Python histograms.histogram方法代码示例

# 需要导入模块: from numpy.lib import histograms [as 别名]
# 或者: from numpy.lib.histograms import histogram [as 别名]
def test_normed(self):
        sup = suppress_warnings()
        with sup:
            rec = sup.record(np.VisibleDeprecationWarning, '.*normed.*')
            # Check that the integral of the density equals 1.
            n = 100
            v = np.random.rand(n)
            a, b = histogram(v, normed=True)
            area = np.sum(a * np.diff(b))
            assert_almost_equal(area, 1)
            assert_equal(len(rec), 1)

        sup = suppress_warnings()
        with sup:
            rec = sup.record(np.VisibleDeprecationWarning, '.*normed.*')
            # Check with non-constant bin widths (buggy but backwards
            # compatible)
            v = np.arange(10)
            bins = [0, 1, 5, 9, 10]
            a, b = histogram(v, bins, normed=True)
            area = np.sum(a * np.diff(b))
            assert_almost_equal(area, 1)
            assert_equal(len(rec), 1) 

# 需要导入模块: from numpy.lib import histograms [as 别名]
# 或者: from numpy.lib.histograms import histogram [as 别名]
def test_outliers(self):
        # Check that outliers are not tallied
        a = np.arange(10) + .5

        # Lower outliers
        h, b = histogram(a, range=[0, 9])
        assert_equal(h.sum(), 9)

        # Upper outliers
        h, b = histogram(a, range=[1, 10])
        assert_equal(h.sum(), 9)

        # Normalization
        h, b = histogram(a, range=[1, 9], density=True)
        assert_almost_equal((h * np.diff(b)).sum(), 1, decimal=15)

        # Weights
        w = np.arange(10) + .5
        h, b = histogram(a, range=[1, 9], weights=w, density=True)
        assert_equal((h * np.diff(b)).sum(), 1)

        h, b = histogram(a, bins=8, range=[1, 9], weights=w)
        assert_equal(h, w[1:-1]) 

# 需要导入模块: from numpy.lib import histograms [as 别名]
# 或者: from numpy.lib.histograms import histogram [as 别名]
def test_bool_conversion(self):
        # gh-12107
        # Reference integer histogram
        a = np.array([1, 1, 0], dtype=np.uint8)
        int_hist, int_edges = np.histogram(a)

        # Should raise an warning on booleans
        # Ensure that the histograms are equivalent, need to suppress
        # the warnings to get the actual outputs
        with suppress_warnings() as sup:
            rec = sup.record(RuntimeWarning, 'Converting input from .*')
            hist, edges = np.histogram([True, True, False])
            # A warning should be issued
            assert_equal(len(rec), 1)
            assert_array_equal(hist, int_hist)
            assert_array_equal(edges, int_edges) 

# 需要导入模块: from numpy.lib import histograms [as 别名]
# 或者: from numpy.lib.histograms import histogram [as 别名]
def test_some_nan_values(self):
        # gh-7503
        one_nan = np.array([0, 1, np.nan])
        all_nan = np.array([np.nan, np.nan])

        # the internal comparisons with NaN give warnings
        sup = suppress_warnings()
        sup.filter(RuntimeWarning)
        with sup:
            # can't infer range with nan
            assert_raises(ValueError, histogram, one_nan, bins='auto')
            assert_raises(ValueError, histogram, all_nan, bins='auto')

            # explicit range solves the problem
            h, b = histogram(one_nan, bins='auto', range=(0, 1))
            assert_equal(h.sum(), 2)  # nan is not counted
            h, b = histogram(all_nan, bins='auto', range=(0, 1))
            assert_equal(h.sum(), 0)  # nan is not counted

            # as does an explicit set of bins
            h, b = histogram(one_nan, bins=[0, 1])
            assert_equal(h.sum(), 2)  # nan is not counted
            h, b = histogram(all_nan, bins=[0, 1])
            assert_equal(h.sum(), 0)  # nan is not counted 

