assert rg_meta.num_columns == ncols + 1 # +1 for index
@parquet
@pytest.mark.parametrize(
'data, dtype, min_value, max_value, null_count, num_values', [
([1, 2, 2, None, 4], np.uint8, u'1', u'4', 1, 4),
([1, 2, 2, None, 4], np.uint16, u'1', u'4', 1, 4),
([1, 2, 2, None, 4], np.uint32, u'1', u'4', 1, 4),
([1, 2, 2, None, 4], np.uint64, u'1', u'4', 1, 4),
([-1, 2, 2, None, 4], np.int16, u'-1', u'4', 1, 4),
([-1, 2, 2, None, 4], np.int32, u'-1', u'4', 1, 4),
([-1, 2, 2, None, 4], np.int64, u'-1', u'4', 1, 4),
([-1.1, 2.2, 2.3, None, 4.4], np.float32, u'-1.1', u'4.4', 1, 4),
([-1.1, 2.2, 2.3, None, 4.4], np.float64, u'-1.1', u'4.4', 1, 4),
([u'', u'b', unichar(1000), None, u'aaa'
], str, u' ', frombytes(
(unichar(1000) + u' ').encode('utf-8')), 1, 4),
([True, False, False, True, True], np.bool, u'0', u'1', 0, 5),
])
def test_parquet_column_statistics_api(data, dtype, min_value, max_value,
null_count, num_values):
df = pd.DataFrame({'data': data}, dtype=dtype)
fileh = make_sample_file(df)
meta = fileh.metadata
rg_meta = meta.row_group(0)
col_meta = rg_meta.column(0)
@parquet
@pytest.mark.parametrize(
'data, dtype, min_value, max_value, null_count, num_values',
[
([1, 2, 2, None, 4], np.uint8, u'1', u'4', 1, 4),
([1, 2, 2, None, 4], np.uint16, u'1', u'4', 1, 4),
([1, 2, 2, None, 4], np.uint32, u'1', u'4', 1, 4),
([1, 2, 2, None, 4], np.uint64, u'1', u'4', 1, 4),
([-1, 2, 2, None, 4], np.int16, u'-1', u'4', 1, 4),
([-1, 2, 2, None, 4], np.int32, u'-1', u'4', 1, 4),
([-1, 2, 2, None, 4], np.int64, u'-1', u'4', 1, 4),
([-1.1, 2.2, 2.3, None, 4.4], np.float32, u'-1.1', u'4.4', 1, 4),
([-1.1, 2.2, 2.3, None, 4.4], np.float64, u'-1.1', u'4.4', 1, 4),
(
[u'', u'b', unichar(1000), None, u'aaa'],
str, u' ', frombytes((unichar(1000) + u' ').encode('utf-8')), 1, 4
),
([True, False, False, True, True], np.bool, u'0', u'1', 0, 5),
]
)
def test_parquet_column_statistics_api(
data,
dtype,
min_value,
max_value,
null_count,
num_values):
df = pd.DataFrame({'data': data}, dtype=dtype)
fileh = make_sample_file(df)