n[we}tdZddlmZddlmZmZddlmZmZm Z m Z ddl Z ddl mZmZmZddlmZmZmZmZmZddlmZdd lmZdd lmZmZmZmZm Z dd l!m"Z"dd l#m$Z$m%Z%m&Z&erdd l'm(Z(dldZ)dmdZ*dndodZ+gdZ,gdZ-dpd!Z.dqd%Z/drd(Z0dsd,Z1d-Z2dtd.Z3 dudvd9Z4dwd:Z5 dxdyd?Z6 dzd{dCZ7 d|d}dIZ8 d~ddJZ9 dddNZ:ddRZ; dddTZ< dddVZ=ddYZ>e> ddd[Z?e> ddd\Z@e> ddd]ZAe> ddd^ZBe?e@d_ZCdddbZDdddZEddhZFddkZGdS)z$ Routines for filling missing data. ) annotations)partialwraps) TYPE_CHECKINGAnyLiteralcastN)NaTalgoslib) ArrayLikeAxisIntF ReindexMethodnpt)import_optional_dependency)infer_dtype_from) is_array_likeis_numeric_dtypeis_numeric_v_string_likeis_object_dtypeneeds_i8_conversion)DatetimeTZDtype)is_valid_na_for_dtypeisnana_value_for_dtypeIndexmasknpt.NDArray[np.bool_]lengthintct|r=t||kr"tdt|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)valuerr!s 3lib/python3.11/site-packages/pandas/core/missing.pycheck_value_sizer(4skU u::  &#e**&&#&& d  Larrr returnc:t|\}}t|tjrtj||}nC|}t j|s|g}|||d}d}t|jrd}t|}t|}||}tj |j t}|D]} t|| r|r5tj |j tj} ||| k| |<n<|| k} t| tjs| td} || z}|r|t|z}|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-copyT)r-na_value)r isinstancenpr-arrayconstruct_array_typer is_list_like_from_sequencerrzerosshapeboolrbool_ndarrayto_numpyany) r*values_to_maskr-cls potential_naarr_maskna_masknonnarxnew_masks r' mask_missingrECs"-^<<E>%""U.>>>((**// .,-N++N%e+TTLsy!! II:>""G G8 $E 8CIT * * *D  #C + +   M8CIRX>>>%(]a%7""!8!(BJ77M'00te0LLH H DD{{}} S  Kr)Fmethodstr allow_nearestr8ct|tr%|}|dkrd}n|dkrd}ddg}d}|r|dd}||vrt d|d ||S) Nffillpadbfillbackfillzpad (ffill) or backfill (bfill)nearestz(pad (ffill), backfill (bfill) or nearestzInvalid fill method. Expecting z. Got )r0rGlowerappendr%)rFrH valid_methods expectings r'clean_fill_methodrSs&#  W  FF w  FJ'M1I?Y'''>  ]""T9TTFTTUUU Mr))lineartimeindexvalues)rNzeroslinear quadraticcubic barycentrickroghspline polynomialfrom_derivativespiecewise_polynomialpchipakima cubicsplinerVrc |d}|dvr|tdttz}||vrtd|d|d|dvr|jst|d|S) Norder)r^r_z7You must specify the order of the spline or polynomial.zmethod must be one of z. Got 'z ' instead.)r]rarbz4 interpolation requires that the index be monotonic.)getr% NP_METHODS SP_METHODSis_monotonic_increasing)rFrVkwargsrfvalids r'clean_interp_methodrms JJw  E )))emRSSS  #E UR%RRRRRSSS ;;;, OOO  Mr)howis_valid int | NonecH|dvsJt|dkrdS|jdkr|d}|dkr|dd}n6|dkr0t|dz |ddd z }||}|sdS|S) a+ Retrieves the positional index of the first valid value. Parameters ---------- how : {'first', 'last'} Use this parameter to change between the first or last valid index. is_valid: np.ndarray Mask to find na_values. Returns ------- int or None )firstlastrNaxisrrrs)r$ndimr<argmax)rnroidxpos chk_notnas r'find_valid_indexr}s # # # # # 8}}t}<rUrVrWrNmMz9Index column must be numeric or datetime type when using z_ method other than linear. Try setting a numeric or datetime index column before interpolating.zkInterpolation with NaNs in the index has not been implemented. Try filling those NaNs before interpolating.)pandasrr1aranger$rr-r0rr is_np_dtyper%rr<NotImplementedError)rFrVrmethodsis_numeric_or_datetimes r'get_interp_indexrs       biE ++,,888 U[ ) ) 2%+77 2u{D11   )? !!!!  