def test_map_ignores_missing_value(self, missing):
data = np.array([missing, 'B', 'C'], dtype=object)
la = LabelArray(data, missing_value=missing)
def increment_char(c):
return chr(ord(c) + 1)
result = la.map(increment_char)
expected = LabelArray([missing, 'C', 'D'], missing_value=missing)
assert_equal(result.as_string_array(), expected.as_string_array())
def test_map_ignores_missing_value(self, missing):
data = np.array([missing, 'B', 'C'], dtype=object)
la = LabelArray(data, missing_value=missing)
def increment_char(c):
return chr(ord(c) + 1)
result = la.map(increment_char)
expected = LabelArray([missing, 'C', 'D'], missing_value=missing)
assert_equal(result.as_string_array(), expected.as_string_array())
def test_fortran_contiguous_input(self):
strs = np.array([['a', 'b', 'c', 'd'],
['a', 'b', 'c', 'd'],
['a', 'b', 'c', 'd']], dtype=object)
strs_F = strs.T
self.assertTrue(strs_F.flags.f_contiguous)
arr = LabelArray(
strs_F,
missing_value=None,
categories=['a', 'b', 'c', 'd', None],
)
assert_equal(arr.as_string_array(), strs_F)
arr = LabelArray(
strs_F,
missing_value=None,
)
assert_equal(arr.as_string_array(), strs_F)
def test_fortran_contiguous_input(self):
strs = np.array(
[["a", "b", "c", "d"], ["a", "b", "c", "d"], ["a", "b", "c", "d"]],
dtype=object,
)
strs_F = strs.T
assert strs_F.flags.f_contiguous
arr = LabelArray(
strs_F,
missing_value=None,
categories=["a", "b", "c", "d", None],
)
assert_equal(arr.as_string_array(), strs_F)
arr = LabelArray(
strs_F,
missing_value=None,
)
assert_equal(arr.as_string_array(), strs_F)
def test_map_never_increases_code_storage_size(self):
# This tests a pathological case where a user maps an impure function
# that returns a different label on every invocation, which in a naive
# implementation could cause us to need to **increase** the size of our
# codes after a map.
#
# This doesn't happen, however, because we guarantee that the user's
# mapping function will be called on each unique category exactly once,
# which means we can never increase the number of categories in the
# LabelArray after mapping.
# Using all but one of the categories so that we still fit in a uint8
# with an extra category for None as a missing value.
categories = self.create_categories(8, plus_one=False)[:-1]
larger_categories = self.create_categories(16, plus_one=False)
# Double the length of the categories so that we have to increase the
# required size after our map.
categories_twice = categories + categories
arr = LabelArray(categories_twice, missing_value=None)
assert_equal(arr.itemsize, 1)
gen_unique_categories = iter(larger_categories)
def new_string_every_time(c):
# Return a new unique category every time so that every result is
# different.
return next(gen_unique_categories)
result = arr.map(new_string_every_time)
# Result should still be of size 1.
assert_equal(result.itemsize, 1)
# Result should be the first `len(categories)` entries from the larger
# categories, repeated twice.
expected = LabelArray(
larger_categories[:len(categories)] * 2,
missing_value=None,
)
assert_equal(result.as_string_array(), expected.as_string_array())
def test_map_never_increases_code_storage_size(self):
# This tests a pathological case where a user maps an impure function
# that returns a different label on every invocation, which in a naive
# implementation could cause us to need to **increase** the size of our
# codes after a map.
#
# This doesn't happen, however, because we guarantee that the user's
# mapping function will be called on each unique category exactly once,
# which means we can never increase the number of categories in the
# LabelArray after mapping.
# Using all but one of the categories so that we still fit in a uint8
# with an extra category for None as a missing value.
categories = self.create_categories(8, plus_one=False)[:-1]
larger_categories = self.create_categories(16, plus_one=False)
# Double the length of the categories so that we have to increase the
# required size after our map.
categories_twice = categories + categories
arr = LabelArray(categories_twice, missing_value=None)
assert_equal(arr.itemsize, 1)
gen_unique_categories = iter(larger_categories)
def new_string_every_time(c):
# Return a new unique category every time so that every result is
# different.
return next(gen_unique_categories)
result = arr.map(new_string_every_time)
# Result should still be of size 1.
assert_equal(result.itemsize, 1)
# Result should be the first `len(categories)` entries from the larger
# categories, repeated twice.
expected = LabelArray(
larger_categories[:len(categories)] * 2,
missing_value=None,
)
assert_equal(result.as_string_array(), expected.as_string_array())
def test_map_shrinks_code_storage_if_possible(self):
arr = LabelArray(
# Drop the last value so we fit in a uint16 with None as a missing
# value.
self.create_categories(16, plus_one=False)[:-1],
missing_value=None,
)
self.assertEqual(arr.itemsize, 2)
def either_A_or_B(s):
return ('A', 'B')[sum(ord(c) for c in s) % 2]
result = arr.map(either_A_or_B)
self.assertEqual(set(result.categories), {'A', 'B', None})
self.assertEqual(result.itemsize, 1)
assert_equal(
np.vectorize(either_A_or_B)(arr.as_string_array()),
result.as_string_array(),
)
def test_map_shrinks_code_storage_if_possible(self):
arr = LabelArray(
# Drop the last value so we fit in a uint16 with None as a missing
# value.
self.create_categories(16, plus_one=False)[:-1],
missing_value=None,
)
self.assertEqual(arr.itemsize, 2)
def either_A_or_B(s):
return ('A', 'B')[sum(ord(c) for c in s) % 2]
result = arr.map(either_A_or_B)
self.assertEqual(set(result.categories), {'A', 'B', None})
self.assertEqual(result.itemsize, 1)
assert_equal(
np.vectorize(either_A_or_B)(arr.as_string_array()),
result.as_string_array(),
)
