"""Test functions for 1D array set operations.
"""
import numpy as np
from numpy.testing import (assert_array_equal, assert_equal,
assert_raises, assert_raises_regex)
from numpy.lib.arraysetops import (
ediff1d, intersect1d, setxor1d, union1d, setdiff1d, unique, in1d, isin
)
import pytest
class TestSetOps:
def test_intersect1d(self):
# unique inputs
a = np.array([5, 7, 1, 2])
b = np.array([2, 4, 3, 1, 5])
ec = np.array([1, 2, 5])
c = intersect1d(a, b, assume_unique=True)
assert_array_equal(c, ec)
# non-unique inputs
a = np.array([5, 5, 7, 1, 2])
b = np.array([2, 1, 4, 3, 3, 1, 5])
ed = np.array([1, 2, 5])
c = intersect1d(a, b)
assert_array_equal(c, ed)
assert_array_equal([], intersect1d([], []))
def test_intersect1d_array_like(self):
# See gh-11772
class Test:
def __array__(self):
return np.arange(3)
a = Test()
res = intersect1d(a, a)
assert_array_equal(res, a)
res = intersect1d([1, 2, 3], [1, 2, 3])
assert_array_equal(res, [1, 2, 3])
def test_intersect1d_indices(self):
# unique inputs
a = np.array([1, 2, 3, 4])
b = np.array([2, 1, 4, 6])
c, i1, i2 = intersect1d(a, b, assume_unique=True, return_indices=True)
ee = np.array([1, 2, 4])
assert_array_equal(c, ee)
assert_array_equal(a[i1], ee)
assert_array_equal(b[i2], ee)
# non-unique inputs
a = np.array([1, 2, 2, 3, 4, 3, 2])
b = np.array([1, 8, 4, 2, 2, 3, 2, 3])
c, i1, i2 = intersect1d(a, b, return_indices=True)
ef = np.array([1, 2, 3, 4])
assert_array_equal(c, ef)
assert_array_equal(a[i1], ef)
assert_array_equal(b[i2], ef)
# non1d, unique inputs
a = np.array([[2, 4, 5, 6], [7, 8, 1, 15]])
b = np.array([[3, 2, 7, 6], [10, 12, 8, 9]])
c, i1, i2 = intersect1d(a, b, assume_unique=True, return_indices=True)
ui1 = np.unravel_index(i1, a.shape)
ui2 = np.unravel_index(i2, b.shape)
ea = np.array([2, 6, 7, 8])
assert_array_equal(ea, a[ui1])
assert_array_equal(ea, b[ui2])
# non1d, not assumed to be uniqueinputs
a = np.array([[2, 4, 5, 6, 6], [4, 7, 8, 7, 2]])
b = np.array([[3, 2, 7, 7], [10, 12, 8, 7]])
c, i1, i2 = intersect1d(a, b, return_indices=True)
ui1 = np.unravel_index(i1, a.shape)
ui2 = np.unravel_index(i2, b.shape)
ea = np.array([2, 7, 8])
assert_array_equal(ea, a[ui1])
assert_array_equal(ea, b[ui2])
def test_setxor1d(self):
a = np.array([5, 7, 1, 2])
b = np.array([2, 4, 3, 1, 5])
ec = np.array([3, 4, 7])
c = setxor1d(a, b)
assert_array_equal(c, ec)
a = np.array([1, 2, 3])
b = np.array([6, 5, 4])
ec = np.array([1, 2, 3, 4, 5, 6])
c = setxor1d(a, b)
assert_array_equal(c, ec)
a = np.array([1, 8, 2, 3])
b = np.array([6, 5, 4, 8])
ec = np.array([1, 2, 3, 4, 5, 6])
c = setxor1d(a, b)
assert_array_equal(c, ec)
assert_array_equal([], setxor1d([], []))
def test_ediff1d(self):
zero_elem = np.array([])
one_elem = np.array([1])
two_elem = np.array([1, 2])
assert_array_equal([], ediff1d(zero_elem))
assert_array_equal([0], ediff1d(zero_elem, to_begin=0))
assert_array_equal([0], ediff1d(zero_elem, to_end=0))
assert_array_equal([-1, 0], ediff1d(zero_elem, to_begin=-1, to_end=0))
assert_array_equal([], ediff1d(one_elem))
