From e6ef75004358c25a6047c075c1884aaf2f7005b8 Mon Sep 17 00:00:00 2001
From: veljanin <veljkojovanovic1991@gmail.com>
Date: Wed, 2 Oct 2024 09:56:12 +0200
Subject: [PATCH 1/6] Handling the case where converting empty categorical to
'pyarrow' dtype_backend results in error. Since conversion of non-empty
categorical returns categorical of 'numpy_nullable' dtype_backend, now,
instead of raising an error, we ensure empty categorical is returned as well.
---
pandas/core/dtypes/cast.py | 10 +++++++---
.../tests/frame/methods/test_convert_dtypes.py | 16 ++++++++++++++++
.../tests/series/methods/test_convert_dtypes.py | 13 +++++++++++++
3 files changed, 36 insertions(+), 3 deletions(-)
diff --git a/pandas/core/dtypes/cast.py b/pandas/core/dtypes/cast.py
index 6ba07b1761557..dee3452136438 100644
--- a/pandas/core/dtypes/cast.py
+++ b/pandas/core/dtypes/cast.py
@@ -1112,7 +1112,7 @@ def convert_dtypes(
else:
inferred_dtype = input_array.dtype
-
+
if dtype_backend == "pyarrow":
from pandas.core.arrays.arrow.array import to_pyarrow_type
from pandas.core.arrays.string_ import StringDtype
@@ -1145,12 +1145,16 @@ def convert_dtypes(
and isna(input_array).all()
):
import pyarrow as pa
-
+
pa_type = pa.null()
else:
pa_type = to_pyarrow_type(base_dtype)
if pa_type is not None:
- inferred_dtype = ArrowDtype(pa_type)
+ if isna(input_array).all() and hasattr(input_array, 'categories'):
+ inferred_dtype = input_array.dtype
+ else:
+ inferred_dtype = ArrowDtype(pa_type)
+
elif dtype_backend == "numpy_nullable" and isinstance(inferred_dtype, ArrowDtype):
# GH 53648
inferred_dtype = _arrow_dtype_mapping()[inferred_dtype.pyarrow_dtype]
diff --git a/pandas/tests/frame/methods/test_convert_dtypes.py b/pandas/tests/frame/methods/test_convert_dtypes.py
index e7f6e5d625d3e..29a05652b38a2 100644
--- a/pandas/tests/frame/methods/test_convert_dtypes.py
+++ b/pandas/tests/frame/methods/test_convert_dtypes.py
@@ -34,6 +34,22 @@ def test_convert_empty(self):
# Empty DataFrame can pass convert_dtypes, see GH#40393
empty_df = pd.DataFrame()
tm.assert_frame_equal(empty_df, empty_df.convert_dtypes())
+
+ def test_convert_empty_categorical_to_pyarrow(self):
+ df = pd.DataFrame(
+ {
+ "A": pd.Series(pd.Categorical([None] * 5)),
+ "B": pd.Series(pd.Categorical([None] * 5, categories=["B1", "B2"])),
+ }
+ )
+ converted = df.convert_dtypes(dtype_backend="pyarrow")
+ expected = df
+ tm.assert_frame_equal(converted, expected)
+
+ assert df.A.dtype == "category", "Dtype in column A is not 'category'"
+ assert df.B.dtype == "category", "Dtype in column B is not 'category'"
+ assert df.A.cat.categories.empty, "Categories in column A are not empty"
+ assert (df.B.cat.categories == ["B1", "B2"]).all(), "Categories in column A are not empty"
def test_convert_dtypes_retain_column_names(self):
# GH#41435
diff --git a/pandas/tests/series/methods/test_convert_dtypes.py b/pandas/tests/series/methods/test_convert_dtypes.py
index 90c4056a39e84..cc2635c35e798 100644
--- a/pandas/tests/series/methods/test_convert_dtypes.py
+++ b/pandas/tests/series/methods/test_convert_dtypes.py
@@ -297,3 +297,16 @@ def test_convert_dtypes_pyarrow_null(self):
result = ser.convert_dtypes(dtype_backend="pyarrow")
expected = pd.Series([None, None], dtype=pd.ArrowDtype(pa.null()))
tm.assert_series_equal(result, expected)
+
+ def test_convert_empty_categorical_to_pyarrow(self):
+ ser = pd.Series(pd.Series(pd.Categorical([None] * 5)))
+
+ converted = ser.convert_dtypes(dtype_backend="pyarrow")
+ expected = ser
