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

feat: add series.sample (identical to existing dataframe.sample) #187

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.

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 6 commits into from
Nov 9, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
16 changes: 16 additions & 0 deletions 16 bigframes/series.py
Original file line number Diff line number Diff line change
Expand Up @@ -1447,6 +1447,22 @@ def map(
result_df = self_df.join(map_df, on="series")
return result_df[self.name]

def sample(
self,
n: Optional[int] = None,
frac: Optional[float] = None,
*,
random_state: Optional[int] = None,
) -> Series:
if n is not None and frac is not None:
raise ValueError("Only one of 'n' or 'frac' parameter can be specified.")

ns = (n,) if n is not None else ()
fracs = (frac,) if frac is not None else ()
return Series(
self._block._split(ns=ns, fracs=fracs, random_state=random_state)[0]
)

def __array_ufunc__(
self, ufunc: numpy.ufunc, method: str, *inputs, **kwargs
) -> Series:
Expand Down
27 changes: 27 additions & 0 deletions 27 tests/system/small/test_series.py
Original file line number Diff line number Diff line change
Expand Up @@ -2922,3 +2922,30 @@ def test_map_series_input_duplicates_error(scalars_dfs):
scalars_pandas_df.int64_too.map(pd_map_series)
with pytest.raises(pd.errors.InvalidIndexError):
scalars_df.int64_too.map(bf_map_series, verify_integrity=True)


@pytest.mark.parametrize(
("frac", "n", "random_state"),
[
(None, 4, None),
(0.5, None, None),
(None, 4, 10),
(0.5, None, 10),
(None, None, None),
],
ids=[
"n_wo_random_state",
"frac_wo_random_state",
"n_w_random_state",
"frac_w_random_state",
"n_default",
],
)
def test_sample(scalars_dfs, frac, n, random_state):
scalars_df, _ = scalars_dfs
df = scalars_df.int64_col.sample(frac=frac, n=n, random_state=random_state)
bf_result = df.to_pandas()

n = 1 if n is None else n
expected_sample_size = round(frac * scalars_df.shape[0]) if frac is not None else n
assert bf_result.shape[0] == expected_sample_size
Morty Proxy This is a proxified and sanitized view of the page, visit original site.