numpy 2.4.1__pp311-pypy311_pp73-macosx_14_0_arm64.whl

numpy/random/tests/test_randomstate_regression.py

@@ -0,0 +1,213 @@
+import sys
+
+import pytest
+
+import numpy as np
+from numpy import random
+from numpy.testing import assert_, assert_array_equal, assert_raises
+
+
+class TestRegression:
+
+    def test_VonMises_range(self):
+        # Make sure generated random variables are in [-pi, pi].
+        # Regression test for ticket #986.
+        for mu in np.linspace(-7., 7., 5):
+            r = random.vonmises(mu, 1, 50)
+            assert_(np.all(r > -np.pi) and np.all(r <= np.pi))
+
+    def test_hypergeometric_range(self):
+        # Test for ticket #921
+        assert_(np.all(random.hypergeometric(3, 18, 11, size=10) < 4))
+        assert_(np.all(random.hypergeometric(18, 3, 11, size=10) > 0))
+
+        # Test for ticket #5623
+        args = [
+            (2**20 - 2, 2**20 - 2, 2**20 - 2),  # Check for 32-bit systems
+        ]
+        is_64bits = sys.maxsize > 2**32
+        if is_64bits and sys.platform != 'win32':
+            # Check for 64-bit systems
+            args.append((2**40 - 2, 2**40 - 2, 2**40 - 2))
+        for arg in args:
+            assert_(random.hypergeometric(*arg) > 0)
+
+    def test_logseries_convergence(self):
+        # Test for ticket #923
+        N = 1000
+        random.seed(0)
+        rvsn = random.logseries(0.8, size=N)
+        # these two frequency counts should be close to theoretical
+        # numbers with this large sample
+        # theoretical large N result is 0.49706795
+        freq = np.sum(rvsn == 1) / N
+        msg = f'Frequency was {freq:f}, should be > 0.45'
+        assert_(freq > 0.45, msg)
+        # theoretical large N result is 0.19882718
+        freq = np.sum(rvsn == 2) / N
+        msg = f'Frequency was {freq:f}, should be < 0.23'
+        assert_(freq < 0.23, msg)
+
+    def test_shuffle_mixed_dimension(self):
+        # Test for trac ticket #2074
+        for t in [[1, 2, 3, None],
+                  [(1, 1), (2, 2), (3, 3), None],
+                  [1, (2, 2), (3, 3), None],
+                  [(1, 1), 2, 3, None]]:
+            rng = random.RandomState(12345)
+            shuffled = list(t)
+            rng.shuffle(shuffled)
+            expected = np.array([t[0], t[3], t[1], t[2]], dtype=object)
+            assert_array_equal(np.array(shuffled, dtype=object), expected)
+
+    def test_call_within_randomstate(self):
+        # Check that custom RandomState does not call into global state
+        m = random.RandomState()
+        res = np.array([0, 8, 7, 2, 1, 9, 4, 7, 0, 3])
+        for i in range(3):
+            random.seed(i)
+            m.seed(4321)
+            # If m.state is not honored, the result will change
+            assert_array_equal(m.choice(10, size=10, p=np.ones(10) / 10.), res)
+
+    def test_multivariate_normal_size_types(self):
+        # Test for multivariate_normal issue with 'size' argument.
+        # Check that the multivariate_normal size argument can be a
+        # numpy integer.
+        random.multivariate_normal([0], [[0]], size=1)
+        random.multivariate_normal([0], [[0]], size=np.int_(1))
+        random.multivariate_normal([0], [[0]], size=np.int64(1))
+
+    def test_beta_small_parameters(self):
+        # Test that beta with small a and b parameters does not produce
+        # NaNs due to roundoff errors causing 0 / 0, gh-5851
+        random.seed(1234567890)
+        x = random.beta(0.0001, 0.0001, size=100)
+        assert_(not np.any(np.isnan(x)), 'Nans in random.beta')
+
+    def test_choice_sum_of_probs_tolerance(self):
+        # The sum of probs should be 1.0 with some tolerance.
