2i*UdZddlmZddlmZddlmZmZmZm Z m Z ddl Z ddl mZddlmZmZmZddlmZmZmZmZmZdd lmZdd lmZdd lmZmZm Z m!Z!m"Z"dd l#m$Z$m%Z%m&Z&dd l'm(Z(m)Z)m*Z*erddl+m,Z,ddlm-Z-ddl.m/Z/edZ0de1d<d8dZ2d9dZ3e dd d:dZ4e d;dZ4dd ddZ8 d?d Z9d@d!Z: dAd"Z;dBd#Z< dC dDd$Z=dEd%Z> dF dGd&Z? dH dId'Z@ dJ dKd(ZA dL dMd)ZB dN dOd*ZC dP dQd+ZD dR dSd,ZEdTd-ZFeF dU dVd.ZGeF dU dVd/ZHeF dU dVd0ZIeF dU dWd1ZJ dXd2ZK dXd3ZLeGeHd4ZMdYdZd5ZNd[d6ZO d\d7ZPy)]z$ Routines for filling missing data. ) annotations)wraps) TYPE_CHECKINGAnyLiteralcastoverloadN) is_nan_na)NaTalgoslib) ArrayLikeAxisIntF ReindexMethodnpt)import_optional_dependency)infer_dtype_from) is_array_like is_bool_dtypeis_numeric_dtypeis_object_dtypeneeds_i8_conversion) ArrowDtypeBaseMaskedDtypeDatetimeTZDtype)is_valid_na_for_dtypeisnana_value_for_dtype)Callable) TypeAlias)Index) not-a-knotclampednaturalperiodicr!_CubicBCcvt|r-t||k7rtdt|d|||}|S)zJ Validate the size of the values passed to ExtensionArray.fillna. z'Length of 'value' does not match. Got (z ) expected )rlen ValueError)valuemasklengths J/var/www/html/acx/venv/lib/python3.12/site-packages/pandas/core/missing.pycheck_value_sizer/>sPU u: 9#e*F#H& d  Lct|\}}t|jttfrt j |rtj|rts|jjdk(rt|jtr3tj|j|jz}|Sddl m}|j|j j#dj%}|S|jjdvr'tj&|j(t*}|St|r t|Stj&|j(t*}t-|jr-t/|jst j0|r |St/|jr#t-|rt j0|s |St-|jrt|t2r |St5|jrt|}|||k(||<|S||k(}t|tj6s|j%t*d}|}|S)a? Return a masking array of same size/shape as arr with entries equaling value set to True. Parameters ---------- arr : ArrayLike value : scalar-like Caller has ensured `not is_list_like(value)` and that it can be held by `arr`. Returns ------- np.ndarray[bool] frNFiudtype)r5na_value)r isinstancer5rrr is_floatnpisnanr kind_datarpyarrow.computecomputeis_nan _pa_array fill_nullto_numpyzerosshapeboolrris_boolstrrndarray)arrr+r5r,pcarr_masknew_masks r. mask_missingrMMs $E*LE5 399 ;< LL  HHUO  99>>S #))_5xx *chhj[8 -yy/99%@IIK YY^^t #88CIIT2DK E{Cy 88CIIT *D#cii( KK  , K) cii %5e%  ]":9+VF8TUU Mr0)lineartimeindexvalues)r\zeroslinear quadraticcubic barycentrickroghspline polynomialfrom_derivativespiecewise_polynomialpchipakima cubicsplinec |jd}|dvr | tdttz}||vrtd|d|d|dvr|jst|d|S) Norder)rkrlz7You must specify the order of the spline or polynomial.zmethod must be one of z. Got 'z ' instead.)rjrnroz4 interpolation requires that the index be monotonic.)getr* NP_METHODS SP_METHODSis_monotonic_increasing)rTrckwargsrsvalids r.clean_interp_methodrzs JJw E ))emRSS  #E U1%xzRSS ;;,,(NO  Mr0c|dvsJt|dk(ry|jdk(r|jd}|dk(r|ddj}n*|dk(r%t|dz |ddd jz }|}|sy|S) a+ Retrieves the positional index of the first valid value. Parameters ---------- how : {'first', 'last'} Use this parameter to change between the first or last valid index. is_valid: np.ndarray Mask to find na_values. Returns ------- int or None )firstlastrNaxisr|r})r)ndimanyargmax)howis_valididxpos chk_notnas