관리-도구
편집 파일: nanfunctions.cpython-37.pyc
B ��Fd�� � @ s� d Z ddlmZmZmZ ddlZddlZddlm Z ddddd d d d d ddddg Z dd� Z dd� Z d1dd�Z ddejfdd�Zddejfdd�Zd2dd �Zd3dd�Zdddejfd d�Zdddejfd d�Zd4d d�Zd5d d�Zdddejfd d �Zd6d"d#�Zd7d$d%�Zd8d&d'�Zddd!ejfd(d �Zddd!d)ejfd*d �Z d9d+d,�Z d:d-d.�Z ddddejfd/d �Z ddddejfd0d�Z dS );as Functions that ignore NaN. Functions --------- - `nanmin` -- minimum non-NaN value - `nanmax` -- maximum non-NaN value - `nanargmin` -- index of minimum non-NaN value - `nanargmax` -- index of maximum non-NaN value - `nansum` -- sum of non-NaN values - `nanprod` -- product of non-NaN values - `nancumsum` -- cumulative sum of non-NaN values - `nancumprod` -- cumulative product of non-NaN values - `nanmean` -- mean of non-NaN values - `nanvar` -- variance of non-NaN values - `nanstd` -- standard deviation of non-NaN values - `nanmedian` -- median of non-NaN values - `nanpercentile` -- qth percentile of non-NaN values � )�division�absolute_import�print_functionN)�_ureduce�nansum�nanmax�nanmin� nanargmax� nanargmin�nanmean� nanmedian� nanpercentile�nanvar�nanstd�nanprod� nancumsum� nancumprodc C sf t j| ddd�} | jt jkr&| | k}n t| jjt j�rBt �| �}nd}|dk r^t j| ||d� | |fS )a� If `a` is of inexact type, make a copy of `a`, replace NaNs with the `val` value, and return the copy together with a boolean mask marking the locations where NaNs were present. If `a` is not of inexact type, do nothing and return `a` together with a mask of None. Note that scalars will end up as array scalars, which is important for using the result as the value of the out argument in some operations. Parameters ---------- a : array-like Input array. val : float NaN values are set to val before doing the operation. Returns ------- y : ndarray If `a` is of inexact type, return a copy of `a` with the NaNs replaced by the fill value, otherwise return `a`. mask: {bool, None} If `a` is of inexact type, return a boolean mask marking locations of NaNs, otherwise return None. T)Zsubok�copyN)�where) �np�array�dtype�object_� issubclass�type�inexact�isnan�copyto)�a�val�mask� r! �I/opt/alt/python37/lib64/python3.7/site-packages/numpy/lib/nanfunctions.py� _replace_nan$ s r# c C s0 t | tj�r tj| ||dd� n | j�|�} | S )a\ Replace values in `a` with NaN where `mask` is True. This differs from copyto in that it will deal with the case where `a` is a numpy scalar. Parameters ---------- a : ndarray or numpy scalar Array or numpy scalar some of whose values are to be replaced by val. val : numpy scalar Value used a replacement. mask : ndarray, scalar Boolean array. Where True the corresponding element of `a` is replaced by `val`. Broadcasts. Returns ------- res : ndarray, scalar Array with elements replaced or scalar `val`. �unsafe)r �casting)� isinstancer �ndarrayr r r )r r r r! r! r" �_copytoP s r( c C s� t jddd��j t| t j�rJ|dkr6t j| || dd�S t j| ||dd�S n*|dkrb| j�| | �S t j| ||dd�S W dQ R X dS )a� Compute a/b ignoring invalid results. If `a` is an array the division is done in place. If `a` is a scalar, then its type is preserved in the output. If out is None, then then a is used instead so that the division is in place. Note that this is only called with `a` an inexact type. Parameters ---------- a : {ndarray, numpy scalar} Numerator. Expected to be of inexact type but not checked. b : {ndarray, numpy scalar} Denominator. out : ndarray, optional Alternate output array in which to place the result. The default is ``None``; if provided, it must have the same shape as the expected output, but the type will be cast if necessary. Returns ------- ret : {ndarray, numpy scalar} The return value is a/b. If `a` was an ndarray the division is done in place. If `a` is a numpy scalar, the division preserves its type. �ignore)�invalid�divideNr$ )�outr% )r Zerrstater& r' r+ r r )r �br, r! r! r" �_divide_by_countm s r. c C s� i }|t jk r||d< t| �t jkrj| jt jkrjt jj| f||d�|��}t �|�� � r�t j dt dd� ntt | t j �\} }t j| f||d�|��}|dkr�|S t j|fd|i|��}t � |�r�t|t j|�}t j dt dd� |S )a+ Return minimum of an array or minimum along an axis, ignoring any NaNs. When all-NaN slices are encountered a ``RuntimeWarning`` is raised and Nan is returned for that slice. Parameters ---------- a : array_like Array containing numbers whose minimum is desired. If `a` is not an array, a conversion is attempted. axis : int, optional Axis along which the minimum is computed. The default is to compute the minimum of the flattened array. out : ndarray, optional Alternate output array in which to place