diff options
Diffstat (limited to 'numpy/lib')
| -rw-r--r-- | numpy/lib/function_base.py | 112 | ||||
| -rw-r--r-- | numpy/lib/histograms.py | 26 | ||||
| -rw-r--r-- | numpy/lib/tests/test_function_base.py | 12 | ||||
| -rw-r--r-- | numpy/lib/tests/test_histograms.py | 16 | ||||
| -rw-r--r-- | numpy/lib/tests/test_twodim_base.py | 6 | ||||
| -rw-r--r-- | numpy/lib/twodim_base.py | 14 |
6 files changed, 165 insertions, 21 deletions
diff --git a/numpy/lib/function_base.py b/numpy/lib/function_base.py index 9a680dd55..1a43da8b0 100644 --- a/numpy/lib/function_base.py +++ b/numpy/lib/function_base.py @@ -31,7 +31,7 @@ from numpy.core.function_base import add_newdoc from numpy.lib.twodim_base import diag from .utils import deprecate from numpy.core.multiarray import ( - _insert, add_docstring, digitize, bincount, normalize_axis_index, + _insert, add_docstring, bincount, normalize_axis_index, _monotonicity, interp as compiled_interp, interp_complex as compiled_interp_complex ) from numpy.core.umath import _add_newdoc_ufunc as add_newdoc_ufunc @@ -4493,3 +4493,113 @@ def append(arr, values, axis=None): values = ravel(values) axis = arr.ndim-1 return concatenate((arr, values), axis=axis) + + +def digitize(x, bins, right=False): + """ + Return the indices of the bins to which each value in input array belongs. + + ========= ============= ============================ + `right` order of bins returned index `i` satisfies + ========= ============= ============================ + ``False`` increasing ``bins[i-1] <= x < bins[i]`` + ``True`` increasing ``bins[i-1] < x <= bins[i]`` + ``False`` decreasing ``bins[i-1] > x >= bins[i]`` + ``True`` decreasing ``bins[i-1] >= x > bins[i]`` + ========= ============= ============================ + + If values in `x` are beyond the bounds of `bins`, 0 or ``len(bins)`` is + returned as appropriate. + + Parameters + ---------- + x : array_like + Input array to be binned. Prior to NumPy 1.10.0, this array had to + be 1-dimensional, but can now have any shape. + bins : array_like + Array of bins. It has to be 1-dimensional and monotonic. + right : bool, optional + Indicating whether the intervals include the right or the left bin + edge. Default behavior is (right==False) indicating that the interval + does not include the right edge. The left bin end is open in this + case, i.e., bins[i-1] <= x < bins[i] is the default behavior for + monotonically increasing bins. + + Returns + ------- + indices : ndarray of ints + Output array of indices, of same shape as `x`. + + Raises + ------ + ValueError + If `bins` is not monotonic. + TypeError + If the type of the input is complex. + + See Also + -------- + bincount, histogram, unique, searchsorted + + Notes + ----- + If values in `x` are such that they fall outside the bin range, + attempting to index `bins` with the indices that `digitize` returns + will result in an IndexError. + + .. versionadded:: 1.10.0 + + `np.digitize` is implemented in terms of `np.searchsorted`. This means + that a binary search is used to bin the values, which scales much better + for larger number of bins than the previous linear search. It also removes + the requirement for the input array to be 1-dimensional. + + For monotonically _increasing_ `bins`, the following are equivalent:: + + np.digitize(x, bins, right=True) + np.searchsorted(bins, x, side='left') + + Note that as the order of the arguments are reversed, the side must be too. + The `searchsorted` call is marginally faster, as it does not do any + monotonicity checks. Perhaps more importantly, it supports all dtypes. + + Examples + -------- + >>> x = np.array([0.2, 6.4, 3.0, 1.6]) + >>> bins = np.array([0.0, 1.0, 2.5, 4.0, 10.0]) + >>> inds = np.digitize(x, bins) + >>> inds + array([1, 4, 3, 2]) + >>> for n in range(x.size): + ... print(bins[inds[n]-1], "<=", x[n], "<", bins[inds[n]]) + ... + 0.0 <= 0.2 < 1.0 + 4.0 <= 6.4 < 10.0 + 2.5 <= 3.0 < 4.0 + 1.0 <= 1.6 < 2.5 + + >>> x = np.array([1.2, 10.0, 12.4, 15.5, 20.]) + >>> bins = np.array([0, 5, 10, 15, 20]) + >>> np.digitize(x,bins,right=True) + array([1, 2, 3, 4, 4]) + >>> np.digitize(x,bins,right=False) + array([1, 3, 3, 4, 5]) + """ + x = _nx.asarray(x) + bins = _nx.asarray(bins) + + # here