Skip to content

chore: Use fixture for list/str accessor tests #992

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 10 commits into from
Sep 17, 2024
Merged

chore: Use fixture for list/str accessor tests #992

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
70b1742
chore: Use fixture for list/str accessor tests
sycai Sep 16, 2024
9994d26
fix format
sycai Sep 16, 2024
6f5daae
Merge branch 'main' into b364405145
sycai Sep 16, 2024
e7edcdf
🦉 Updates from OwlBot post-processor
gcf-owl-bot[bot] Sep 16, 2024
5314c9d
Merge branch 'b364405145' of https://github.com/googleapis/python-big…
gcf-owl-bot[bot] Sep 16, 2024
9a9d0ac
add more type coverage in tests
sycai Sep 16, 2024
f27dda7
fix format
sycai Sep 16, 2024
2c0eeb3
remove unnecessary dep
sycai Sep 16, 2024
40ccad9
remove import
sycai Sep 16, 2024
930e3cb
Merge branch 'main' into b364405145
sycai Sep 17, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions tests/data/repeated.jsonl
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
{"rowindex": 0, "int_list_col": [1], "bool_list_col": [true], "float_list_col": [1.2, 2.3], "date_list_col": ["2021-07-21"], "date_time_list_col": ["2021-07-21 11:39:45"], "numeric_list_col": [1.2, 2.3, 3.4], "string_list_col": ["abc", "de", "f"]}
{"rowindex": 1, "int_list_col": [1,2], "bool_list_col": [true, false], "float_list_col": [1.1], "date_list_col": ["2021-07-21", "1987-03-28"], "date_time_list_col": ["1999-03-14 17:22:00"], "numeric_list_col": [5.5, 2.3], "string_list_col": ["a", "bc", "de"]}
{"rowindex": 2, "int_list_col": [1,2,3], "bool_list_col": [true], "float_list_col": [0.5, -1.9, 2.3], "date_list_col": ["2017-08-01", "2004-11-22"], "date_time_list_col": ["1979-06-03 03:20:45"], "numeric_list_col": [1.7], "string_list_col": ["", "a"]}
42 changes: 42 additions & 0 deletions tests/data/repeated_schema.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,42 @@
[
{
"name": "rowindex",
"type": "INTEGER",
"mode": "REQUIRED"
},
{
"name": "int_list_col",
"type": "INTEGER",
"mode": "REPEATED"
},
{
"name": "bool_list_col",
"type": "BOOLEAN",
"mode": "REPEATED"
},
{
"name": "float_list_col",
"type": "FLOAT",
"mode": "REPEATED"
},
{
"name": "date_list_col",
"type": "DATE",
"mode": "REPEATED"
},
{
"name": "date_time_list_col",
"type": "DATETIME",
"mode": "REPEATED"
},
{
"name": "numeric_list_col",
"type": "NUMERIC",
"mode": "REPEATED"
},
{
"name": "string_list_col",
"type": "STRING",
"mode": "REPEATED"
}
]
27 changes: 27 additions & 0 deletions tests/system/conftest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,7 @@
import bigframes
import bigframes.dataframe
import bigframes.pandas as bpd
import bigframes.series
import tests.system.utils

# Use this to control the number of cloud functions being deleted in a single
Expand Down Expand Up @@ -294,6 +295,7 @@ def load_test_data_tables(
("scalars", "scalars_schema.json", "scalars.jsonl"),
("scalars_too", "scalars_schema.json", "scalars.jsonl"),
("nested", "nested_schema.json", "nested.jsonl"),
("repeated", "repeated_schema.json", "repeated.jsonl"),
("penguins", "penguins_schema.json", "penguins.jsonl"),
("time_series", "time_series_schema.json", "time_series.jsonl"),
("hockey_players", "hockey_players.json", "hockey_players.jsonl"),
Expand Down Expand Up @@ -370,6 +372,11 @@ def nested_table_id(test_data_tables) -> str:
return test_data_tables["nested"]


@pytest.fixture(scope="session")
def repeated_table_id(test_data_tables) -> str:
return test_data_tables["repeated"]


@pytest.fixture(scope="session")
def penguins_table_id(test_data_tables) -> str:
return test_data_tables["penguins"]
Expand Down Expand Up @@ -410,6 +417,26 @@ def nested_pandas_df() -> pd.DataFrame:
return df


@pytest.fixture(scope="session")
def repeated_df(
repeated_table_id: str, session: bigframes.Session
) -> bigframes.dataframe.DataFrame:
"""Returns a DataFrame containing columns of list type."""
return session.read_gbq(repeated_table_id, index_col="rowindex")


@pytest.fixture(scope="session")
def repeated_pandas_df() -> pd.DataFrame:
"""Returns a DataFrame containing columns of list type."""

df = pd.read_json(
DATA_DIR / "repeated.jsonl",
lines=True,
)
df = df.set_index("rowindex")
return df