the result. The default is ``None``; if provided, it must have the same shape as the expected output, but the type will be cast if necessary. See `doc.ufuncs` for details. .. versionadded:: 1.8.0 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 original `a`. If the value is anything but the default, then `keepdims` will be passed through to the `min` method of sub-classes of `ndarray`. If the sub-classes methods does not implement `keepdims` any exceptions will be raised. .. versionadded:: 1.8.0 Returns ------- nanmin : ndarray An array with the same shape as `a`, with the specified axis removed. If `a` is a 0-d array, or if axis is None, an ndarray scalar is returned. The same dtype as `a` is returned. See Also -------- nanmax : The maximum value of an array along a given axis, ignoring any NaNs. amin : The minimum value of an array along a given axis, propagating any NaNs. fmin : Element-wise minimum of two arrays, ignoring any NaNs. minimum : Element-wise minimum of two arrays, propagating any NaNs. isnan : Shows which elements are Not a Number (NaN). isfinite: Shows which elements are neither NaN nor infinity. amax, fmax, maximum Notes ----- NumPy uses the IEEE Standard for Binary Floating-Point for Arithmetic (IEEE 754). This means that Not a Number is not equivalent to infinity. Positive infinity is treated as a very large number and negative infinity is treated as a very small (i.e. negative) number. If the input has a integer type the function is equivalent to np.min. Examples -------- >>> a = np.array([[1, 2], [3, np.nan]]) >>> np.nanmin(a) 1.0 >>> np.nanmin(a, axis=0) array([ 1., 2.]) >>> np.nanmin(a, axis=1) array([ 1., 3.]) When positive infinity and negative infinity are present: >>> np.nanmin([1, 2, np.nan, np.inf]) 1.0 >>> np.nanmin([1, 2, np.nan, np.NINF]) -inf �keepdims)�axisr, zAll-NaN axis encountered� )� stacklevelNr0 )r �_NoValuer r' r r �fmin�reducer �any�warnings�warn�RuntimeWarningr# �infZamin�allr( �nan)r r0 r, r/ �kwargs�resr r! r! r" r � s T c C s� i }|t jk r||d< t| �t jkrj| jt jkrjt jj| f||d�|��}t �|�� � r�t j dt dd� ntt | t j �\} }t j| f||d�|��}|dkr�|S t j|fd|i|��}t � |�r�t|t j|�}t j dt dd� |S ) a. Return the maximum of an array or maximum along an axis, ignoring any NaNs. When all-NaN slices are encountered a ``RuntimeWarning`` is raised and NaN is returned for that slice. Parameters ---------- a : array_like Array containing numbers whose maximum is desired. If `a` is not an array, a conversion is attempted. axis : int, optional Axis along which the maximum is computed. The default is to compute the maximum of the flattened array. out : ndarray, optional Alternate output array in which to place the result. The default is ``None``; if provided, it must have the same shape as the expected output, but the type will be cast if necessary. See `doc.ufuncs` for details. .. versionadded:: 1.8.0 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 original `a`. If the value is anything but the default, then `keepdims` will be passed through to the `max` method of sub-classes of `ndarray`. If the sub-classes methods does not implement `keepdims` any exceptions will be raised. .. versionadded:: 1.8.0 Returns ------- nanmax : ndarray An array with the same shape as `a`, with the specified axis removed. If `a` is a 0-d array, or if axis is None, an ndarray scalar is returned. The same dtype as `a` is returned. See Also -------- nanmin : The minimum value of an array along a given axis, ignoring any NaNs. amax : The maximum value of an array along a given axis, propagating any NaNs. fmax : Element-wise maximum of two arrays, ignoring any NaNs. maximum : Element-wise maximum of two arrays, propagating any NaNs. isnan : Shows which elements are Not a Number (NaN). isfinite: Shows which elements are neither NaN nor infinity. amin, fmin, minimum Notes ----- NumPy uses the IEEE Standard for Binary Floating-Point for Arithmetic (IEEE 754). This means that Not a Number is not equivalent to infinity. Positive infinity is treated as a very large number and negative infinity is treated as a very small (i.e. negative) number. If the input has a integer type the function is equivalent to np.max. Examples -------- >>> a = np.array([[1, 2], [3, np.nan]]) >>> np.nanmax(a) 3.0 >>> np.nanmax(a, axis=0) array([ 3., 2.]) >>> np.nanmax(a, axis=1) array([ 2., 3.]) When positive infinity and negative infinity are present: >>> np.nanmax([1, 2, np.nan, np.NINF]) 2.0 >>> np.nanmax([1, 2, np.nan, np.inf]) inf