o ҷh}@szdZddlmZddlmZmZddlmZmZm Z m Z ddl Z ddl mZmZmZddlmZmZmZmZmZddlmZdd lmZdd lmZmZmZmZm Z dd l!m"Z"dd l#m$Z$m%Z%m&Z&erjdd l'm(Z(dddZ)dddZ*ddddZ+gd Z,gd!Z-dd$d%Z.dd)d*Z/dd-d.Z0dd2d3Z1d4d5Z2dd6d7Z3 8  9  dddBdCZ4ddDdEZ5 8  9    dddJdKZ6   dddOdPZ7   dddVdWZ8  dddXdYZ9  Z ddd]d^Z:ddbdcZ; d   dddedfZ< dddhdiZ=ddldmZ>e>  dddodpZ?e>  dddqdrZ@e>  dddsdtZAe> dddudvZBe?e@dwZCdddzd{ZDdd}d~ZEdddZFdddZGdS)z$ 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_]lengthintcCs8t|rt||krtdt|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 r%F/var/www/html/venv/lib/python3.10/site-packages/pandas/core/missing.pycheck_value_size4s  r'arrr returnc Cst|\}}t|tjrtj||d}n|}t|s |g}|j||dd}d}t |jr6d}t |}t |}||}tj |j t d}|D]1} t|| rQqI|retj |j tjd} ||| k| |<n|| k} t| tjsv| jt dd} || O}qI|r|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*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_maskr%r%r& mask_missingCs6          rBFmethodstr allow_nearestr5cCsjt|tr|}|dkrd}n|dkrd}ddg}d}|r%|dd}||vr3td|d ||S) Nffillpadbfillbackfillzpad (ffill) or backfill (bfill)nearestz(pad (ffill), backfill (bfill) or nearestzInvalid fill method. Expecting z. Got )r-rDlowerappendr#)rCrE valid_methods expectingr%r%r&clean_fill_methods  rO)lineartimeindexvalues)rJzeroslinear quadraticcubic barycentrickroghspline polynomialfrom_derivativespiecewise_polynomialpchipakima cubicsplinerRrcKsh|d}|dvr|durtdtt}||vr$td|d|d|dvr2|js2t|d|S) Norder)rZr[z7You must specify the order of the spline or polynomial.zmethod must be one of z. Got 'z ' instead.)rYr]r^z4 interpolation requires that the index be monotonic.)getr# NP_METHODS SP_METHODSis_monotonic_increasing)rCrRkwargsravalidr%r%r&clean_interp_methods rhhowis_valid int | NonecCs|dvsJt|dkrdS|jdkr|jdd}|dkr&|dd}n|dkr9t|d|ddd }||}|sAdS|S) a+ Retrieves the positional index of the first valid value. Parameters ---------- how : {'first', 'last'} Use this parameter to change between the first or last valid index. is_valid: np.ndarray Mask to find na_values. Returns ------- int or None )firstlastrNaxisrlrm)r"ndimr9argmax)rirjidxpos chk_notnar%r%r&find_valid_indexs    rwlimit_direction&Literal['forward', 'backward', 'both']cCs2gd}|}||vrtd|d|d|S)N)forwardbackwardbothz*Invalid limit_direction: expecting one of z, got 'z'.rKr#)rxvalid_limit_directionsr%r%r&validate_limit_directionsr limit_area str | None#Literal['inside', 'outside'] | NonecCs:|durddg}|}||vrtd|d|d|S)Ninsideoutsidez%Invalid limit_area: expecting one of z, got .r})rvalid_limit_areasr%r%r&validate_limit_areasrcCsd|dur|dvr d}|Sd}|S|dvr |dkr td|d|dvr0|dkr0td|d|S)N)rIrHr{rz)rGrFz0`limit_direction` must be 'forward' for method ``z1`limit_direction` must be 'backward' for method `)r#)rxrCr%r%r&infer_limit_directions    rcCs|dkrddlm}|tt|}n$hd}t|jp)t|jtp)t |jd}||vr8|s8t d|dt | rBtd|S) NrPrr>rQrRrSrJmMz9Index 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.)pandasrr.aranger"rr*r-rr is_np_dtyper#rr9NotImplementedError)rCrRrmethodsis_numeric_or_datetimer%r%r&get_interp_indexs(      rrPrzdata np.ndarrayrqr limit fill_value Any | NoneNonec  st|fit|jrt|jdddkr%t|js#tddtt|tj ddt |dfd d } t | ||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)compatrQzStime-weighted interpolation only works on Series or DataFrames with a DatetimeIndexrSN)nobsryvaluesrr)rc s$td|dddS)NF)indicesrrCrrxrr bounds_errorr%)_interpolate_1d)rrrrfrlimit_area_validatedrxrCr%r&func]s z$interpolate_2d_inplace..func)rrr)r) rhrr*rrr#rrr validate_limit_index_to_interp_indicesr.apply_along_axis) rrRrqrCrrxrrrfrr%rr&interpolate_2d_inplace1s   rcCsb|j}t|jr |d}|dkr|}ttj|}|St|}|dvr/|jtjkr/t |}|S)zE Convert Index to ndarray of indices to pass to NumPy/SciPy. i8rP)rSrR) _valuesrr*viewrr.r7asarrayobject_r maybe_convert_objects)rRrCxarrindsr%r%r&rus      rrrrrac Kst|} | } | s dS| rdStt| } td| d} | dur&d} tt| }td| d}|dur:t|}ttd|t| }|dkrT|tt | |dB}n|dkrc|tt | d|B}ntt | ||}|d krv|||BO}n|d kr| ||}||O}t |}|j j d v}|r| d }|tvrt|| }t|| || ||| ||| <nt|| || || f||||d | || <|rtj||<dStj||<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. Nrlrirjrrmrorzr{rrrr)rCrrra)rr9allsetr. flatnonzerorwranger" _interp_limitsortedr*kindrrcargsortinterp_interpolate_scipy_wrapperr r$nan)rrrCrrxrrrrarfinvalidrgall_nansfirst_valid_index start_nanslast_valid_indexend_nans preserve_nansmid_nansis_datetimelikeindexerr%r%r&rsf           rr@ynew_xcKs"|d}td|dddlm} t|}| j| jtttt | j d} gd} || vrD|dkr2|} n|} | j ||| ||d } | |}|S|d krit |sP|dkrWt d || j||fd |i|} | |}|S|jjsq|}|jjsy|}|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)rXrYr\r]r`r_r^)rJrTrUrVrWr[r[)rrrrZz;order needs to be specified and greater than 0; got order: k)rrrr.rbarycentric_interpolatekrogh_interpolate_from_derivatives_cubicspline_interpolate_akima_interpolatepchip_interpolateinterp1drr#UnivariateSplineflags writeabler+)r@rrrCrrrarfrr alt_methodsinterp1d_methodsrterpnew_yr%r%r&rsN       rxiyiderint | list[int] | None extrapolatec Cs4ddlm}|jj}|||dd||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. rrrrro)ordersr)rrBPolyr\reshape) rrr@rarrrrCmr%r%r&r>s )rcCs(ddlm}|j|||d}|||dS)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, rrrp)nu)rrAkima1DInterpolator)rrr@rrqrPr%r%r&rps * r not-a-knotbc_typestr | tuple[Any, Any]cCs(ddlm}|j|||||d}||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)rqrr)rr