E{{ ! /   Lr)rTrdata np.ndarrayrwrlimit fill_value Any | NoneNonec  t|fit|jrt|jddkr%t |jst ddt t| tj dt| d   fd } tj | ||dS)z Column-wise application of _interpolate_1d. Notes ----- Alters 'data' in-place. The signature does differ from _interpolate_1d because it only includes what is needed for Block.interpolate. F)compatrUzStime-weighted interpolation only works on Series or DataFrames with a DatetimeIndexrWN)nobsryvaluesrr+rc 2td|dddS)NF)indicesrrFrr~rr bounds_error)_interpolate_1d)rrrrkrlimit_area_validatedr~rFs r'funcz$interpolate_2d_inplace..func]sM  ++!  r))rrr+r) rmrr-rrr%rrr validate_limit_index_to_interp_indicesr1apply_along_axis) rrVrwrFrr~rrrkrrrs ``` `` @@r'interpolate_2d_inplacer1s!,00000Z44B' 5AAA  "5;//    .??O.z::  d% 8 8 8E&uf55G             *dD)))))r)c.|j}t|jr|d}|dkr|}t t j|}nAt j|}|dvr)|jt jkrtj |}|S)zE Convert Index to ndarray of indices to pass to NumPy/SciPy. i8rT)rWrV) _valuesrr-viewr r1r:asarrayobject_r maybe_convert_objects)rVrFxarrindss r'rrus =D4:&&yy BJ%%z$ ( ( (zRZ''066 Kr)rrrrfc  t|} | } | sdS| rdStt j| } t d| } | d} tt| }t d| }|t|}ttd|zt| }|dkr"|tt| |dz}nF|dkr"|tt| d|z}ntt| ||}|d kr |||zz}n|d kr | |z |z }||z}t|}|j j d v}|r| d }|tvrRt j|| }t j|| || ||| ||| <n)t#|| || || f||||d | || <|rt$j||<ntj||<dS)a Logic for the 1-d interpolation. The input indices and yvalues will each be 1-d arrays of the same length. Bounds_error is currently hardcoded to False since non-scipy ones don't take it as an argument. Notes ----- Fills 'yvalues' in-place. Nrrrnrorrsrurrrrrr)rFrrrf)rr<allsetr1 flatnonzeror}ranger$ _interp_limitsortedr-kindrrhargsortinterp_interpolate_scipy_wrapperr r&nan)rrrFrr~rrrrfrkinvalidrlall_nansfirst_valid_index start_nanslast_valid_indexend_nans preserve_nansmid_nansis_datetimelikeindexers r'rrs07mmG HE 99;; yy{{2>'**++H(WuEEE U,--..J'FUCCCw<<5--s5zz::;;H)##"Swq)I)I%J%JJ J & & 3}Wa'G'G#H#HH M'5%@@AA Xh.. y j(83! =))Mm(D0O%,,t$$ *WU^,,9 G genW5wu~g7N  6 EN EN G   !%      (!$ !#  Fr)rCynew_xc |d}td|ddlm} tj|}| j| jtttt| j d} gd} || vr1|dkr|} n|} | ||| || } | |}n|d krDt|s|dkrtd || j||fd |i|} | |}ns|jjs|}|jjs|}|jjs|}| |} | |||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)r\r]r`rardrcrb)rNrXrYrZr[r_r_)rrrr^z;order needs to be specified and greater than 0; got order: k)rrrr1rbarycentric_interpolatekrogh_interpolate_from_derivatives_cubicspline_interpolate_akima_interpolatepchip_interpolateinterp1drr%UnivariateSplineflags writeabler.)rCrrrFrrrfrkrr alt_methodsinterp1d_methodsrterpnew_ys r'rrs 5 5 5Ewe4444!!!!!! Ju  E#:.- 1/#.K!!! \ ! !DDD## qt $  U  8   ;; 5A::UeUU ,{+AqDDEDVDDU w  Aw  A{$ !JJLLE6"Q5++F++ Lr)xiyiderint | list[int] | None extrapolatecddlm}|jj}|||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. rrrxru)ordersr)rrBPolyr`reshape) rrrCrfrrrrFms r'rr>sWR"!!!!!  /Fr2::b!$$U LLLA 1Q44Kr)cXddlm}||||}|||S)aQ 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; 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, rrrv)nu)rrAkima1DInterpolator)rrrCrrwrPs r'rrpsCT"!!!!!''BT'::A 1Q3<<<r) not-a-knotbc_typestr | tuple[Any, Any]cXddlm}||||||}||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)rwrr)rr CubicSpline)rrrCrwrrrrs r'rrsKZ"!!!!! BT7    A 1Q44Kr)rWLiteral['pad', 'backfill']Literal['inside', 'outside']cvt|}|}|std|}|d}td|}|t|}t ||||dkr d|||d z<n'|d krdx|d|<||d zd<nt d t j||<dSdS) 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: {'inside', 'outside'} Limit area for interpolation. Notes ----- Modifies values in-place. rrrNrrs)rFrrFrurz*limit_area should be 'inside' or 'outside')rrr}r$pad_or_backfill_inplacer%r1r)rWrFrrrrorrrss r'_interpolate_with_limit_arears26llGxH ;;==! Wx@@@ =EFX>>> <v;;D      ! !