[jira] [Updated] (ARROW-11538) [Python] Seg Fault with pandas.Timestamp filter

["Josh (Jira)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/ARROW-11538?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Josh updated ARROW-11538:
-------------------------
    Description: 
The first two tests pass but the third gives: Fatal Python error: Segmentation fault

All three pass in with pyarrow=2.0.0
{code:java}
import pandas
import pyarrow as pa
import pyarrow.dataset as ds
import pyarrow.parquet as pq
import pytest


@pytest.fixture
def data_path(tmp_path):
    path = tmp_path / "data.parquet"
    df = pandas.DataFrame(
        [
            ["A", pandas.Timestamp("2020-11-04")],
        ],
        columns=["name", "date"],
    )
    table = pa.Table.from_pandas(df)
    pq.write_table(table, path, version="2.0")
    return df, path


@pytest.mark.parametrize(
    "filter",
    [
        None,
        ds.field("date") == "2020-11-04",
        ds.field("date") == pandas.Timestamp("2020-11-04"),
    ],
)
def test_dataset_filter(filter, data_path):
    data, path = data_path

    dataset = ds.dataset(path, format="parquet")
    assert data.equals(dataset.to_table(filter=filter).to_pandas())

{code}

  was:
The first two tests pass but the third gives: Fatal Python error: Segmentation fault

All three pass in with pyarrow=2.0.0
{code:java}
import pandas
import pyarrow as pa
import pyarrow.dataset as ds
import pyarrow.parquet as pq
import pytest


@pytest.fixture
def data_path(tmp_path):
    path = tmp_path / "data.parquet"
    df = pandas.DataFrame(
        [
            ["A", pandas.Timestamp("2020-11-04")],
        ],
        columns=["name", "date"],
    )
    table = pa.Table.from_pandas(df)
    pq.write_table(table, path, version="2.0")
    return df, path


def test_dataset(data_path):
    data, path = data_path

    dataset = ds.dataset(path, format="parquet")
    assert data.equals(dataset.to_table().to_pandas())


@pytest.mark.parametrize(
    "filter",
    [
        None,
        ds.field("date") == "2020-11-04",
        ds.field("date") == pandas.Timestamp("2020-11-04"),
    ],
)
def test_dataset_filter(filter, data_path):
    data, path = data_path

    dataset = ds.dataset(path, format="parquet")
    assert data.equals(dataset.to_table(filter=filter).to_pandas())

{code}


> [Python] Seg Fault with pandas.Timestamp filter
> -----------------------------------------------
>
>                 Key: ARROW-11538
>                 URL: https://issues.apache.org/jira/browse/ARROW-11538
>             Project: Apache Arrow
>          Issue Type: Bug
>          Components: Python
>    Affects Versions: 3.0.0
>         Environment: platform: Linux 64bit
> conda env:
> conda create -n pya python=3.8 pyarrow=3.0.0 pandas=1.2.1 pytest -c conda-forge
>            Reporter: Josh
>            Priority: Minor
>
> The first two tests pass but the third gives: Fatal Python error: Segmentation fault
> All three pass in with pyarrow=2.0.0
> {code:java}
> import pandas
> import pyarrow as pa
> import pyarrow.dataset as ds
> import pyarrow.parquet as pq
> import pytest
> @pytest.fixture
> def data_path(tmp_path):
>     path = tmp_path / "data.parquet"
>     df = pandas.DataFrame(
>         [
>             ["A", pandas.Timestamp("2020-11-04")],
>         ],
>         columns=["name", "date"],
>     )
>     table = pa.Table.from_pandas(df)
>     pq.write_table(table, path, version="2.0")
>     return df, path
> @pytest.mark.parametrize(
>     "filter",
>     [
>         None,
>         ds.field("date") == "2020-11-04",
>         ds.field("date") == pandas.Timestamp("2020-11-04"),
>     ],
> )
> def test_dataset_filter(filter, data_path):
>     data, path = data_path
>     dataset = ds.dataset(path, format="parquet")
>     assert data.equals(dataset.to_table(filter=filter).to_pandas())
> {code}



--
This message was sent by Atlassian Jira
(v8.3.4#803005)