r.find_valid_indexrs # ## # 8}}}<b B  r0c^|*ddg}|j}||vrtd|d|d|S)Ninsideoutsidez%Invalid limit_area: expecting one of z, got .r) limit_areavalid_limit_areass r.validate_limit_arear%sV%y1%%' . .78I7J&,a!  r0c| |dvrd}|Sd}|S|dvr|dk7rtd|d|dvr|dk7rtd|d|S)N)r[rZrr)rYrXz0`limit_direction` must be 'forward' for method ``z1`limit_direction` must be 'backward' for method `)r*)rrTs r.infer_limit_directionr3s * *(O (O  % %/Y*FB6(!L  * **/LCF81M  r0c|dk(rddlm}|t|}nhd}t|jxs<t |jt xs tj|jd}ttz}||vr||vr |std|dtd|d t|jr td |S) Nrar) RangeIndex>rbrcrdr\mMz9Index column must be numeric or datetime type when using z_ method other than linear. Try setting a numeric or datetime index column before interpolating. Can not interpolate with method=rzkInterpolation with NaNs in the index has not been implemented. Try filling those NaNs before interpolating.)pandasrr)rr5r7rr is_np_dtyperurvr*rrNotImplementedError)rTrcrmethodsis_numeric_or_datetimerys r.get_interp_indexrHs %3u:&8 U[[ ) 2%++7 2u{{D1  Z' U?W$-C #H%%%?xqIJ J E{! /  Lr0c  t|fi t|jrt|jddk(r"t |js t ddt t| tjdt| d   fd } tj| ||y) 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)compatrbzStime-weighted interpolation only works on Series or DataFrames with a DatetimeIndexrdN)nobslimitc 0td|dd y)NF) indicesyvaluesrTrrr fill_value bounds_errorr,rR)_interpolate_1d) rrrrxrlimit_area_validatedrr,rTs r.funcz$interpolate_2d_inplace..funcs7  ++!  r0)r np.ndarrayreturnNone) rzrr5rrr*rrr validate_limit_index_to_interp_indicesr9apply_along_axis) datarcrrTrrrrr,rxrrrs ``` ``` @@r.interpolate_2d_inplacerks.00Z4' 5A  "5;;/   .?O.z:  d% 8E&uf5G  dD)r0cF|j}t|jr|jd}|dk(r|}t t j |}|St j|}|dvr2|jt jk(rtj|}|S)zE Convert Index to ndarray of indices to pass to NumPy/SciPy. i8ra)rdrc) _valuesrr5viewrr9rHasarrayobject_r maybe_convert_objects)rcrTxarrindss r.rrs ==D4::&yy BJJ% K zz$ ( (zzRZZ'006 Kr0c  | | } n t|} | } | jsy| jrytj| } t d| }|d}tj |}t d| }| t|}tj d|zt| }|dk(r"tj|t| |d}nG|dk(r"tj|t| d|}n tjt| ||}|d k(r-tj||}tj||}nK|d k(rFtj| |d }tj||d }tj||}|jjd v}|r|jd}|tvrBtj || }tj"|| || ||| ||| <nt%|| || || f||||d| || <| d| ddd | |<y|rt&j(||<ytj*||<y)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|)rrrr}rrrrrT assume_uniquerr)rTrrrsF)rrallr9 flatnonzeroraranger)union1d _interp_limitunique setdiff1dr5r;rruargsortinterp_interpolate_scipy_wrapperr r+nan)rrrTrrrrrrsr,rxinvalidryall_nansfirst_valid_index start_nanslast_valid_indexend_nans preserve_nansmid_nansis_datetimelikeindexers r.rrsj0 w- HE 99; yy{~~g&H(WuE ,-J'FUCw<yy--s5z:H)# :}WeQ/OP J & 8]7Au-MN  -"FG X =*=  =(; y <<*DI<<($G =(; mm((D0O,,t$ **WU^,99 G genW5wu~g7N 6 EN EN G   !%     Q"]  !