+        # For low precision dtypes the tolerance was too tight.
+        # See numpy github issue 6123.
+        random.seed(1234)
+        a = [1, 2, 3]
+        counts = [4, 4, 2]
+        for dt in np.float16, np.float32, np.float64:
+            probs = np.array(counts, dtype=dt) / sum(counts)
+            c = random.choice(a, p=probs)
+            assert_(c in a)
+            assert_raises(ValueError, random.choice, a, p=probs * 0.9)
+
+    def test_shuffle_of_array_of_different_length_strings(self):
+        # Test that permuting an array of different length strings
+        # will not cause a segfault on garbage collection
+        # Tests gh-7710
+        random.seed(1234)
+
+        a = np.array(['a', 'a' * 1000])
+
+        for _ in range(100):
+            random.shuffle(a)
+
+        # Force Garbage Collection - should not segfault.
+        import gc
+        gc.collect()
+
+    def test_shuffle_of_array_of_objects(self):
+        # Test that permuting an array of objects will not cause
+        # a segfault on garbage collection.
+        # See gh-7719
+        random.seed(1234)
+        a = np.array([np.arange(1), np.arange(4)], dtype=object)
+
+        for _ in range(1000):
+            random.shuffle(a)
+
+        # Force Garbage Collection - should not segfault.
+        import gc
+        gc.collect()
+
+    def test_permutation_subclass(self):
+        class N(np.ndarray):
+            pass
+
+        rng = random.RandomState(1)
+        orig = np.arange(3).view(N)
+        perm = rng.permutation(orig)
+        assert_array_equal(perm, np.array([0, 2, 1]))
+        assert_array_equal(orig, np.arange(3).view(N))
+
+        class M:
+            a = np.arange(5)
+
+            def __array__(self, dtype=None, copy=None):
+                return self.a
+
+        rng = random.RandomState(1)
+        m = M()
+        perm = rng.permutation(m)
+        assert_array_equal(perm, np.array([2, 1, 4, 0, 3]))
+        assert_array_equal(m.__array__(), np.arange(5))
+
+    def test_warns_byteorder(self):
+        # GH 13159
+        other_byteord_dt = '<i4' if sys.byteorder == 'big' else '>i4'
+        with pytest.deprecated_call(match='non-native byteorder is not'):
+            random.randint(0, 200, size=10, dtype=other_byteord_dt)
+
+    def test_named_argument_initialization(self):
+        # GH 13669
+        rs1 = np.random.RandomState(123456789)
+        rs2 = np.random.RandomState(seed=123456789)
+        assert rs1.randint(0, 100) == rs2.randint(0, 100)
+
+    def test_choice_retun_dtype(self):
+        # GH 9867, now long since the NumPy default changed.
+        c = np.random.choice(10, p=[.1] * 10, size=2)
+        assert c.dtype == np.dtype(np.long)
+        c = np.random.choice(10, p=[.1] * 10, replace=False, size=2)
+        assert c.dtype == np.dtype(np.long)
+        c = np.random.choice(10, size=2)
+        assert c.dtype == np.dtype(np.long)
+        c = np.random.choice(10, replace=False, size=2)
+        assert c.dtype == np.dtype(np.long)
+
+    @pytest.mark.skipif(np.iinfo('l').max < 2**32,
+                        reason='Cannot test with 32-bit C long')
+    def test_randint_117(self):
+        # GH 14189
+        rng = random.RandomState(0)
+        expected = np.array([2357136044, 2546248239, 3071714933, 3626093760,
+                             2588848963, 3684848379, 2340255427, 3638918503,
+                             1819583497, 2678185683], dtype='int64')
+        actual = rng.randint(2**32, size=10)
+        assert_array_equal(actual, expected)
+
+    def test_p_zero_stream(self):
+        # Regression test for gh-14522.  Ensure that future versions
+        # generate the same variates as version 1.16.