r/ )r0 r, zAll-NaN slice encounteredr1 )r2 Nr0 zAll-NaN axis encountered)r r3 r r' r r �fmaxr5 r r6 r7 r8 r9 r# r: Zamaxr; r( r< )r r0 r, r/ r= r> r r! r! r" r s T c C sJ t | tj�\} }tj| |d�}|dk rFtj||d�}t�|�rFtd��|S )a Return the indices of the minimum values in the specified axis ignoring NaNs. For all-NaN slices ``ValueError`` is raised. Warning: the results cannot be trusted if a slice contains only NaNs and Infs. Parameters ---------- a : array_like Input data. axis : int, optional Axis along which to operate. By default flattened input is used. Returns ------- index_array : ndarray An array of indices or a single index value. See Also -------- argmin, nanargmax Examples -------- >>> a = np.array([[np.nan, 4], [2, 3]]) >>> np.argmin(a) 0 >>> np.nanargmin(a) 2 >>> np.nanargmin(a, axis=0) array([1, 1]) >>> np.nanargmin(a, axis=1) array([1, 0]) )r0 NzAll-NaN slice encountered)r# r r: Zargminr; r6 � ValueError)r r0 r r> r! r! r" r n s # c C sL t | tj �\} }tj| |d�}|dk rHtj||d�}t�|�rHtd��|S )a Return the indices of the maximum values in the specified axis ignoring NaNs. For all-NaN slices ``ValueError`` is raised. Warning: the results cannot be trusted if a slice contains only NaNs and -Infs. Parameters ---------- a : array_like Input data. axis : int, optional Axis along which to operate. By default flattened input is used. Returns ------- index_array : ndarray An array of indices or a single index value. See Also -------- argmax, nanargmin Examples -------- >>> a = np.array([[np.nan, 4], [2, 3]]) >>> np.argmax(a) 0 >>> np.nanargmax(a) 1 >>> np.nanargmax(a, axis=0) array([1, 0]) >>> np.nanargmax(a, axis=1) array([1, 1]) )r0 NzAll-NaN slice encountered)r# r r: Zargmaxr; r6 r@ )r r0 r r> r! r! r" r � s $ c C s" t | d�\} }tj| ||||d�S )at Return the sum of array elements over a given axis treating Not a Numbers (NaNs) as zero. In NumPy versions <= 1.8.0 Nan is returned for slices that are all-NaN or empty. In later versions zero is returned. Parameters ---------- a : array_like Array containing numbers whose sum is desired. If `a` is not an array, a conversion is attempted. axis : int, optional Axis along which the sum is computed. The default is to compute the sum of the flattened array. dtype : data-type, optional The type of the returned array and of the accumulator in which the elements are summed. By default, the dtype of `a` is used. An exception is when `a` has an integer type with less precision than the platform (u)intp. In that case, the default will be either (u)int32 or (u)int64 depending on whether the platform is 32 or 64 bits. For inexact inputs, dtype must be inexact. .. versionadded:: 1.8.0 out : ndarray, optional Alternate output array in which to place the result. The default is ``None``. If provided, it must have the same shape as the expected output, but the type will be cast if necessary. See `doc.ufuncs` for details. The casting of NaN to integer can yield unexpected results. .. versionadded:: 1.8.0 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 original `a`. If the value is anything but the default, then `keepdims` will be passed through to the `mean` or `sum` methods of sub-classes of `ndarray`. If the sub-classes methods does not implement `keepdims` any exceptions will be raised. .. versionadded:: 1.8.0 Returns ------- nansum : ndarray. A new array holding the result is returned unless `out` is specified, in which it is returned. The result has the same size as `a`, and the same shape as `a` if `axis` is not None or `a` is a 1-d array. See Also -------- numpy.sum : Sum across array propagating NaNs. isnan : Show which elements are NaN. isfinite: Show which elements are not NaN or +/-inf. Notes ----- If both positive and negative infinity are present, the sum will be Not A Number (NaN). Examples -------- >>> np.nansum(1) 1 >>> np.nansum([1]) 1 >>> np.nansum([1, np.nan]) 1.0 >>> a = np.array([[1, 1], [1, np.nan]]) >>> np.nansum(a) 3.0 >>> np.nansum(a, axis=0) array([ 2., 1.]) >>> np.nansum([1, np.nan, np.inf]) inf >>> np.nansum([1, np.nan, np.NINF]) -inf >>> np.nansum([1, np.nan, np.inf, -np.inf]) # both +/- infinity present nan r )r0 r r, r/ )r# r �sum)r r0 r r, r/ r r! r! r" r � s Vc C s" t | d�\} }tj| ||||d�S )a Return the product of array elements over a given axis treating Not a Numbers (NaNs) as ones. One is returned for slices that are all-NaN or empty. .. versionadded:: 1.10.0 Parameters ---------- a : array_like Array containing numbers whose sum is desired. If `a` is