# 需要导入模块: from numpy.lib import histograms [as 别名]
# 或者: from numpy.lib.histograms import histogram [as 别名]
def test_datetime(self):
        begin = np.datetime64('2000-01-01', 'D')
        offsets = np.array([0, 0, 1, 1, 2, 3, 5, 10, 20])
        bins = np.array([0, 2, 7, 20])
        dates = begin + offsets
        date_bins = begin + bins

        td = np.dtype('timedelta64[D]')

        # Results should be the same for integer offsets or datetime values.
        # For now, only explicit bins are supported, since linspace does not
        # work on datetimes or timedeltas
        d_count, d_edge = histogram(dates, bins=date_bins)
        t_count, t_edge = histogram(offsets.astype(td), bins=bins.astype(td))
        i_count, i_edge = histogram(offsets, bins=bins)

        assert_equal(d_count, i_count)
        assert_equal(t_count, i_count)

        assert_equal((d_edge - begin).astype(int), i_edge)
        assert_equal(t_edge.astype(int), i_edge)

        assert_equal(d_edge.dtype, dates.dtype)
        assert_equal(t_edge.dtype, td) 

# 需要导入模块: from numpy.lib import histograms [as 别名]
# 或者: from numpy.lib.histograms import histogram [as 别名]
def do_precision_upper_bound(self, float_small, float_large):
        eps = np.finfo(float_large).eps

        arr = np.array([1.0], float_small)
        range = np.array([0.0, 1.0 - eps], float_large)

        # test is looking for behavior when the bounds change between dtypes
        if range.astype(float_small)[-1] != 1:
            return

        # previously crashed
        count, x_loc = np.histogram(arr, bins=1, range=range)
        assert_equal(count, [1])

        # gh-10322 means that the type comes from arr - this may change
        assert_equal(x_loc.dtype, float_small) 

# 需要导入模块: from numpy.lib import histograms [as 别名]
# 或者: from numpy.lib.histograms import histogram [as 别名]
def test_simple(self):
        """
        Straightforward testing with a mixture of linspace data (for
        consistency). All test values have been precomputed and the values
        shouldn't change
        """
        # Some basic sanity checking, with some fixed data.
        # Checking for the correct number of bins
        basic_test = {50:   {'fd': 4,  'scott': 4,  'rice': 8,  'sturges': 7,
                             'doane': 8, 'sqrt': 8, 'auto': 7, 'stone': 2},
                      500:  {'fd': 8,  'scott': 8,  'rice': 16, 'sturges': 10,
                             'doane': 12, 'sqrt': 23, 'auto': 10, 'stone': 9},
                      5000: {'fd': 17, 'scott': 17, 'rice': 35, 'sturges': 14,
                             'doane': 17, 'sqrt': 71, 'auto': 17, 'stone': 20}}

        for testlen, expectedResults in basic_test.items():
            # Create some sort of non uniform data to test with
            # (2 peak uniform mixture)
            x1 = np.linspace(-10, -1, testlen // 5 * 2)
            x2 = np.linspace(1, 10, testlen // 5 * 3)
            x = np.concatenate((x1, x2))
            for estimator, numbins in expectedResults.items():
                a, b = np.histogram(x, estimator)
                assert_equal(len(a), numbins, err_msg="For the {0} estimator "
                             "with datasize of {1}".format(estimator, testlen)) 

# 需要导入模块: from numpy.lib import histograms [as 别名]
# 或者: from numpy.lib.histograms import histogram [as 别名]
def test_small(self):
        """
        Smaller datasets have the potential to cause issues with the data
        adaptive methods, especially the FD method. All bin numbers have been
        precalculated.
        """
        small_dat = {1: {'fd': 1, 'scott': 1, 'rice': 1, 'sturges': 1,
                         'doane': 1, 'sqrt': 1, 'stone': 1},
                     2: {'fd': 2, 'scott': 1, 'rice': 3, 'sturges': 2,
                         'doane': 1, 'sqrt': 2, 'stone': 1},
                     3: {'fd': 2, 'scott': 2, 'rice': 3, 'sturges': 3,
                         'doane': 3, 'sqrt': 2, 'stone': 1}}

        for testlen, expectedResults in small_dat.items():
            testdat = np.arange(testlen)
            for estimator, expbins in expectedResults.items():
                a, b = np.histogram(testdat, estimator)
                assert_equal(len(a), expbins, err_msg="For the {0} estimator "
                             "with datasize of {1}".format(estimator, testlen)) 

