Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Appearance settings

fix: correctly handle null values when initializing fingerprint ordering #210

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鈥檒l occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Nov 16, 2023
Merged

fix: correctly handle null values when initializing fingerprint ordering #210

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
aadbfb1
fix: correctly handle null values when initializing fingerprint ordering
TrevorBergeron Nov 16, 2023
7744e2b
fix mypy
TrevorBergeron Nov 16, 2023
2764510
fix mypy 2
TrevorBergeron Nov 16, 2023
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
9 changes: 6 additions & 3 deletions 9 bigframes/session/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1120,8 +1120,9 @@ def _create_total_ordering(
ordering_hash_part = guid.generate_guid("bigframes_ordering_")
ordering_rand_part = guid.generate_guid("bigframes_ordering_")

# All inputs into hash must be non-null or resulting hash will be null
str_values = list(
map(lambda col: _convert_to_string(table[col]), table.columns)
map(lambda col: _convert_to_nonnull_string(table[col]), table.columns)
)
full_row_str = (
str_values[0].concat(*str_values[1:])
Expand Down Expand Up @@ -1419,7 +1420,7 @@ def _can_cluster_bq(field: bigquery.SchemaField):
)


def _convert_to_string(column: ibis_types.Column) -> ibis_types.StringColumn:
def _convert_to_nonnull_string(column: ibis_types.Column) -> ibis_types.StringValue:
col_type = column.type()
if (
col_type.is_numeric()
Expand All @@ -1436,4 +1437,6 @@ def _convert_to_string(column: ibis_types.Column) -> ibis_types.StringColumn:
# TO_JSON_STRING works with all data types, but isn't the most efficient
# Needed for JSON, STRUCT and ARRAY datatypes
result = vendored_ibis_ops.ToJsonString(column).to_expr() # type: ignore
return typing.cast(ibis_types.StringColumn, result)
# Escape backslashes and use backslash as delineator
escaped = typing.cast(ibis_types.StringColumn, result.fillna("")).replace("\\", "\\\\") # type: ignore
return typing.cast(ibis_types.StringColumn, ibis.literal("\\")).concat(escaped)
8 changes: 8 additions & 0 deletions 8 tests/system/small/test_dataframe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2703,6 +2703,14 @@ def test_sample(scalars_dfs, frac, n, random_state):
assert bf_result.shape[1] == scalars_df.shape[1]


def test_sample_determinism(penguins_df_default_index):
df = penguins_df_default_index.sample(n=100, random_state=12345).head(15)
bf_result = df.to_pandas()
bf_result2 = df.to_pandas()

pandas.testing.assert_frame_equal(bf_result, bf_result2)


def test_sample_raises_value_error(scalars_dfs):
scalars_df, _ = scalars_dfs
with pytest.raises(
Expand Down
Morty Proxy This is a proxified and sanitized view of the page, visit original site.