ehdZddlmZddlmZddlZddlmZddl m Z m Z er ddl m Z ddlmZd d Z d d Z dd Zy)zH Module containing utilities for NDFrame.sample() and .GroupBy.sample() ) annotations) TYPE_CHECKINGN)lib) ABCDataFrame ABCSeries)AxisInt)NDFramect|tr|j|j|}t|tr2t|t r|dk(r ||}ntdtdt|tr |j}n |j}||dj}t||j|k7r tdtj|r td |dkjr td t!j"|}|jr|j%}d||<|S#t $r}t d|d}~wwxYw) z Process and validate the `weights` argument to `NDFrame.sample` and `.GroupBy.sample`. Returns `weights` as an ndarray[np.float64], validated except for normalizing weights (because that must be done groupwise in groupby sampling). rz+String passed to weights not a valid columnNzLStrings can only be passed to weights when sampling from rows on a DataFramez@Strings cannot be passed as weights when sampling from a Series.float64)dtypez5Weights and axis to be sampled must be of same lengthz*weight vector may not include `inf` valuesz.weight vector many not include negative values) isinstancerreindexaxesstrrKeyError ValueError _constructor_constructor_sliced_valueslenshaperhas_infsanynpisnancopy)objweightsaxiserrfuncmissings P/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/pandas/core/sample.pypreprocess_weightsr$sT'9%//#((4.1'3 c< (qy!'lG !" R #y!&&7),44G 7|syy&PQQ ||GEFF! IJJhhwG{{},,. NI "EsE E( E##E(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$Only integers accepted as `n` valueszJReplace has to be set to `True` when upsampling the population `frac` > 1.z@A negative number of rows requested. Please provide `frac` >= 0.)r)nfracreplaces r#process_sampling_sizer*Ps yT\ , H+ 4+KLL  q5O  q5A:CD D H !8G8  !8R  Hc|&|j}|dk7r||z }n td|j||||jtj dS)ac Randomly sample `size` indices in `np.arange(obj_len)` Parameters ---------- obj_len : int The length of the indices being considered size : int The number of values to choose replace : bool Allow or disallow sampling of the same row more than once. weights : np.ndarray[np.float64] or None If None, equal probability weighting, otherwise weights according to the vector normalized random_state: np.random.RandomState or np.random.Generator State used for the random sampling Returns ------- np.ndarray[np.intp] rz$Invalid weights: weights sum to zero)sizer)pF)r)sumrchoiceastyperintp)obj_lenr-r)r random_state weight_sums r#sampler6ush8[[] ? *GCD D   wT7g  N U U e V r+)rr rrreturn np.ndarray)r' int | Noner(z float | Noner)boolr7r9) r3intr-r;r)r:rznp.ndarray | Noner4z+np.random.RandomState | np.random.Generatorr7r8)__doc__ __future__rtypingrnumpyr pandas._libsrpandas.core.dtypes.genericrrpandas._typingrpandas.core.genericr r$r*r6r+r#rEs#  &+6r" " %" 04" " J% % %% % > %  %r+