assert_array_equal([1], ediff1d(two_elem))
assert_array_equal([7, 1, 9], ediff1d(two_elem, to_begin=7, to_end=9))
assert_array_equal([5, 6, 1, 7, 8],
ediff1d(two_elem, to_begin=[5, 6], to_end=[7, 8]))
assert_array_equal([1, 9], ediff1d(two_elem, to_end=9))
assert_array_equal([1, 7, 8], ediff1d(two_elem, to_end=[7, 8]))
assert_array_equal([7, 1], ediff1d(two_elem, to_begin=7))
assert_array_equal([5, 6, 1], ediff1d(two_elem, to_begin=[5, 6]))
@pytest.mark.parametrize("ary, prepend, append", [
# should fail because trying to cast
# np.nan standard floating point value
# into an integer array:
(np.array([1, 2, 3], dtype=np.int64),
None,
np.nan),
# should fail because attempting
# to downcast to int type:
(np.array([1, 2, 3], dtype=np.int64),
np.array([5, 7, 2], dtype=np.float32),
None),
# should fail because attempting to cast
# two special floating point values
# to integers (on both sides of ary):
(np.array([1., 3., 9.], dtype=np.int8),
np.nan,
np.nan),
])
def test_ediff1d_forbidden_type_casts(self, ary, prepend, append):
# verify resolution of gh-11490
# specifically, raise an appropriate
# Exception when attempting to append or
# prepend with an incompatible type
msg = 'must be compatible'
with assert_raises_regex(TypeError, msg):
ediff1d(ary=ary,
to_end=append,
to_begin=prepend)
@pytest.mark.parametrize(
"ary,prepend,append,expected",
[
(np.array([1, 2, 3], dtype=np.int16),
2**16, # will be cast to int16 under same kind rule.
2**16 + 4,
np.array([0, 1, 1, 4], dtype=np.int16)),
(np.array([1, 2, 3], dtype=np.float32),
np.array([5], dtype=np.float64),
None,
np.array([5, 1, 1], dtype=np.float32)),
(np.array([1, 2, 3], dtype=np.int32),
0,
0,
np.array([0, 1, 1, 0], dtype=np.int32)),
(np.array([1, 2, 3], dtype=np.int64),
3,
-9,
np.array([3, 1, 1, -9], dtype=np.int64)),
]
)
def test_ediff1d_scalar_handling(self,
ary,
prepend,
append,
expected):
# maintain backwards-compatibility
# of scalar prepend / append behavior
# in ediff1d following fix for gh-11490
actual = np.ediff1d(ary=ary,
to_end=append,
to_begin=prepend)
assert_equal(actual, expected)
assert actual.dtype == expected.dtype
def test_isin(self):
# the tests for in1d cover most of isin's behavior
# if in1d is removed, would need to change those tests to test
# isin instead.
def _isin_slow(a, b):
b = np.asarray(b).flatten().tolist()
return a in b
isin_slow = np.vectorize(_isin_slow, otypes=[bool], excluded={1})
def assert_isin_equal(a, b):
x = isin(a, b)
y = isin_slow(a, b)
assert_array_equal(x, y)
# multidimensional arrays in both arguments
a = np.arange(24).reshape([2, 3, 4])
b = np.array([[10, 20, 30], [0, 1, 3], [11, 22, 33]])
assert_isin_equal(a, b)
# array-likes as both arguments
c = [(9, 8), (7, 6)]
d = (9, 7)
assert_isin_equal(c, d)
# zero-d array:
f = np.array(3)
assert_isin_equal(f, b)
assert_isin_equal(a, f)
assert_isin_equal(f, f)
# scalar:
assert_isin_equal(5, b)
assert_isin_equal(a, 6)
assert_isin_equal(5, 6)
# empty array-like:
x = []
assert_isin_equal(x, b)
assert_isin_equal(a, x)
assert_isin_equal(x, x)
def test_in1d(self):
