o ŀg@s~dZddlmZddlmZddlZddlmZddl m Z m Z er.ddl m Z ddlmZd"ddZd#ddZd$d d!ZdS)%zH Module containing utilities for NDFrame.sample() and .GroupBy.sample() ) annotations) TYPE_CHECKINGN)lib) ABCDataFrame ABCSeries)AxisInt)NDFrameobjraxisrreturn np.ndarrayc Cst|tr ||j|}t|tr;t|tr7|dkr3z||}Wnty2}ztd|d}~wwtdtdt|trD|j}n|j }||ddj }t ||j |kr[tdt |rdtd |dkrntd t|}|r|}d||<|S) z Process and validate the `weights` argument to `NDFrame.sample` and `.GroupBy.sample`. Returns `weights` as an ndarray[np.float64], validated except for normalizing weights (because that must be done groupwise in groupby sampling). rz+String passed to weights not a valid columnNzLStrings can only be passed to weights when sampling from rows on a DataFramez@Strings cannot be passed as weights when sampling from a Series.float64)dtypez5Weights and axis to be sampled must be of same lengthz*weight vector may not include `inf` valuesz.weight vector many not include negative values) isinstancerreindexaxesstrrKeyError ValueError _constructor_constructor_sliced_valueslenshaperhas_infsanynpisnancopy)r weightsr errfuncmissingr#F/var/www/html/myenv/lib/python3.10/site-packages/pandas/core/sample.pypreprocess_weightssH        r%n int | Nonefrac float | NonereplaceboolcCs|dur |dur d}|S|dur|durtd|dur0|dkr$td|ddkr.td|S|dus6J|dkr@|s@td|dkrHtd|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$Only integers accepted as `n` valueszJReplace has to be set to `True` when upsampling the population `frac` > 1.z@A negative number of rows requested. Please provide `frac` >= 0.)r)r&r(r*r#r#r$process_sampling_sizePs.   r-obj_lenintsizernp.ndarray | None random_state+np.random.RandomState | np.random.GeneratorcCsH|dur|}|dkr||}ntd|j||||djtjddS)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$Invalid weights: weights sum to zero)r0r*pF)r)sumrchoiceastyperintp)r.r0r*rr2 weight_sumr#r#r$sampleus r:)r rr rr r )r&r'r(r)r*r+r r') r.r/r0r/r*r+rr1r2r3r r )__doc__ __future__rtypingrnumpyr pandas._libsrpandas.core.dtypes.genericrrpandas._typingrpandas.core.genericrr%r-r:r#r#r#r$s       9%