def test_series_median_parallel1(self):
# create `kde.parquet` file
ParquetGenerator.gen_kde_pq()
def test_impl():
df = pq.read_table('kde.parquet').to_pandas()
S = df.points
return S.median()
hpat_func = hpat.jit(test_impl)
self.assertEqual(hpat_func(), test_impl())
def test_series_sort_values_parallel1(self):
# create `kde.parquet` file
ParquetGenerator.gen_kde_pq()
def test_impl():
df = pq.read_table('kde.parquet').to_pandas()
S = df.points
return S.sort_values()
hpat_func = hpat.jit(test_impl)
np.testing.assert_array_equal(hpat_func(), test_impl())
def test_string_NA_box(self):
# create `example.parquet` file
ParquetGenerator.gen_pq_test()
def test_impl():
df = pq.read_table('example.parquet').to_pandas()
return df.five
hpat_func = hpat.jit(test_impl)
# XXX just checking isna() since Pandas uses None in this case
# instead of nan for some reason
np.testing.assert_array_equal(hpat_func().isna(), test_impl().isna())
def test_sort_parallel_single_col(self):
# create `kde.parquet` file
ParquetGenerator.gen_kde_pq()
# TODO: better parallel sort test
def test_impl():
df = pd.read_parquet('kde.parquet')
df.sort_values('points', inplace=True)
res = df.points.values
return res
hpat_func = hpat.jit(locals={'res:return': 'distributed'})(test_impl)
save_min_samples = hpat.hiframes.sort.MIN_SAMPLES
try:
hpat.hiframes.sort.MIN_SAMPLES = 10
res = hpat_func()
self.assertTrue((np.diff(res) >= 0).all())
finally:
# restore global val
hpat.hiframes.sort.MIN_SAMPLES = save_min_samples