# 需要导入模块: from numpy.lib import histograms [as 别名]
# 或者: from numpy.lib.histograms import histogram [as 别名]
def test_outlier(self):
        """
        Check the FD, Scott and Doane with outliers.

        The FD estimates a smaller binwidth since it's less affected by
        outliers. Since the range is so (artificially) large, this means more
        bins, most of which will be empty, but the data of interest usually is
        unaffected. The Scott estimator is more affected and returns fewer bins,
        despite most of the variance being in one area of the data. The Doane
        estimator lies somewhere between the other two.
        """
        xcenter = np.linspace(-10, 10, 50)
        outlier_dataset = np.hstack((np.linspace(-110, -100, 5), xcenter))

        outlier_resultdict = {'fd': 21, 'scott': 5, 'doane': 11, 'stone': 6}

        for estimator, numbins in outlier_resultdict.items():
            a, b = np.histogram(outlier_dataset, estimator)
            assert_equal(len(a), numbins) 

# 需要导入模块: from numpy.lib import histograms [as 别名]
# 或者: from numpy.lib.histograms import histogram [as 别名]
def test_scott_vs_stone(self):
        """Verify that Scott's rule and Stone's rule converges for normally distributed data"""

        def nbins_ratio(seed, size):
            rng = np.random.RandomState(seed)
            x = rng.normal(loc=0, scale=2, size=size)
            a, b = len(np.histogram(x, 'stone')[0]), len(np.histogram(x, 'scott')[0])
            return a / (a + b)

        ll = [[nbins_ratio(seed, size) for size in np.geomspace(start=10, stop=100, num=4).round().astype(int)]
              for seed in range(256)]

        # the average difference between the two methods decreases as the dataset size increases.
        assert_almost_equal(abs(np.mean(ll, axis=0) - 0.5),
                            [0.1065248,
                             0.0968844,
                             0.0331818,
                             0.0178057],
                            decimal=3) 

# 需要导入模块: from numpy.lib import histograms [as 别名]
# 或者: from numpy.lib.histograms import histogram [as 别名]
def test_one_bin(self):
        # Ticket 632
        hist, edges = histogram([1, 2, 3, 4], [1, 2])
        assert_array_equal(hist, [2, ])
        assert_array_equal(edges, [1, 2])
        assert_raises(ValueError, histogram, [1, 2], bins=0)
        h, e = histogram([1, 2], bins=1)
        assert_equal(h, np.array([2]))
        assert_allclose(e, np.array([1., 2.])) 

# 需要导入模块: from numpy.lib import histograms [as 别名]
# 或者: from numpy.lib.histograms import histogram [as 别名]
def test_density(self):
        # Check that the integral of the density equals 1.
        n = 100
        v = np.random.rand(n)
        a, b = histogram(v, density=True)
        area = np.sum(a * np.diff(b))
        assert_almost_equal(area, 1)

        # Check with non-constant bin widths
        v = np.arange(10)
        bins = [0, 1, 3, 6, 10]
        a, b = histogram(v, bins, density=True)
        assert_array_equal(a, .1)
        assert_equal(np.sum(a * np.diff(b)), 1)

        # Test that passing False works too
        a, b = histogram(v, bins, density=False)
        assert_array_equal(a, [1, 2, 3, 4])

        # Variale bin widths are especially useful to deal with
        # infinities.
        v = np.arange(10)
        bins = [0, 1, 3, 6, np.inf]
        a, b = histogram(v, bins, density=True)
        assert_array_equal(a, [.1, .1, .1, 0.])

