Skip to content
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

Jump to bottom

remove upper bound of plugin dependencies for flytekit-polars #2514

Merged
merged 8 commits into from
Aug 23, 2024
Merged

remove upper bound of plugin dependencies for flytekit-polars #2514

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
ff742a1
remove upper bound of plugin dependencies for flytekit-polars
Mecoli1219 Jun 19, 2024
5fb3f76
Update plugins/flytekit-polars/setup.py
Mecoli1219 Jul 4, 2024
db109cb
Fix deprecated function for polars
Mecoli1219 Jul 13, 2024
de7c3a1
lint
Mecoli1219 Aug 22, 2024
9c9bfd7
avoid polar describe()
Mecoli1219 Aug 22, 2024
dc1940d
Change frame_equal into assert_frame_equal
Mecoli1219 Aug 22, 2024
26edf04
Update html format
Mecoli1219 Aug 22, 2024
ef58401
Remain the polars describe function
Mecoli1219 Aug 22, 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: 1 addition & 2 deletions plugins/flytekit-polars/flytekitplugins/polars/sd_transformers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,8 +26,7 @@ class PolarsDataFrameRenderer:

def to_html(self, df: pl.DataFrame) -> str:
assert isinstance(df, pl.DataFrame)
describe_df = df.describe()
return pd.DataFrame(describe_df.transpose(), columns=describe_df.columns).to_html(index=False)
return df.describe().to_pandas().to_html(index=False)


class PolarsDataFrameToParquetEncodingHandler(StructuredDatasetEncoder):
Expand Down
2 changes: 1 addition & 1 deletion plugins/flytekit-polars/setup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@

microlib_name = f"flytekitplugins-{PLUGIN_NAME}"

plugin_requires = ["flytekit>=1.3.0b2,<2.0.0", "polars>=0.8.27,<0.17.0", "pandas"]
plugin_requires = ["flytekit>=1.3.0b2,<2.0.0", "polars>=0.8.27", "pandas"]

__version__ = "0.0.0+develop"

Expand Down
16 changes: 10 additions & 6 deletions plugins/flytekit-polars/tests/test_polars_plugin_sd.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,13 +4,17 @@
import polars as pl
from flytekitplugins.polars.sd_transformers import PolarsDataFrameRenderer
from typing_extensions import Annotated
from packaging import version
from polars.testing import assert_frame_equal

from flytekit import kwtypes, task, workflow
from flytekit.types.structured.structured_dataset import PARQUET, StructuredDataset

subset_schema = Annotated[StructuredDataset, kwtypes(col2=str), PARQUET]
full_schema = Annotated[StructuredDataset, PARQUET]

polars_version = pl.__version__


def test_polars_workflow_subset():
@task
Expand Down Expand Up @@ -65,9 +69,9 @@ def wf() -> full_schema:

def test_polars_renderer():
df = pl.DataFrame({"col1": [1, 3, 2], "col2": list("abc")})
assert PolarsDataFrameRenderer().to_html(df) == pd.DataFrame(
df.describe().transpose(), columns=df.describe().columns
).to_html(index=False)
assert PolarsDataFrameRenderer().to_html(df) == df.describe().to_pandas().to_html(
index=False
)


def test_parquet_to_polars():
Expand All @@ -80,7 +84,7 @@ def create_sd() -> StructuredDataset:

sd = create_sd()
polars_df = sd.open(pl.DataFrame).all()
assert pl.DataFrame(data).frame_equal(polars_df)
assert_frame_equal(polars_df, pl.DataFrame(data))

tmp = tempfile.mktemp()
pl.DataFrame(data).write_parquet(tmp)
Expand All @@ -90,11 +94,11 @@ def t1(sd: StructuredDataset) -> pl.DataFrame:
return sd.open(pl.DataFrame).all()

sd = StructuredDataset(uri=tmp)
assert t1(sd=sd).frame_equal(polars_df)
assert_frame_equal(t1(sd=sd), polars_df)

@task
def t2(sd: StructuredDataset) -> StructuredDataset:
return StructuredDataset(dataframe=sd.open(pl.DataFrame).all())

sd = StructuredDataset(uri=tmp)
assert t2(sd=sd).open(pl.DataFrame).all().frame_equal(polars_df)
assert_frame_equal(t2(sd=sd).open(pl.DataFrame).all(), polars_df)
Loading