bMhƉdZddlmZddlmZddlmZmZmZm Z m Z ddl Z ddl mZmZmZddlmZmZmZmZmZddlmZdd lmZdd lmZmZmZmZm Z m!Z!dd l"m#Z#dd l$m%Z%m&Z&m'Z'erdd l(m)Z)dzdZ*d{dZ+e ddd|dZ,e d}d"Z,d#dd~d%Z,gd&Z-gd'Z.dd+Z/dd/Z0dd2Z1dd6Z2dd9Z3dd:Z4 dddEZ5ddFZ6 dddKZ7 dddOZ8 dddUZ9 dddVZ: dddZZ;dd]Z< ddd_Z= dddaZ>dddZ?e? dddfZ@e? dddgZAe? dddhZBe? dddiZCddkZDddlZEe@eAdmZFdddpZGddrZHddvZIddyZJdS)z$ Routines for filling missing data. ) annotations)wraps) TYPE_CHECKINGAnyLiteralcastoverloadN)NaTalgoslib) ArrayLikeAxisIntF ReindexMethodnpt)import_optional_dependency)infer_dtype_from) is_array_like is_bool_dtypeis_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)valuer r"s S/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/pandas/core/missing.pycheck_value_sizer)3skU u::  &#e**&&#&& d  Larrr returnc.t|\}}t|tjrtj||}nC|}t j|s|g}|||d}d}t|jrd}t|}t|}||}tj |j t}t|jr)t|jst|jrnt|jr)t|jrt|jsn|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_sequencerrzerosshapeboolrrrbool_ndarrayto_numpyany) r+values_to_maskr.cls potential_naarr_maskna_masknonnar xnew_masks r( mask_missingrFBs"-^<<E>%""U.>>>((**// .,-N++N%e+TTLsy!! II:>""G G8 $E 8CIT * * *D##!ci((! %+ & &! ci  ! U[ ) )!ek**!  ! !A'Q// !Q!x BBBH),X!);HX&&"axH%h ;;Q#+#4#44%#4#P#P {{}} S  Kr*. allow_nearestmethod,Literal['ffill', 'pad', 'bfill', 'backfill']rHLiteral[False]Literal['pad', 'backfill']cdSNrIrHs r(clean_fill_methodrQ Cr*7Literal['ffill', 'pad', 'bfill', 'backfill', 'nearest'] Literal[True]%Literal['pad', 'backfill', 'nearest']cdSrNrOrPs r(rQrQrRr*Fr9ct|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 )r1strlowerappendr&)rIrH valid_methods expectings r(rQrQs &#  W  FF w  FJ'M1I?Y'''>  ]""T9TTFTTUUU Mr*)lineartimeindexvalues)r\zeroslinear quadraticcubic barycentrickroghspline polynomialfrom_derivativespiecewise_polynomialpchipakima cubicspliner]rdrc |d}|dvr|tdttz}||vrtd|d|d|dvr|jst|d|S) Norder)rlrmz7You must specify the order of the spline or polynomial.zmethod must be one of z. Got 'z ' instead.)rkrorpz4 interpolation requires that the index be monotonic.)getr& NP_METHODS SP_METHODSis_monotonic_increasing)rIrdkwargsrtvalids r(clean_interp_methodr{s 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 )firstlastrNaxisrr)r%ndimr=argmax)r|r}idxpos chk_notnas r(find_valid_indexrs # # # # # 8}}t}<rcrdrer\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.zkInterpolation with NaNs in the index has not been implemented. Try filling those NaNs before interpolating.)pandasrr2aranger%rr.r1rr is_np_dtyper&rr=NotImplementedError)rIrdrmethodsis_numeric_or_datetimes r(get_interp_indexr8s       biE ++,,888 U[ ) ) 2%+77 2u{D11   )? !!!!  