U f/ep@sdZddlmZddlmZmZddlmZmZm Z ddl Z ddl m Z mZddlmZmZmZddlmZdd lmZdd lmZmZmZdd lmZmZmZerdd lm Z d ddddZ!dd dddZ"dsddddZ#ddddgZ$dd d!d"d#d$d%d&d'd(d)d*d+d,gZ%d-d.d-d/d0d1Z&d-d2d3d4d5Z'dtd d-dd8d2d-d9d:dd9d; d d?d@Z)dvd.d d9d2d-d9d:dd2dA dBdCZ*dwdDdEZ+dxdFdGZ,dydHdIZ-dzdKdLZ.dd-d2d9ddMdNdOZ/d{d-dPd2d9dQdRdSZ0d|dTd dUdVdWZ1dXdXdYdZd[Z2e2d}d d2dTd\d]d^d_Z3e2d~d d2dTd\d]d`daZ4e2ddbdcZ5e2ddddeZ6e3e4dfZ7dddhdidjZ8dkdlZ9d dmdndoZ:d ddpdqdrZ;dS)z$ Routines for filling missing data. ) annotations)partialwraps) TYPE_CHECKINGAnycastN)algoslib) ArrayLikeAxisF)import_optional_dependency)infer_dtype_from) is_array_likeis_numeric_v_string_likeneeds_i8_conversion)is_valid_na_for_dtypeisnana_value_for_dtype)Index np.ndarrayint)masklengthcCs8t|r4t||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)valuerrr7/tmp/pip-unpacked-wheel-tiezk1ph/pandas/core/missing.pycheck_value_size-s rr )arrreturncCsvt|\}}tj||d}t|}||}tj|jtd}|D]}t||rPq@|||kO}q@|rr|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] dtype) rnparrayrzerosshapeboolrany)r Zvalues_to_maskr#Zna_maskZnonnarxrrr mask_missing<s    r+Fr( allow_nearestcCsv|dkr dSt|tr8|}|dkr,d}n |dkr8d}ddg}d}|rV|dd}||krrtd |d ||S) N)NZasfreqZffillpadZbfillbackfillzpad (ffill) or backfill (bfill)nearestz(pad (ffill), backfill (bfill) or nearestzInvalid fill method. Expecting z. Got ) isinstancestrlowerappendr)methodr-Z valid_methodsZ expectingrrrclean_fill_methodfs   r6lineartimeindexvaluesr0zeroslinear quadraticcubic barycentrickroghspline polynomialfrom_derivativespiecewise_polynomialpchipakima cubicspliner2r)r5r9r!cKsh|d}|dkr"|dkr"tdtt}||krHtd|d|d|dkrd|jsdt|d|S) Norder)rArBz7You must specify the order of the spline or polynomial.zmethod must be one of z. Got 'z ' instead.)r@rDrEz4 interpolation requires that the index be monotonic.)getr NP_METHODS SP_METHODSZ is_monotonic)r5r9kwargsrHvalidrrrclean_interp_methods rNz int | None)howr!cCs|dks tt|dkrdSt|}|jdkr:|d}|dkrT|dd}n&|dkrzt|d|ddd}||}|sdS|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 )firstlastrNrPrQ)AssertionErrorrrndimr)Zargmax)r:rOZis_validZidxposZ chk_notnarrrfind_valid_indexs     rWr.forwardz Index | Nonez str | Nonez Any | None) datar5axisr9limitlimit_direction limit_area fill_valuecoercedowncastc Ksz t|} Wntk r$d} YnX| dk rR|dk r>tdt|| |||d} n,|dk s^ttf||||||||d| } | S)zS Wrapper to dispatch to either interpolate_2d or interpolate_2d_with_fill. Nz&Cannot pass both fill_value and methodr5rZr[r])rYr9rZr5r[r\r]r^)r6rinterpolate_2drUinterpolate_2d_with_fill) rYr5rZr9r[r\r]r^r_r`rLmZ interp_valuesrrrinterpolate_array_2ds8     re) rYr9rZr5r[r\r]r^r!c  sVtft|jr(t|jdddddfdd } t| ||S)z Column-wise application of interpolate_1d. Notes ----- The signature does differs