not an array, a conversion is attempted. axis : int, optional Axis along which the product is computed. The default is to compute the product of the flattened array. dtype : data-type, optional The type of the returned array and of the accumulator in which the elements are summed. By default, the dtype of `a` is used. An exception is when `a` has an integer type with less precision than the platform (u)intp. In that case, the default will be either (u)int32 or (u)int64 depending on whether the platform is 32 or 64 bits. For inexact inputs, dtype must be inexact. out : ndarray, optional Alternate output array in which to place the result. The default is ``None``. If provided, it must have the same shape as the expected output, but the type will be cast if necessary. See `doc.ufuncs` for details. The casting of NaN to integer can yield unexpected results. keepdims : bool, optional If 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 original `arr`. Returns ------- nanprod : ndarray A new array holding the result is returned unless `out` is specified, in which case it is returned. See Also -------- numpy.prod : Product across array propagating NaNs. isnan : Show which elements are NaN. Examples -------- >>> np.nanprod(1) 1 >>> np.nanprod([1]) 1 >>> np.nanprod([1, np.nan]) 1.0 >>> a = np.array([[1, 2], [3, np.nan]]) >>> np.nanprod(a) 6.0 >>> np.nanprod(a, axis=0) array([ 3., 2.]) � )r0 r r, r/ )r# r �prod)r r0 r r, r/ r r! r! r" r ! s =c C s t | d�\} }tj| |||d�S )a� Return the cumulative sum of array elements over a given axis treating Not a Numbers (NaNs) as zero. The cumulative sum does not change when NaNs are encountered and leading NaNs are replaced by zeros. Zeros are returned for slices that are all-NaN or empty. .. versionadded:: 1.12.0 Parameters ---------- a : array_like Input array. axis : int, optional Axis along which the cumulative sum is computed. The default (None) is to compute the cumsum over the flattened array. dtype : dtype, optional Type of the returned array and of the accumulator in which the elements are summed. If `dtype` is not specified, it defaults to the dtype of `a`, unless `a` has an integer dtype with a precision less than that of the default platform integer. In that case, the default platform integer is used. 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. See `doc.ufuncs` (Section "Output arguments") for more details. Returns ------- nancumsum : ndarray. A new array holding the result is returned unless `out` is specified, in which it is returned. The result has the same size as `a`, and the same shape as `a` if `axis` is not None or `a` is a 1-d array. See Also -------- numpy.cumsum : Cumulative sum across array propagating NaNs. isnan : Show which elements are NaN. Examples -------- >>> np.nancumsum(1) array([1]) >>> np.nancumsum([1]) array([1]) >>> np.nancumsum([1, np.nan]) array([ 1., 1.]) >>> a = np.array([[1, 2], [3, np.nan]]) >>> np.nancumsum(a) array([ 1., 3., 6., 6.]) >>> np.nancumsum(a, axis=0) array([[ 1., 2.], [ 4., 2.]]) >>> np.nancumsum(a, axis=1) array([[ 1., 3.], [ 3., 3.]]) r )r0 r r, )r# r Zcumsum)r r0 r r, r r! r! r" r b s =c C s t | d�\} }tj| |||d�S )aS Return the cumulative product of array elements over a given axis treating Not a Numbers (NaNs) as one. The cumulative product does not change when NaNs are encountered and leading NaNs are replaced by ones. Ones are returned for slices that are all-NaN or empty. .. versionadded:: 1.12.0 Parameters ---------- a : array_like Input array. axis : int, optional Axis along which the cumulative product is computed. By default the input is flattened. dtype : dtype, optional Type of the returned array, as well as of the accumulator in which the elements are multiplied. If *dtype* is not specified, it defaults to the dtype of `a`, unless `a` has an integer dtype with a precision less than that of the default platform integer. In that case, the default platform integer is used instead. 