o
    i+u                     @  s0  d Z ddlmZ ddlmZmZ ddlmZmZm	Z	 ddl
ZddlmZmZ ddlmZmZmZmZ ddlmZ dd	lmZ dd
lmZmZmZ ddlmZmZmZ erZddl m!Z! drddZ"dsddZ#dtduddZ$g dZ%g d Z&dvd$d%Z'dwd(d)Z(	*				+				dxdyd8d9Z)	:		+		dzd{d;d<Z*d|d=d>Z+	:		+				d}d~dCdDZ,	ddEdFZ-ddGdHZ.ddIdJZ/ddLdMZ0ddOdPZ1	*			dddRdSZ2	dddUdVZ3ddYdZZ4e4		ddd\d]Z5e4		ddd^d_Z6e4ddd`daZ7e4dddbdcZ8e5e6ddZ9dddgdhZ:ddidjZ;ddldmZ<ddpdqZ=dS )z$
Routines for filling missing data.
    )annotations)partialwraps)TYPE_CHECKINGAnycastN)algoslib)	ArrayLikeAxisFnpt)import_optional_dependency)infer_dtype_from)is_array_likeis_numeric_v_string_likeneeds_i8_conversion)is_valid_na_for_dtypeisnana_value_for_dtype)Indexmasknpt.NDArray[np.bool_]lengthintc                 C  s8   t | rt| |krtdt|  d| | | } | S )zJ
    Validate the size of the values passed to ExtensionArray.fillna.
    z'Length of 'value' does not match. Got (z)  expected )r   len
ValueError)valuer   r    r   N/var/www/edux/Edux_v2/venv/lib/python3.10/site-packages/pandas/core/missing.pycheck_value_size.   s   r    arrr
   returnc                 C  s   t |\}}tj||d}t|}||  }tj| jtd}|D ]}t| |r(q | |k}t|tj	s9|j
tdd}||O }q | rH|t| O }|S )a	  
    Return a masking array of same size/shape as arr
    with entries equaling any member of values_to_mask set to True

    Parameters
    ----------
    arr : ArrayLike
    values_to_mask: list, tuple, or scalar

    Returns
    -------
    np.ndarray[bool]
    )dtypeF)r#   na_value)r   nparrayr   zerosshapeboolr   
isinstancendarrayto_numpyany)r!   values_to_maskr#   na_masknonnar   xnew_maskr   r   r   mask_missing=   s   


r3   Fmethod
str | Noneallow_nearestr)   c                 C  sv   | dv rd S t | tr|  } | dkrd} n| dkrd} ddg}d}|r+|d d}| |vr9td	| d
|  | S )N)Nasfreqffillpadbfillbackfillzpad (ffill) or backfill (bfill)nearestz(pad (ffill), backfill (bfill) or nearestzInvalid fill method. Expecting z. Got )r*   strlowerappendr   )r4   r6   valid_methods	expectingr   r   r   clean_fill_methodk   s    

rB   )lineartimeindexvalues)r<   zeroslinear	quadraticcubicbarycentrickroghspline
polynomialfrom_derivativespiecewise_polynomialpchipakimacubicspliner=   rE   r   c                 K  sh   | d}| dv r|d u rtdtt }| |vr$td| d|  d| dv r2|js2t|  d| S )	Norder)rM   rN   z7You must specify the order of the spline or polynomial.zmethod must be one of z. Got 'z
' instead.)rL   rP   rQ   z4 interpolation requires that the index be monotonic.)getr   
NP_METHODS
SP_METHODSis_monotonic_increasing)r4   rE   kwargsrT   validr   r   r   clean_interp_method   s   
r[   how
int | Nonec                C  s   |dv sJ t | dkrdS t|  }| jdkr|jdd}|dkr+|dd  }n|dkr>t | d |ddd	   }|| }|sFdS |S )
a  
    Retrieves the index of the first valid value.

    Parameters
    ----------
    values : ndarray or ExtensionArray
    how : {'first', 'last'}
        Use this parameter to change between the first or last valid index.

    Returns
    -------
    int or None
    )firstlastr   N      axisr^   r_   )r   r   ndimr-   argmax)rF   r\   is_valididxpos	chk_notnar   r   r   find_valid_index   s   

rj   r9   forwarddata
np.ndarrayrc   Index | Nonelimitlimit_direction
limit_area
fill_value
Any | NonecoercedowncastNonec
                 K  s   zt |}W n ty   d}Y nw |dur)|durtdt| ||||d dS |dus/J td| |||||||d|
 dS )z
    Wrapper to dispatch to either interpolate_2d or _interpolate_2d_with_fill.

