Source code for mars.tensor.reduction.nanstd

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# Copyright 1999-2021 Alibaba Group Holding Ltd.
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# See the License for the specific language governing permissions and
# limitations under the License.

from ..arithmetic.sqrt import sqrt
from .nanvar import nanvar

[docs]def nanstd( a, axis=None, dtype=None, out=None, ddof=0, keepdims=None, combine_size=None ): """ 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 tensor elements. The standard deviation is computed for the flattened tensor 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. 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 tensor. dtype : dtype, optional Type to use in computing the standard deviation. For tensors of integer type the default is float64, for tensors of float types it is the same as the tensor type. out : Tensor, optional Alternative output tensor 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. combine_size: int, optional The number of chunks to combine. 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 tensor. 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 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 -------- >>> import mars.tensor as mt >>> a = mt.array([[1, mt.nan], [3, 4]]) >>> mt.nanstd(a).execute() 1.247219128924647 >>> mt.nanstd(a, axis=0).execute() array([ 1., 0.]) >>> mt.nanstd(a, axis=1).execute() array([ 0., 0.5]) """ ret = sqrt( nanvar( a, axis=axis, dtype=dtype, out=out, ddof=ddof, keepdims=keepdims, combine_size=combine_size, ) ) if dtype is not None and ret.dtype != dtype: ret = ret.astype(dtype) return ret