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 of the resulting values will be cast if necessary. Returns ------- nancumprod : ndarray A new array holding the result is returned unless `out` is specified, in which case it is returned. See Also -------- numpy.cumprod : Cumulative product across array propagating NaNs. isnan : Show which elements are NaN. Examples -------- >>> np.nancumprod(1) array([1]) >>> np.nancumprod([1]) array([1]) >>> np.nancumprod([1, np.nan]) array([ 1., 1.]) >>> a = np.array([[1, 2], [3, np.nan]]) >>> np.nancumprod(a) array([ 1., 2., 6., 6.]) >>> np.nancumprod(a, axis=0) array([[ 1., 2.], [ 3., 2.]]) >>> np.nancumprod(a, axis=1) array([[ 1., 2.], [ 3., 3.]]) rB )r0 r r, )r# r Zcumprod)r r0 r r, r r! r! r" r � s :c C s� t | d�\}}|dkr*tj|||||d�S |dk r<t�|�}|dk rZt|jtj�sZtd��|dk rzt|jjtj�sztd��tj| |tj |d�}tj|||||d�}t |||d�} |dk} | � � r�t j dtd d � | S ) a� Compute the arithmetic mean along the specified axis, ignoring NaNs. Returns the average of the array elements. The average is taken over the flattened array by default, otherwise over the specified axis. `float64` intermediate and return values are used for integer inputs. For all-NaN slices, NaN is returned and a `RuntimeWarning` is raised. .. versionadded:: 1.8.0 Parameters ---------- a : array_like Array containing numbers whose mean is desired. If `a` is not an array, a conversion is attempted. axis : int, optional Axis along which the means are computed. The default is to compute the mean of the flattened array. dtype : data-type, optional Type to use in computing the mean. For integer inputs, the default is `float64`; for inexact inputs, it is the same as the input dtype. out : ndarray, optional Alternate output array in which to place the result. The default is ``None``; if provided, it must have the same shape as the expected output, but the type will be cast if necessary. See `doc.ufuncs` for details. 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 original `a`. If the value is anything but the default, then `keepdims` will be passed through to the `mean` or `sum` methods of sub-classes of `ndarray`. If the sub-classes methods does not implement `keepdims` any exceptions will be raised. Returns ------- m : ndarray, see dtype parameter above If `out=None`, returns a new array containing the mean values, otherwise a reference to the output array is returned. Nan is returned for slices that contain only NaNs. See Also -------- average : Weighted average mean : Arithmetic mean taken while not ignoring NaNs var, nanvar Notes ----- The arithmetic mean is the sum of the non-NaN elements along the axis divided by the number of non-NaN elements. Note that for floating-point input, the mean is computed using the same precision the input has. Depending on the input data, this can cause the results to be inaccurate, especially for `float32`. Specifying a higher-precision accumulator using the `dtype` keyword can alleviate this issue. Examples -------- >>> a = np.array([[1, np.nan], [3, 4]]) >>> np.nanmean(a) 2.6666666666666665 >>> np.nanmean(a, axis=0) array([ 2., 4.]) >>> np.nanmean(a, axis=1) array([ 1., 3.5]) r N)r0 r r, r/ z+If a is inexact, then dtype must be inexactz)If a is inexact, then out must be inexact)r0 r r/ )r, zMean of empty slicer1 )r2 )r# r Zmeanr r r r � TypeErrorrA �intpr. r6 r7 r8 r9 ) r r0 r r, r/ �arrr �cntZtot�avg�isbadr! r! r" r � s J Fc C s� t �| �}t �|�d }|j| jkr:tjdtdd� t jS |jdkrRt j| |d�S |r\| }n| � � }| |j d� ||j d� }|||d|j� < t j|d|j � dd�S dS )zu Private function for rank 1 arrays. Compute the median ignoring NaNs. See nanmedian for parameter usage r zAll-NaN slice encountered� )r2 )�overwrite_inputNT) r r r �sizer7 r8 r9 r< �medianr )�arr1drK �c�s�x�enonanr! r! r" � _nanmedian1dB s "rS c C s� |dks| j dkr@| �� }|dkr,t||�S t||�|d< |S n@| j| dk r\t| |||�S t�t|| |�}|dk r|||d< |S dS )z� Private function that doesn't support extended axis or keepdims. These methods are extended to this function using _ureduce See nanmedian for parameter usage NrB .iX )�ndim�ravelrS �shape�_nanmedian_smallr �apply_along_axis)r r0 r, rK �part�resultr! r! r" � _nanmedian[ s r[ c C s| t j�| t �| ��} t jj| ||d�}x,tt �|j�� ��D ]}t j dt dd� q<W |dk rp|� t j �|d< |S |� t j �S )z� sort + indexing median, faster for small medians along multiple dimensions due to the high overhead of apply_along_axis see nanmedian for parameter usage )r0 rK zAll-NaN slice encounteredrJ )r2 N.)r �maZ masked_arrayr rM �rangeZ count_nonzeror rU r7 r8 r9 Zfilledr< )r r0 r, rK �m�ir! r! r" rW u s rW c C s\ t �| �} | jdkr&t j| |||d�S t| t|||d�\}}|rT|t jk rT|�|�S |S dS )a Compute the median along the specified axis, while ignoring NaNs. Returns the median of the array elements. .. versionadded:: 1.9.0 Parameters ---------- a : array_like Input array or object that can be converted to an array. axis : {int, sequence of int, None}, optional Axis or axes along which the medians are computed. The default is to compute the median along a flattened version of the array. A sequence of axes is supported since version 1.9.0. 