+        rng = random.RandomState(12345)
+        assert_array_equal(rng.binomial(1, [0, 0.25, 0.5, 0.75, 1]),
+                           [0, 0, 0, 1, 1])
+
+    def test_n_zero_stream(self):
+        # Regression test for gh-14522.  Ensure that future versions
+        # generate the same variates as version 1.16.
+        rng = random.RandomState(8675309)
+        expected = np.array([[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
+                             [3, 4, 2, 3, 3, 1, 5, 3, 1, 3]])
+        assert_array_equal(rng.binomial([[0], [10]], 0.25, size=(2, 10)),
+                           expected)
+
+
+def test_multinomial_empty():
+    # gh-20483
+    # Ensure that empty p-vals are correctly handled
+    assert random.multinomial(10, []).shape == (0,)
+    assert random.multinomial(3, [], size=(7, 5, 3)).shape == (7, 5, 3, 0)
+
+
+def test_multinomial_1d_pval():
+    # gh-20483
+    with pytest.raises(TypeError, match="pvals must be a 1-d"):
+        random.multinomial(10, 0.3)

numpy/random/tests/test_regression.py

@@ -0,0 +1,175 @@
+import inspect
+import sys
+
+import pytest
+
+import numpy as np
+from numpy import random
+from numpy.testing import IS_PYPY, assert_, assert_array_equal, assert_raises
+
+
+class TestRegression:
+
+    def test_VonMises_range(self):
+        # Make sure generated random variables are in [-pi, pi].
+        # Regression test for ticket #986.
+        for mu in np.linspace(-7., 7., 5):
+            r = random.mtrand.vonmises(mu, 1, 50)
+            assert_(np.all(r > -np.pi) and np.all(r <= np.pi))
+
+    def test_hypergeometric_range(self):
+        # Test for ticket #921
+        assert_(np.all(np.random.hypergeometric(3, 18, 11, size=10) < 4))
+        assert_(np.all(np.random.hypergeometric(18, 3, 11, size=10) > 0))
+
+        # Test for ticket #5623
+        args = [
+            (2**20 - 2, 2**20 - 2, 2**20 - 2),  # Check for 32-bit systems
+        ]
+        is_64bits = sys.maxsize > 2**32
+        if is_64bits and sys.platform != 'win32':
+            # Check for 64-bit systems
+            args.append((2**40 - 2, 2**40 - 2, 2**40 - 2))
+        for arg in args:
+            assert_(np.random.hypergeometric(*arg) > 0)
+
+    def test_logseries_convergence(self):
+        # Test for ticket #923
+        N = 1000
+        np.random.seed(0)
+        rvsn = np.random.logseries(0.8, size=N)
+        # these two frequency counts should be close to theoretical
+        # numbers with this large sample
+        # theoretical large N result is 0.49706795
+        freq = np.sum(rvsn == 1) / N
+        msg = f'Frequency was {freq:f}, should be > 0.45'
+        assert_(freq > 0.45, msg)
+        # theoretical large N result is 0.19882718
+        freq = np.sum(rvsn == 2) / N
+        msg = f'Frequency was {freq:f}, should be < 0.23'
+        assert_(freq < 0.23, msg)
+
+    def test_shuffle_mixed_dimension(self):
+        # Test for trac ticket #2074
+        for t in [[1, 2, 3, None],
+                  [(1, 1), (2, 2), (3, 3), None],
+                  [1, (2, 2), (3, 3), None],
+                  [(1, 1), 2, 3, None]]:
+            rng = np.random.RandomState(12345)
+            shuffled = list(t)
+            rng.shuffle(shuffled)
+            expected = np.array([t[0], t[3], t[1], t[2]], dtype=object)
+            assert_array_equal(np.array(shuffled, dtype=object), expected)
+
+    def test_call_within_randomstate(self):
+        # Check that custom RandomState does not call into global state
+        m = np.random.RandomState()
+        res = np.array([0, 8, 7, 2, 1, 9, 4, 7, 0, 3])
+        for i in range(3):
+            np.random.seed(i)
+            m.seed(4321)
+            # If m.state is not honored, the result will change
+            assert_array_equal(m.choice(10, size=10, p=np.ones(10) / 10.), res)
+
+    def test_multivariate_normal_size_types(self):
+        # Test for multivariate_normal issue with 'size' argument.
