def test_typestr():
assert (str(ak.type(ak.to_categorical(ak.Array(
[1.1, 2.2, 2.2, 3.3])))) == "4 * categorical[type=float64]")
assert (str(
ak.type(ak.to_categorical(ak.Array(
[1.1, 2.2, None, 2.2, 3.3])))) == "5 * categorical[type=?float64]")
assert (str(
ak.type(ak.to_categorical(ak.Array(
["one", "two", "two",
"three"])))) == "4 * categorical[type=string]")
assert (str(
ak.type(
ak.to_categorical(ak.Array(
["one", "two", None, "two",
"three"])))) == "5 * categorical[type=option[string]]")
def test_arraytype_categorical_1():
text = str(
ak.to_categorical(
ak.Array(["one", "one", "two", "three", "one", "three"])).type)
parsedtype = ak.types.from_datashape(text, True)
assert isinstance(parsedtype, ak.types.ArrayType)
assert str(parsedtype) == text
def test():
array = ak.to_categorical(ak.Array([321, 1.1, 123, 1.1, 999, 1.1, 2.0]))
assert ak.to_list(array * 10) == [3210, 11, 1230, 11, 9990, 11, 20]
array = ak.Array(["HAL"])
with pytest.raises(ValueError):
array + 1
def test_jim4():
text = str(
ak.to_categorical(ak.Array([1.1, 1.1, 2.2, 3.3, 1.1, 3.3])).type)
print(text)
parsedtype = deduce_type(text, True)
assert isinstance(parsedtype, ak.types.ArrayType)
assert str(parsedtype) == text
def test_to_categorical_masked():
content = ak.Array(
["one", "two", "three", "one", "one", "two", "three", "two"]).layout
index = ak.layout.Index64(
np.array([0, 1, 2, 3, 4, 5, 6, 7, 0, 1, 2, 3], dtype=np.int64))
indexedarray = ak.layout.IndexedArray64(index, content)
mask = ak.layout.Index8(
np.array([
False,
False,
False,
True,
False,
False,
False,
True,
False,
False,
False,
True,
]))
array = ak.Array(
ak.layout.ByteMaskedArray(mask, indexedarray, valid_when=False))
assert not ak.is_categorical(array)
categorical = ak.to_categorical(array)
assert ak.is_categorical(categorical)
assert ak.to_list(array) == categorical.tolist()
assert ak.to_list(categorical.layout.content) == ["one", "two", "three"]
not_categorical = ak.from_categorical(categorical)
assert not ak.is_categorical(not_categorical)
assert ak.categories(categorical).tolist() == ["one", "two", "three"]
def test_jim3():
text = str(
ak.to_categorical(
ak.Array(["one", "one", "two", "three", "one", "three"])).type)
print(text)
parsedtype = deduce_type(text, True)
assert isinstance(parsedtype, ak.types.ArrayType)
assert str(parsedtype) == text
def test_to_categorical_nested():
array = ak.Array([["one", "two", "three"], [], ["one", "two"], ["three"]])
assert not ak.is_categorical(array)
categorical = ak.to_categorical(array)
assert ak.is_categorical(categorical)
assert ak.to_list(array) == categorical.tolist()
not_categorical = ak.from_categorical(categorical)
assert not ak.is_categorical(not_categorical)
assert ak.categories(categorical).tolist() == ["one", "two", "three"]
def test_to_categorical_numbers():
array = ak.Array([1.1, 2.2, 3.3, 1.1, 2.2, 3.3, 1.1, 2.2, 3.3])
assert not ak.is_categorical(array)
categorical = ak.to_categorical(array)
assert ak.is_categorical(categorical)
assert ak.to_list(array) == categorical.tolist()
assert ak.to_list(categorical.layout.content) == [1.1, 2.2, 3.3]
not_categorical = ak.from_categorical(categorical)
assert not ak.is_categorical(not_categorical)
assert ak.categories(categorical).tolist() == [1.1, 2.2, 3.3]
def test_to_categorical():
array = ak.Array(
["one", "two", "three", "one", "two", "three", "one", "two", "three"])
assert not ak.is_categorical(array)
categorical = ak.to_categorical(array)
assert ak.is_categorical(categorical)
assert ak.to_list(array) == categorical.tolist()
assert ak.to_list(categorical.layout.content) == ["one", "two", "three"]
not_categorical = ak.from_categorical(categorical)
assert not ak.is_categorical(not_categorical)
assert ak.categories(categorical).tolist() == ["one", "two", "three"]
def test_to_categorical_masked():
content = ak.Array([
"one",
"two",
"three",
"one",
"one",
"two",
"three",
"two",
"one",
"two",
"three",
"three",
]).layout
mask = ak.layout.Index8(
np.array([
False,
False,
False,
True,
False,
False,
False,
True,
False,
False,
False,
True,
]))
array = ak.Array(ak.layout.ByteMaskedArray(mask, content,
valid_when=False))
assert not ak.is_categorical(array)
categorical = ak.to_categorical(array)
assert ak.is_categorical(categorical)
assert ak.to_list(array) == categorical.tolist()
assert ak.to_list(categorical.layout.content) == ["one", "two", "three"]
not_categorical = ak.from_categorical(categorical)
assert not ak.is_categorical(not_categorical)
assert ak.categories(categorical).tolist() == ["one", "two", "three"]
def test_zip():
x = ak.Array([1.1, 2.2, 3.3])
y = ak.Array(["one", "two", "three"])
assert ak.zip({
"x": x,
"y": y
}).tolist() == [
{
"x": 1.1,
"y": "one"
},
{
"x": 2.2,
"y": "two"
},
{
"x": 3.3,
"y": "three"
},
]
y = ak.to_categorical(y)
assert ak.zip({
"x": x,
"y": y
}).tolist() == [
{
"x": 1.1,
"y": "one"
},
{
"x": 2.2,
"y": "two"
},
{
"x": 3.3,
"y": "three"
},
]
def test_categorical_is_valid():
# validate a categorical array by its content
arr = ak.Array([2019, 2020, 2021, 2020, 2019])
categorical = ak.to_categorical(arr)
assert ak.is_valid(categorical)
def test_arraytype_categorical_2():
text = str(
ak.to_categorical(ak.Array([1.1, 1.1, 2.2, 3.3, 1.1, 3.3])).type)
parsedtype = ak.types.from_datashape(text, True)
assert isinstance(parsedtype, ak.types.ArrayType)
assert str(parsedtype) == text
