def test_step_return_values_win():
under_test = ConnectFourGame()
under_test.board = np.array(
[
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[2, 2, 2, 0, 0, 0, 0],
[1, 1, 1, 0, 0, 0, 0],
]
)
expected_observation = np.array(
[
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[2, 2, 2, 0, 0, 0, 0],
[1, 1, 1, 1, 0, 0, 0],
]
)
expected_reward = 100.0
expected_done = True
expected_info = {}
observation, reward, done, info = under_test.step(3)
assert np.array_equal(observation, expected_observation)
assert expected_reward == reward
assert expected_done == done
assert expected_info == info
def test_not_is_draw_with_full_board_and_winner():
under_test = ConnectFourGame()
under_test.board = np.array(
[
[2, 1, 2, 2, 1, 2, 1],
[2, 1, 2, 2, 1, 2, 1],
[2, 1, 2, 2, 1, 2, 1],
[1, 2, 1, 2, 2, 1, 2],
[1, 2, 1, 1, 2, 1, 1],
[1, 2, 1, 1, 2, 1, 2],
]
)
assert not under_test.is_draw()
def test_not_is_draw():
under_test = ConnectFourGame()
under_test.board = np.array(
[
[1, 0, 2, 0, 2, 0, 0],
[1, 0, 2, 0, 1, 0, 0],
[2, 0, 1, 0, 2, 0, 0],
[1, 0, 2, 0, 1, 0, 0],
[1, 0, 2, 0, 2, 0, 1],
[1, 0, 2, 0, 1, 1, 2],
]
)
assert not under_test.is_draw()
def test_error_if_col_full():
under_test = ConnectFourGame()
under_test.board = np.array(
[
[2, 0, 0, 0, 0, 0, 0],
[1, 0, 0, 0, 0, 0, 0],
[2, 0, 0, 0, 0, 0, 0],
[1, 0, 0, 0, 0, 0, 0],
[2, 0, 0, 0, 0, 0, 0],
[1, 0, 0, 0, 0, 0, 0],
]
)
with pytest.raises(ValueError):
under_test.step(0)
def test_get_valid_moves_with_some_columns_full():
under_test = ConnectFourGame()
under_test.board = np.array(
[
[1, 0, 2, 0, 2, 0, 0],
[1, 0, 2, 0, 1, 0, 0],
[2, 0, 1, 0, 2, 0, 0],
[1, 0, 2, 0, 1, 0, 0],
[1, 0, 2, 0, 2, 0, 1],
[1, 0, 2, 0, 1, 1, 2],
]
)
expected = [1, 3, 5, 6]
actual = under_test.get_valid_moves()
assert actual == expected
def test_step_return_values_draw():
under_test = ConnectFourGame()
under_test.board = np.array(
[
[0, 1, 2, 2, 1, 2, 1],
[2, 1, 2, 2, 1, 2, 1],
[2, 1, 2, 2, 1, 2, 1],
[1, 2, 1, 1, 2, 1, 2],
[1, 2, 1, 1, 2, 1, 1],
[1, 2, 1, 1, 2, 1, 2],
]
)
under_test.turn = "O"
expected_observation = np.array(
[
[2, 1, 2, 2, 1, 2, 1],
[2, 1, 2, 2, 1, 2, 1],
[2, 1, 2, 2, 1, 2, 1],
[1, 2, 1, 1, 2, 1, 2],
[1, 2, 1, 1, 2, 1, 1],
[1, 2, 1, 1, 2, 1, 2],
]
)
expected_reward = -50.0
expected_done = True
expected_info = {}
observation, reward, done, info = under_test.step(0)
assert np.array_equal(observation, expected_observation)
assert expected_reward == reward
assert expected_done == done
assert expected_info == info