def test_categorical_transform():
categories = ["apple", "orange", "banana", None, True, False, 3]
cat = Categorical(categories)
apple = [1.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]
orange = [0.0, 1.0, 0.0, 0.0, 0.0, 0.0, 0.0]
banana = [0.0, 0.0, 1.0, 0.0, 0.0, 0.0, 0.0]
none = [0.0, 0.0, 0.0, 1.0, 0.0, 0.0, 0.0]
true = [0.0, 0.0, 0.0, 0.0, 1.0, 0.0, 0.0]
false = [0.0, 0.0, 0.0, 0.0, 0.0, 1.0, 0.0]
three = [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 1.0]
assert_equal(cat.transformed_size, 7)
assert_equal(cat.transformed_size, cat.transform(["apple"]).size)
assert_array_equal(cat.transform(categories),
[apple, orange, banana, none, true, false, three])
assert_array_equal(cat.transform(["apple", "orange"]), [apple, orange])
assert_array_equal(cat.transform(["apple", "banana"]), [apple, banana])
assert_array_equal(cat.inverse_transform([apple, orange]),
["apple", "orange"])
assert_array_equal(cat.inverse_transform([apple, banana]),
["apple", "banana"])
ent_inverse = cat.inverse_transform(
[apple, orange, banana, none, true, false, three])
assert_array_equal(ent_inverse, categories)
def test_categorical_transform_binary():
categories = ["apple", "orange"]
cat = Categorical(categories)
apple = [0.0]
orange = [1.0]
assert_equal(cat.transformed_size, 1)
assert_equal(cat.transformed_size, cat.transform(["apple"]).size)
assert_array_equal(cat.transform(categories), [apple, orange])
assert_array_equal(cat.transform(["apple", "orange"]), [apple, orange])
assert_array_equal(cat.inverse_transform([apple, orange]),
["apple", "orange"])
ent_inverse = cat.inverse_transform([apple, orange])
assert_array_equal(ent_inverse, categories)
def test_categorical_identity():
categories = ["cat", "dog", "rat"]
cat = Categorical(categories, transform="identity")
samples = cat.rvs(100)
assert all([t in categories for t in cat.rvs(100)])
transformed = cat.transform(samples)
assert_array_equal(transformed, samples)
assert_array_equal(samples, cat.inverse_transform(transformed))
def test_categorical_string():
categories = [1, 2, 3]
categories_transformed = ["1", "2", "3"]
cat = Categorical(categories, transform="string")
samples = cat.rvs(100)
assert all([t in categories for t in cat.rvs(100)])
transformed = cat.transform(samples)
assert all([t in categories_transformed for t in transformed])
assert_array_equal(samples, cat.inverse_transform(transformed))
def test_normalize_categorical():
categories = ["cat", "dog", "rat"]
a = Categorical(categories, transform="normalize")
for i in range(len(categories)):
assert a.rvs(random_state=i)[0] in categories
assert a.inverse_transform([0.0]) == [categories[0]]
assert a.inverse_transform([0.5]) == [categories[1]]
assert a.inverse_transform([1.0]) == [categories[2]]
assert_array_equal(categories, a.inverse_transform([0.0, 0.5, 1]))
categories = [1, 2, 3]
a = Categorical(categories, transform="normalize")
assert_array_equal(categories,
np.sort(np.unique(a.rvs(100, random_state=1))))
assert_array_equal(categories, a.inverse_transform([0.0, 0.5, 1.0]))
categories = [1.0, 2.0, 3.0]
a = Categorical(categories, transform="normalize")
assert_array_equal(categories,
np.sort(np.unique(a.rvs(100, random_state=1))))
assert_array_equal(categories, a.inverse_transform([0.0, 0.5, 1.0]))
categories = [1, 2, 3]
a = Categorical(categories, transform="string")
a.set_transformer("normalize")
assert_array_equal(categories,
np.sort(np.unique(a.rvs(100, random_state=1))))
assert_array_equal(categories, a.inverse_transform([0.0, 0.5, 1.0]))