        # Taken from a bug report from N. Becker on the numpy-discussion
        # mailing list Aug. 6, 2010.
        counts, dmy = np.histogram(
            [1, 2, 3, 4], [0.5, 1.5, np.inf], density=True)
        assert_equal(counts, [.25, 0]) 

# 需要导入模块: from numpy.lib import histograms [as 别名]
# 或者: from numpy.lib.histograms import histogram [as 别名]
def test_type(self):
        # Check the type of the returned histogram
        a = np.arange(10) + .5
        h, b = histogram(a)
        assert_(np.issubdtype(h.dtype, np.integer))

        h, b = histogram(a, density=True)
        assert_(np.issubdtype(h.dtype, np.floating))

        h, b = histogram(a, weights=np.ones(10, int))
        assert_(np.issubdtype(h.dtype, np.integer))

        h, b = histogram(a, weights=np.ones(10, float))
        assert_(np.issubdtype(h.dtype, np.floating)) 

# 需要导入模块: from numpy.lib import histograms [as 别名]
# 或者: from numpy.lib.histograms import histogram [as 别名]
def test_weights(self):
        v = np.random.rand(100)
        w = np.ones(100) * 5
        a, b = histogram(v)
        na, nb = histogram(v, density=True)
        wa, wb = histogram(v, weights=w)
        nwa, nwb = histogram(v, weights=w, density=True)
        assert_array_almost_equal(a * 5, wa)
        assert_array_almost_equal(na, nwa)

        # Check weights are properly applied.
        v = np.linspace(0, 10, 10)
        w = np.concatenate((np.zeros(5), np.ones(5)))
        wa, wb = histogram(v, bins=np.arange(11), weights=w)
        assert_array_almost_equal(wa, w)

        # Check with integer weights
        wa, wb = histogram([1, 2, 2, 4], bins=4, weights=[4, 3, 2, 1])
        assert_array_equal(wa, [4, 5, 0, 1])
        wa, wb = histogram(
            [1, 2, 2, 4], bins=4, weights=[4, 3, 2, 1], density=True)
        assert_array_almost_equal(wa, np.array([4, 5, 0, 1]) / 10. / 3. * 4)

        # Check weights with non-uniform bin widths
        a, b = histogram(
            np.arange(9), [0, 1, 3, 6, 10],
            weights=[2, 1, 1, 1, 1, 1, 1, 1, 1], density=True)
        assert_almost_equal(a, [.2, .1, .1, .075]) 

# 需要导入模块: from numpy.lib import histograms [as 别名]
# 或者: from numpy.lib.histograms import histogram [as 别名]
def test_exotic_weights(self):

        # Test the use of weights that are not integer or floats, but e.g.
        # complex numbers or object types.

        # Complex weights
        values = np.array([1.3, 2.5, 2.3])
        weights = np.array([1, -1, 2]) + 1j * np.array([2, 1, 2])

        # Check with custom bins
        wa, wb = histogram(values, bins=[0, 2, 3], weights=weights)
        assert_array_almost_equal(wa, np.array([1, 1]) + 1j * np.array([2, 3]))

        # Check with even bins
        wa, wb = histogram(values, bins=2, range=[1, 3], weights=weights)
        assert_array_almost_equal(wa, np.array([1, 1]) + 1j * np.array([2, 3]))

        # Decimal weights
        from decimal import Decimal
        values = np.array([1.3, 2.5, 2.3])
        weights = np.array([Decimal(1), Decimal(2), Decimal(3)])

        # Check with custom bins
        wa, wb = histogram(values, bins=[0, 2, 3], weights=weights)
        assert_array_almost_equal(wa, [Decimal(1), Decimal(5)])

        # Check with even bins
        wa, wb = histogram(values, bins=2, range=[1, 3], weights=weights)
        assert_array_almost_equal(wa, [Decimal(1), Decimal(5)])