U
|
¬ý°d¦ ã @ s d Z ddlmZ ddlmZ ddlZddlmZ ddl m
|
Z
|
ddl m Z m Z er\ddlmZ d d
|
d d d dZdddddddZdddddd dddZdS )zH
|
Module containing utilities for NDFrame.sample() and .GroupBy.sample()
|
é )Ú annotations)Ú TYPE_CHECKINGN)Úlib)ÚAxisInt)Ú ABCDataFrameÚ ABCSeries)ÚNDFramer r z
|
np.ndarray)ÚobjÚaxisÚreturnc
|
C s t |tr| | j| ¡}t |trt | tr||dkrrz | | }W qz tk
|
rn } ztd|W 5 d}~X Y qzX qtdntdt | tr| j}n| j }||ddj
|
}t || j | krÄtdt |¡rÖtd |dk ¡ rêtd
|
t |¡}| ¡ r| ¡ }d||< |S ) zþ
|
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).
|
r z+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.Úfloat64)Zdtypez5Weights and axis to be sampled must be of same lengthz*weight vector may not include `inf` valuesz.weight vector many not include negative values)Ú
|
isinstancer ZreindexZaxesÚstrr ÚKeyErrorÚ
|
ValueErrorZ _constructorZ_constructor_slicedZ_valuesÚlenÚshaper Zhas_infsÚanyÚnpÚisnanÚcopy)r Úweightsr
|
ÚerrÚfuncÚmissing© r úId:\z\workplace\vscode\pyvenv\venv\Lib\site-packages\pandas/core/sample.pyÚpreprocess_weights sD
|
|
|
ÿþÿÿ
|
|
|
|
r z
|
int | Nonez float | NoneÚbool)ÚnÚfracÚreplacer c C s | dkr|dkrd} nx| dk r0|dk r0t dn^| dk r^| dk rHt d| d dkrt dn0|dk sjt|dkr~|s~t d|dk rt d| S ) zâ
|
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.
|
Né z0Please enter a value for `frac` OR `n`, not bothr z=A negative number of rows requested. Please provide `n` >= 0.z$Only integers accepted as `n` valueszJReplace has to be set to `True` when upsampling the population `frac` > 1.z@A negative number of rows requested. Please provide `frac` >= 0.)r ÚAssertionError)r r r! r r r Úprocess_sampling_sizeO s*
|
ÿ
|
ÿÿr$ Úintznp.ndarray | Nonez+np.random.RandomState | np.random.Generator)Úobj_lenÚsizer! r Ú random_stater c C sH |dk r*| ¡ }|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]
|
Nr z$Invalid weights: weights sum to zero)r' r! ÚpF)r )Úsumr ÚchoiceZastyper Zintp)r& r' r! r r( Z
|
weight_sumr r r Úsamplet s
|
ÿr, )Ú__doc__Ú
|
__future__r Útypingr Únumpyr Z pandas._libsr Zpandas._typingr Zpandas.core.dtypes.genericr r Zpandas.core.genericr r r$ r, r r r r Ú<module> s 9%
|