from interpolate_1d because it only includes what is needed for Block.interpolate. F)compatr)yvaluesr!c s tf|ddS)NF)xvaluesrgr5r[r\r]r^ bounds_error)interpolate_1d)rgr^r9rLr[r]r\r5rrfuncs z&interpolate_2d_with_fill..func)rNrr#rr$apply_along_axis) rYr9rZr5r[r\r]r^rLrlrrkrrcs   rc) rhrgr5r[r\r]r^rirHc Kst|} | } | s8tj|jtjd} | tj| S| rD|S|dkrbt |j s^t dd}dddg} | }|| krt d| d |d |d k rd d g}| }||krt d|d|dt jd |d}tt| }t|dd}|d krd}tt|}t|dd}|d kr&t|}ttd|t| }|||}|dkrh|tt| |dB}n0|dkr|tt| d|B}ntt| ||}|d kr|||BO}n|d kr||O}t|}|} |j}t |j r|d}|dkr|}n,t|}|dkr*|j tjkr*t|}|tkrjt|| }t|| || ||| || | <n.t || || || f||||d| | | <tj| |<| S)z Logic for the 1-d interpolation. The result should be 1-d, inputs xvalues 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. r"r8zStime-weighted interpolation only works on Series or DataFrames with a DatetimeIndexr:rXZbackwardZbothz*Invalid limit_direction: expecting one of z, got 'z'.Ninsideoutsidez%Invalid limit_area: expecting one of z, got .)Znobsr[rPrOrrQrSi8r7)r:r9)r5r^rirH)!rr)r$emptyr'Zfloat64fillnanallrr#rr3rZvalidate_limitsetZ flatnonzerorWranger _interp_limitsortedcopy_valuesviewasarrayZobject_r Zmaybe_convert_objectsrJZargsortZinterp_interpolate_scipy_wrapper)rhrgr5r[r\r]r^rirHrLinvalidrMresultZvalid_limit_directionsZvalid_limit_areasZall_nansZfirst_valid_indexZ start_nansZlast_valid_indexZend_nansZmid_nansZ preserve_nansZxarrZindsZindexerrrrrj,s                    rjcKsx|d}td|dddlm} t|}| j| jttd} t|ddrb|j d | d }}|d krv| j | d <n"|d krt | d <n|d krt | d <d dddddg} || kr|dkr|}| j|||||d} | |} n|dkr&t|s|dkrtd|| j||fd|i|} | |} nN|jjs8|}|jjsJ|}|jjs\|}| |}||||f|} | S)z Passed off to scipy.interpolate.interp1d. method is scipy's kind. Returns an array interpolated at new_x. Add any new methods to the list in _clean_interp_method. z interpolation requires SciPy.scipy)extrar interpolate)r?r@rCrDZ _is_all_datesFrrrErFrGr0r;r<r=r>rB)kindr^rirAz;order needs to be specified and greater than 0; got order: k)r rrr$r~Zbarycentric_interpolateZkrogh_interpolate_from_derivativesgetattrr|ZastypeZpchip_interpolate_akima_interpolate_cubicspline_interpolateZinterp1drrZUnivariateSplineflagsZ writeabler{)r*yZnew_xr5r^rirHrLrrZ alt_methodsZinterp1d_methodsZterpZnew_yrrrrsf             rc 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. rrrTrS)Zorders extrapolate)rrZBPolyrCreshape) xiyir*rHderrrr5rdrrrrs" rcCs(ddlm}|j|||d}|||dS)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, rr)rZ)nu)rrZAkima1DInterpolator)rrr*rrZrPrrrr1s$ r not-a-knotcCs(ddlm}|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 `_ on Wikiversity. .. [2] Carl de Boor, "A Practical Guide to Splines", Springer-Verlag, 1978. rr)rZbc_typer)rrZ CubicSpline)rrr*rZrrrrrrrr\sF