diff options
Diffstat (limited to 'numpy/lib/function_base.py')
| -rw-r--r-- | numpy/lib/function_base.py | 386 |
1 files changed, 40 insertions, 346 deletions
diff --git a/numpy/lib/function_base.py b/numpy/lib/function_base.py index 17f99a065..9336579af 100644 --- a/numpy/lib/function_base.py +++ b/numpy/lib/function_base.py @@ -1,15 +1,14 @@ from __future__ import division, absolute_import, print_function __docformat__ = "restructuredtext en" -__all__ = ['select', 'piecewise', 'trim_zeros', 'copy', 'iterable', - 'percentile', 'diff', 'gradient', 'angle', 'unwrap', 'sort_complex', - 'disp', 'extract', 'place', 'nansum', 'nanmax', 'nanargmax', - 'nanargmin', 'nanmin', 'vectorize', 'asarray_chkfinite', 'average', - 'histogram', 'histogramdd', 'bincount', 'digitize', 'cov', - 'corrcoef', 'msort', 'median', 'sinc', 'hamming', 'hanning', - 'bartlett', 'blackman', 'kaiser', 'trapz', 'i0', 'add_newdoc', - 'add_docstring', 'meshgrid', 'delete', 'insert', 'append', 'interp', - 'add_newdoc_ufunc'] +__all__ = [ + 'select', 'piecewise', 'trim_zeros', 'copy', 'iterable', 'percentile', + 'diff', 'gradient', 'angle', 'unwrap', 'sort_complex', 'disp', + 'extract', 'place', 'vectorize', 'asarray_chkfinite', 'average', + 'histogram', 'histogramdd', 'bincount', 'digitize', 'cov', 'corrcoef', + 'msort', 'median', 'sinc', 'hamming', 'hanning', 'bartlett', + 'blackman', 'kaiser', 'trapz', 'i0', 'add_newdoc', 'add_docstring', + 'meshgrid', 'delete', 'insert', 'append', 'interp', 'add_newdoc_ufunc'] import warnings import types @@ -22,7 +21,7 @@ from numpy.core.numeric import ScalarType, dot, where, newaxis, intp, \ integer, isscalar from numpy.core.umath import pi, multiply, add, arctan2, \ frompyfunc, isnan, cos, less_equal, sqrt, sin, mod, exp, log10 -from numpy.core.fromnumeric import ravel, nonzero, choose, sort, mean +from numpy.core.fromnumeric import ravel, nonzero, choose, sort, partition, mean from numpy.core.numerictypes import typecodes, number from numpy.core import atleast_1d, atleast_2d from numpy.lib.twodim_base import diag @@ -1361,331 +1360,6 @@ def place(arr, mask, vals): """ return _insert(arr, mask, vals) -def _nanop(op, fill, a, axis=None): - """ - General operation on arrays with not-a-number values. - - Parameters - ---------- - op : callable - Operation to perform. - fill : float - NaN values are set to fill before doing the operation. - a : array-like - Input array. - axis : {int, None}, optional - Axis along which the operation is computed. - By default the input is flattened. - - Returns - ------- - y : {ndarray, scalar} - Processed data. - - """ - y = array(a, subok=True) - - # We only need to take care of NaN's in floating point arrays - dt = y.dtype - if np.issubdtype(dt, np.integer) or np.issubdtype(dt, np.bool_): - return op(y, axis=axis) - - mask = isnan(a) - # y[mask] = fill - # We can't use fancy indexing here as it'll mess w/ MaskedArrays - # Instead, let's fill the array directly... - np.copyto(y, fill, where=mask) - res = op(y, axis=axis) - mask_all_along_axis = mask.all(axis=axis) - - # Along some axes, only nan's were encountered. As such, any values - # calculated along that axis should be set to nan. - if mask_all_along_axis.any(): - if np.isscalar(res): - res = np.nan - else: - res[mask_all_along_axis] = np.nan - - return res - -def nansum(a, axis=None): - """ - Return the sum of array elements over a given axis treating - Not a Numbers (NaNs) as zero. - - 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. - - Returns - ------- - y : 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, a scalar is returned with - the same dtype as `a`. - - See Also - -------- - numpy.sum : Sum across array including Not a Numbers. - isnan : Shows which elements