for compatibility, searchsorted below is happy to take this + if np.issubdtype(x.dtype, _nx.complexfloating): + raise TypeError("x may not be complex") + + mono = _monotonicity(bins) + if mono == 0: + raise ValueError("bins must be monotonically increasing or decreasing") + + # this is backwards because the arguments below are swapped + side = 'left' if right else 'right' + if mono == -1: + # reverse the bins, and invert the results + return len(bins) - _nx.searchsorted(bins[::-1], x, side=side) + else: + return _nx.searchsorted(bins, x, side=side) diff --git a/numpy/lib/histograms.py b/numpy/lib/histograms.py index ad7215504..422b356f7 100644 --- a/numpy/lib/histograms.py +++ b/numpy/lib/histograms.py @@ -812,7 +812,8 @@ def histogram(a, bins=10, range=None, normed=None, weights=None, return n, bin_edges -def histogramdd(sample, bins=10, range=None, normed=False, weights=None): +def histogramdd(sample, bins=10, range=None, normed=None, weights=None, + density=None): """ Compute the multidimensional histogram of some data. @@ -845,9 +846,14 @@ def histogramdd(sample, bins=10, range=None, normed=False, weights=None): An entry of None in the sequence results in the minimum and maximum values being used for the corresponding dimension. The default, None, is equivalent to passing a tuple of D None values. + density : bool, optional + If False, the default, returns the number of samples in each bin. + If True, returns the probability *density* function at the bin, + ``bin_count / sample_count / bin_volume``. normed : bool, optional - If False, returns the number of samples in each bin. If True, - returns the bin density ``bin_count / sample_count / bin_volume``. + An alias for the density argument that behaves identically. To avoid + confusion with the broken normed argument to `histogram`, `density` + should be preferred. weights : (N,) array_like, optional An array of values `w_i` weighing each sample `(x_i, y_i, z_i, ...)`. Weights are normalized to 1 if normed is True. If normed is False, @@ -961,8 +967,18 @@ def histogramdd(sample, bins=10, range=None, normed=False, weights=None): core = D*(slice(1, -1),) hist = hist[core] - # Normalize if normed is True - if normed: + # handle the aliasing normed argument + if normed is None: + if density is None: + density = False + elif density is None: + # an explicit normed argument was passed, alias it to the new name + density = normed + else: + raise TypeError("Cannot specify both 'normed' and 'density'") + + if density: + # calculate the probability density function s = hist.sum() for i in _range(D): shape = np.ones(D, int) diff --git a/numpy/lib/tests/test_function_base.py b/numpy/lib/tests/test_function_base.py index d2a9181db..ba5b90e8c 100644 --- a/numpy/lib/tests/test_function_base.py +++ b/numpy/lib/tests/test_function_base.py @@ -1510,6 +1510,18 @@ class TestDigitize(object): assert_(not isinstance(digitize(b, a, False), A)) assert_(not isinstance(digitize(b, a, True), A)) + def test_large_integers_increasing(self): + # gh-11022 + x = 2**54 # loses precision in a float + assert_equal(np.digitize(x, [x - 1, x + 1]), 1) + + @pytest.mark.xfail( + reason="gh-11022: np.core.multiarray._monoticity loses precision") + def test_large_integers_decreasing(self): + # gh-11022 + x = 2**54 # loses precision in a float + assert_equal(np.digitize(x, [x + 1, x - 1]), 1) + class TestUnwrap(object): diff --git a/numpy/lib/tests/test_histograms.py b/numpy/lib/tests/test_histograms.py index d22aa5a27..f136b5c81 100644 --- a/numpy/lib/tests/test_histograms.py +++ b/numpy/lib/tests/test_histograms.py @@ -547,13 +547,13 @@ class TestHistogramdd(object): # Check normalization ed = [[-2, 0, 2], [0, 1, 2, 3], [0, 1, 2, 3]] - H, edges = histogramdd(x, bins=ed, normed=True) + H, edges = histogramdd(x, bins=ed, density=True) assert_(np.all(H == answer / 12.)) # Check that H has the correct shape. H, edges = histogramdd(x, (2, 3, 4), range=[[-1, 1], [0, 3], [0, 4]], - normed=True) + density=True) answer = np.array([[[0, 1, 0, 0], [0, 0, 1, 0], [1, 0, 0, 0]], [[0, 1, 0, 0], [0, 0, 1, 0], [0, 0, 1, 0]]]) assert_array_almost_equal(H, answer / 6., 4) @@ -599,10 +599,10 @@ class TestHistogramdd(object): def test_weights(self): v = np.random.rand(100, 2) hist, edges = histogramdd(v) - n_hist, edges = histogramdd(v, normed=True) + n_hist, edges = histogramdd(v, density=True) w_hist, edges = histogramdd(v, weights=np.ones(100)) assert_array_equal(w_hist, hist) - w_hist, edges = histogramdd(v, weights=np.ones(100) * 2, normed=True) + w_hist, edges = histogramdd(v, weights=np.ones(100) * 2, density=True) assert_array_equal(w_hist, n_hist) w_hist, edges = histogramdd(v, weights=np.ones(100, int) * 2) assert_array_equal(w_hist, 2 * hist) @@ -708,7 +708,7 @@ class TestHistogramdd(object): assert_equal(hist[0, 0], 1) - def test_normed_non_uniform_2d(self): + def test_density_non_uniform_2d(self): # Defines the following grid: # # 0 2 8 @@ -732,14 +732,14 @@ class TestHistogramdd(object): assert_equal(hist, relative_areas) # resulting histogram should be uniform, since counts and areas are propotional - hist, edges = histogramdd((y, x), bins=(y_edges, x_edges), normed=True) + hist, edges = histogramdd((y, x), bins=(y_edges, x_edges), density=True) assert_equal(hist, 1 / (8*8)) - def test_normed_non_uniform_1d(self): + def test_density_non_uniform_1d(self): # compare to histogram to show the results are the same v = np.arange(10) bins = np.array([0, 1, 3, 6, 10]) hist, edges = histogram(v, bins, density=True) - hist_dd, edges_dd = histogramdd((v,), (bins,), normed=True) + hist_dd, edges_dd = histogramdd((v,), (bins,), density=True) assert_equal(hist, hist_dd) assert_equal(edges, edges_dd[0]) diff --git a/numpy/lib/tests/test_twodim_base.py b/numpy/lib/tests/test_twodim_base.py index d3a072af3..bf93b4adb 100644 --- a/numpy/lib/tests/test_twodim_base.py +++ b/numpy/lib/tests/test_twodim_base.py @@ -208,7 +208,7 @@ class TestHistogram2d(object): x = array([1, 1, 2, 3, 4, 4, 4, 5]) y = array([1, 3, 2, 0, 1, 2, 3, 4]) H, xed, yed = histogram2d( - x, y, (6, 5), range=[[0, 6], [0, 5]], normed=True) + x, y, (6, 5), range=[[0, 6], [0, 5]], density=True) answer = array( [[0., 0, 0, 0, 0], [0, 1, 0, 1, 0], @@ -220,11 +220,11 @@ class TestHistogram2d(object): assert_array_equal(xed, np.linspace(0, 6, 7)) assert_array_equal(yed, np.linspace(0, 5, 6)) - def test_norm(self): + def test_density(self): x = array([1, 2, 3, 1, 2, 3, 1, 2, 3]) y = array([1, 1, 1, 2, 2, 2, 3, 3, 3]) H, xed, yed = histogram2d( - x, y, [[1, 2, 3, 5], [1, 2, 3, 5]], normed=True) + x, y, [[1, 2, 3, 5], [1, 2, 3, 5]], density=True) answer = array([[1, 1, .5], [1, 1, .5], [.5, .5, .25]])/9. diff --git a/numpy/lib/twodim_base.py b/numpy/lib/twodim_base.py index cca316e9a..98efba191 100644 --- a/numpy/lib/twodim_base.py +++ b/numpy/lib/twodim_base.py @@ -530,7 +530,8 @@ def vander(x, N=None, increasing=False): return v -def histogram2d(x, y, bins=10, range=None, normed=False, weights=None): +def histogram2d(x, y, bins=10, range=None, normed=None, weights=None, + density=None): """ Compute the bi-dimensional histogram of two data samples. @@ -560,9 +561,14 @@ def histogram2d(x, y, bins=10, range=None, normed=False, weights=None): (if not specified explicitly in the `bins` parameters): ``[[xmin, xmax], [ymin, ymax]]``. All values outside of this range will be considered outliers and not tallied in the histogram. + density : bool, optional + If False, the default, returns the number of samples in each bin. + If True, returns the probability *density* function at the bin, + ``bin_count / sample_count / bin_area``. normed : bool, optional - If False, returns the number of samples in each bin. If True, - returns the bin density ``bin_count / sample_count / bin_area``. + An alias for the density argument that behaves identically. To avoid + confusion with the broken normed argument to `histogram`, `density` + should be preferred. weights : array_like, shape(N,), optional An array of values ``w_i`` weighing each sample ``(x_i, y_i)``. Weights are normalized to 1 if `normed` is True. If `normed` is @@ -652,7 +658,7 @@ def histogram2d(x, y, bins=10, range=None, normed=False, weights=None): if N != 1 and N != 2: xedges = yedges = asarray(bins) bins = [xedges, yedges] - hist, edges = histogramdd([x, y], bins, range, normed, weights) + hist, edges = histogramdd([x, y], bins, range, normed, weights, density) return hist, edges[0], edges[1] |