    Notes
    -----
    Alters 'data' in-place.
    Nz&Cannot pass both fill_value and method)r4   rc   ro   rq   )rl   rE   rc   r4   ro   rp   rq   rr   r   )rB   r   interpolate_2d_interpolate_2d_with_fill)rl   r4   rc   rE   ro   rp   rq   rr   rt   ru   rY   mr   r   r   interpolate_array_2d   s<   	rz   rC   c                   s   t |fi  t | jrt| jdd dkr%t|js#tddg d}	 |	vr<td|	 d d	d
urWddg}
 |
vrWtd|
 d dtjd
dt	|d fdd}t
|||  d
S )z
    Column-wise application of _interpolate_1d.

    Notes
    -----
    Alters 'data' in-place.

    The signature does differ from _interpolate_1d because it only
    includes what is needed for Block.interpolate.
    F)compatrD   zStime-weighted interpolation only works on Series or DataFrames with a DatetimeIndexrF   )rk   backwardbothz*Invalid limit_direction: expecting one of z, got 'z'.Ninsideoutsidez%Invalid limit_area: expecting one of z, got .)nobsro   yvaluesrm   r"   rv   c                   s$   t d|  dd d S )NF)indicesr   r4   ro   rp   rq   rr   bounds_errorr   )_interpolate_1d)r   rr   r   rY   ro   rq   rp   r4   r   r   funcA  s   	
z'_interpolate_2d_with_fill.<locals>.func)r   rm   r"   rv   )r[   r   r#   r   r   r   r>   r   validate_limit_index_to_interp_indicesr%   apply_along_axis)rl   rE   rc   r4   ro   rp   rq   rr   rY   valid_limit_directionsvalid_limit_areasr   r   r   r   rx     sB   

rx   c                 C  sb   | j }t|jr|d}|dkr|}ttj|}|S t|}|dv r/|jtjkr/t	
|}|S )zE
    Convert Index to ndarray of indices to pass to NumPy/SciPy.
    i8rC   )rF   rE   )_valuesr   r#   viewr   r%   r+   asarrayobject_r	   maybe_convert_objects)rE   r4   xarrindsr   r   r   r   Z  s   



r   r   r   r   rT   c	                 K  s  t |}
|
 }| sdS | rdS tt|
}t|dd}|du r&d}tt|}t|dd}|du r:t|}ttd| t|}|dkrT|tt	|
|dB }n|dkrc|tt	|
d|B }ntt	|
||}|d	krv|||B O }n|d
kr|| | }||O }t
|}|tv rt| | }t| |
 | | | || | ||
< nt| | || | |
 f||||d|	||
< tj||< dS )a  
    Logic for the 1-d interpolation.  The input
    indices and yvalues will each be 1-d arrays of the same length.

    Bounds_error is currently hardcoded to False since non-scipy ones don't
    take it as an argument.

    Notes
    -----
    Fills 'yvalues' in-place.
    Nr^   r\   r   r_   ra   rk   r|   r~   r   )r4   rr   r   rT   )r   r-   allsetr%   flatnonzerorj   ranger   _interp_limitsortedrV   argsortinterp_interpolate_scipy_wrappernan)r   r   r4   ro   rp   rq   rr   r   rT   rY   invalidrZ   all_nansfirst_valid_index
start_nanslast_valid_indexend_nanspreserve_nansmid_nansindexerr   r   r   r   p  sZ   


r   c                 K  sn  | d}t d|d ddlm}	 t|}|	j|	jttd}
t| ddr1| j	
d	|
d	} }|d
kr;|	j|
d
< n|dkrDt|
d< n|dkrLt|
d< g d}||v rj|dkrZ|}|	j| ||||d}||}|S |dkrt|sv|dkr}td| |	j| |fd|i|}||}|S | jjs|  } |jjs| }|jjs| }|
| }|| ||fi |}|S )z
    Passed off to scipy.interpolate.interp1d. method is scipy's kind.
    Returns an array interpolated at new_x.  Add any new methods to
    the list in _clean_interp_method.
    z interpolation requires SciPy.scipy)extrar   interpolate)rK   rL   rO   rP   _is_all_datesFr   rQ   rR   rS   )r<   rG   rH   rI   rJ   rN   rN   )kindrr   r   rM   z;order needs to be specified and greater than 0; got order: k)r   r   r   r%   r   barycentric_interpolatekrogh_interpolate_from_derivativesgetattrr   astypepchip_interpolate_akima_interpolate_cubicspline_interpolateinterp1dr   r   UnivariateSplineflags	writeablecopy)r1   ynew_xr4   rr   r   rT   rY   r   r   alt_methodsinterp1d_methodsterpnew_yr   r   r   r     sV   



r   c           	      C  s4   ddl m} |jj}|| |dd||d}||S )a  
    Convenience function for interpolate.BPoly.from_derivatives.