(-GED1H$ % % 9 $ $49 9GFUFOgdQhjj11IJJ J&w+!!r)rKc|.tjtt|||||dS|dkrdnd}|jdkr?|dkrt d|td|jz}t|}||}t|d }||| dS) 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)rFrrrc|SNrrCs r'z)pad_or_backfill_inplace..\sr)c|jSr)Trs r'rz)pad_or_backfill_inplace..\sr)ruz0cannot interpolate on a ndim == 1 with axis != 0rurt)ryr) r1rrrryAssertionErrorrtupler7rS get_fill_func)rWrFrwrrtransftvaluesrs r'rr+s8  ,%      !   $ "aiikkkmmF{a 199 !STT TdV\&9 : :;; v & &FfVnnG a ( ( (DD Fr)npt.NDArray[np.bool_] | Nonecf|t|}|tj}|Sr)rrr1uint8)rWrs r' _fillna_preprms,  |F|| 99RX  D Kr)rrcftddfd }tt|S)z> Wrapper to handle datetime64 and timedelta64 dtypes. Nrrpct|jrQ|t|}|d||\}}||j|fS|||S)Nr)rr)rr-rr)rWrrresultrs r'new_funcz&_datetimelike_compat..new_func~s{ v| , , 3|F||4 D 1 1TJJJLFD;;v|,,d2 2tF%d3333r)NN)rrp)rr r)rrs` r'_datetimelike_compatrysJ  4[[ 4 4 4 4 4 4[ 4 8  r)(tuple[np.ndarray, npt.NDArray[np.bool_]]cXt||}tj|||||fSNr)rr pad_inplacerWrrs r'_pad_1drs5  % %D fd%0000 4<r)cXt||}tj|||||fSr)rr backfill_inplacers r' _backfill_1drs5  % %D 64u5555 4<r)cjt||}|jrtj|||n ||fSr)rsizer pad_2d_inplacers r'_pad_2dr#sG  % %D {  VT77777 4<r)cjt||}|jrtj|||n ||fSr)rr!r backfill_2d_inplacers r' _backfill_2dr&sG  % %D {  !&$e<<<<< 4<r)rKrMrurycpt|}|dkr t|Sttd|S)Nrur')rS _fill_methodsr#r&)rFrys r'r r s6 v & &F qyyV$$ 5 5f ==r)ReindexMethod | Nonec,|dSt|dS)NT)rH)rS)rFs r'clean_reindex_fill_methodr,s ~t V4 8 8 88r)rfw_limitbw_limitct|t}t}dfd }|:|dkr(ttj|d}n |||}|Y|dkr|St ||ddd|}tdz tj|z }|dkr|S||zS) ak Get indexers of values that won't be filled because they exceed the limits. Parameters ---------- invalid : np.ndarray[bool] fw_limit : int or None forward limit to index bw_limit : int or None backward limit to index Returns ------- set of indexers Notes ----- This is equivalent to the more readable, but slower .. code-block:: python def _interp_limit(invalid, fw_limit, bw_limit): for x in np.where(invalid)[0]: if invalid[max(0, x - fw_limit):x + bw_limit + 1].all(): yield x rr"c \t|}t||dzd}tt j|d|ztt j|d|dzdkdz}|S)Nrur)min_rolling_windowrrr1wherecumsum)rrwindowedidxNs r'innerz_interp_limit..innersE1 "7EAI66::1=="(8$$Q'%/003 Hw{{++3355: ; ;A >4 4   r)Nrrxru)rr")r$rr1r3listr)rr-r.f_idxb_idxr8 b_idx_invr7s @r'rrsB G A EEE EEE q==))!,--EEE'8,,E q==LUU744R4=(;;< [ [True, True], [True, False], [False, True], [True, False], ] Nrxru)r7strides)r7r@r1r stride_tricks as_strided)r=r>r7r@s r'r2r2sb GCRCLAGBK&014f= =Ei19R=**G 6  * *1E7 * K KKr))rr r!r")r*r r+r )F)rFrGrHr8)rFrGrVrr+rG)rnrGror r+rp)r~rGr+r)rrr+r)rVrr+r)rTNrNN)rrrVrrwrrFrGrrpr~rGrrrrr+r)rVrrFrGr+r)rTNrNNFN)rrrrrFrGrrpr~rGrrrrrr8rfrpr+r)NFN) rCrrrrrrFrGrr8)NrF) rrrrrCrrrrr8)rr) rrrrrCrrrrwr)rrN) rrrrrCrrwrrr) rWrrFrrrprrr+r)rKrNN) rWrrFrrwrrrprrr+rr)rr r+r )rrr+rr)rWrrrprr r+r)rWrrrprr )rrprr r)ryr")r+r*)rr r-rpr.rp)r=r r>r"r+r )H__doc__ __future__r functoolsrrtypingrrrr numpyr1 pandas._libsr r r pandas._typingr rrrrpandas.compat._optionalrpandas.core.dtypes.castrpandas.core.dtypes.commonrrrrrpandas.core.dtypes.dtypesrpandas.core.dtypes.missingrrrrrr(rErSrhrirmr}rrrrrrrrrrrrrrrrrr#r&r)r r,rr2rr)r'rOs\#""""" ?>>>>>444444655555     9999x(3 2 2  $&####L        &F$!!A*A*A*A*A*H2$6:!i i i i i b DDDDDV "# /////l#$ .....j%1 SSSSSl1!1!1!1!l*/6: ? ? ? ? ? F26     ()-)-)-     KO      \:: >>>>>9999 >>>>BLLLLLLr)