def test_expand_col_no_dummy(data_raw):
expander = DataFrameETL(cols_to_drop=['fruits'],
dummy_na=None,
fill_value=-1.0)
expander.fit(data_raw)
arr = expander._expand_col(data_raw, 'pid')
arr_exp = np.array([[1., 0., 0.], [0., 1., 0.], [0., 0., 1.]])
assert_almost_equal(arr, arr_exp)
arr = expander._expand_col(data_raw, 'animal')
arr_exp = np.array([[1., 0.], [0., 1.], [-1., -1.]])
assert_almost_equal(arr, arr_exp)
def test_expand_col(data_raw):
expander = DataFrameETL(cols_to_drop=['fruits'],
dummy_na='expanded',
fill_value=-1.0)
expander.fit(data_raw)
# should expand even if there are no NaNs
arr = expander._expand_col(data_raw, 'pid')
arr_exp = np.array([[1., 0., 0., 0.], [0., 1., 0., 0.], [0., 0., 1., 0.]])
assert_almost_equal(arr, arr_exp)
arr = expander._expand_col(data_raw, 'animal')
arr_exp = np.array([[1., 0., 0.], [0., 1., 0.], [-1., -1., 1.]])
assert_almost_equal(arr, arr_exp)
def test_expand_col_few_levels_no_dummy(data_few_levels, few_levels_expected):
expander = DataFrameETL(cols_to_expand=['pid', 'fruits', 'animal'],
dummy_na=False,
fill_value=99.)
expander.fit(data_few_levels)
arr = expander._expand_col(data_few_levels, 'pid')
expected_array = np.asarray(few_levels_expected[['pid_NaN', 'pid_a']])
assert_almost_equal(arr, expected_array)
arr = expander._expand_col(data_few_levels, 'fruits')
expected_array = np.asarray(few_levels_expected[['fruits_1.0']])
assert_almost_equal(arr, expected_array)
arr = expander._expand_col(data_few_levels, 'animal')
expected_array = np.asarray(few_levels_expected[['animal_cat']])
assert_almost_equal(arr, expected_array)
def test_expand_col_numeric_no_dummy(data_raw):
expander = DataFrameETL(cols_to_drop=['pid', 'djinn_type', 'animal'],
cols_to_expand=['fruits'],
dummy_na=False,
fill_value=np.nan)
expander.fit(data_raw)
arr = expander._expand_col(data_raw, 'fruits')
arr_exp = np.array([[1., 0.], [np.nan, np.nan], [0., 1.]])
assert_almost_equal(arr, arr_exp)