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 (of the output) 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. If `overwrite_input` is ``True`` and `a` 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 original `a`. If this is anything but the default value it will be passed through (in the special case of an empty array) to the `mean` function of the underlying array. If the array is a sub-class and `mean` does not have the kwarg `keepdims` this will raise a RuntimeError. Returns ------- median : ndarray A new array holding the result. If the input contains integers or floats smaller than ``float64``, then the output data-type is ``np.float64``. Otherwise, the data-type of the output is the same as that of the input. If `out` is specified, that array is returned instead. See Also -------- mean, median, percentile Notes ----- Given a vector ``V`` of length ``N``, the median of ``V`` is the middle value of a sorted copy of ``V``, ``V_sorted`` - i.e., ``V_sorted[(N-1)/2]``, when ``N`` is odd and the average of the two middle values of ``V_sorted`` when ``N`` is even. Examples -------- >>> a = np.array([[10.0, 7, 4], [3, 2, 1]]) >>> a[0, 1] = np.nan >>> a array([[ 10., nan, 4.], [ 3., 2., 1.]]) >>> np.median(a) nan >>> np.nanmedian(a) 3.0 >>> np.nanmedian(a, axis=0) array([ 6.5, 2., 2.5]) >>> np.median(a, axis=1) array([ 7., 2.]) >>> b = a.copy() >>> np.nanmedian(b, axis=1, overwrite_input=True) array([ 7., 2.]) >>> assert not np.all(a==b) >>> b = a.copy() >>> np.nanmedian(b, axis=None, overwrite_input=True) 3.0 >>> assert not np.all(a==b) r )r, r/ )�funcr0 r, rK N)r � asanyarrayrL r r r[ r3 �reshape)r r0 r, rK r/ �r�kr! r! r" r � s T �linearc C s� t �| �} t �|�}| jdkr0t j| |||d�S t| t|||||d�\}}|r�|t jk r�|jdkrl|�|�S |�t |�g| �S n|S dS )a. Compute the qth percentile of the data along the specified axis, while ignoring nan values. Returns the qth percentile(s) of the array elements. .. versionadded:: 1.9.0 Parameters ---------- a : array_like Input array or object that can be converted to an array. q : float in range of [0,100] (or sequence of floats) Percentile to compute, which must be between 0 and 100 inclusive. axis : {int, sequence of int, None}, optional Axis or axes along which the percentiles are computed. The default is to compute the percentile(s) along a flattened version of the array. A sequence of axes is supported since version 1.9.0. 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 (of the output) 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 `percentile`. This will save memory when you do not need to preserve the contents of the input array. In this case you should not make any assumptions about the contents of the input `a` after this function completes -- treat it as undefined. Default is False. If `a` is not already an array, this parameter will have no effect as `a` will be converted to an array internally regardless of the value of this parameter. interpolation : {'linear', 'lower', 'higher', 'midpoint', 'nearest'} This optional parameter specifies the interpolation method to use when the desired quantile lies between two data points ``i < j``: * linear: ``i + (j - i) * fraction``, where ``fraction`` is the fractional part of the index surrounded by ``i`` and ``j``. * lower: ``i``. * higher: ``j``. * nearest: ``i`` or ``j``, whichever is nearest. * midpoint: ``(i + j) / 2``. 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 original array `a`. If this is anything but the default value it will be passed through (in the special case of an empty array) to the `mean` function of the underlying array. If the array is a sub-class and `mean` does not have the kwarg `keepdims` this will raise a RuntimeError. Returns ------- percentile : scalar or ndarray If `q` is a single percentile and `axis=None`, then the result is a scalar. If multiple percentiles are given, first axis of the result corresponds to the percentiles. The other axes are the axes that remain after the reduction of `a`. If the input contains integers or floats smaller than ``float64``, the output data-type is ``float64``. Otherwise, the output data-type is the same as that of the input. If `out` is specified, that array is returned instead. See Also -------- nanmean, nanmedian, percentile, median, mean Notes ----- Given a vector ``V`` of length ``N``, the ``q``-th percentile of ``V`` is the value ``q/100`` of the way from the minimum to the