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

TST(string dtype): Resolve HDF5 xfails in test_round_trip.py #60627

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open

TST(string dtype): Resolve HDF5 xfails in test_round_trip.py #60627

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
2be559a
TST(string dtype): Resolve HDF5 xfails in test_put.py
rhshadrach Dec 30, 2024
ad6ed76
TST(string dtype): Resolve HDF5 xfails in test_round_trip.py
rhshadrach Dec 30, 2024
2a292f2
Merge branch 'str_hdf5_put_xfails' of https://github.com/rhshadrach/p…
rhshadrach Dec 30, 2024
7db8deb
TST(string dtype): Resolve HDF5 xfails in test_round_trip.py
rhshadrach Dec 30, 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
26 changes: 21 additions & 5 deletions pandas/io/pytables.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,6 +86,7 @@
PeriodArray,
)
from pandas.core.arrays.datetimes import tz_to_dtype
from pandas.core.arrays.string_ import BaseStringArray
import pandas.core.common as com
from pandas.core.computation.pytables import (
PyTablesExpr,
Expand Down Expand Up @@ -1949,6 +1950,7 @@ def _write_to_group(
def _read_group(self, group: Node):
s = self._create_storer(group)
s.infer_axes()
print(type(s), s)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
print(type(s), s)

return s.read()

def _identify_group(self, key: str, append: bool) -> Node:
Expand Down Expand Up @@ -3185,6 +3187,8 @@ def write_array(
# both self._filters and EA

value = extract_array(obj, extract_numpy=True)
if isinstance(value, BaseStringArray):
value = value.to_numpy()

if key in self.group:
self._handle.remove_node(self.group, key)
Expand Down Expand Up @@ -3294,7 +3298,12 @@ def read(
index = self.read_index("index", start=start, stop=stop)
values = self.read_array("values", start=start, stop=stop)
result = Series(values, index=index, name=self.name, copy=False)
if using_string_dtype() and is_string_array(values, skipna=True):
if (
using_string_dtype()
and isinstance(values, np.ndarray)
and len(values) > 0
and is_string_array(values, skipna=True)
):
result = result.astype(StringDtype(na_value=np.nan))
return result

Expand Down Expand Up @@ -3363,7 +3372,12 @@ def read(

columns = items[items.get_indexer(blk_items)]
df = DataFrame(values.T, columns=columns, index=axes[1], copy=False)
if using_string_dtype() and is_string_array(values, skipna=True):
if (
using_string_dtype()
and isinstance(values, np.ndarray)
and len(df) > 0
and is_string_array(values, skipna=True)
):
df = df.astype(StringDtype(na_value=np.nan))
dfs.append(df)

Expand Down Expand Up @@ -4737,9 +4751,11 @@ def read(
df = DataFrame._from_arrays([values], columns=cols_, index=index_)
if not (using_string_dtype() and values.dtype.kind == "O"):
assert (df.dtypes == values.dtype).all(), (df.dtypes, values.dtype)
if using_string_dtype() and is_string_array(
values, # type: ignore[arg-type]
skipna=True,
if (
using_string_dtype()
and isinstance(values, np.ndarray)
and len(df) > 0
and is_string_array(values, skipna=True)
):
df = df.astype(StringDtype(na_value=np.nan))
frames.append(df)
Expand Down
43 changes: 30 additions & 13 deletions pandas/tests/io/pytables/test_put.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,8 +3,6 @@
import numpy as np
import pytest

from pandas._config import using_string_dtype

from pandas._libs.tslibs import Timestamp

import pandas as pd
Expand All @@ -26,7 +24,6 @@

pytestmark = [
pytest.mark.single_cpu,
pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False),
]


Expand Down Expand Up @@ -99,7 +96,7 @@ def test_api_default_format(tmp_path, setup_path):
assert store.get_storer("df4").is_table


def test_put(setup_path):
def test_put(setup_path, using_infer_string):
with ensure_clean_store(setup_path) as store:
ts = Series(
np.arange(10, dtype=np.float64), index=date_range("2020-01-01", periods=10)
Expand Down Expand Up @@ -133,7 +130,11 @@ def test_put(setup_path):

# overwrite table
store.put("c", df[:10], format="table", append=False)
tm.assert_frame_equal(df[:10], store["c"])
expected = df[:10]
if using_infer_string:
expected.columns = expected.columns.astype("str")
result = store["c"]
tm.assert_frame_equal(result, expected)


def test_put_string_index(setup_path):
Expand Down Expand Up @@ -162,7 +163,7 @@ def test_put_string_index(setup_path):
tm.assert_frame_equal(store["b"], df)


def test_put_compression(setup_path):
def test_put_compression(setup_path, using_infer_string):
with ensure_clean_store(setup_path) as store:
df = DataFrame(
np.random.default_rng(2).standard_normal((10, 4)),
Expand All @@ -171,7 +172,11 @@ def test_put_compression(setup_path):
)

store.put("c", df, format="table", complib="zlib")
tm.assert_frame_equal(store["c"], df)
expected = df
if using_infer_string:
expected.columns = expected.columns.astype("str")
result = store["c"]
tm.assert_frame_equal(result, expected)

# can't compress if format='fixed'
msg = "Compression not supported on Fixed format stores"
Expand All @@ -180,7 +185,7 @@ def test_put_compression(setup_path):


@td.skip_if_windows
def test_put_compression_blosc(setup_path):
def test_put_compression_blosc(setup_path, using_infer_string):
df = DataFrame(
np.random.default_rng(2).standard_normal((10, 4)),
columns=Index(list("ABCD"), dtype=object),
Expand All @@ -194,10 +199,14 @@ def test_put_compression_blosc(setup_path):
store.put("b", df, format="fixed", complib="blosc")

store.put("c", df, format="table", complib="blosc")
tm.assert_frame_equal(store["c"], df)
expected = df
if using_infer_string:
expected.columns = expected.columns.astype("str")
result = store["c"]
tm.assert_frame_equal(result, expected)


def test_put_mixed_type(setup_path, performance_warning):
def test_put_mixed_type(setup_path, performance_warning, using_infer_string):
df = DataFrame(
np.random.default_rng(2).standard_normal((10, 4)),
columns=Index(list("ABCD"), dtype=object),
Expand All @@ -223,8 +232,11 @@ def test_put_mixed_type(setup_path, performance_warning):
with tm.assert_produces_warning(performance_warning):
store.put("df", df)

expected = store.get("df")
tm.assert_frame_equal(expected, df)
expected = df
if using_infer_string:
expected.columns = expected.columns.astype("str")
result = store.get("df")
tm.assert_frame_equal(result, expected)


@pytest.mark.parametrize("format", ["table", "fixed"])
Expand Down Expand Up @@ -253,7 +265,7 @@ def test_store_index_types(setup_path, format, index):
tm.assert_frame_equal(df, store["df"])


def test_column_multiindex(setup_path):
def test_column_multiindex(setup_path, using_infer_string):
# GH 4710
# recreate multi-indexes properly

Expand All @@ -264,6 +276,11 @@ def test_column_multiindex(setup_path):
expected = df.set_axis(df.index.to_numpy())

with ensure_clean_store(setup_path) as store:
if using_infer_string:
msg = "Saving a MultiIndex with an extension dtype is not supported."
with pytest.raises(NotImplementedError, match=msg):
store.put("df", df)
return
store.put("df", df)
tm.assert_frame_equal(
store["df"], expected, check_index_type=True, check_column_type=True
Expand Down
Loading
Loading