk(rd k(sJJttdd dd k(sJttdddd dd k(sJttdddd d ddk(sJddl}|jttddd|jttdddy)Nr"r#x)r"r#rD)r$r$r%r%r$r$r%r%)r&r'r&r'r&r'r&r')yr. )r- r!)r-r,r__123{)asdfasdf) rrkeysr1r7floatshapelenpytestraisesrr4)d1d2rQs rtest_demo_datarUsK 3S !B "'')  // c7F FF c7F FF c7==BHHUO ++ c7==D  3 B "'') c ** r#w<3r#w< ,1 ,, ,, yr*3/ 0B 66 yc34S9 :b @@ yc3Q?D E KK MM*ic7; MM)YS3M?r*cTeZdZdZ d dZdZdZdZdZdZ d Z d Z d Z d Z eZy)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. Nc||_||_||_||_||_|js| t d| t dyy)Nz)contrast= requires force_categorical=Truez'levels= requires force_categorical=True)_varname_force_categorical _contrast_levelsorigin ValueError)selfvarnameforce_categoricalcontrastrr\s r__init__zLookupFactor.__init__s_  "3!  &&# !LMM! !JKK"'r*c|jSN)rXr^s rrzLookupFactor.names }}r*cN|jjd|jdS)N()) __class____name__rXres r__repr__zLookupFactor.__repr__s>>22DMMBBr*ct|txrj|j|jk(xrO|j|jk(xr4|j|jk(xr|j |j k(Srd) isinstancerrXrYrZr[r^others r__eq__zLookupFactor.__eq__sm ul + . / .''5+C+CC .%//1 .  -  r*c||k( Srdr3rns r__ne__zLookupFactor.__ne__s5=  r*cztt|j|j|j|j fSrd)hashrrXrYrZr[res r__hash__zLookupFactor.__hash__s5 ''    r*cy)Nrr3)r^stateeval_envs rmemorize_passes_neededz#LookupFactor.memorize_passes_neededsr*cJrdr3)r^rw which_passrs rmemorize_chunkzLookupFactor.memorize_chunkr*cJrdr3)r^rwr{s rmemorize_finishzLookupFactor.memorize_finishr}r*c||j}|jr"t||j|j}|S)N)rar)rXrYrrZr[)r^memorize_staterrs revalzLookupFactor.evals4T]]#  " "ednnT\\JE r*)FNNN)rj __module__ __qualname____doc__rbrrkrprrruryr|rrr __getstate__r3r*rrrsI8TX LC !   Lr*rc@td}|jdk(sJ|tdk(sJ|tdk7sJt|ttdk(sJt|ttdk7sJ|jiddidk(sJ|jiddidk(sJt |dk(sJ|j Jtdd}|j dk(sJtdd d d }|jidgd i}|j gd k(sJ|jd k(sJ|jd k(sJddl }|jttdd |jttdd ttdy)Nr"r#r r zLookupFactor('a')asdf)r\cTCONTRAST)r r )r`rar)r r r rnc)ra)r) rrrtrreprr\rrarrQrRr]r )l_a l_with_originl_cboxrQs rtest_LookupFactorrsh s C 88:  ,s# ## ,s# ## 9\#./ // 9\#./ // 88Ba !Q && 88Ba !Q && 9+ ++ ::  V4M   6 )) sdZPV WC ((2Y' (C 88y  <<: %% ::  MM*lD:MF MM*lDM@|C()r*)__all__rnumpyr7patsyrpatsy.categoricalr patsy.utilrr rr)rrUobjectrrr3r*rrsG 46&R F5p@,V6Vr*r*