$  "$  r0c |d}td|ddlm} tj|}| j | j tttt| jd} gd} || vr*|dk(r|} n|} | j||| || } | |}|S|d k(r>t|s|dkrtd || j||fd |i|} | |}|S|jj s|j#}|jj s|j#}|jj s|j#}| j%|d } | td|d|j'dd | |||fi|}|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)rirjrmrnrqrpro)r\rerfrgrhrlrl)r;rrrkz;order needs to be specified and greater than 0; got order: kNrrdowncast)rrrr9rbarycentric_interpolatekrogh_interpolate_from_derivatives_cubicspline_interpolate_akima_interpolatepchip_interpolateinterp1drr*UnivariateSplineflags writeablecopyrtpop)xynew_xrTrrrsrxrr alt_methodsinterp1d_methodsr;terpnew_ys r.rr1sh4 5Ewe4! JJu E#::..- 1/#..9K!! \ !DD## qt $ U 2 L1 8  ;5A:MeWU ,{++AqDEDVDU " Lww  Aww  A{{$$JJLEvt, <?xqIJ J  :t$Q5+F+ Lr0cddlm}|jj}|||j dd||}||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. rrrr)orders extrapolate)rrBPolyrmreshape) xiyirrsderrrrTms r.rr~s?R"   / /Fr2::b!$U LA Q4Kr0cJddlm}|j|||}|||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 : np.ndarray A sorted list of x-coordinates, of length N. yi : np.ndarray 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 : np.ndarray Of length M. der : int, optional How many 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, rrr)nu)rrAkima1DInterpolator)rrrrrrPs r.rrs+P"''BT':A Q3<r0cJddlm}|j|||||}||S)ag Convenience function for cubic spline data interpolator. See `scipy.interpolate.CubicSpline` for details. Parameters ---------- xi : np.ndarray, shape (n,) 1-d array containing values of the independent variable. Values must be real, finite and in strictly increasing order. yi : np.ndarray 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 : np.ndarray, 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 `_ on Wikiversity. .. [2] Carl de Boor, "A Practical Guide to Splines", Springer-Verlag, 1978. rr)rbc_typer)rr CubicSpline)rrrrrrrrs r.rrs3Z" BT7   A Q4Kr0c|dk(rdnd}|jdk(r/|dk7r td|jdg|j}t |}||}t |d}||||y ) 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. rc|SrQrRrs r.z)pad_or_backfill_inplace..Qsr0c|jSrQ)Trs r.r z)pad_or_backfill_inplace..Qs r0rz1cannot interpolate on an ndim == 1 with axis != 0r~)r)rrN)rAssertionErrorrrDrU get_fill_func)rdrTrrrtransftvaluesrs r.pad_or_backfill_inplacer5sw8#aikmF{{a 19 !TU U 2V\\ 23 v &FVnG a (D*5r0c | t|}|SrQ)r)rdr,s r. _fillna_prepras  |F| Kr0cZt d dfd }tt|S)z> Wrapper to handle datetime64 and timedelta64 dtypes. ct|jrH| t|}|jd|||\}}|j|j|fS||||S)Nr)rrr,)rr5rr)rdrrr,resultrs r.new_funcz&_datetimelike_compat..new_funcqsj v|| ,|F| D!:DLFD;;v||,d2 2F%JTJJr0NNN)r int | Noner#Literal['inside', 'outside'] | None)rrr)rrs` r._datetimelike_compatrlsK  4[!:>  KK8KK$ 8 r0ct||}||js t||tj|||||fSN)r)rr_fill_limit_area_1dr pad_inplacerdrrr,s r._pad_1dr sD  %DdhhjD*- fd%0 4<r0ct||}||js t||tj|||||fSr)rrrr backfill_inplacers r. _backfill_1dr#sD  %DdhhjD*- 64u5 4<r0ct||}| t|||jrtj|||||fSr)r_fill_limit_area_2dsizer pad_2d_inplacers r._pad_2dr(sC  %DD*- {{ VT7 4<r0ct||}| t|||jrtj|||||fS ||fSr)rr%r&r backfill_2d_inplacers r. _backfill_2dr+sT  %DD*- {{ !!