# we use two different sizes for the b array here to test the
# two different paths in in1d().
for mult in (1, 10):
# One check without np.array to make sure lists are handled correct
a = [5, 7, 1, 2]
b = [2, 4, 3, 1, 5] * mult
ec = np.array([True, False, True, True])
c = in1d(a, b, assume_unique=True)
assert_array_equal(c, ec)
a[0] = 8
ec = np.array([False, False, True, True])
c = in1d(a, b, assume_unique=True)
assert_array_equal(c, ec)
a[0], a[3] = 4, 8
ec = np.array([True, False, True, False])
c = in1d(a, b, assume_unique=True)
assert_array_equal(c, ec)
a = np.array([5, 4, 5, 3, 4, 4, 3, 4, 3, 5, 2, 1, 5, 5])
b = [2, 3, 4] * mult
ec = [False, True, False, True, True, True, True, True, True,
False, True, False, False, False]
c = in1d(a, b)
assert_array_equal(c, ec)
b = b + [5, 5, 4] * mult
ec = [True, True, True, True, True, True, True, True, True, True,
True, False, True, True]
c = in1d(a, b)
assert_array_equal(c, ec)
a = np.array([5, 7, 1, 2])
b = np.array([2, 4, 3, 1, 5] * mult)
ec = np.array([True, False, True, True])
c = in1d(a, b)
assert_array_equal(c, ec)
a = np.array([5, 7, 1, 1, 2])
b = np.array([2, 4, 3, 3, 1, 5] * mult)
ec = np.array([True, False, True, True, True])
c = in1d(a, b)
assert_array_equal(c, ec)
a = np.array([5, 5])
b = np.array([2, 2] * mult)
ec = np.array([False, False])
c = in1d(a, b)
assert_array_equal(c, ec)
a = np.array([5])
b = np.array([2])
ec = np.array([False])
c = in1d(a, b)
assert_array_equal(c, ec)
assert_array_equal(in1d([], []), [])
def test_in1d_char_array(self):
a = np.array(['a', 'b', 'c', 'd', 'e', 'c', 'e', 'b'])
b = np.array(['a', 'c'])
ec = np.array([True, False, True, False, False, True, False, False])
c = in1d(a, b)
assert_array_equal(c, ec)
def test_in1d_invert(self):
"Test in1d's invert parameter"
# We use two different sizes for the b array here to test the
# two different paths in in1d().
for mult in (1, 10):
a = np.array([5, 4, 5, 3, 4, 4, 3, 4, 3, 5, 2, 1, 5, 5])
b = [2, 3, 4] * mult
assert_array_equal(np.invert(in1d(a, b)), in1d(a, b, invert=True))
def test_in1d_ravel(self):
# Test that in1d ravels its input arrays. This is not documented
# behavior however. The test is to ensure consistentency.
a = np.arange(6).reshape(2, 3)
b = np.arange(3, 9).reshape(3, 2)
long_b = np.arange(3, 63).reshape(30, 2)
ec = np.array([False, False, False, True, True, True])
assert_array_equal(in1d(a, b, assume_unique=True), ec)
assert_array_equal(in1d(a, b, assume_unique=False), ec)
assert_array_equal(in1d(a, long_b, assume_unique=True), ec)
assert_array_equal(in1d(a, long_b, assume_unique=False), ec)
def test_in1d_first_array_is_object(self):
ar1 = [None]
ar2 = np.array([1]*10)
expected = np.array([False])
result = np.in1d(ar1, ar2)
assert_array_equal(result, expected)
def test_in1d_second_array_is_object(self):
ar1 = 1
ar2 = np.array([None]*10)
expected = np.array([False])
result = np.in1d(ar1, ar2)
assert_array_equal(result, expected)
def test_in1d_both_arrays_are_object(self):
ar1 = [None]
ar2 = np.array([None]*10)
expected = np.array([True])
result = np.in1d(ar1, ar2)
assert_array_equal(result, expected)
Loading ...