    Construct a piecewise polynomial in the Bernstein basis, compatible
    with the specified values and derivatives at breakpoints.

    Parameters
    ----------
    xi : array-like
        sorted 1D array of x-coordinates
    yi : array-like or list of array-likes
        yi[i][j] is the j-th derivative known at xi[i]
    order: None or int or array-like of ints. Default: None.
        Specifies the degree of local polynomials. If not None, some
        derivatives are ignored.
    der : int or list
        How many derivatives to extract; None for all potentially nonzero
        derivatives (that is a number equal to the number of points), or a
        list of derivatives to extract. This number includes the function
        value as 0th derivative.
     extrapolate : bool, optional
        Whether to extrapolate to ouf-of-bounds points based on first and last
        intervals, or to return NaNs. Default: True.

    See Also
    --------
    scipy.interpolate.BPoly.from_derivatives

    Returns
    -------
    y : scalar or array-like
        The result, of length R or length M or M by R.
    r   r   rd   ra   )ordersextrapolate)r   r   BPolyrO   reshape)	xiyir1   rT   derr   r   r4   ry   r   r   r   r     s   "r   c                 C  s(   ddl m} |j| ||d}|||dS )a[  
    Convenience function for akima interpolation.
    xi and yi are arrays of values used to approximate some function f,
    with ``yi = f(xi)``.

    See `Akima1DInterpolator` for details.

    Parameters
    ----------
    xi : array-like
        A sorted list of x-coordinates, of length N.
    yi : array-like
        A 1-D array of real values.  `yi`'s length along the interpolation
        axis must be equal to the length of `xi`. If N-D array, use axis
        parameter to select correct axis.
    x : scalar or array-like
        Of length M.
    der : int, optional
        How many derivatives to extract; None for all potentially
        nonzero derivatives (that is a number equal to the number
        of points), or a list of derivatives to extract. This number
        includes the function value as 0th derivative.
    axis : int, optional
        Axis in the yi array corresponding to the x-coordinate values.

    See Also
    --------
    scipy.interpolate.Akima1DInterpolator

    Returns
    -------
    y : scalar or array-like
        The result, of length R or length M or M by R,

    r   r   rb   )nu)r   r   Akima1DInterpolator)r   r   r1   r   rc   r   Pr   r   r   r   E  s   $r   
not-a-knotc                 C  s(   ddl m} |j| ||||d}||S )aq  
    Convenience function for cubic spline data interpolator.

    See `scipy.interpolate.CubicSpline` for details.

    Parameters
    ----------
    xi : array-like, shape (n,)
        1-d array containing values of the independent variable.
        Values must be real, finite and in strictly increasing order.
    yi : array-like
        Array containing values of the dependent variable. It can have
        arbitrary number of dimensions, but the length along ``axis``
        (see below) must match the length of ``x``. Values must be finite.
    x : scalar or array-like, shape (m,)
    axis : int, optional
        Axis along which `y` is assumed to be varying. Meaning that for
        ``x[i]`` the corresponding values are ``np.take(y, i, axis=axis)``.
        Default is 0.
    bc_type : string or 2-tuple, optional
        Boundary condition type. Two additional equations, given by the
        boundary conditions, are required to determine all coefficients of
        polynomials on each segment [2]_.
        If `bc_type` is a string, then the specified condition will be applied
        at both ends of a spline. Available conditions are:
        * 'not-a-knot' (default): The first and second segment at a curve end
          are the same polynomial. It is a good default when there is no
          information on boundary conditions.
        * 'periodic': The interpolated functions is assumed to be periodic
          of period ``x[-1] - x[0]``. The first and last value of `y` must be
          identical: ``y[0] == y[-1]``. This boundary condition will result in
          ``y'[0] == y'[-1]`` and ``y''[0] == y''[-1]``.
        * 'clamped': The first derivative at curves ends are zero. Assuming
          a 1D `y`, ``bc_type=((1, 0.0), (1, 0.0))`` is the same condition.
        * 'natural': The second derivative at curve ends are zero. Assuming
          a 1D `y`, ``bc_type=((2, 0.0), (2, 0.0))`` is the same condition.
        If `bc_type` is a 2-tuple, the first and the second value will be
        applied at the curve start and end respectively. The tuple values can
        be one of the previously mentioned strings (except 'periodic') or a
        tuple `(order, deriv_values)` allowing to specify arbitrary
        derivatives at curve ends:
        * `order`: the derivative order, 1 or 2.
        * `deriv_value`: array-like containing derivative values, shape must
          be the same as `y`, excluding ``axis`` dimension. For example, if
          `y` is 1D, then `deriv_value` must be a scalar. If `y` is 3D with
          the shape (n0, n1, n2) and axis=2, then `deriv_value` must be 2D
          and have the shape (n0, n1).
    extrapolate : {bool, 'periodic', None}, optional
        If bool, determines whether to extrapolate to out-of-bounds points
        based on first and last intervals, or to return NaNs. If 'periodic',
        periodic extrapolation is used. If None (default), ``extrapolate`` is
        set to 'periodic' for ``bc_type='periodic'`` and to True otherwise.

