def test_instantiated_fit_values(self):
encoder = OneHotEncoder(fit_values=["0", "1", "2"])
expected = [(1, 0, 0), (0, 1, 0), (0, 0, 1), (0, 1, 0)]
actual = encoder.encode(["0", "1", "2", "1"])
self.assertEqual(actual, expected)
def test_error_if_unkonwn_false(self):
encoder = OneHotEncoder(error_if_unknown=False).fit(["0", "1", "2"])
try:
actual = encoder.encode(["5"])
except:
self.fail("An exception was raised when it shouldn't have been")
self.assertEqual(actual, [(0, 0, 0)])
def test_performance_encode(self):
encoder = OneHotEncoder(list(range(1000)), error_if_unknown=False)
to_encode = [100, 200, 300, 400, -1] * 100000
time = min(
timeit.repeat(lambda: encoder.encode(to_encode),
repeat=50,
number=1))
#was approximately 0.040
self.assertLess(time, 1)
def test_error_if_unkonwn_true(self):
encoder = OneHotEncoder(error_if_unknown=True).fit(
["1", "1", "1", "0", "0"])
with self.assertRaises(Exception):
self.assertEqual(encoder.encode(["2"]), [(0)])
def test_singular_if_binary(self):
encoder = OneHotEncoder(singular_if_binary=True).fit(
["1", "1", "1", "0", "0"])
self.assertEqual(encoder.encode(["0"]), [(0, )])
self.assertEqual(encoder.encode(["1"]), [(1, )])