B { `-@sdZddddddddd d d d d ddddddddddddddddddd d!d"d#d$d%d&d'd(d)d*d+d,d-g-Zd.d/lZd.d/lZd0d1lmZd0d2lmZmZm Z m Z m Z m Z m Z mZmZmZmZmZmZmZmZmZmZmZmZmZmZmZd.d/lZd.d3lmZm Z d.d/l!mm"Z"d.d4l#m$Z$d.d5l%m&Z&d.d6l'm(Z(d.d7l)m*Z*d8d9Z+dsd:dZ,e-fd;dZ.dd>Z0Gd?d@d@e0Z1GdAdBdBe0Z2GdCdDdDe0Z3GdEdFdFe0Z4e4dZ5e4dZ6e4dZ7e2d-Z8Z9e2dZ:e2d Z;e2dZe1dZ?dGdHZ@dIdZAejAjeA_dJdZBeBjd/k rRejBjd/ejBjCdKDdLeB_dtdNdZEdudOd!ZFdvdPdQZGdwdRd ZHdxdSd ZIdTd ZJdUd ZKejLfdVdZMejLfdWdZNdydXdZOdzdYd*ZPd{dZdZQd|d[d(ZRd}d\dZSd~d]dZTd^d+ZUdd_d'ZVddadbZWddcdZXd/d`ejLd`ejLfdddZYGdedfdfe*ZZGdgdhdheZZ[e[Z\didZ]ddjd$Z^dkdZ_ddld#Z`dmdnZadodZbdpdZcddqd,Zdeeejdjedjed_ddrd%Zfeeejfjefjef_d/S)z Masked arrays add-ons. A collection of utilities for `numpy.ma`. :author: Pierre Gerard-Marchant :contact: pierregm_at_uga_dot_edu :version: $Id: extras.py 3473 2007-10-29 15:18:13Z jarrod.millman $ apply_along_axisapply_over_axes atleast_1d atleast_2d atleast_3daverage clump_maskedclump_unmasked column_stack compress_cols compress_ndcompress_rowcols compress_rows count_maskedcorrcoefcovdiagflatdotdstackediff1dflatnotmasked_contiguousflatnotmasked_edgeshsplithstackisinin1d intersect1d mask_cols mask_rowcols mask_rows masked_allmasked_all_likemedianmr_notmasked_contiguousnotmasked_edgespolyfit row_stack setdiff1dsetxor1dstackuniqueunion1dvandervstackN)core) MaskedArrayMAErroraddarrayasarray concatenatefilledcountgetmask getmaskarraymake_mask_descrmasked masked_arraymask_ornomaskonessortzerosgetdataget_masked_subclassrr)ndarrayr4)normalize_axis_index)normalize_axis_tuple)_ureduce)AxisConcatenatorcCst|tttfS)z6 Is seq a sequence (ndarray, list or tuple)? ) isinstancerEtuplelist)seqrN3/tmp/pip-unpacked-wheel-4iou4664/numpy/ma/extras.py issequence+srPcCst|}||S)a Count the number of masked elements along the given axis. Parameters ---------- arr : array_like An array with (possibly) masked elements. axis : int, optional Axis along which to count. If None (default), a flattened version of the array is used. Returns ------- count : int, ndarray The total number of masked elements (axis=None) or the number of masked elements along each slice of the given axis. See Also -------- MaskedArray.count : Count non-masked elements. Examples -------- >>> import numpy.ma as ma >>> a = np.arange(9).reshape((3,3)) >>> a = ma.array(a) >>> a[1, 0] = ma.masked >>> a[1, 2] = ma.masked >>> a[2, 1] = ma.masked >>> a masked_array( data=[[0, 1, 2], [--, 4, --], [6, --, 8]], mask=[[False, False, False], [ True, False, True], [False, True, False]], fill_value=999999) >>> ma.count_masked(a) 3 When the `axis` keyword is used an array is returned. >>> ma.count_masked(a, axis=0) array([1, 1, 1]) >>> ma.count_masked(a, axis=1) array([0, 2, 1]) )r:sum)arraxismrNrNrOr3s2cCs$tt||t|t|d}|S)a Empty masked array with all elements masked. Return an empty masked array of the given shape and dtype, where all the data are masked. Parameters ---------- shape : tuple Shape of the required MaskedArray. dtype : dtype, optional Data type of the output. Returns ------- a : MaskedArray A masked array with all data masked. See Also -------- masked_all_like : Empty masked array modelled on an existing array. Examples -------- >>> import numpy.ma as ma >>> ma.masked_all((3, 3)) masked_array( data=[[--, --, --], [--, --, --], [--, --, --]], mask=[[ True, True, True], [ True, True, True], [ True, True, True]], fill_value=1e+20, dtype=float64) The `dtype` parameter defines the underlying data type. >>> a = ma.masked_all((3, 3)) >>> a.dtype dtype('float64') >>> a = ma.masked_all((3, 3), dtype=np.int32) >>> a.dtype dtype('int32') )mask)r=npemptyr@r;)shapedtypearNrNrOris/ cCs,t|t}tj|jt|jd|_|S)a Empty masked array with the properties of an existing array. Return an empty masked array of the same shape and dtype as the array `arr`, where all the data are masked. Parameters ---------- arr : ndarray An array describing the shape and dtype of the required MaskedArray. Returns ------- a : MaskedArray A masked array with all data masked. Raises ------ AttributeError If `arr` doesn't have a shape attribute (i.e. not an ndarray) See Also -------- masked_all : Empty masked array with all elements masked. Examples -------- >>> import numpy.ma as ma >>> arr = np.zeros((2, 3), dtype=np.float32) >>> arr array([[0., 0., 0.], [0., 0., 0.]], dtype=float32) >>> ma.masked_all_like(arr) masked_array( data=[[--, --, --], [--, --, --]], mask=[[ True, True, True], [ True, True, True]], fill_value=1e+20, dtype=float32) The dtype of the masked array matches the dtype of `arr`. >>> arr.dtype dtype('float32') >>> ma.masked_all_like(arr).dtype dtype('float32') )rY) rVZ empty_likeviewr1r@rXr;rY_mask)rRrZrNrNrOr s2c@s(eZdZdZddZddZddZdS) _fromnxfunctionaV Defines a wrapper to adapt NumPy functions to masked arrays. An instance of `_fromnxfunction` can be called with the same parameters as the wrapped NumPy function. The docstring of `newfunc` is adapted from the wrapped function as well, see `getdoc`. This class should not be used directly. Instead, one of its extensions that provides support for a specific type of input should be used. Parameters ---------- funcname : str The name of the function to be adapted. The function should be in the NumPy namespace (i.e. ``np.funcname``). cCs||_||_dS)N)__name__getdoc__doc__)selffuncnamerNrNrO__init__sz_fromnxfunction.__init__cCsFtt|jd}t|dd}|rB|jt|}d}d|||fSdS)a  Retrieve the docstring and signature from the function. The ``__doc__`` attribute of the function is used as the docstring for the new masked array version of the function. A note on application of the function to the mask is appended. .. warning:: If the function docstring already contained a Notes section, the new docstring will have two Notes sections instead of appending a note to the existing section. Parameters ---------- None Nr`zLNotes ----- The function is applied to both the _data and the _mask, if any. )getattrrVr^maZget_object_signaturejoin)raZnpfuncdocsigZlocdocrNrNrOr_s z_fromnxfunction.getdoccOsdS)NrN)raargsparamsrNrNrO__call__ sz_fromnxfunction.__call__N)r^ __module__ __qualname__r`rcr_rlrNrNrNrOr]sr]c@seZdZdZddZdS)_fromnxfunction_singlez A version of `_fromnxfunction` that is called with a single array argument followed by auxiliary args that are passed verbatim for both the data and mask calls. cOstt|j}t|trJ||f||}|t|f||}t||dS|t|f||}|t|f||}t||dSdS)N)rU) rerVr^rJrEZ __array__r:r=r5)raxrjrkfunc_d_mrNrNrOrls   z_fromnxfunction_single.__call__N)r^rmrnr`rlrNrNrNrOrosroc@seZdZdZddZdS)_fromnxfunction_seqz A version of `_fromnxfunction` that is called with a single sequence of arrays followed by auxiliary args that are passed verbatim for both the data and mask calls. cOsTtt|j}|tdd|Df||}|tdd|Df||}t||dS)NcSsg|]}t|qSrN)rVr5).0rZrNrNrO (sz0_fromnxfunction_seq.__call__..cSsg|] }t|qSrN)r:)rurZrNrNrOrv)s)rU)rerVr^rKr=)rarprjrkrqrrrsrNrNrOrl&s z_fromnxfunction_seq.__call__N)r^rmrnr`rlrNrNrNrOrt srtc@seZdZdZddZdS)_fromnxfunction_argsa A version of `_fromnxfunction` that is called with multiple array arguments. The first non-array-like input marks the beginning of the arguments that are passed verbatim for both the data and mask calls. Array arguments are processed independently and the results are returned in a list. If only one array is found, the return value is just the processed array instead of a list. c Ostt|j}g}t|}x,t|dkrDt|drD||dqWg}xH|D]@}|t|f||}|t |f||}|t ||dqPWt|dkr|dS|S)Nr.)rUr/) rerVr^rLlenrPappendpopr5r:r=) rarjrkrqarraysresrprrrsrNrNrOrl6s   z_fromnxfunction_args.__call__N)r^rmrnr`rlrNrNrNrOrw-srwc@seZdZdZddZdS)_fromnxfunction_allargsa A version of `_fromnxfunction` that is called with multiple array arguments. Similar to `_fromnxfunction_args` except that all args are converted to arrays even if they are not so already. This makes it possible to process scalars as 1-D arrays. Only keyword arguments are passed through verbatim for the data and mask calls. Arrays arguments are processed independently and the results are returned in a list. If only one arg is present, the return value is just the processed array instead of a list. cOsjtt|j}g}x@|D]8}|t|f|}|t|f|}|t||dqWt|dkrf|dS|S)N)rUr/r.)rerVr^r5r:ryr=rx)rarjrkrqr|rprrrsrNrNrOrlQs   z _fromnxfunction_allargs.__call__N)r^rmrnr`rlrNrNrNrOr}Fs r}cCsJd}x@|t|krDx&t||dr8|||||d<qW|d7}qW|S)zFlatten a sequence in place.r.