+        # Check that the multivariate_normal size argument can be a
+        # numpy integer.
+        np.random.multivariate_normal([0], [[0]], size=1)
+        np.random.multivariate_normal([0], [[0]], size=np.int_(1))
+        np.random.multivariate_normal([0], [[0]], size=np.int64(1))
+
+    def test_beta_small_parameters(self):
+        # Test that beta with small a and b parameters does not produce
+        # NaNs due to roundoff errors causing 0 / 0, gh-5851
+        np.random.seed(1234567890)
+        x = np.random.beta(0.0001, 0.0001, size=100)
+        assert_(not np.any(np.isnan(x)), 'Nans in np.random.beta')
+
+    def test_choice_sum_of_probs_tolerance(self):
+        # The sum of probs should be 1.0 with some tolerance.
+        # For low precision dtypes the tolerance was too tight.
+        # See numpy github issue 6123.
+        np.random.seed(1234)
+        a = [1, 2, 3]
+        counts = [4, 4, 2]
+        for dt in np.float16, np.float32, np.float64:
+            probs = np.array(counts, dtype=dt) / sum(counts)
+            c = np.random.choice(a, p=probs)
+            assert_(c in a)
+            assert_raises(ValueError, np.random.choice, a, p=probs * 0.9)
+
+    def test_shuffle_of_array_of_different_length_strings(self):
+        # Test that permuting an array of different length strings
+        # will not cause a segfault on garbage collection
+        # Tests gh-7710
+        np.random.seed(1234)
+
+        a = np.array(['a', 'a' * 1000])
+
+        for _ in range(100):
+            np.random.shuffle(a)
+
+        # Force Garbage Collection - should not segfault.
+        import gc
+        gc.collect()
+
+    def test_shuffle_of_array_of_objects(self):
+        # Test that permuting an array of objects will not cause
+        # a segfault on garbage collection.
+        # See gh-7719
+        np.random.seed(1234)
+        a = np.array([np.arange(1), np.arange(4)], dtype=object)
+
+        for _ in range(1000):
+            np.random.shuffle(a)
+
+        # Force Garbage Collection - should not segfault.
+        import gc
+        gc.collect()
+
+    def test_permutation_subclass(self):
+        class N(np.ndarray):
+            pass
+
+        rng = np.random.RandomState(1)
+        orig = np.arange(3).view(N)
+        perm = rng.permutation(orig)
+        assert_array_equal(perm, np.array([0, 2, 1]))
+        assert_array_equal(orig, np.arange(3).view(N))
+
+        class M:
+            a = np.arange(5)
+
+            def __array__(self, dtype=None, copy=None):
+                return self.a
+
+        rng = np.random.RandomState(1)
+        m = M()
+        perm = rng.permutation(m)
+        assert_array_equal(perm, np.array([2, 1, 4, 0, 3]))
+        assert_array_equal(m.__array__(), np.arange(5))
+
+    @pytest.mark.skipif(sys.flags.optimize == 2, reason="Python running -OO")
+    @pytest.mark.skipif(IS_PYPY, reason="PyPy does not modify tp_doc")
+    @pytest.mark.parametrize(
+        "cls",
+        [
+            random.Generator,
+            random.MT19937,
+            random.PCG64,
+            random.PCG64DXSM,
+            random.Philox,
+            random.RandomState,
+            random.SFC64,
+            random.BitGenerator,
+            random.SeedSequence,
+            random.bit_generator.SeedlessSeedSequence,
+        ],
+    )
+    def test_inspect_signature(self, cls: type) -> None:
+        assert hasattr(cls, "__text_signature__")
+        try:
+            inspect.signature(cls)
+        except ValueError:
+            pytest.fail(f"invalid signature: {cls.__module__}.{cls.__qualname__}")

numpy/random/tests/test_seed_sequence.py

@@ -0,0 +1,79 @@
+import numpy as np
+from numpy.random import SeedSequence
+from numpy.testing import assert_array_compare, assert_array_equal
+
+
+def test_reference_data():
+    """ Check that SeedSequence generates data the same as the C++ reference.