CubicSpline)rrr@rqrrrrr%r%r&rs M rrSLiteral['pad', 'backfill']Literal['inside', 'outside']cCst|}|}|sWtd|d}|durd}td|d}|dur%t|}t|||d|dkr9d|||d <n|d krLd|d|<||d d<ntd tj||<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. rlrNrrm)rCrrFrorz*limit_area should be 'inside' or 'outside')rrrwr"pad_or_backfill_inplacer#r.r)rSrCrrrrjrlrmr%r%r&_interpolate_with_limit_areas*  rrGcCs|durttt|||d||dS|dkrddndd}|jdkr6|dkr,td|td |j}t |}||}t |d d }|||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)rCrrrcSs|SNr%r@r%r%r&\sz)pad_or_backfill_inplace..cSs|jSr)Trr%r%r&r\sroz0cannot interpolate on a ndim == 1 with axis != 0rorn)rsr) r.rrrrsAssertionErrorrtupler4rO get_fill_func)rSrCrqrrtransftvaluesrr%r%r&r+s,    rnpt.NDArray[np.bool_] | NonecCs |durt|}|tj}|Sr)rrr.uint8)rSrr%r%r& _fillna_prepms rrrcs"tddfdd }tt|S)z> Wrapper to handle datetime64 and timedelta64 dtypes. NrrkcsPt|jr!|dur t|}|d||d\}}||j|fS|||dS)Nr)rr)rr*rr)rSrrresultrr%r&new_func~s z&_datetimelike_compat..new_funcNN)rrk)rrr)rrr%rr&_datetimelike_compatys r(tuple[np.ndarray, npt.NDArray[np.bool_]]cC"t||}tj|||d||fSNr)rr pad_inplacerSrrr%r%r&_pad_1d rcCrr)rr backfill_inplacerr%r%r& _backfill_1drrcC2t||}|jrtj|||d||fS ||fSr)rsizer pad_2d_inplacerr%r%r&_pad_2ds r cCrr)rr r backfill_2d_inplacerr%r%r& _backfill_2ds r rGrIrorscCs&t|}|dkr t|Sttd|S)Nror)rO _fill_methodsr r )rCrsr%r%r&rsrReindexMethod | NonecCs|durdSt|ddS)NT)rE)rO)rCr%r%r&clean_reindex_fill_methods rrfw_limitbw_limitcst|t}t}d fdd }|dur(|dkr#tt|d}n|||}|durO|dkr2|St||ddd|}tdt|}|dkrO|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 rr!cs`t|}t||dd}tt|d|tt|d|ddkdB}|S)Nror)min_rolling_windowrrr.wherecumsum)rrwindowedidxNr%r&inners "z_interp_limit..innerNrrrro)rr!)r"rr.rlistr)rrrf_idxb_idxr b_idx_invr%rr&rs ! rawindowcCsJ|jdd|jd|d|f}|j|jdf}tjjj|||dS)z [True, True, False, True, False], 2 -> [ [True, True], [True, False], [False, True], [True, False], ] Nrrro)r4strides)r4r#r.r stride_tricks as_strided)r!r"r4r#r%r%r&rs$ r)rrr r!)r(r r)r)F)rCrDrEr5)rCrDrRrr)rD)rirDrjrr)rk)rxrDr)ry)rrr)r)rRrr)r)rPNrzNN)rrrRrrqr rCrDrrkrxrDrrrrr)r)rRrrCrDr)r)rPNrzNNFN)rrrrrCrDrrkrxrDrrrrrr5rarkr)r)NFN) r@rrrrrrCrDrr5)NrF) rrrrr@rrrrr5)rr) rrrrr@rrrrqr )rrN) rrrrr@rrqr rr) rSrrCrrrkrrr)r)rGrNN) rSrrCrrqr rrkrrr)rr)rrr)r)rrr)rr)rSrrrkrrr)r)rSrrrkrr)rrkrrr)rsr!)r)r)rrrrkrrk)r!rr"r!r)r)H__doc__ __future__r functoolsrrtypingrrrrnumpyr. pandas._libsr r r pandas._typingr r rrrpandas.compat._optionalrpandas.core.dtypes.castrpandas.core.dtypes.commonrrrrrpandas.core.dtypes.dtypesrpandas.core.dtypes.missingrrrrrr'rBrOrcrdrhrwrrrrrrrrrrrrrrrrrr r rrrrrr%r%r%r&s        <   &  # D q K 6 5 V6 C      A