maximum in a sorted copy of ``V``. The values and distances of the two nearest neighbors as well as the `interpolation` parameter will determine the percentile if the normalized ranking does not match the location of ``q`` exactly. This function is the same as the median if ``q=50``, the same as the minimum if ``q=0`` and the same as the maximum if ``q=100``. Examples -------- >>> a = np.array([[10., 7., 4.], [3., 2., 1.]]) >>> a[0][1] = np.nan >>> a array([[ 10., nan, 4.], [ 3., 2., 1.]]) >>> np.percentile(a, 50) nan >>> np.nanpercentile(a, 50) 3.5 >>> np.nanpercentile(a, 50, axis=0) array([ 6.5, 2., 2.5]) >>> np.nanpercentile(a, 50, axis=1, keepdims=True) array([[ 7.], [ 2.]]) >>> m = np.nanpercentile(a, 50, axis=0) >>> out = np.zeros_like(m) >>> np.nanpercentile(a, 50, axis=0, out=out) array([ 6.5, 2., 2.5]) >>> m array([ 6.5, 2. , 2.5]) >>> b = a.copy() >>> np.nanpercentile(b, 50, axis=1, overwrite_input=True) array([ 7., 2.]) >>> assert not np.all(a==b) r )r, r/ )r` �qr0 r, rK � interpolationN) r ra rL r r �_nanpercentiler3 rT rb �len) r rf r0 r, rK rg r/ rc rd r! r! r" r � s s c C sh |dks| j dkr*| �� }t||||�}n*t�t|| |||�}|j dkrTt�||�}|dk rd||d< |S )z� Private function that doesn't support extended axis or keepdims. These methods are extended to this function using _ureduce See nanpercentile for parameter usage NrB r .)rT rU �_nanpercentile1dr rX Zrollaxis)r rf r0 r, rK rg rY rZ r! r! r" rh n s rh c C s� t �| �}t �|�d }|j| jkr\tjdtdd� |jdkrDt jS t jt � t |�f� S n�|jdkrxt j | |||d�S |r�| }n| � � }| |j d� ||j d� }|||d|j� < t j |d|j � |d|d�S dS )z~ Private function for rank 1 arrays. Compute percentile ignoring NaNs. See nanpercentile for parameter usage r zAll-NaN slice encounteredrJ )r2 )rK rg NT) r r r rL r7 r8 r9 rT r< Zonesri Z percentiler )rN rf rK rg rO rP rQ rR r! r! r" rj � s" "rj c C s� t | d�\}}|dkr,tj||||||d�S |dk r>t�|�}|dk r\t|jtj�s\td��|dk r|t|jjtj�s|td��t|�tjkr�tj }nd}tj | |tj |d�} tj ||||d�} t | | �} tj || |dd � t|d|�}t|jjtj��rtj||�� |d �j} ntj|||d �} tj | ||||d �} | j| jk �rL| �|�} | | } t | | �} | dk}t�|��r�tjd td d� t| tj|�} | S )a� Compute the variance along the specified axis, while ignoring NaNs. Returns the variance of the array elements, a measure of the spread of a distribution. The variance is computed for the flattened array by default, otherwise over the specified axis. For all-NaN slices or slices with zero degrees of freedom, NaN is returned and a `RuntimeWarning` is raised. .. versionadded:: 1.8.0 Parameters ---------- a : array_like Array containing numbers whose variance is desired. If `a` is not an array, a conversion is attempted. axis : int, optional Axis along which the variance is computed. The default is to compute the variance of the flattened array. dtype : data-type, optional Type to use in computing the variance. For arrays of integer type the default is `float32`; for arrays of float types it is the same as the array type. out : ndarray, optional Alternate output array in which to place the result. It must have the same shape as the expected output, but the type is cast if necessary. ddof : int, optional "Delta Degrees of Freedom": the divisor used in the calculation is ``N - ddof``, where ``N`` represents the number of non-NaN elements. By default `ddof` is zero. 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 original `a`. Returns ------- variance : ndarray, see dtype parameter above If `out` is None, return a new array containing the variance, otherwise return a reference to the output array. If ddof is >= the number of non-NaN elements in a slice or the slice contains only NaNs, then the result for that slice is NaN. See Also -------- std : Standard deviation mean : Average var : Variance while not ignoring NaNs nanstd, nanmean numpy.doc.ufuncs : Section "Output arguments" Notes ----- The variance is the average of the squared deviations from the mean, i.e., ``var = mean(abs(x - x.mean())**2)``. The mean is normally calculated as ``x.sum() / N``, where ``N = len(x)``. If, however, `ddof` is specified, the divisor ``N - ddof`` is used instead. In standard statistical practice, ``ddof=1`` provides an unbiased estimator of the variance of a hypothetical infinite population. ``ddof=0`` provides a maximum likelihood estimate of the variance for normally distributed variables. Note that for complex numbers, the absolute value is taken before squaring, so that the result is always real and nonnegative. For floating-point input, the variance is computed using