__iter__r/)rxhasattr)rMkrNrNrOflatten_inplaceos  rcOs~t|ddd}|j}t||}dg|d}t|d}tt|}||tdd||<t |j  |} | ||||t |f||} t| } | sy t| Wntk rd} YnXg} | r| t | jt| t} | | t |<t| }d}x||kr|dd7<d}xJ||| |krt|d|krt||dd7<d||<|d8}q,W| ||||t |f||} | | t |<| t | j|d7}q Wnft| ddd} |}tddg| j||<| ||t| }| }t|j } | j | |<| t | jt| } t| t} | | t t|<d}x||kr0|dd7<d}xJ||||kr|d|kr||dd7<d||<|d8}qW| ||| ||||t |f||} | | t t|<| t | j|d7}qbWtt | }t|d sbtj | |d }nt | |d }t||_|S) z0 (This docstring should be overwritten) FT)copysubokr.r/ONr\)rY)r4ndimrFrVrBrLrangeremoveslicer5rXZtakeputrKtolistZisscalarrx TypeErrorryrYobjectproductrrmaxrrfZdefault_fill_value fill_value)Zfunc1drSrRrjkwargsndindiZindlistZoutshaper|ZasscalarZdtypesZoutarrZNtotrnjZ holdshapeZ max_dtypesresultrNrNrOrys            "        "     cCst|}|j}t|jdkr"|f}xd|D]\}|dkr<||}||f}||}|j|jkr^|}q(t||}|j|jkr||}q(tdq(W|S)z. (This docstring will be overwritten) r.z7function is not returning an array of the correct shape)r5rr4rfZ expand_dims ValueError)rqrZaxesvalNrSrjr|rNrNrOrs      ZNotesao Examples -------- >>> a = np.ma.arange(24).reshape(2,3,4) >>> a[:,0,1] = np.ma.masked >>> a[:,1,:] = np.ma.masked >>> a masked_array( data=[[[0, --, 2, 3], [--, --, --, --], [8, 9, 10, 11]], [[12, --, 14, 15], [--, --, --, --], [20, 21, 22, 23]]], mask=[[[False, True, False, False], [ True, True, True, True], [False, False, False, False]], [[False, True, False, False], [ True, True, True, True], [False, False, False, False]]], fill_value=999999) >>> np.ma.apply_over_axes(np.ma.sum, a, [0,2]) masked_array( data=[[[46], [--], [124]]], mask=[[[False], [ True], [False]]], fill_value=999999) Tuple axis arguments to ufuncs are equivalent: >>> np.ma.sum(a, axis=(0,2)).reshape((1,-1,1)) masked_array( data=[[[46], [--], [124]]], mask=[[[False], [ True], [False]]], fill_value=999999) Fc Cs`t|}t|}|dkr6||}|j||}nt|}t|jjtj tj frjt |j|jd}nt |j|j}|j |j kr|dkrt d|jdkrt d|j d|j |krtdt||jdd|j }|d |}|tk r||j}|j||d }tj|||d ||}|rX|j |j krPt||j }||fS|SdS) an Return the weighted average of array over the given axis. Parameters ---------- a : array_like Data to be averaged. Masked entries are not taken into account in the computation. axis : int, optional Axis along which to average `a`. If None, averaging is done over the flattened array. weights : array_like, optional The importance that each element has in the computation of the average. The weights array can either be 1-D (in which case its length must be the size of `a` along the given axis) or of the same shape as `a`. If ``weights=None``, then all data in `a` are assumed to have a weight equal to one. The 1-D calculation is:: avg = sum(a * weights) / sum(weights) The only constraint on `weights` is that `sum(weights)` must not be 0. returned : bool, optional Flag indicating whether a tuple ``(result, sum of weights)`` should be returned as output (True), or just the result (False). Default is False. Returns ------- average, [sum_of_weights] : (tuple of) scalar or MaskedArray The average along the specified axis. When returned is `True`, return a tuple with the average as the first element and the sum of the weights as the second element. The return type is `np.float64` if `a` is of integer type and floats smaller than `float64`, or the input data-type, otherwise. If returned, `sum_of_weights` is always `float64`. Examples -------- >>> a = np.ma.array([1., 2., 3., 4.], mask=[False, False, True, True]) >>> np.ma.average(a, weights=[3, 1, 0, 0]) 1.25 >>> x = np.ma.arange(6.).reshape(3, 2) >>> x masked_array( data=[[0., 1.], [2., 3.], [4., 5.]], mask=False, fill_value=1e+20) >>> avg, sumweights = np.ma.average(x, axis=0, weights=[1, 2, 3], ... returned=True) >>> avg masked_array(data=[2.6666666666666665, 3.6666666666666665], mask=[False, False], fill_value=1e+20) NZf8z;Axis must be specified when shapes of a and weights differ.r/z81D weights expected when shapes of a and weights differ.r.z5Length of weights not compatible with specified axis.)r/r)rSrY)rY)r5r9meanrYtyper8rV asanyarray issubclassintegerZbool_Z result_typerXrrrZ broadcast_toZswapaxesr?rUrQmultiplyr) rZrSweightsZreturnedrTavgZsclZwgtZ result_dtyperNrNrOrs<;       cCsxt|dsLtjt|dd||||d}t|tjrHd|jkrHt|ddS|St|t |||d\}}|rp| |S|Sd S) a> Compute the median along the specified axis. Returns the median of the array elements. Parameters ---------- a : array_like Input array or object that can be converted to an array. axis : int, optional Axis along which the medians are computed. The default (None) is to compute the median along a flattened version of the array. out : ndarray, optional Alternative output array in which to place the result. It must have the same shape and buffer length as the expected output but the type will be cast if necessary. overwrite_input : bool, optional If True, then allow use of memory of input array (a) for calculations. The input array will be modified by the call to median. This will save memory when you do not need to preserve the contents of the input array. Treat the input as