    See Also
    --------
    scipy.interpolate.CubicHermiteSpline

    Returns
    -------
    y : scalar or array-like
        The result, of shape (m,)

    References
    ----------
    .. [1] `Cubic Spline Interpolation
            <https://en.wikiversity.org/wiki/Cubic_Spline_Interpolation>`_
            on Wikiversity.
    .. [2] Carl de Boor, "A Practical Guide to Splines", Springer-Verlag, 1978.
    r   r   )rc   bc_typer   )r   r   CubicSpline)r   r   r1   rc   r   r   r   r   r   r   r   r   p  s
   F
r   rF   c                 C  s   t | }| sMt| dd}|du rd}t| dd}|du r"t| }t| ||d |dkr6d|||d	 < n|d
krHd |d|< ||d	 d< tj| |< dS )a  
    Apply interpolation and limit_area logic to values along a to-be-specified axis.

    Parameters
    ----------
    values: np.ndarray
        Input array.
    method: str
        Interpolation method. Could be "bfill" or "pad"
    limit: int, optional
        Index limit on interpolation.
    limit_area: str
        Limit area for interpolation. Can be "inside" or "outside"

    Notes
    -----
    Modifies values in-place.
    r^   r   Nr   r_   )r4   ro   r~   Fra   r   )r   r   rj   r   rw   r%   r   )rF   r4   ro   rq   r   r^   r_   r   r   r   _interpolate_with_limit_area  s&   
r   r   c                 C  s   |durt tt|||d||  dS |dkrdd ndd }| jdkr6|dkr,td| td	| j } t	|}|| }|d
krJt
||d dS t||d dS )a  
    Perform an actual interpolation of values, values will be make 2-d if
    needed fills inplace, returns the result.

    Parameters
    ----------
    values: np.ndarray
        Input array.
    method: str, default "pad"
        Interpolation method. Could be "bfill" or "pad"
    axis: 0 or 1
        Interpolation axis
    limit: int, optional
        Index limit on interpolation.
    limit_area: str, optional
        Limit area for interpolation. Can be "inside" or "outside"