E{{ ! /   Lr*rbrdata np.ndarrayrrlimit fill_value Any | NoneNonec  t|fi t|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)compatrczStime-weighted interpolation only works on Series or DataFrames with a DatetimeIndexreN)nobsryvaluesrr,rc 4td|dd dS)NF) indicesrrIrrrr bounds_errorr rO)_interpolate_1d) rrrryrlimit_area_validatedrr rIs r(funcz$interpolate_2d_inplace..funcsP  ++!  r*)rrr,r) r{rr.rrr&rrr validate_limit_index_to_interp_indicesr2apply_along_axis) rrdrrIrrrrr ryrrrs ``` ``` @@r(interpolate_2d_inplacerWs'.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. i8rb)rerd) _valuesrr.viewrr2r;asarrayobject_r maybe_convert_objects)rdrIxarrindss r(rrs =D4:&&yy BJ%%z$ ( ( (zRZ''066 Kr*rrrrtc  | | } nt|} | } | 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 | || <| d| dd<d| |<n!|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. Nrr|r}rrrrrrrrr)rIrrrtFT)rr=allsetr2 flatnonzerorranger% _interp_limitsortedr.kindrrvargsortinterp_interpolate_scipy_wrapperr r'nan)rrrIrrrrrrtr ryinvalidrzall_nansfirst_valid_index start_nanslast_valid_indexend_nans preserve_nansmid_nansis_datetimelikeindexers r(rrs0 w-- 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   !%       QQQ"] (!$ !#  Fr*rDynew_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)rjrkrnrorrrqrp)r\rfrgrhrirmrm)rrrrlz;order needs to be specified and greater than 0; got order: k)rrrr2rbarycentric_interpolatekrogh_interpolate_from_derivatives_cubicspline_interpolate_akima_interpolatepchip_interpolateinterp1drr&UnivariateSplineflags writeabler/)rDrrrIrrrtryrr alt_methodsinterp1d_methodsrterpnew_ys r(rr%s 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. rrrr)ordersr)rrBPolyrnreshape) rrrDrtrrrrIms r(rrlsWR"!!!!!  /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, rrr)nu)rrAkima1DInterpolator)rrrDrrrPs r(rrsCT"!!!!!''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)rrr)rr CubicSpline)rrrDrrrrrs r(rrsKZ"!!!!! BT7    A 1Q44Kr*reLiteral['inside', 'outside']cxt|}|}|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. rrNrr)rIrrrFrrz*limit_area should be 'inside' or 'outside')rrrr%pad_or_backfill_inplacer&r2r)rerIrrrr}rrs r(_interpolate_with_limit_arear %s26llGxH ;;==! Wx@@@ =EFX>>> <v;;D !       ! !(-GED1H$ % % 9 $ $49 9GFUFOgdQhjj11IJJ J&w-!!r*rYc$|dkrdnd}|jdkr?