diff options
Diffstat (limited to 'numpy/ma/core.py')
| -rw-r--r-- | numpy/ma/core.py | 377 |
1 files changed, 272 insertions, 105 deletions
diff --git a/numpy/ma/core.py b/numpy/ma/core.py index 59ba3a593..2fe326885 100644 --- a/numpy/ma/core.py +++ b/numpy/ma/core.py @@ -2310,7 +2310,7 @@ def masked_values(x, value, rtol=1e-5, atol=1e-8, copy=True, shrink=True): mask=False, fill_value=2.1) - Unlike `masked_equal`, `masked_values` can perform approximate equalities. + Unlike `masked_equal`, `masked_values` can perform approximate equalities. >>> ma.masked_values(x, 2.1, atol=1e-1) masked_array(data=[1.0, 1.1, --, 1.1, 3.0], @@ -2356,8 +2356,13 @@ def masked_invalid(a, copy=True): fill_value=1e+20) """ - - return masked_where(~(np.isfinite(getdata(a))), a, copy=copy) + a = np.array(a, copy=False, subok=True) + res = masked_where(~(np.isfinite(a)), a, copy=copy) + # masked_invalid previously never returned nomask as a mask and doing so + # threw off matplotlib (gh-22842). So use shrink=False: + if res._mask is nomask: + res._mask = make_mask_none(res.shape, res.dtype) + return res ############################################################################### # Printing options # @@ -2852,7 +2857,7 @@ class MaskedArray(ndarray): mask = np.array( [getmaskarray(np.asanyarray(m, dtype=_data.dtype)) for m in data], dtype=mdtype) - except ValueError: + except (ValueError, TypeError): # If data is nested mask = nomask # Force shrinking of the mask if needed (and possible) @@ -2865,11 +2870,17 @@ class MaskedArray(ndarray): _data._mask = _data._mask.copy() # Reset the shape of the original mask if getmask(data) is not nomask: - data._mask.shape = data.shape + # gh-21022 encounters an issue here + # because data._mask.shape is not writeable, but + # the op was also pointless in that case, because + # the shapes were the same, so we can at least + # avoid that path + if data._mask.shape != data.shape: + data._mask.shape = data.shape else: # Case 2. : With a mask in input. # If mask is boolean, create an array of True or False - + # if users pass `mask=None` be forgiving here and cast it False # for speed; although the default is `mask=nomask` and can differ. if mask is None: @@ -2922,7 +2933,7 @@ class MaskedArray(ndarray): else: _data._mask = np.logical_or(mask, _data._mask) _data._sharedmask = False - + # Update fill_value. if fill_value is None: fill_value = getattr(data, '_fill_value', None) @@ -3329,6 +3340,10 @@ class MaskedArray(ndarray): # Note: Don't try to check for m.any(), that'll take too long return dout + # setitem may put NaNs into integer arrays or occasionally overflow a + # float. But this may happen in masked values, so avoid otherwise + # correct warnings (as is typical also in masked calculations). + @np.errstate(over='ignore', invalid='ignore') def __setitem__(self, indx, value): """ x.__setitem__(i, y) <==> x[i]=y @@ -4620,6 +4635,7 @@ class MaskedArray(ndarray): otherwise. 'K' means to read the elements in the order they occur in memory, except for reversing the data when strides are negative. By default, 'C' index order is used. + (Masked arrays currently use 'A' on the data when 'K' is passed.) Returns ------- @@ -4646,6 +4662,13 @@ class MaskedArray(ndarray): fill_value=999999) """ + # The order of _data and _mask could be different (it shouldn't be + # normally). Passing order `K` or `A` would be incorrect. + # So we ignore the mask memory order. + # TODO: We don't actually support K, so use A instead. We could + # try to guess this correct by sorting strides or deprecate. + if order in "kKaA": + order = "F" if self._data.flags.fnc else "C" r = ndarray.ravel(self._data, order=order).view(type(self)) r._update_from(self) if self._mask is not nomask: @@ -6295,6 +6318,12 @@ class MaskedArray(ndarray): memo[id(self)] = copied for (k, v) in self.