undefined, but it will probably be fully or partially sorted. Default is False. Note that, if `overwrite_input` is True, and the input is not already an `ndarray`, an error will be raised. keepdims : bool, optional If this is set to True, the axes which are reduced are left in the result as dimensions with size one. With this option, the result will broadcast correctly against the input array. .. versionadded:: 1.10.0 Returns ------- median : ndarray A new array holding the result is returned unless out is specified, in which case a reference to out is returned. Return data-type is `float64` for integers and floats smaller than `float64`, or the input data-type, otherwise. See Also -------- mean Notes ----- Given a vector ``V`` with ``N`` non masked values, the median of ``V`` is the middle value of a sorted copy of ``V`` (``Vs``) - i.e. ``Vs[(N-1)/2]``, when ``N`` is odd, or ``{Vs[N/2 - 1] + Vs[N/2]}/2`` when ``N`` is even. Examples -------- >>> x = np.ma.array(np.arange(8), mask=[0]*4 + [1]*4) >>> np.ma.median(x) 1.5 >>> x = np.ma.array(np.arange(10).reshape(2, 5), mask=[0]*6 + [1]*4) >>> np.ma.median(x) 2.5 >>> np.ma.median(x, axis=-1, overwrite_input=True) masked_array(data=[2.0, 5.0], mask=[False, False], fill_value=1e+20) rUT)r)rSoutoverwrite_inputkeepdimsr/F)r)rqrSrrN) rrVr!rCrJrErr=rH_medianreshape)rZrSrrrrTrrrNrNrOr!sB     csdt|jtjrtj}nd}|rRdkr>|j|dq`|j|d|nt||ddkrndn tjj dkrt dgj}t dd|<t |}tj j ||dSjdkrt}ttd\}}||d|d} tjtjrZjdkrZ| j|d} |sDtj| dd |d } tjj| |} n | j |d} tj | rtjstj S| Std d }|d} |ddk}t|| | d} tj| | gd } tj| d }fdd}||tjtjrNtj j||d} tj| jdd| jd tjj| |} ntj j ||d} | S)N)r)rSrr.)rSrr/)rg@safe)ZcastingrT)rSr)rScsFtj|rBtjjdd|j@}tj|j|<d|j|<dS)NT)rSrF)rVrf is_maskedallrUminimum_fill_valuedata)srep)asortedrSrNrOreplace_maskeds z_median..replace_maskedZunsafe)rVZ issubdtyperYZinexactinfravelrArFrrXrrKrfrr8divmodsizerQZ true_dividelibutilsZ_median_nancheckrrrUrwherer6Ztake_along_axisr)rZrSrrrZindexercountsidxZoddZmidrhlZlhZlow_highrrN)rrSrOrsZ       rcCst|}t|}|dkr(tt|j}n t||j}|tksD|sJ|jS| rZt gS|j}xR|D]J}tt t|t t|d|j}|t df||j|df}qfW|S)aSuppress slices from multiple dimensions which contain masked values. Parameters ---------- x : array_like, MaskedArray The array to operate on. If not a MaskedArray instance (or if no array elements are masked), `x` is interpreted as a MaskedArray with `mask` set to `nomask`. axis : tuple of ints or int, optional Which dimensions to suppress slices from can be configured with this parameter. - If axis is a tuple of ints, those are the axes to suppress slices from. - If axis is an int, then that is the only axis to suppress slices from. - If axis is None, all axis are selected. Returns ------- compress_array : ndarray The compressed array. Nr/)rS) r5r9rKrrrGr?any_datarnxarrayrLr)rprSrTrZaxrrNrNrOr 's  $&cCs"t|jdkrtdt||dS)a Suppress the rows and/or columns of a 2-D array that contain masked values. The suppression behavior is selected with the `axis` parameter. - If axis is None, both rows and columns are suppressed. - If axis is 0, only rows are suppressed. - If axis is 1 or -1, only columns are suppressed. Parameters ---------- x : array_like, MaskedArray The array to operate on. If not a MaskedArray instance (or if no array elements are masked), `x` is interpreted as a MaskedArray with `mask` set to `nomask`. Must be a 2D array. axis : int, optional Axis along which to perform the operation. Default is None. Returns ------- compressed_array : ndarray The compressed array. Examples -------- >>> x = np.ma.array(np.arange(9).reshape(3, 3), mask=[[1, 0, 0], ... [1, 0, 0], ... [0, 0, 0]]) >>> x masked_array( data=[[--, 1, 2], [--, 4, 5], [6, 7, 8]], mask=[[ True, False, False], [ True, False, False], [False, False, False]], fill_value=999999) >>> np.ma.compress_rowcols(x) array([[7, 8]]) >>> np.ma.compress_rowcols(x, 0) array([[6, 7, 8]]) >>> np.ma.compress_rowcols(x, 1) array([[1, 2], [4, 5], [7, 8]]) rz*compress_rowcols works for 2D arrays only.)rS)r5rNotImplementedErrorr )rprSrNrNrOr Qs2cCs$t|}|jdkrtdt|dS)z Suppress whole rows of a 2-D array that contain masked values. This is equivalent to ``np.ma.compress_rowcols(a, 0)``, see `extras.compress_rowcols` for details. See Also -------- extras.compress_rowcols rz'compress_rows works for 2D arrays only.r.)r5rrr )rZrNrNrOr s  cCs$t|}|jdkrtdt|dS)z Suppress whole columns of a 2-D array that contain masked values. This is equivalent to ``np.ma.compress_rowcols(a, 