bMhzdZddlmZddlmZddlZddlmZddl m Z m Z er ddl m Z ddlmZddZd dZd!dZdS)"zH Module containing utilities for NDFrame.sample() and .GroupBy.sample() ) annotations) TYPE_CHECKINGN)lib) ABCDataFrame ABCSeries)AxisInt)NDFrameobjr axisrreturn np.ndarrayc@t|tr ||j|}t|tret|t rA|dkr, ||}n@#t $r}t d|d}~wwxYwtdtdt|tr|j}n|j }||dj }t||j |krtdtj|rtd |dkrtd t!j|}|r|}d||<|S) z Process and validate the `weights` argument to `NDFrame.sample` and `.GroupBy.sample`. Returns `weights` as an ndarray[np.float64], validated except for normalizing weights (because that must be done groupwise in groupby sampling). rz+String passed to weights not a valid columnNzLStrings can only be passed to weights when sampling from rows on a DataFramez@Strings cannot be passed as weights when sampling from a Series.float64)dtypez5Weights and axis to be sampled must be of same lengthz*weight vector may not include `inf` valuesz.weight vector many not include negative values) isinstancerreindexaxesstrrKeyError ValueError _constructor_constructor_sliced_valueslenshaperhas_infsanynpisnancopy)r weightsr errfuncmissings R/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/pandas/core/sample.pypreprocess_weightsr&s'9%%2//#(4.11'3 c< ( ( qyy!'lGG"E !" R #y!!'&d7),,,4G 7||sy&&PQQQ |GGEFFF! KIJJJhwG{{}},,.. Ns'A00 B:B  Bn int | Nonefrac float | Nonereplaceboolc||d}ns||td|.|dkrtd|dzdkrtdn0|J|dkr|std|dkrtd|S) z Process and validate the `n` and `frac` arguments to `NDFrame.sample` and `.GroupBy.sample`. Returns None if `frac` should be used (variable sampling sizes), otherwise returns the constant sampling size. Nz0Please enter a value for `frac` OR `n`, not bothrz=A negative number of rows requested. Please provide `n` >= 0.z$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)r'r)r+s r%process_sampling_sizer/Ps yT\  4+KLLL  q55O  q5A::CDD D  !88G88  !88R  Hobj_lenintsizer!np.ndarray | None random_state+np.random.RandomState | np.random.Generatorc|/|}|dkr||z }ntd|||||tjdS)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] Nrz$Invalid weights: weights sum to zero)r3r+pF)r )sumrchoiceastyperintp)r1r3r+r!r5 weight_sums r%sampler>usw8[[]] ?? *GGCDD D   wT7g  N N U U e V  r0)r r r rr r )r'r(r)r*r+r,r r() r1r2r3r2r+r,r!r4r5r6r r )__doc__ __future__rtypingrnumpyr pandas._libsrpandas.core.dtypes.genericrrpandas._typingrpandas.core.genericr r&r/r>r0r%rHs#"""""  ,&&&&&&++++++6666r" " " " J%%%%%%r0