&$e< 4< 4<r0c|}|j}t||dddjz dz }|dk(rd|d|d||dzdy|dk(r d||dz|yy)aPrepare 1d mask for ffill/bfill with limit_area. Caller is responsible for checking at least one value of mask is False. When called, mask will no longer faithfully represent when the corresponding are NA or not. Parameters ---------- mask : np.ndarray[bool, ndim=1] Mask representing NA values when filling. limit_area : { "outside", "inside" } Whether to limit filling to outside or inside the outer most non-NA value. NrrrFr)rr))r,rneg_maskr|r}s r.rrs{ uH OO E x=8DbD>002 2Q 6DXVe  TAXZ y !&UQY !r0c|j}|dk(rPtjj|dtjj|dddddddz}nQtjj|dtjj|dddddddz}d||j<y)aPrepare 2d mask for ffill/bfill with limit_area. When called, mask will no longer faithfully represent when the corresponding are NA or not. Parameters ---------- mask : np.ndarray[bool, ndim=1] Mask representing NA values when filling. limit_area : { "outside", "inside" } Whether to limit filling to outside or inside the outer most non-NA value. rrrNrF)r r9maximum accumulate)r,rr-la_masks r.r%r%swHY JJ ! !( ! 3jj##HTrTN#;DbDA B ZZ " "8! " 4 4zz$$Xdd^!$.inner5sE1 66'';;GUQYOSSTUVjj HHX q !E ) HHw{++335: ;A >  r0NrFrrr)rint)r)r9arrayint64r< intersect1d)rfw_limitbw_limitf_idxb_idxrrAr@s @r.rrsB G A HHRrxx (E HHRrxx (EM q=HHW%a(E!M'8,E q=LEE'$B$-::E1} >>%m DDr0)r,npt.NDArray[np.bool_]r-rB)rIrrrJ)rTz,Literal['ffill', 'pad', 'bfill', 'backfill']rOzLiteral[False]rLiteral['pad', 'backfill'])rT7Literal['ffill', 'pad', 'bfill', 'backfill', 'nearest']rOz Literal[True]r%Literal['pad', 'backfill', 'nearest'])rTrLrOrErrM)rTrGrcr"rrG)rrGrrJrr)rrGrz&Literal['forward', 'backward', 'both'])r str | Nonerr)rz-Literal['backward', 'forward', 'both'] | NonerTrGrz&Literal['backward', 'forward', 'both'])rcr"rr")raNrNNN)rrrcr"rrrTrGrrrrGrrNr Any | Nonerr)rcr"rTrGrr)raNrNNFNN)rrrrrTrGrrrrGrrrrOrrErsrrr)NFN) rrrrrrrTrGrrE)NrF) rrrrrrrzint | list[int] | NonerrE)rr) rrrrrrrrBrr)rr#N)rrrrrrrrrz_CubicBC | tuple[Any, Any]rz!Literal['periodic'] | bool | Nonerr)rYrNN) rdrrTrKrrrrrrrrrQ)r,npt.NDArray[np.bool_] | NonerrJ)rrrrr) rdrrrrrr,rPrz(tuple[np.ndarray, npt.NDArray[np.bool_]])rrrrr,rP)r,rJrzLiteral['outside', 'inside']rr)r)rrB)rzReindexMethod | None)rrJrFrrGrrr)Q__doc__ __future__r functoolsrtypingrrrrr numpyr9pandas._configr pandas._libsr r r pandas._typingrrrrrpandas.compat._optionalrpandas.core.dtypes.castrpandas.core.dtypes.commonrrrrrpandas.core.dtypes.dtypesrrrpandas.core.dtypes.missingrrrcollections.abcr r!rr"r'__annotations__r/rMrUrurvrzrrrrrrrrrrrrrrrr r#r(r+rr%r4r r6rrRr0r.r`s#$ ?4  ( !"PQHiQ L^ %(% 8%"% % % 0 C0!0+ 0 0  C+ 43  $&$N  +  BLO+* N$!! =* =* =* =*  =*  =*  =*=*=* =*@2$6:! m m m  m   m  m 4 m m m  m  m j JJJ J  J  Jb "# //// /  /l ,,,, ,  ,f*659 SSSS  S ( S 3 SSp*/6: )6 )6 &)6 )6  )6 4 )6  )6Z26.66:)-     4  '  .  6:)-     4  '  .  6:)-     4  '  .  6:)-  4 ' $' '-I' '4 -I > \: >9 @E "@E.8@EDN@E@Er0