1)``, see `extras.compress_rowcols` for details. See Also -------- extras.compress_rowcols rz'compress_cols works for 2D arrays only.r/)r5rrr )rZrNrNrOr s  cCs$|tjk rtjdtddt|dS)a Mask rows of a 2D array that contain masked values. This function is a shortcut to ``mask_rowcols`` with `axis` equal to 0. See Also -------- mask_rowcols : Mask rows and/or columns of a 2D array. masked_where : Mask where a condition is met. Examples -------- >>> import numpy.ma as ma >>> a = np.zeros((3, 3), dtype=int) >>> a[1, 1] = 1 >>> a array([[0, 0, 0], [0, 1, 0], [0, 0, 0]]) >>> a = ma.masked_equal(a, 1) >>> a masked_array( data=[[0, 0, 0], [0, --, 0], [0, 0, 0]], mask=[[False, False, False], [False, True, False], [False, False, False]], fill_value=1) >>> ma.mask_rows(a) masked_array( data=[[0, 0, 0], [--, --, --], [0, 0, 0]], mask=[[False, False, False], [ True, True, True], [False, False, False]], fill_value=1) zTThe axis argument has always been ignored, in future passing it will raise TypeErrorr) stacklevelr.)rV_NoValuewarningswarnDeprecationWarningr)rZrSrNrNrOrs *  cCs$|tjk rtjdtddt|dS)a Mask columns of a 2D array that contain masked values. This function is a shortcut to ``mask_rowcols`` with `axis` equal to 1. See Also -------- mask_rowcols : Mask rows and/or columns of a 2D array. masked_where : Mask where a condition is met. Examples -------- >>> import numpy.ma as ma >>> a = np.zeros((3, 3), dtype=int) >>> a[1, 1] = 1 >>> a array([[0, 0, 0], [0, 1, 0], [0, 0, 0]]) >>> a = ma.masked_equal(a, 1) >>> a masked_array( data=[[0, 0, 0], [0, --, 0], [0, 0, 0]], mask=[[False, False, False], [False, True, False], [False, False, False]], fill_value=1) >>> ma.mask_cols(a) masked_array( data=[[0, --, 0], [0, --, 0], [0, --, 0]], mask=[[False, True, False], [False, True, False], [False, True, False]], fill_value=1) zTThe axis argument has always been ignored, in future passing it will raise TypeErrorr)rr/)rVrrrrr)rZrSrNrNrOrs )  cCsht|j}|dd|dd}|g}|dk r>|d||dk rP||t|dkrdt|}|S)a! Compute the differences between consecutive elements of an array. This function is the equivalent of `numpy.ediff1d` that takes masked values into account, see `numpy.ediff1d` for details. See Also -------- numpy.ediff1d : Equivalent function for ndarrays. r/Nrr.)rfrZflatinsertryrxr)rRZto_endZto_beginZedr{rNrNrOrs    cCsLtj|||d}t|tr>t|}|dt|d<t|}n |t}|S)a Finds the unique elements of an array. Masked values are considered the same element (masked). The output array is always a masked array. See `numpy.unique` for more details. See Also -------- numpy.unique : Equivalent function for ndarrays. ) return_indexreturn_inverser.)rVr*rJrKrLr[r1)ar1rroutputrNrNrOr*/s    cCsV|rt||f}ntt|t|f}||dd|dd|ddkS)a> Returns the unique elements common to both arrays. Masked values are considered equal one to the other. The output is always a masked array. See `numpy.intersect1d` for more details. See Also -------- numpy.intersect1d : Equivalent function for ndarrays. Examples -------- >>> x = np.ma.array([1, 3, 3, 3], mask=[0, 0, 0, 1]) >>> y = np.ma.array([3, 1, 1, 1], mask=[0, 0, 0, 1]) >>> np.ma.intersect1d(x, y) masked_array(data=[1, 3, --], mask=[False, False, True], fill_value=999999) Nrr/)rfr6r*rA)rar2 assume_uniqueauxrNrNrOrGs cCs|st|}t|}t||f}|jdkr0|S||}tdg|dd|ddkdgf}|dd|ddk}||S)z Set exclusive-or of 1-D arrays with unique elements. The output is always a masked array. See `numpy.setxor1d` for more details. See Also -------- numpy.setxor1d : Equivalent function for ndarrays. r.Tr/Nr)r*rfr6rrAr7)rrrrZauxfflagZflag2rNrNrOr(gs  (c Cs|st|dd\}}t|}t||f}|jdd}||}|r\|dd|ddk}n|dd|ddk}t||gf} |jdddt|} |r| | S| | |SdS)a Test whether each element of an array is also present in a second array. The output is always a masked array. See `numpy.in1d` for more details. We recommend using :func:`isin` instead of `in1d` for new code. See Also -------- isin : Version of this function that preserves the shape of ar1. numpy.in1d : Equivalent function for ndarrays. Notes ----- .. versionadded:: 1.4.0 T)rZ mergesort)kindr/Nr)r*rfr6Zargsortrx) rrrinvertZrev_idxarorderZsarZbool_arrZindxrNrNrOrs cCs"t|}t||||d|jS)a| Calculates `element in test_elements`, broadcasting over `element` only. The output is always a masked array of the same shape as `element`. See `numpy.isin` for more details. See Also -------- in1d : Flattened version of this function. numpy.isin : Equivalent function for ndarrays. Notes ----- .. versionadded:: 1.13.0 )rr)rfr5rrrX)elementZ test_elementsrrrNrNrOrs cCsttj||fddS)z Union of two arrays. The output is always a masked array. See `numpy.union1d` for more details. See also -------- numpy.union1d : Equivalent function for ndarrays. N)rS)r*rfr6)rrrNrNrOr+s cCs8|rt|}nt|}t|}|t||dddS)a Set difference of 1D arrays with unique elements. The output is always a masked array. See `numpy.setdiff1d` for more details. See Also -------- numpy.setdiff1d : Equivalent function for ndarrays. Examples -------- >>> x = np.ma.array([1, 2, 3, 4], mask=[0, 1, 0, 1]) >>> np.ma.setdiff1d(x, [1, 2]) masked_array(data=[3, --], mask=[False, True], fill_value=999999) T)rr)rfr5rr*r)rrrrNrNrOr's Tc Cs\tj|ddtd}t|}|s0|r0td|jddkrBd}tt|}d|}|rht ddf}n dt df}|dkrt | t}nt|ddtd }t|}|s|rtd|s|r|j|jkrt ||} | tk r| }|_|_}d|_d|_t||f|}t t ||f| t}||j|d |8}|||fS) z_ Private function for the computation of covariance and correlation coefficients. rT)ndminrrYzCannot process masked data.r.r/NF)rrrY)rS)rfr4floatr:rrrXintboolrrVZ logical_notZastype logical_orr?r\ _sharedmaskr6r) rpyrowvar allow_maskedZxmaskrStupxnotmaskZymaskZ common_maskrNrNrO _covhelpers8        rc Cs|dk r|t|krtd|dkr2|r.d}nd}t||||\}}}|s~t|j|d|}t|j|dd|}n2t||jd|}t||jdd|}|S)aJ Estimate the covariance matrix. Except for the handling of missing data this function does the same as `numpy.cov`. For more details and examples, see `numpy.cov`. By default, masked values are recognized as such. If `x` and `y` have the same shape, a common mask is allocated: if ``x[i,j]`` is masked, then ``y[i,j]`` will also be masked. Setting `allow_masked` to False will raise an exception if values are missing in either of the input arrays. Parameters ---------- x : array_like A 1-D or 2-D array containing multiple variables and observations. Each row of `x` represents a variable, and each column a single observation of all those variables. Also see `rowvar` below. y : array_like, optional An additional set of variables and observations. `y` has the same form as `x`. rowvar : bool, optional If `rowvar` is True (default), then each row represents a variable, with observations in the columns. Otherwise, the relationship is transposed: each column represents a variable, while the rows contain observations. bias : bool, optional Default normalization (False) is by ``(N-1)``, where ``N`` is the number of observations given (unbiased estimate). If `bias` is True, then normalization is by ``N``. This keyword can be overridden by the keyword ``ddof`` in numpy versions >= 1.5. allow_masked : bool, optional If True, masked values are propagated pair-wise: if a value is masked in `x`, the corresponding value is masked in `y`. If False, raises a `ValueError` exception when some values are missing. ddof : {None, int}, optional If not ``None`` normalization is by ``(N - ddof)``, where ``N`` is the number of observations; this overrides the value implied by ``bias``. The default value is ``None``. .. versionadded:: 1.5 Raises ------ ValueError Raised if some values are missing and `allow_masked` is False. See Also -------- numpy.cov Nzddof must be an integerr.r/g?F)strict)rrrrVrTconjsqueeze) rprrbiasrddofrfactrrNrNrOrs6cCsd}|tjk s|tjk r(tj|tddt||||\}}}|spt|j|d}t|j|dd| } n.t||jd}t||jdd| } yt | } Wnt k rdSX| rt t j| | } n$t| } d| _|jd|} |r~xvt| dD]f} x^t| d| D]L}tt|| ||fjdd}t t j|| | |f<| || f<q&WqWnxt| dD]v} xnt| d| D]\}tt|d d | f|d d |ffjdd}t t j|| | |f<| || f<qWqW| | S) a6 Return Pearson product-moment correlation coefficients. Except for the handling of missing data this function does the same as `numpy.corrcoef`. For more details and examples, see `numpy.corrcoef`. Parameters ---------- x : array_like A 1-D or 2-D array containing multiple variables and observations. Each row of `x` represents a variable, and each column a single observation of all those variables. Also see `rowvar` below. y : array_like, optional An additional set of variables and observations. `y` has the same shape as `x`. rowvar : bool, optional If `rowvar` is True (default), then each row represents a variable, with observations in the columns. Otherwise, the relationship is transposed: each column represents a variable, while the rows contain observations. bias : _NoValue, optional Has no effect, do not use. .. deprecated:: 1.10.0 allow_masked : bool, optional If True, masked values are propagated pair-wise: if a value is masked in `x`, the corresponding value is masked in `y`. If False, raises an