are Not a Number (NaN). - isfinite: Shows which elements are not: Not a Number, positive and - negative infinity - - 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. - If positive or negative infinity are present the result is positive or - negative infinity. But if both positive and negative infinity are present, - the result is Not A Number (NaN). - - Arithmetic is modular when using integer types (all elements of `a` must - be finite i.e. no elements that are NaNs, positive infinity and negative - infinity because NaNs are floating point types), and no error is raised - on overflow. - - - 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.]) - - When positive infinity and negative infinity are present - - >>> np.nansum([1, np.nan, np.inf]) - inf - >>> np.nansum([1, np.nan, np.NINF]) - -inf - >>> np.nansum([1, np.nan, np.inf, np.NINF]) - nan - - """ - return _nanop(np.sum, 0, a, axis) - -def nanmin(a, axis=None): - """ - Return the minimum of an array or minimum along an axis, ignoring any NaNs. - - 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. - - 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 - - """ - a = np.asanyarray(a) - if axis is not None: - return np.fmin.reduce(a, axis) - else: - return np.fmin.reduce(a.flat) - -def nanargmin(a, axis=None): - """ - Return indices of the minimum values over an axis, ignoring NaNs. - - 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]) - - """ - return _nanop(np.argmin, np.inf, a, axis) - -def nanmax(a, axis=None): - """ - Return the maximum of an array or maximum along an axis, ignoring any NaNs. - - 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. - - 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 - - """ - a = np.asanyarray(a) - if axis is not None: - return np.fmax.reduce(a, axis) - else: - return np.fmax.reduce(a.flat) - -def nanargmax(a, axis=None): - """ - Return indices of the maximum values over an axis, ignoring NaNs. - - 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]) - - """ - return _nanop(np.argmax, -np.inf, a, axis) - def disp(mesg, device=None, linefeed=True): """ Display a message on a device. @@ -2996,30 +2670,50 @@ def median(a, axis=None, out=None, overwrite_input=False): >>> assert not np.all(a==b) """ + if axis is not None and axis >= a.ndim: + raise IndexError("axis %d out of bounds (%d)" % (axis, a.ndim)) + if overwrite_input: if axis is None: - sorted = a.ravel() - sorted.sort() + part = a.ravel() + sz = part.size + if sz % 2 == 0: + szh = sz // 2 + part.partition((szh - 1, szh)) + else: + part.partition((sz - 1) // 2) else: - a.sort(axis=axis) - sorted = a + sz = a.shape[axis] + if sz % 2 == 0: + szh = sz // 2 + a.partition((szh - 1, szh), axis=axis) + else: + a.partition((sz - 1) // 2, axis=axis) + part = a else: - sorted = sort(a, axis=axis) - if sorted.shape == (): + if axis is None: + sz = a.size + else: + sz = a.shape[axis] + if sz % 2 == 0: + part = partition(a, ((sz // 2) - 1, sz // 2), axis=axis) + else: + part = partition(a, (sz - 1) // 2, axis=axis) + if part.shape == (): # make 0-D arrays work - return sorted.item() + return part.item() if axis is None: axis = 0 - indexer = [slice(None)] * sorted.ndim - index = int(sorted.shape[axis]/2) - if sorted.shape[axis] % 2 == 1: + indexer = [slice(None)] * part.ndim + index = part.shape[axis] // 2 + if part.shape[axis] % 2 == 1: # index with slice to allow mean (below) to work indexer[axis] = slice(index, index+1) else: indexer[axis] = slice(index-1, index+1) # Use mean in odd and even case to coerce data type # and check, use out array. - return mean(sorted[indexer], axis=axis, out=out) + return mean(part[indexer], axis=axis, out=out) def percentile(a, q, axis=None, out=None, overwrite_input=False): """ |