|dkrtd|td|jz}t |}||}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. rc|SrNrOrDs r(z)pad_or_backfill_inplace..vsr*c|jSrN)Trs r(rz)pad_or_backfill_inplace..vsr*rz0cannot interpolate on a ndim == 1 with axis != 0rr)r)rrN)rAssertionErrorrtupler8rQ get_fill_func)rerIrrrtransftvaluesrs r(r r Zs8#aiikkkmmF{a 199 !STT TdV\&9 : :;; v & &FfVnnG a ( ( (DD*555555r*npt.NDArray[np.bool_] | Nonec(|t|}|SrN)r)rer s r( _fillna_preprs  |F|| Kr*rrclt ddfd }tt|S) z> Wrapper to handle datetime64 and timedelta64 dtypes. Nrr~rrct|jrR|t|}|d|||\}}||j|fS||||S)Nr)rrr )rr.rr)rerrr resultrs r(new_funcz&_datetimelike_compat..new_funcs v| , , 3|F||4 D!!:DLFD;;v|,,d2 2tF%JTJJJJr*NNN)rr~rr)rrr)rrs` r(_datetimelike_compatr!s\  4[[!:>  KKKKKK[K$ 8  r*(tuple[np.ndarray, npt.NDArray[np.bool_]]ct||}|$|st||tj|||||fSN)r)rr_fill_limit_area_1dr pad_inplacererrr s r(_pad_1dr(sX  % %DdhhjjD*--- fd%0000 4<r*ct||}|$|st||tj|||||fSr$)rrr%r backfill_inplacer's r( _backfill_1dr+sX  % %DdhhjjD*--- 64u5555 4<r*ct||}|t|||jrtj|||n ||fSr$)r_fill_limit_area_2dsizer pad_2d_inplacer's r(_pad_2dr0s]  % %DD*--- {  VT77777 4<r*ct||}|t|||jrtj|||n ||fSr$)rr-r.r backfill_2d_inplacer's r( _backfill_2dr3s]  % %DD*--- {  !&$e<<<<< 4<r*Literal['outside', 'inside']c|}|}t||dddz dz }|dkrd|d|<d||dzd<dS|dkr d||dz|<dSdS)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_maskrrs r(r%r%s uH OO  E x==8DDbD>0022 2Q 6DXVeV  TAXZZ y !&UQY  ! r*c|j}|dkrVtj|dtj|dddddddz}nWtj|dtj|dddddddz}d||j<dS)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)rr2maximum accumulate)r rr6la_masks r(r-r-swHY J ! !( ! 3 3j##HTTrTN#;;DDbDA B Z " "8! " 4 4 4z$$Xddd^!$<.inner\sE1 "7EAI66::1=="(8$$Q'%/003 Hw{{++3355: ; ;A >4 4   r*Nrrr)rr#)r%rr2rGlistr)rrArBf_idxb_idxrL b_idx_invrKs @r(rr7sB G A EEE EEE q==))!,--EEE'8,,E q==LUU744R4=(;;< [ [True, True], [True, False], [False, True], [True, False], ] Nrr)r8strides)r8rTr2r stride_tricks as_strided)rQrRr8rTs r(rFrFxsb GCRCLAGBK&014f= =Ei19R=**G 6  * *1E7 * K KKr*)r r!r"r#)r+r r,r!)rIrJrHrKr,rL)rIrSrHrTr,rU)rIrSrHr9r,rU)rIr]rdrr,r])r|r]r}r!r,r~)rr]r,r)rrr,r)rrrIr]r,r)rdrr,r)rbNrNNN)rrrdrrrrIr]rr~rr]rrrrr,r)rdrrIr]r,r)rbNrNNFNN)rrrrrIr]rr~rr]rrrrrr9rtr~r,r)NFN) rDrrrrrrIr]rr9)NrF) rrrrrDrrrrr9)rr) rrrrrDrrrrr)rrN) rrrrrDrrrrr) rerrIrLrr~rr r,r)rYrNN) rerrIrLrrrr~rrr,rrN)r rr,r!)rrr,rr ) rerrr~rrr rr,r")rerrr~rrr r)rr~rrr r)r r!rr4r,rr)rr#)r,r>)rr!rAr~rBr~)rQr!rRr#r,r!)K__doc__ __future__r functoolsrtypingrrrrr numpyr2 pandas._libsr r r pandas._typingr rrrrpandas.compat._optionalrpandas.core.dtypes.castrpandas.core.dtypes.commonrrrrrrpandas.core.dtypes.dtypesrpandas.core.dtypes.missingrrrrrr)rFrQrvrwr{rrrrrrrrrrrrr r rr!r(r+r0r3r%r-r=rr@rrFrOr*r(rcs#""""" ?>>>>>444444655555     FFFFR %(    43 2 2  $&####L        *F$!! C*C*C*C*C*L2$6:! o o o o o n DDDDDV "# /////l#$ .....j%1 SSSSSl2!2!2!2!n*/6: )6)6)6)6)6Z2666:)-     6:)-     6:)- $6:)- $''''4> \:: >>>>>9999 >>>>BLLLLLLr*