+ tm.assert_series_equal(converted, expected)
+
+ assert ser.dtype == "category", "Series dtype is not 'category'"
+ assert ser.cat.categories.empty, "Series categories are not empty"
+
+ ser2 = pd.Series(pd.Series(pd.Categorical([None] * 5, categories=["S1", "S2"])))
+ assert (ser2.cat.categories == ["S1", "S2"]).all(), "Series categories are not empty"
From 94769a1cc1e5fc089864337dc56324d705b18376 Mon Sep 17 00:00:00 2001
From: veljanin <veljkojovanovic1991@gmail.com>
Date: Fri, 4 Oct 2024 11:48:40 +0200
Subject: [PATCH 2/6] additional revisions
---
doc/source/whatsnew/v3.0.0.rst | 2 +-
pandas/core/dtypes/cast.py | 7 +++--
.../frame/methods/test_convert_dtypes.py | 23 +++++++++------
.../series/methods/test_convert_dtypes.py | 29 +++++++++++--------
4 files changed, 36 insertions(+), 25 deletions(-)
diff --git a/doc/source/whatsnew/v3.0.0.rst b/doc/source/whatsnew/v3.0.0.rst
index a5b4560a47bc4..d6dde366506c2 100644
--- a/doc/source/whatsnew/v3.0.0.rst
+++ b/doc/source/whatsnew/v3.0.0.rst
@@ -544,7 +544,7 @@ Bug fixes
Categorical
^^^^^^^^^^^
--
+- Bug in :func:`convert_dtypes` with ``dtype_backend='pyarrow'`` parameter where empty categorical series raise error or get converted to null[pyarrow] (:issue:`59934`)
-
Datetimelike
diff --git a/pandas/core/dtypes/cast.py b/pandas/core/dtypes/cast.py
index dee3452136438..c7272a517497c 100644
--- a/pandas/core/dtypes/cast.py
+++ b/pandas/core/dtypes/cast.py
@@ -1112,7 +1112,7 @@ def convert_dtypes(
else:
inferred_dtype = input_array.dtype
-
+
if dtype_backend == "pyarrow":
from pandas.core.arrays.arrow.array import to_pyarrow_type
from pandas.core.arrays.string_ import StringDtype
@@ -1143,14 +1143,15 @@ def convert_dtypes(
base_dtype.kind == "O" # type: ignore[union-attr]
and input_array.size > 0
and isna(input_array).all()
+ and not isinstance(input_array.dtype, CategoricalDtype)
):
import pyarrow as pa
-
+
pa_type = pa.null()
else:
pa_type = to_pyarrow_type(base_dtype)
if pa_type is not None:
- if isna(input_array).all() and hasattr(input_array, 'categories'):
+ if isna(input_array).all() and hasattr(input_array, "categories"):
inferred_dtype = input_array.dtype
else:
inferred_dtype = ArrowDtype(pa_type)
diff --git a/pandas/tests/frame/methods/test_convert_dtypes.py b/pandas/tests/frame/methods/test_convert_dtypes.py
index 29a05652b38a2..5a0010d06a951 100644
--- a/pandas/tests/frame/methods/test_convert_dtypes.py
+++ b/pandas/tests/frame/methods/test_convert_dtypes.py
@@ -34,22 +34,27 @@ def test_convert_empty(self):
# Empty DataFrame can pass convert_dtypes, see GH#40393
empty_df = pd.DataFrame()
tm.assert_frame_equal(empty_df, empty_df.convert_dtypes())
-
+
def test_convert_empty_categorical_to_pyarrow(self):
+ # GH#59934
df = pd.DataFrame(
{
- "A": pd.Series(pd.Categorical([None] * 5)),
- "B": pd.Series(pd.Categorical([None] * 5, categories=["B1", "B2"])),
- }
+ "A": pd.Categorical([None] * 5),
+ "B": pd.Categorical([None] * 5, categories=["B1", "B2"]),
+ }
)
converted = df.convert_dtypes(dtype_backend="pyarrow")
expected = df
tm.assert_frame_equal(converted, expected)
-
- assert df.A.dtype == "category", "Dtype in column A is not 'category'"
- assert df.B.dtype == "category", "Dtype in column B is not 'category'"
- assert df.A.cat.categories.empty, "Categories in column A are not empty"
- assert (df.B.cat.categories == ["B1", "B2"]).all(), "Categories in column A are not empty"
+
+ assert converted.A.dtype == "category", "Dtype in column A is not 'category'"