the same precision the input has. Depending on the input data, this can cause the results to be inaccurate, especially for `float32` (see example below). Specifying a higher-accuracy accumulator using the ``dtype`` keyword can alleviate this issue. For this function to work on sub-classes of ndarray, they must define `sum` with the kwarg `keepdims` Examples -------- >>> a = np.array([[1, np.nan], [3, 4]]) >>> np.var(a) 1.5555555555555554 >>> np.nanvar(a, axis=0) array([ 1., 0.]) >>> np.nanvar(a, axis=1) array([ 0., 0.25]) r N)r0 r r, �ddofr/ z+If a is inexact, then dtype must be inexactz)If a is inexact, then out must be inexactT)r0 r r/ r$ )r, r% )r, )r0 r r, r/ z"Degrees of freedom <= 0 for slice.r1 )r2 )r# r �varr r r r rD Zmatrixr3 rA rE r. �subtractr( Zcomplexfloating�multiply�conj�realrT Zsqueezer6 r7 r8 r9 r< )r r0 r r, rk r/ rF r Z _keepdimsrG rH Zsqrrl ZdofrI r! r! r" r � s> Z c C sF t | |||||d�}t|tj�r0tj||d�}n|j�t�|��}|S )a� Compute the standard deviation along the specified axis, while ignoring NaNs. Returns the standard deviation, a measure of the spread of a distribution, of the non-NaN array elements. The standard deviation is computed for the flattened array by default, otherwise over the specified axis. For all-NaN slices or slices with zero degrees of freedom, NaN is returned and a `RuntimeWarning` is raised. .. versionadded:: 1.8.0 Parameters ---------- a : array_like Calculate the standard deviation of the non-NaN values. axis : int, optional Axis along which the standard deviation is computed. The default is to compute the standard deviation of the flattened array. dtype : dtype, optional Type to use in computing the standard deviation. For arrays of integer type the default is float64, for arrays of float types it is the same as the array type. out : ndarray, optional Alternative output array in which to place the result. It must have the same shape as the expected output but the type (of the calculated values) will be cast if necessary. ddof : int, optional Means Delta Degrees of Freedom. The divisor used in calculations is ``N - ddof``, where ``N`` represents the number of non-NaN elements. By default `ddof` is zero. 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 original `a`. If this value is anything but the default it is passed through as-is to the relevant functions of the sub-classes. If these functions do not have a `keepdims` kwarg, a RuntimeError will be raised. Returns ------- standard_deviation : ndarray, see dtype parameter above. If `out` is None, return a new array containing the standard deviation, otherwise return a reference to the output array. If ddof is >= the number of non-NaN elements in a slice or the slice contains only NaNs, then the result for that slice is NaN. See Also -------- var, mean, std nanvar, nanmean numpy.doc.ufuncs : Section "Output arguments" Notes ----- The standard deviation is the square root of the average of the squared deviations from the mean: ``std = sqrt(mean(abs(x - x.mean())**2))``. The average squared deviation is normally calculated as ``x.sum() / N``, where ``N = len(x)``. If, however, `ddof` is specified, the divisor ``N - ddof`` is used instead. In standard statistical practice, ``ddof=1`` provides an unbiased estimator of the variance of the infinite population. ``ddof=0`` provides a maximum likelihood estimate of the variance for normally distributed variables. The standard deviation computed in this function is the square root of the estimated variance, so even with ``ddof=1``, it will not be an unbiased estimate of the standard deviation per se. Note that, for complex numbers, `std` takes the absolute value before squaring, so that the result is always real and nonnegative. For floating-point input, the *std* is computed using the same precision the input has. Depending on the input data, this can cause the results to be inaccurate, especially for float32 (see example below). Specifying a higher-accuracy accumulator using the `dtype` keyword can alleviate this issue. Examples -------- >>> a = np.array([[1, np.nan], [3, 4]]) >>> np.nanstd(a) 1.247219128924647 >>> np.nanstd(a, axis=0) array([ 1., 0.]) >>> np.nanstd(a, axis=1) array([ 0., 0.5]) )r0 r r, rk r/ )r, )r r& r r' �sqrtr r )r r0 r r, rk r/ rl Zstdr! r! r" r 4 s ^ )N)N)N)NNN)NNN)F)NNF)NNF)NNFre )Fre )!�__doc__� __future__r r r r7 �numpyr Znumpy.lib.function_baser �__all__r# r( r. r3 r r r r r r r r r rS r[ rW r r rh rj r r r! r! r! r" �<module> s@ , )ll , -ZA A >a b