ujdZddlmZddlmZddlZddlmZddl m Z m Z erddl m Z mZddlmZ d d Z d d Z dd Zy)zH Module containing utilities for NDFrame.sample() and .GroupBy.sample() ) annotations) TYPE_CHECKINGN)lib) ABCDataFrame ABCSeries)AxisIntListLike)NDFramect|tr|j|j|}t|tr2t|t r|dk(r ||}ntdtdt|tr |j}n |j}tj||djtj}t||j|k7r tdt!j"|r td |dkj%r td tj&|}|j%r|j)}d||<|S#t $r}t d|d}~wwxYw) z Process and validate the `weights` argument to `NDFrame.sample` and `.GroupBy.sample`. Returns `weights` as an ndarray[np.float64], validated except for normalizing weights (because that must be done groupwise in groupby sampling). rz+String passed to weights not a valid columnNzLStrings can only be passed to weights when sampling from rows on a DataFramez@Strings cannot be passed as weights when sampling from a Series.float64)dtypez5Weights and axis to be sampled must be of same lengthz+weights vector may not include `inf` valuesz.weights vector may not include negative values) isinstancerreindexaxesstrrKeyError ValueError _constructor_constructor_slicednpasarray_valuesr lenshaperhas_infsanyisnancopy)objweightsaxiserrfunc weights_arrmissings ]/var/www/html/python-recuperauto-other/env/lib/python3.12/site-packages/pandas/core/sample.pypreprocess_weightsr'sh'9%//#((4.1'3 c< (qy!'lG !" R #y!&&**T';CC2::VK ;399T?*PQQ ||K FGGaIJJhh{#G{{}!&&(  G I "EsE11 F : FF c||d}|S| | td|%|dkr td|dzdk7r td|S|J|dkDr |s td|dkr td|S)z Process and validate the `n` and `frac` arguments to `NDFrame.sample` and `.GroupBy.sample`. Returns None if `frac` should be used (variable sampling sizes), otherwise returns the constant sampling size. z0Please enter a value for `frac` OR `n`, not bothrz=A negative number of rows requested. Please provide `n` >= 0.z$Only integers accepted as `n` valueszJReplace has to be set to `True` when upsampling the population `frac` > 1.z@A negative number of rows requested. Please provide `frac` >= 0.)r)nfracreplaces r&process_sampling_sizer-Vs yT\ , H+ 4+KLL  q5O  q5A:CD D H !8G8  !8R  Hc|M|j}|dk7r||z }n td|J|s!||jzdkDr td|j||||j t j dS)ad Randomly sample `size` indices in `np.arange(obj_len)`. Parameters ---------- obj_len : int The length of the indices being considered size : int The number of values to choose replace : bool Allow or disallow sampling of the same row more than once. weights : np.ndarray[np.float64] or None If None, equal probability weighting, otherwise weights according to the vector normalized random_state: np.random.RandomState or np.random.Generator State used for the random sampling Returns ------- np.ndarray[np.intp] rz$Invalid weights: weights sum to zeror)zWeighted sampling cannot be achieved with replace=False. Either set replace=True or use smaller weights. See the docstring of sample for details.)sizer,pF)r)sumrmaxchoiceastyperintp)obj_lenr0r,r random_state weight_sums r&sampler:{s8[[] ? *GCD D"""4'++-/!3&    wT7g  N U U e V r.)rr r zstr | ListLiker!rreturn np.ndarray)r* int | Noner+z float | Noner,boolr;r=) r7intr0r?r,r>r znp.ndarray | Noner8z+np.random.RandomState | np.random.Generatorr;r<)__doc__ __future__rtypingrnumpyr pandas._libsrpandas.core.dtypes.genericrrpandas._typingrr pandas.core.genericr r'r-r:r.r&rIs#   ,8 8)81888v" " %" 04" " J- - -- - > -  -r.