r)r:r5r[r]r!cCst|}|st|dd}|dkr(d}t|dd}|dkrDt|}t|||d}|dkrld|||d <n$|d krd|d|<||d d<tj||<|S) a Apply interpolation and limit_area logic to values along a to-be-specified axis. Parameters ---------- values: array-like Input array. method: str Interpolation method. Could be "bfill" or "pad" limit: int, optional Index limit on interpolation. limit_area: str Limit area for interpolation. Can be "inside" or "outside" Returns ------- values: array-like Interpolated array. rPrqNrrQ)r5r[rnFrSro)rrvrWrrbr$ru)r:r5r[r]rrPrQrrr_interpolate_with_limit_areas&   rr rac Cs|dk r"ttt|||d||S|dkr2ddndd}|j}|jdkrn|dkrZtd|td |j}t |}||}|d krt ||d \}} nt ||d \}} ||}|dkr|d}|S) a7 Perform an actual interpolation of values, values will be make 2-d if needed fills inplace, returns the result. Parameters ---------- values: array-like 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" Returns ------- values: array-like Interpolated array. N)r5r[r]rcSs|SNrr*rrrz interpolate_2d..cSs|jSr)TrrrrrrrSz0cannot interpolate on a ndim == 1 with axis != 0)rSr.r[) r$rmrrrVrUrtupler'r6_pad_2d _backfill_2d) r:r5rZr[r]ZtransfrVZtvaluesr_rrrrbs4  rbznp.ndarray | None)rr!cCs |dkrt|}|tj}|Sr)rr}r$Zuint8)r:rrrr _fillna_preps rr )rlr!cs tdfdd }tt|S)z> Wrapper to handle datetime64 and timedelta64 dtypes. NcsPt|jrB|dkrt|}|d||d\}}||j|fS|||dS)Nrr)r[r)rr#rr})r:r[rrrlrrnew_func,s  z&_datetimelike_compat..new_func)NN)rrr )rlrrrr_datetimelike_compat's rztuple[np.ndarray, np.ndarray])r:r[rr!cCs"t||}tj|||d||fSNr)rrZ pad_inplacer:r[rrrr_pad_1d;s rcCs"t||}tj|||d||fSr)rrZbackfill_inplacerrrr _backfill_1dFs rcCs0t||}t|jr(tj|||dn||fSr)rr$rvr'rZpad_2d_inplacerrrrrQs  rcCs0t||}t|jr(tj|||dn||fSr)rr$rvr'rZbackfill_2d_inplacerrrrr]s  rr.r/rS)rVcCs&t|}|dkrt|Sttd|S)NrSr)r6 _fill_methodsrr)r5rVrrr get_fill_funclsrcCs t|ddS)NTr,)r6)r5rrrclean_reindex_fill_methodssr)rcst|t}t}fdd}|dk rN|dkrDtt|d}n |||}|dk r|dkrb|St||ddd|}tdt|}|dkr|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 cs`t|}t||dd}tt|d|tt|d|ddkdB}|S)NrSr)min_rolling_windowrvrwr$whereZcumsum)rr[ZwindowedidxNrrinners  "z_interp_limit..innerNrrTrS)rrwr$rlistr~)rZfw_limitZbw_limitZf_idxZb_idxrZ b_idx_invrrrryws   ry)awindowcCsJ|jdd|jd|d|f}|j|jdf}tjjj|||dS)z [True, True, False, True, False], 2 -> [ [True, True], [True, False], [False, True], [True, False], ] NrTrS)r'strides)r'rr$r Z stride_tricksZ as_strided)rrr'rrrrrs $r)F) r.rNNrXNNFN)r7NrXNN)r7NrXNNFN)NFN)NrF)rr)rrN)r.rNN)N)NN)NN)NN)NN)rS)<__doc__ __future__r functoolsrrtypingrrrZnumpyr$Z pandas._libsrr Zpandas._typingr r r Zpandas.compat._optionalr Zpandas.core.dtypes.castrZpandas.core.dtypes.commonrrrZpandas.core.dtypes.missingrrrZpandasrrr+r6rJrKrNrWrercrjrrrrrrbrrrrrrrrrryrrrrrs    * '"6 1  F + + O3A     A