    Notes
    -----
    Modifies values in-place.
    N)r4   ro   rq   r   c                 S  s   | S Nr   r1   r   r   r   <lambda>"  s    z interpolate_2d.<locals>.<lambda>c                 S  s   | j S r   )Tr   r   r   r   r   "  s    ra   z0cannot interpolate on a ndim == 1 with axis != 0ra   r9   ro   )r%   r   r   r   re   AssertionErrorr   tupler(   rB   _pad_2d_backfill_2d)rF   r4   rc   ro   rq   transftvaluesr   r   r   rw     s0   	
rw   npt.NDArray[np.bool_] | Nonec                 C  s    |d u rt | }|tj}|S r   )r   r   r%   uint8)rF   r   r   r   r   _fillna_prep6  s   r   r   r   c                   s    t  d fdd	}tt|S )z>
    Wrapper to handle datetime64 and timedelta64 dtypes.
    Nc                   sP   t | jr!|d u rt| } | d||d\}}|| j|fS  | ||dS )Nr   )ro   r   )r   r#   r   r   )rF   ro   r   resultr   r   r   new_funcG  s   
z&_datetimelike_compat.<locals>.new_funcNN)r   r   r   )r   r   r   r   r   _datetimelike_compatB  s   
r   (tuple[np.ndarray, npt.NDArray[np.bool_]]c                 C  "   t | |}tj| ||d | |fS Nr   )r   r   pad_inplacerF   ro   r   r   r   r   _pad_1dV     
r   c                 C  r   r   )r   r   backfill_inplacer   r   r   r   _backfill_1da  r   r   c                 C  8   t | |}t| jrtj| ||d | |fS 	 | |fS r   )r   r%   r   r(   r   pad_2d_inplacer   r   r   r   r   l     
r   c                 C  r   r   )r   r%   r   r(   r   backfill_2d_inplacer   r   r   r   r   x  r   r   r9   r;   ra   re   c                 C  s&   t | } |dkrt|  S ttd|  S )Nra   r   )rB   _fill_methodsr   r   )r4   re   r   r   r   get_fill_func  s   r   c                 C  s   t | ddS )NT)r6   )rB   )r4   r   r   r   clean_reindex_fill_method  s   r   r   c                   s   t |  t }t } fdd}|dur'|dkr"tt| d }n|| |}|durN|dkr1|S t|| ddd |}t d t| }|dkrN|S ||@ S )ak  
    Get indexers of values that won't be filled
    because they exceed the limits.

    Parameters
    ----------
    invalid : np.ndarray[bool]
    fw_limit : int or None
        forward limit to index
    bw_limit : int or None
        backward limit to index

    Returns
    -------
    set of indexers

    Notes
    -----
    This is equivalent to the more readable, but slower

    .. code-block:: python

        def _interp_limit(invalid, fw_limit, bw_limit):
            for x in np.where(invalid)[0]:
                if invalid[max(0, x - fw_limit):x + bw_limit + 1].all():
                    yield x
    c                   s`   t | }t| |d d}tt|d | tt| d |d    dkd B }|S )Nra   r   )min_rolling_windowr   r   r%   wherecumsum)r   ro   windowedidxNr   r   inner  s   
"z_interp_limit.<locals>.innerNr   rd   ra   )r   r   r%   r   listr   )r   fw_limitbw_limitf_idxb_idxr   	b_idx_invr   r   r   r     s    
r   awindowc                 C  sJ   | j dd | j d | d |f }| j| jd f }tjjj| ||dS )z
    [True, True, False, True, False], 2 ->

    [
        [True,  True],
        [True, False],
        [False, True],
        [True, False],
    ]
    Nrd   ra   )r(   strides)r(   r  r%   r	   stride_tricks
as_strided)r  r  r(   r  r   r   r   r     s   $r   )r   r   r   r   )r!   r
   r"   r   )F)r4   r5   r6   r)   )r4   r=   rE   r   r"   r=   )r\   r=   r"   r]   )	r9   r   NNrk   NNFN)rl   rm   r4   r=   rc   r   rE   rn   ro   r]   rp   r=   rq   r5   rr   rs   rt   r)   ru   r5   r"   rv   )rC   Nrk   NN)rl   rm   rE   r   rc   r   r4   r=   ro   r]   rp   r=   rq   r5   rr   rs   r"   rv   )rE   r   r4   r=   r"   rm   )rC   Nrk   NNFN)r   rm   r   rm   r4   r5   ro   r]   rp   r=   rq   r5   rr   rs   r   r)   rT   r]   )NFN)Nr   F)r   r   )r   r   N)
rF   rm   r4   r=   ro   r]   rq   r5   r"   rv   )r9   r   NN)rF   rm   r4   r=   rc   r   ro   r]   rq   r5   r"   rv   r   )r   r   r"   r   )r   r   r"   r   r   )rF   rm   ro   r]   r   r   r"   r   )rF   rm   r   r   )r   r   r   )re   r   )r"   r5   )r   r   )r  r   r  r   r"   r   )>__doc__
__future__r   	functoolsr   r   typingr   r   r   numpyr%   pandas._libsr   r	   pandas._typingr
   r   r   r   pandas.compat._optionalr   pandas.core.dtypes.castr   pandas.core.dtypes.commonr   r   r   pandas.core.dtypes.missingr   r   r   pandasr   r    r3   rB   rV   rW   r[   rj   rz   rx   r   r   r   r   r   r   r   rw   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   <module>   s    

.

':
Se

F
+
+
O2H





A