diff options
Diffstat (limited to 'numpy/lib/nanfunctions.py')
| -rw-r--r-- | numpy/lib/nanfunctions.py | 108 |
1 files changed, 56 insertions, 52 deletions
diff --git a/numpy/lib/nanfunctions.py b/numpy/lib/nanfunctions.py index b3f3bfc69..16e363d7c 100644 --- a/numpy/lib/nanfunctions.py +++ b/numpy/lib/nanfunctions.py @@ -23,7 +23,7 @@ from __future__ import division, absolute_import, print_function import warnings import numpy as np -from numpy.lib.function_base import _ureduce as _ureduce +from numpy.lib import function_base __all__ = [ @@ -198,8 +198,8 @@ def nanmin(a, axis=None, out=None, keepdims=np._NoValue): 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 + axis : {int, tuple of int, None}, optional + Axis or axes 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 @@ -306,8 +306,8 @@ def nanmax(a, axis=None, out=None, keepdims=np._NoValue): 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 + axis : {int, tuple of int, None}, optional + Axis or axes 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 @@ -497,7 +497,7 @@ def nansum(a, axis=None, dtype=None, out=None, keepdims=np._NoValue): 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 + In NumPy versions <= 1.9.0 Nan is returned for slices that are all-NaN or empty. In later versions zero is returned. Parameters @@ -505,8 +505,8 @@ def nansum(a, axis=None, dtype=None, out=None, keepdims=np._NoValue): 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 + axis : {int, tuple of int, None}, optional + Axis or axes 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 @@ -596,8 +596,8 @@ def nanprod(a, axis=None, dtype=None, out=None, keepdims=np._NoValue): a : array_like Array containing numbers whose product 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 + axis : {int, tuple of int, None}, optional + Axis or axes 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 @@ -791,8 +791,8 @@ def nanmean(a, axis=None, dtype=None, out=None, keepdims=np._NoValue): 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 + axis : {int, tuple of int, None}, optional + Axis or axes 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 @@ -1017,8 +1017,8 @@ def nanmedian(a, axis=None, out=None, overwrite_input=False, keepdims=np._NoValu if a.size == 0: return np.nanmean(a, axis, out=out, keepdims=keepdims) - r, k = _ureduce(a, func=_nanmedian, axis=axis, out=out, - overwrite_input=overwrite_input) + r, k = function_base._ureduce(a, func=_nanmedian, axis=axis, out=out, + overwrite_input=overwrite_input) if keepdims and keepdims is not np._NoValue: return r.reshape(k) else: @@ -1038,36 +1038,30 @@ def nanpercentile(a, q, axis=None, out=None, overwrite_input=False, 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 + Input array or object that can be converted to an array, containing + nan values to be ignored. + q : array_like of float + Percentile or sequence of percentiles to compute, which must be between + 0 and 100 inclusive. + axis : {int, tuple 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. + 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 (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. + If True, then allow the input array `a` to be modified by intermediate + calculations, to save memory. In this case, the contents of the input + `a` after this function completes is undefined. 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``. + * 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. @@ -1097,7 +1091,9 @@ def nanpercentile(a, q, axis=None, out=None, overwrite_input=False, See Also -------- - nanmean, nanmedian, percentile, median, mean + nanmean + nanmedian : equivalent to ``nanpercentile(..., 50)`` + percentile, median, mean Notes ----- @@ -1139,36 +1135,44 @@ def nanpercentile(a, q, axis=None, out=None, overwrite_input=False, >>> assert not np.all(a==b) """ - a = np.asanyarray(a) - q = np.asanyarray(q) + q = np.true_divide(q, 100.0) # handles the asarray for us too + if not function_base._quantile_is_valid(q): + raise ValueError("Percentiles must be in the range [0, 100]") + return _nanquantile_unchecked( + a, q, axis, out, overwrite_input, interpolation, keepdims) + + +def _nanquantile_unchecked(a, q, axis=None, out=None, overwrite_input=False, + interpolation='linear', keepdims=np._NoValue): + """Assumes that q is in [0, 1], and is an ndarray""" # apply_along_axis in _nanpercentile doesn't handle empty arrays well, # so deal them upfront if a.size == 0: return np.nanmean(a, axis, out=out, keepdims=keepdims) - r, k = _ureduce(a, func=_nanpercentile, q=q, axis=axis, out=out, - overwrite_input=overwrite_input, - interpolation=interpolation) + r, k = function_base._ureduce( + a, func=_nanquantile_ureduce_func, q=q, axis=axis, out=out, + overwrite_input=overwrite_input, interpolation=interpolation + ) if keepdims and keepdims is not np._NoValue: return r.reshape(q.shape + k) else: return r -def _nanpercentile(a, q, axis=None, out=None, overwrite_input=False, - interpolation='linear'): +def _nanquantile_ureduce_func(a, q, axis=None, out=None, overwrite_input=False, + interpolation='linear'): """ Private function that doesn't support extended axis or keepdims. These methods are extended to this function using _ureduce See nanpercentile for parameter usage - """ if axis is None or a.ndim == 1: part = a.ravel() - result = _nanpercentile1d(part, q, overwrite_input, interpolation) + result = _nanquantile_1d(part, q, overwrite_input, interpolation) else: - result = np.apply_along_axis(_nanpercentile1d, axis, a, q, + result = np.apply_along_axis(_nanquantile_1d, axis, a, q, overwrite_input, interpolation) # apply_along_axis fills in collapsed axis with results. # Move that axis to the beginning to match percentile's @@ -1181,9 +1185,9 @@ def _nanpercentile(a, q, axis=None, out=None, overwrite_input=False, return result -def _nanpercentile1d(arr1d, q, overwrite_input=False, interpolation='linear'): +def _nanquantile_1d(arr1d, q, overwrite_input=False, interpolation='linear'): """ - Private function for rank 1 arrays. Compute percentile ignoring NaNs. + Private function for rank 1 arrays. Compute quantile ignoring NaNs. See nanpercentile for parameter usage """ arr1d, overwrite_input = _remove_nan_1d(arr1d, @@ -1191,8 +1195,8 @@ def _nanpercentile1d(arr1d, q, overwrite_input=False, interpolation='linear'): if arr1d.size == 0: return np.full(q.shape, np.nan)[()] # convert to scalar - return np.percentile(arr1d, q, overwrite_input=overwrite_input, - interpolation=interpolation) + return function_base._quantile_unchecked( + arr1d, q, overwrite_input=overwrite_input, interpolation=interpolation) def nanvar(a, axis=None, dtype=None, out=None, ddof=0, keepdims=np._NoValue): @@ -1213,8 +1217,8 @@ def nanvar(a, axis=None, dtype=None, out=None, ddof=0, keepdims=np._NoValue): 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 + axis : {int, tuple of int, None}, optional + Axis or axes 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 @@ -1355,8 +1359,8 @@ def nanstd(a, axis=None, dtype=None, out=None, ddof=0, keepdims=np._NoValue): ---------- 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 + axis : {int, tuple of int, None}, optional + Axis or axes 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 |