__dict__.items(): copied.__dict__[k] = deepcopy(v, memo) + # as clearly documented for np.copy(), you need to use + # deepcopy() directly for arrays of object type that may + # contain compound types--you cannot depend on normal + # copy semantics to do the right thing here + if self.dtype.hasobject: + copied._data[...] = deepcopy(copied._data) return copied @@ -6991,6 +7020,21 @@ def sort(a, axis=-1, kind=None, order=None, endwith=True, fill_value=None): See Also -------- MaskedArray.sort : equivalent method + + Examples + -------- + >>> import numpy.ma as ma + >>> x = [11.2, -3.973, 0.801, -1.41] + >>> mask = [0, 0, 0, 1] + >>> masked_x = ma.masked_array(x, mask) + >>> masked_x + masked_array(data=[11.2, -3.973, 0.801, --], + mask=[False, False, False, True], + fill_value=1e+20) + >>> ma.sort(masked_x) + masked_array(data=[-3.973, 0.801, 11.2, --], + mask=[False, False, False, True], + fill_value=1e+20) """ a = np.array(a, copy=True, subok=True) if axis is None: @@ -7016,6 +7060,29 @@ def compressed(x): -------- ma.MaskedArray.compressed : Equivalent method. + Examples + -------- + + Create an array with negative values masked: + + >>> import numpy as np + >>> x = np.array([[1, -1, 0], [2, -1, 3], [7, 4, -1]]) + >>> masked_x = np.ma.masked_array(x, mask=x < 0) + >>> masked_x + masked_array( + data=[[1, --, 0], + [2, --, 3], + [7, 4, --]], + mask=[[False, True, False], + [False, True, False], + [False, False, True]], + fill_value=999999) + + Compress the masked array into a 1-D array of non-masked values: + + >>> np.ma.compressed(masked_x) + array([1, 0, 2, 3, 7, 4]) + """ return asanyarray(x).compressed() @@ -7091,6 +7158,38 @@ def diag(v, k=0): -------- numpy.diag : Equivalent function for ndarrays. + Examples + -------- + + Create an array with negative values masked: + + >>> import numpy as np + >>> x = np.array([[11.2, -3.973, 18], [0.801, -1.41, 12], [7, 33, -12]]) + >>> masked_x = np.ma.masked_array(x, mask=x < 0) + >>> masked_x + masked_array( + data=[[11.2, --, 18.0], + [0.801, --, 12.0], + [7.0, 33.0, --]], + mask=[[False, True, False], + [False, True, False], + [False, False, True]], + fill_value=1e+20) + + Isolate the main diagonal from the masked array: + + >>> np.ma.diag(masked_x) + masked_array(data=[11.2, --, --], + mask=[False, True, True], + fill_value=1e+20) + + Isolate the first diagonal below the main diagonal: + + >>> np.ma.diag(masked_x, -1) + masked_array(data=[0.801, 33.0], + mask=[False, False], + fill_value=1e+20) + """ output = np.diag(v, k).view(MaskedArray) if getmask(v) is not nomask: @@ -7130,6 +7229,21 @@ def right_shift(a, n): -------- numpy.right_shift + Examples + -------- + >>> import numpy.ma as ma + >>> x = [11, 3, 8, 1] + >>> mask = [0, 0, 0, 1] + >>> masked_x = ma.masked_array(x, mask) + >>> masked_x + masked_array(data=[11, 3, 8, --], + mask=[False, False, False, True], + fill_value=999999) + >>> ma.right_shift(masked_x,1) + masked_array(data=[5, 1, 4, --], + mask=[False, False, False, True], + fill_value=999999) + """ m = getmask(a) if m is nomask: @@ -7341,6 +7455,141 @@ def size(obj, axis=None): size.__doc__ = np.size.