exception. Because `bias` is deprecated, this argument needs to be treated as keyword only to avoid a warning. ddof : _NoValue, optional Has no effect, do not use. .. deprecated:: 1.10.0 See Also -------- numpy.corrcoef : Equivalent function in top-level NumPy module. cov : Estimate the covariance matrix. Notes ----- This function accepts but discards arguments `bias` and `ddof`. This is for backwards compatibility with previous versions of this function. These arguments had no effect on the return values of the function and can be safely ignored in this and previous versions of numpy. z/bias and ddof have no effect and are deprecatedr)rg?F)rr/)rSN)rVrrrrrrrrrrfZdiagonalrrsqrtrouterrrrXrrr-varreduce)rprrrrrmsgrrcZdiagZ_denomrrr_xrNrNrOrfs:0 4.2cs8eZdZdZeeZefddZfddZZ S)MAxisConcatenatorz Translate slice objects to concatenation along an axis. For documentation on usage, see `mr_class`. See Also -------- mr_class cs$tt|j|jdd}t||jdS)NF)r)rU)superrmakematrr4rU)clsrRr) __class__rNrOrszMAxisConcatenator.makematcs"t|trtdtt||S)NzUnavailable for masked array.)rJstrr2rr __getitem__)rakey)rrNrOrs zMAxisConcatenator.__getitem__) r^rmrnr` staticmethodr6 classmethodrr __classcell__rNrN)rrOrs  rc@seZdZdZddZdS)mr_classa Translate slice objects to concatenation along the first axis. This is the masked array version of `lib.index_tricks.RClass`. See Also -------- lib.index_tricks.RClass Examples -------- >>> np.ma.mr_[np.ma.array([1,2,3]), 0, 0, np.ma.array([4,5,6])] masked_array(data=[1, 2, 3, ..., 4, 5, 6], mask=False, fill_value=999999) cCst|ddS)Nr.)rrc)rarNrNrOrcszmr_class.__init__N)r^rmrnr`rcrNrNrNrOrsrcCsZt|}|tkst|s.td|jdgSt|}t|dkrR|ddgSdSdS)a Find the indices of the first and last unmasked values. Expects a 1-D `MaskedArray`, returns None if all values are masked. Parameters ---------- a : array_like Input 1-D `MaskedArray` Returns ------- edges : ndarray or None The indices of first and last non-masked value in the array. Returns None if all values are masked. See Also -------- flatnotmasked_contiguous, notmasked_contiguous, notmasked_edges clump_masked, clump_unmasked Notes ----- Only accepts 1-D arrays. Examples -------- >>> a = np.ma.arange(10) >>> np.ma.flatnotmasked_edges(a) array([0, 9]) >>> mask = (a < 3) | (a > 8) | (a == 5) >>> a[mask] = np.ma.masked >>> np.array(a[~a.mask]) array([3, 4, 6, 7, 8]) >>> np.ma.flatnotmasked_edges(a) array([3, 8]) >>> a[:] = np.ma.masked >>> print(np.ma.flatnotmasked_edges(a)) None r.r/rN)r9r?rVrr4rZ flatnonzerorx)rZrTZunmaskedrNrNrOrs-   cst|}dks|jdkr"t|St|}tt|jt|g|jdtfddt |jDtfddt |jDgS)a_ Find the indices of the first and last unmasked values along an axis. If all values are masked, return None. Otherwise, return a list of two tuples, corresponding to the indices of the first and last unmasked values respectively. Parameters ---------- a : array_like The input array. axis : int, optional Axis along which to perform the operation. If None (default), applies to a flattened version of the array. Returns ------- edges : ndarray or list An array of start and end indexes if there are any masked data in the array. If there are no masked data in the array, `edges` is a list of the first and last index. See Also -------- flatnotmasked_contiguous, flatnotmasked_edges, notmasked_contiguous clump_masked, clump_unmasked Examples -------- >>> a = np.arange(9).reshape((3, 3)) >>> m = np.zeros_like(a) >>> m[1:, 1:] = 1 >>> am = np.ma.array(a, mask=m) >>> np.array(am[~am.mask]) array([0, 1, 2, 3, 6]) >>> np.ma.notmasked_edges(am) array([0, 6]) Nr/)rUcsg|]}|qSrN)min compressed)rur)rSrrNrOrv_sz#notmasked_edges..csg|]}|qSrN)rr)rur)rSrrNrOrv`s) r5rrr:r4rVindicesrXrKr)rZrSrTrN)rSrrOr$0s*"cCsrt|}|tkrtd|jgSd}g}xFt|D]4\}}tt|}|sb| t|||||7}q6W|S)a Find contiguous unmasked data in a masked array along the given axis. Parameters ---------- a : narray The input array. Returns ------- slice_list : list A sorted sequence of `slice` objects (start index, end index). ..versionchanged:: 1.15.0 Now returns an empty list instead of None for a fully masked array See Also -------- flatnotmasked_edges, notmasked_contiguous, notmasked_edges clump_masked, clump_unmasked Notes ----- Only accepts 2-D arrays at most. Examples -------- >>> a = np.ma.arange(10) >>> np.ma.flatnotmasked_contiguous(a) [slice(0, 10, None)] >>> mask = (a < 3) | (a > 8) | (a == 5) >>> a[mask] = np.ma.masked >>> np.array(a[~a.mask]) array([3, 4, 6, 7, 8]) >>> np.ma.flatnotmasked_contiguous(a) [slice(3, 5, None), slice(6, 9, None)] >>> a[:] = np.ma.masked >>> np.ma.flatnotmasked_contiguous(a) [] r.) r9r?rr itertoolsgroupbyrrxrLry)rZrTrrrgrrNrNrOrcs,  cCst|}|j}|dkrtd|dks.