@pytest.fixture(scope="session")
def scalars_df_default_index(
scalars_df_index: bigframes.dataframe.DataFrame,
Expand Down
67 changes: 46 additions & 21 deletions tests/system/small/operations/test_lists.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,8 +18,6 @@
import pyarrow as pa
import pytest

import bigframes.pandas as bpd

from ...utils import assert_series_equal


Expand All @@ -32,19 +30,34 @@
pytest.param(slice(0, 2, None), id="default_step_slice"),
],
)
def test_getitem(key):
@pytest.mark.parametrize(
("column_name", "dtype"),
[
pytest.param("int_list_col", pd.ArrowDtype(pa.list_(pa.int64()))),
pytest.param("bool_list_col", pd.ArrowDtype(pa.list_(pa.bool_()))),
pytest.param("float_list_col", pd.ArrowDtype(pa.list_(pa.float64()))),
pytest.param("date_list_col", pd.ArrowDtype(pa.list_(pa.date32()))),
pytest.param("date_time_list_col", pd.ArrowDtype(pa.list_(pa.timestamp("us")))),
pytest.param("numeric_list_col", pd.ArrowDtype(pa.list_(pa.decimal128(38, 9)))),
pytest.param("string_list_col", pd.ArrowDtype(pa.list_(pa.string()))),
],
)
def test_getitem(key, column_name, dtype, repeated_df, repeated_pandas_df):
if packaging.version.Version(pd.__version__) < packaging.version.Version("2.2.0"):
pytest.skip(
"https://pandas.pydata.org/docs/whatsnew/v2.2.0.html#series-list-accessor-for-pyarrow-list-data"
)
data = [[1], [2, 3], [4, 5, 6]]
s = bpd.Series(data, dtype=pd.ArrowDtype(pa.list_(pa.int64())))
pd_s = pd.Series(data, dtype=pd.ArrowDtype(pa.list_(pa.int64())))

bf_result = s.list[key].to_pandas()
pd_result = pd_s.list[key]
bf_result = repeated_df[column_name].list[key].to_pandas()
pd_result = repeated_pandas_df[column_name].astype(dtype).list[key]

assert_series_equal(pd_result, bf_result, check_dtype=False, check_index_type=False)
assert_series_equal(
pd_result,
bf_result,
check_dtype=False,
check_index_type=False,
check_names=False,
)


@pytest.mark.parametrize(
Expand All @@ -60,24 +73,36 @@ def test_getitem(key):
(slice(0, 2, 2), pytest.raises(NotImplementedError)),
],
)
def test_getitem_notsupported(key, expectation):
data = [[1], [2, 3], [4, 5, 6]]
s = bpd.Series(data, dtype=pd.ArrowDtype(pa.list_(pa.int64())))

def test_getitem_notsupported(key, expectation, repeated_df):
with expectation as e:
assert s.list[key] == e
assert repeated_df["int_list_col"].list[key] == e


def test_len():
@pytest.mark.parametrize(
("column_name", "dtype"),
[
pytest.param("int_list_col", pd.ArrowDtype(pa.list_(pa.int64()))),
pytest.param("bool_list_col", pd.ArrowDtype(pa.list_(pa.bool_()))),
pytest.param("float_list_col", pd.ArrowDtype(pa.list_(pa.float64()))),
pytest.param("date_list_col", pd.ArrowDtype(pa.list_(pa.date32()))),
pytest.param("date_time_list_col", pd.ArrowDtype(pa.list_(pa.timestamp("us")))),
pytest.param("numeric_list_col", pd.ArrowDtype(pa.list_(pa.decimal128(38, 9)))),
pytest.param("string_list_col", pd.ArrowDtype(pa.list_(pa.string()))),
],
)
def test_len(column_name, dtype, repeated_df, repeated_pandas_df):
if packaging.version.Version(pd.__version__) < packaging.version.Version("2.2.0"):
pytest.skip(
"https://pandas.pydata.org/docs/whatsnew/v2.2.0.html#series-list-accessor-for-pyarrow-list-data"
)
data = [[], [1], [1, 2], [1, 2, 3]]
s = bpd.Series(data, dtype=pd.ArrowDtype(pa.list_(pa.int64())))
pd_s = pd.Series(data, dtype=pd.ArrowDtype(pa.list_(pa.int64())))

bf_result = s.list.len().to_pandas()
pd_result = pd_s.list.len()
bf_result = repeated_df[column_name].list.len().to_pandas()
pd_result = repeated_pandas_df[column_name].astype(dtype).list.len()

assert_series_equal(pd_result, bf_result, check_dtype=False, check_index_type=False)
assert_series_equal(
pd_result,
bf_result,
check_dtype=False,
check_index_type=False,
check_names=False,
)
25 changes: 16 additions & 9 deletions tests/system/small/operations/test_strings.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -615,21 +615,28 @@ def test_getitem_w_string(scalars_dfs, index):
@pytest.mark.parametrize(
("index"),
[
pytest.param(2, id="int"),
pytest.param(0, id="int"),
pytest.param(slice(None, None, None), id="default_start_slice"),
pytest.param(slice(0, None, 1), id="default_stop_slice"),
pytest.param(slice(0, 2, None), id="default_step_slice"),
pytest.param(slice(0, 0, None), id="single_one_slice"),
],
)
def test_getitem_w_array(index):
data = [[1], [2, 3], [], [4, 5, 6]]
s = bpd.Series(data)
pd_s = pd.Series(data)

bf_result = s.str[index].to_pandas()
pd_result = pd_s.str[index]
# Skip dtype checks here because pandas returns `int64` while BF returns `Int64`.
@pytest.mark.parametrize(
"column_name",
[
pytest.param("int_list_col"),
pytest.param("bool_list_col"),
pytest.param("float_list_col"),
pytest.param("string_list_col"),
# date, date_time and numeric are excluded because their default types are different
# in Pandas and BigFrames
],
)
def test_getitem_w_array(index, column_name, repeated_df, repeated_pandas_df):
bf_result = repeated_df[column_name].str[index].to_pandas()
pd_result = repeated_pandas_df[column_name].str[index]

assert_series_equal(pd_result, bf_result, check_dtype=False, check_index_type=False)


Expand Down