__doc__ +def diff(a, /, n=1, axis=-1, prepend=np._NoValue, append=np._NoValue): + """ + Calculate the n-th discrete difference along the given axis. + The first difference is given by ``out[i] = a[i+1] - a[i]`` along + the given axis, higher differences are calculated by using `diff` + recursively. + Preserves the input mask. + + Parameters + ---------- + a : array_like + Input array + n : int, optional + The number of times values are differenced. If zero, the input + is returned as-is. + axis : int, optional + The axis along which the difference is taken, default is the + last axis. + prepend, append : array_like, optional + Values to prepend or append to `a` along axis prior to + performing the difference. Scalar values are expanded to + arrays with length 1 in the direction of axis and the shape + of the input array in along all other axes. Otherwise the + dimension and shape must match `a` except along axis. + + Returns + ------- + diff : MaskedArray + The n-th differences. The shape of the output is the same as `a` + except along `axis` where the dimension is smaller by `n`. The + type of the output is the same as the type of the difference + between any two elements of `a`. This is the same as the type of + `a` in most cases. A notable exception is `datetime64`, which + results in a `timedelta64` output array. + + See Also + -------- + numpy.diff : Equivalent function in the top-level NumPy module. + + Notes + ----- + Type is preserved for boolean arrays, so the result will contain + `False` when consecutive elements are the same and `True` when they + differ. + + For unsigned integer arrays, the results will also be unsigned. This + should not be surprising, as the result is consistent with + calculating the difference directly: + + >>> u8_arr = np.array([1, 0], dtype=np.uint8) + >>> np.ma.diff(u8_arr) + masked_array(data=[255], + mask=False, + fill_value=999999, + dtype=uint8) + >>> u8_arr[1,...] - u8_arr[0,...] + 255 + + If this is not desirable, then the array should be cast to a larger + integer type first: + + >>> i16_arr = u8_arr.astype(np.int16) + >>> np.ma.diff(i16_arr) + masked_array(data=[-1], + mask=False, + fill_value=999999, + dtype=int16) + + Examples + -------- + >>> a = np.array([1, 2, 3, 4, 7, 0, 2, 3]) + >>> x = np.ma.masked_where(a < 2, a) + >>> np.ma.diff(x) + masked_array(data=[--, 1, 1, 3, --, --, 1], + mask=[ True, False, False, False, True, True, False], + fill_value=999999) + + >>> np.ma.diff(x, n=2) + masked_array(data=[--, 0, 2, --, --, --], + mask=[ True, False, False, True, True, True], + fill_value=999999) + + >>> a = np.array([[1, 3, 1, 5, 10], [0, 1, 5, 6, 8]]) + >>> x = np.ma.masked_equal(a, value=1) + >>> np.ma.diff(x) + masked_array( + data=[[--, --, --, 5], + [--, --, 1, 2]], + mask=[[ True, True, True, False], + [ True, True, False, False]], + fill_value=1) + + >>> np.ma.diff(x, axis=0) + masked_array(data=[[--, --, --, 1, -2]], + mask=[[ True, True, True, False, False]], + fill_value=1) + + """ + if n == 0: + return a + if n < 0: + raise ValueError("order must be non-negative but got " + repr(n)) + + a = np.ma.asanyarray(a) + if a.ndim == 0: + raise ValueError( + "diff requires input that is at least one dimensional" + ) + + combined = [] + if prepend is not np._NoValue: + prepend = np.ma.asanyarray(prepend) + if prepend.ndim == 0: + shape = list(a.shape) + shape[axis] = 1 + prepend = np.broadcast_to(prepend, tuple(shape)) + combined.append(prepend) + + combined.append(a) + + if append is not np._NoValue: + append = np.ma.asanyarray(append) + if append.ndim == 0: + shape = list(a.shape) + shape[axis] = 1 + append = np.broadcast_to(append, tuple(shape)) + combined.append(append) + + if len(combined) > 1: + a = np.ma.concatenate(combined, axis) + + # GH 22465 np.diff without prepend/append preserves the mask + return np.diff(a, n, axis) + + ############################################################################## # Extra functions # ############################################################################## @@ -7568,94 +7817,18 @@ def