|dkr6t|Sg}|dd}ddg}tdd||<x4t|j|D]"}|||<|t|t|qlW|S)a Find contiguous unmasked data in a masked array along the given axis. Parameters ---------- a : array_like The input array. axis : int, optional Axis along which to perform the operation. If None (default), applies to a flattened version of the array, and this is the same as `flatnotmasked_contiguous`. Returns ------- endpoints : list A list of slices (start and end indexes) of unmasked indexes in the array. If the input is 2d and axis is specified, the result is a list of lists. See Also -------- flatnotmasked_edges, flatnotmasked_contiguous, notmasked_edges clump_masked, clump_unmasked Notes ----- Only accepts 2-D arrays at most. Examples -------- >>> a = np.arange(12).reshape((3, 4)) >>> mask = np.zeros_like(a) >>> mask[1:, :-1] = 1; mask[0, 1] = 1; mask[-1, 0] = 0 >>> ma = np.ma.array(a, mask=mask) >>> ma masked_array( data=[[0, --, 2, 3], [--, --, --, 7], [8, --, --, 11]], mask=[[False, True, False, False], [ True, True, True, False], [False, True, True, False]], fill_value=999999) >>> np.array(ma[~ma.mask]) array([ 0, 2, 3, 7, 8, 11]) >>> np.ma.notmasked_contiguous(ma) [slice(0, 1, None), slice(2, 4, None), slice(7, 9, None), slice(11, 12, None)] >>> np.ma.notmasked_contiguous(ma, axis=0) [[slice(0, 1, None), slice(2, 3, None)], [], [slice(0, 1, None)], [slice(0, 3, None)]] >>> np.ma.notmasked_contiguous(ma, axis=1) [[slice(0, 1, None), slice(2, 4, None)], [slice(3, 4, None)], [slice(0, 1, None), slice(3, 4, None)]] rz%Currently limited to atmost 2D array.Nr/r.) r5rrrrrrXryrK)rZrSrrotherrrrNrNrOr#s: c Cs|jdkr|}|dd|ddA}|dd}|drt|dkr\td|jgStd|dg}|ddt|ddd|dddDn8t|dkrgSdd t|ddd|dddD}|dr|t|d|j|S) zv Finds the clumps (groups of data with the same values) for a 1D bool array. Returns a series of slices. r/Nrr.css|]\}}t||VqdS)N)r)ruleftrightrNrNrO sz_ezclump..rcSsg|]\}}t||qSrN)r)rurrrNrNrOrvsz_ezclump..) rrZnonzerorxrrextendzipry)rUrrrNrNrO_ezclumps     & (rcCs,t|dt}|tkr"td|jgSt|S)a Return list of slices corresponding to the unmasked clumps of a 1-D array. (A "clump" is defined as a contiguous region of the array). Parameters ---------- a : ndarray A one-dimensional masked array. Returns ------- slices : list of slice The list of slices, one for each continuous region of unmasked elements in `a`. Notes ----- .. versionadded:: 1.4.0 See Also -------- flatnotmasked_edges, flatnotmasked_contiguous, notmasked_edges notmasked_contiguous, clump_masked Examples -------- >>> a = np.ma.masked_array(np.arange(10)) >>> a[[0, 1, 2, 6, 8, 9]] = np.ma.masked >>> np.ma.clump_unmasked(a) [slice(3, 6, None), slice(7, 8, None)] r\r.)rer?rrr)rZrUrNrNrOrs! cCst|}|tkrgSt|S)a  Returns a list of slices corresponding to the masked clumps of a 1-D array. (A "clump" is defined as a contiguous region of the array). Parameters ---------- a : ndarray A one-dimensional masked array. Returns ------- slices : list of slice The list of slices, one for each continuous region of masked elements in `a`. Notes ----- .. versionadded:: 1.4.0 See Also -------- flatnotmasked_edges, flatnotmasked_contiguous, notmasked_edges notmasked_contiguous, clump_unmasked Examples -------- >>> a = np.ma.masked_array(np.arange(10)) >>> a[[0, 1, 2, 6, 8, 9]] = np.ma.masked >>> np.ma.clump_masked(a) [slice(0, 3, None), slice(6, 7, None), slice(8, 10, None)] )rfr9r?r)rZrUrNrNrOr,s! cCs(t||}t|}|tk r$d||<|S)zD Masked values in the input array result in rows of zeros. r.)rVr,r9r?)rprZ_vanderrTrNrNrOr,Xs  c Cst|}t|}t|}|jdkr2t|t|}n>|jdkrhtt|}|tk rpt||dddf}ntd|dk rt|}|jdkrtd|jd|jdkrtdt|t|}|tk r|} |dk r|| }t || || |||||St |||||||SdS)zE Any masked values in x is propagated in y, and vice-versa. r/rNr.z Expected a 1D or 2D array for y!z expected a 1-d array for weightsz(expected w and y to have the same length) r5r9rr>rr?rrXrVr%) rprdegZrcondfullwrrTZmyZnot_mrNrNrOr%fs.    )N)NNF)NNFF)NNF)N)N)NN)FF)F)F)FF)FF)F)NTT)NTFTN)N)N)N)NFNF)gr`__all__rrr0rfr1r2r3r4r5r6r7r8r9r:r;r<r=r>r?r@rArBrCrDrrZnumpyrVrErZnumpy.core.umathZumathZnumpy.core.multiarrayrFZnumpy.core.numericrGZnumpy.lib.function_baserHZnumpy.lib.index_tricksrIrPrrrr r]rortrwr}rrrr-r&rr rr)rrrrrfindrstriprr!rr r r r rrrrr*rr(rrr+r'rrrrrr"rr$rr#rrrr,Zdoc_noter%rNrNrNrO s   `     6 4:7   P  , j R V * 726    *  ! + I Y7 38 M',  "