+
+    https://gist.github.com/imneme/540829265469e673d045
+    """
+    inputs = [
+        [3735928559, 195939070, 229505742, 305419896],
+        [3668361503, 4165561550, 1661411377, 3634257570],
+        [164546577, 4166754639, 1765190214, 1303880213],
+        [446610472, 3941463886, 522937693, 1882353782],
+        [1864922766, 1719732118, 3882010307, 1776744564],
+        [4141682960, 3310988675, 553637289, 902896340],
+        [1134851934, 2352871630, 3699409824, 2648159817],
+        [1240956131, 3107113773, 1283198141, 1924506131],
+        [2669565031, 579818610, 3042504477, 2774880435],
+        [2766103236, 2883057919, 4029656435, 862374500],
+    ]
+    outputs = [
+        [3914649087, 576849849, 3593928901, 2229911004],
+        [2240804226, 3691353228, 1365957195, 2654016646],
+        [3562296087, 3191708229, 1147942216, 3726991905],
+        [1403443605, 3591372999, 1291086759, 441919183],
+        [1086200464, 2191331643, 560336446, 3658716651],
+        [3249937430, 2346751812, 847844327, 2996632307],
+        [2584285912, 4034195531, 3523502488, 169742686],
+        [959045797, 3875435559, 1886309314, 359682705],
+        [3978441347, 432478529, 3223635119, 138903045],
+        [296367413, 4262059219, 13109864, 3283683422],
+    ]
+    outputs64 = [
+        [2477551240072187391, 9577394838764454085],
+        [15854241394484835714, 11398914698975566411],
+        [13708282465491374871, 16007308345579681096],
+        [15424829579845884309, 1898028439751125927],
+        [9411697742461147792, 15714068361935982142],
+        [10079222287618677782, 12870437757549876199],
+        [17326737873898640088, 729039288628699544],
+        [16644868984619524261, 1544825456798124994],
+        [1857481142255628931, 596584038813451439],
+        [18305404959516669237, 14103312907920476776],
+    ]
+    for seed, expected, expected64 in zip(inputs, outputs, outputs64):
+        expected = np.array(expected, dtype=np.uint32)
+        ss = SeedSequence(seed)
+        state = ss.generate_state(len(expected))
+        assert_array_equal(state, expected)
+        state64 = ss.generate_state(len(expected64), dtype=np.uint64)
+        assert_array_equal(state64, expected64)
+
+
+def test_zero_padding():
+    """ Ensure that the implicit zero-padding does not cause problems.
+    """
+    # Ensure that large integers are inserted in little-endian fashion to avoid
+    # trailing 0s.
+    ss0 = SeedSequence(42)
+    ss1 = SeedSequence(42 << 32)
+    assert_array_compare(
+        np.not_equal,
+        ss0.generate_state(4),
+        ss1.generate_state(4))
+
+    # Ensure backwards compatibility with the original 0.17 release for small
+    # integers and no spawn key.
+    expected42 = np.array([3444837047, 2669555309, 2046530742, 3581440988],
+                          dtype=np.uint32)
+    assert_array_equal(SeedSequence(42).generate_state(4), expected42)
+
+    # Regression test for gh-16539 to ensure that the implicit 0s don't
+    # conflict with spawn keys.
+    assert_array_compare(
+        np.not_equal,
+        SeedSequence(42, spawn_key=(0,)).generate_state(4),
+        expected42)