round_(a, decimals=0, out=None): round = round_ -# Needed by dot, so move here from extras.py. It will still be exported -# from extras.py for compatibility. -def mask_rowcols(a, axis=None): +def _mask_propagate(a, axis): """ - Mask rows and/or columns of a 2D array that contain masked values. - - Mask whole rows and/or columns of a 2D array that contain - masked values. The masking behavior is selected using the - `axis` parameter. - - - If `axis` is None, rows *and* columns are masked. - - If `axis` is 0, only rows are masked. - - If `axis` is 1 or -1, only columns are masked. - - Parameters - ---------- - a : array_like, MaskedArray - The array to mask. If not a MaskedArray instance (or if no array - elements are masked). The result is a MaskedArray with `mask` set - to `nomask` (False). Must be a 2D array. - axis : int, optional - Axis along which to perform the operation. If None, applies to a - flattened version of the array. - - Returns - ------- - a : MaskedArray - A modified version of the input array, masked depending on the value - of the `axis` parameter. - - Raises - ------ - NotImplementedError - If input array `a` is not 2D. - - See Also - -------- - mask_rows : Mask rows of a 2D array that contain masked values. - mask_cols : Mask cols of a 2D array that contain masked values. - masked_where : Mask where a condition is met. - - Notes - ----- - The input array's mask is modified by this function. - - 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_rowcols(a) - masked_array( - data=[[0, --, 0], - [--, --, --], - [0, --, 0]], - mask=[[False, True, False], - [ True, True, True], - [False, True, False]], - fill_value=1) - + Mask whole 1-d vectors of an array that contain masked values. """ a = array(a, subok=False) - if a.ndim != 2: - raise NotImplementedError("mask_rowcols works for 2D arrays only.") m = getmask(a) - # Nothing is masked: return a - if m is nomask or not m.any(): + if m is nomask or not m.any() or axis is None: return a - maskedval = m.nonzero() a._mask = a._mask.copy() - if not axis: - a[np.unique(maskedval[0])] = masked - if axis in [None, 1, -1]: - a[:, np.unique(maskedval[1])] = masked + axes = normalize_axis_tuple(axis, a.ndim) + for ax in axes: + a._mask |= m.any(axis=ax, keepdims=True) return a @@ -7672,10 +7845,6 @@ def dot(a, b, strict=False, out=None): corresponding method, it is recommended that the optional arguments be treated as keyword only. At some point that may be mandatory. - .. note:: - Works only with 2-D arrays at the moment. - - Parameters ---------- a, b : masked_array_like @@ -7719,18 +7888,22 @@ def dot(a, b, strict=False, out=None): fill_value=999999) """ - # !!!: Works only with 2D arrays. There should be a way to get it to run - # with higher dimension - if strict and (a.ndim == 2) and (b.ndim == 2): - a = mask_rowcols(a, 0) - b = mask_rowcols(b, 1) + if strict is True: + if np.ndim(a) == 0 or np.ndim(b) == 0: + pass + elif b.ndim == 1: + a = _mask_propagate(a, a.ndim - 1) + b = _mask_propagate(b, b.ndim - 1) + else: + a = _mask_propagate(a, a.ndim - 1) + b = _mask_propagate(b, b.ndim - 2) am = ~getmaskarray(a) bm = ~getmaskarray(b) if out is None: d = np.dot(filled(a, 0), filled(b, 0)) m = ~np.dot(am, bm) - if d.ndim == 0: + if np.ndim(d) == 0: d = np.asarray(d) r = d.view(get_masked_subclass(a, b)) r.__setmask__(m) @@ -8281,12 +8454,6 @@ clip = _convert2ma( np_ret='clipped_array : ndarray', np_ma_ret='clipped_array : MaskedArray', ) -diff = _convert2ma( - 'diff', - params=dict(fill_value=None, hardmask=False), - np_ret='diff : ndarray', - np_ma_ret='diff : MaskedArray', -) empty = _convert2ma( 'empty', params=dict(fill_value=None, hardmask=False), |