def test_dataframe_groupby_sort(self):
def test_impl(df, param):
return df.groupby('A', sort=param).min()
hpat_func = self.jit(test_impl)
n, m = 1000, 20
np.random.seed(0)
df = pd.DataFrame({
'A': np.random.choice(np.arange(m), n),
'B': np.arange(n, dtype=np.intp),
'C': np.arange(n, dtype=np.float_),
'D': gen_frand_array(n, nancount=n // 2),
})
for value in [True, False]:
with self.subTest(sort=value):
result = hpat_func(df, value) if value else hpat_func(
df, value).sort_index()
result_ref = test_impl(df, value) if value else hpat_func(
df, value).sort_index()
# TODO: implement index classes, as current indexes do not have names
pd.testing.assert_frame_equal(result,
result_ref,
check_names=False)
def test_df_groupby_mean_by_float_sort_false(self):
self._test_df_groupby_method('mean',
usecase_name='by_float_mean',
input_data=[gen_frand_array(n_groups_default)],
groupby_params={'sort': 'False'})