+ assert converted.B.dtype == "category", "Dtype in column B is not 'category'"
+ assert converted.A.cat.categories.empty, "Categories in column A are not empty"
+ assert converted.B.cat.categories.__contains__(
+ "B1"
+ ) and converted.B.cat.categories.__contains__(
+ "B2"
+ ), "Categories in column B doesn't contain adequate categories"
def test_convert_dtypes_retain_column_names(self):
# GH#41435
diff --git a/pandas/tests/series/methods/test_convert_dtypes.py b/pandas/tests/series/methods/test_convert_dtypes.py
index cc2635c35e798..22d4ec6d7906a 100644
--- a/pandas/tests/series/methods/test_convert_dtypes.py
+++ b/pandas/tests/series/methods/test_convert_dtypes.py
@@ -297,16 +297,21 @@ def test_convert_dtypes_pyarrow_null(self):
result = ser.convert_dtypes(dtype_backend="pyarrow")
expected = pd.Series([None, None], dtype=pd.ArrowDtype(pa.null()))
tm.assert_series_equal(result, expected)
-
+
def test_convert_empty_categorical_to_pyarrow(self):
- ser = pd.Series(pd.Series(pd.Categorical([None] * 5)))
-
- converted = ser.convert_dtypes(dtype_backend="pyarrow")
- expected = ser
- tm.assert_series_equal(converted, expected)
-
- assert ser.dtype == "category", "Series dtype is not 'category'"
- assert ser.cat.categories.empty, "Series categories are not empty"
-
- ser2 = pd.Series(pd.Series(pd.Categorical([None] * 5, categories=["S1", "S2"])))
- assert (ser2.cat.categories == ["S1", "S2"]).all(), "Series categories are not empty"
+ # GH#59934
+ ser1 = pd.Series(pd.Categorical([None] * 5))
+ converted1 = ser1.convert_dtypes(dtype_backend="pyarrow")
+ expected = ser1
+
+ tm.assert_series_equal(converted1, expected)
+ assert converted1.dtype == "category", "Series dtype is not 'category'"
+ assert converted1.cat.categories.empty, "Series categories are not empty"
+
+ ser2 = pd.Series(pd.Categorical([None] * 5, categories=["S1", "S2"]))
+ converted2 = ser2.convert_dtypes(dtype_backend="pyarrow")
+ assert converted2.cat.categories.__contains__(
+ "S1"
+ ) and converted2.cat.categories.__contains__(
+ "S2"
+ ), "Categories in ser2 doesn't contain adequate categories"
From 8e879da17e8f97322e945755586c081fb8521c28 Mon Sep 17 00:00:00 2001
From: veljanin <veljkojovanovic1991@gmail.com>
Date: Fri, 4 Oct 2024 11:53:11 +0200
Subject: [PATCH 3/6] removing the change for input_array...
---
pandas/core/dtypes/cast.py | 5 +----
1 file changed, 1 insertion(+), 4 deletions(-)
diff --git a/pandas/core/dtypes/cast.py b/pandas/core/dtypes/cast.py
index c7272a517497c..597f76510618a 100644
--- a/pandas/core/dtypes/cast.py
+++ b/pandas/core/dtypes/cast.py
@@ -1151,10 +1151,7 @@ def convert_dtypes(
else:
pa_type = to_pyarrow_type(base_dtype)
if pa_type is not None:
- if isna(input_array).all() and hasattr(input_array, "categories"):
- inferred_dtype = input_array.dtype
- else:
- inferred_dtype = ArrowDtype(pa_type)
+ inferred_dtype = ArrowDtype(pa_type)
elif dtype_backend == "numpy_nullable" and isinstance(inferred_dtype, ArrowDtype):
# GH 53648
From a5b388263b4cc39fadd37c05c0e832d53a2857bc Mon Sep 17 00:00:00 2001
From: veljanin <veljkojovanovic1991@gmail.com>
Date: Mon, 7 Oct 2024 08:20:04 +0200
Subject: [PATCH 4/6] reverting newline in Series.convert_dtypes and precising
respective docs in whatsnew
---
doc/source/whatsnew/v3.0.0.rst | 2 +-
pandas/core/dtypes/cast.py | 1 -
2 files changed, 1 insertion(+), 2 deletions(-)
diff --git a/doc/source/whatsnew/v3.0.0.rst b/doc/source/whatsnew/v3.0.0.rst
index d6dde366506c2..3c707d7931c97 100644
--- a/doc/source/whatsnew/v3.0.0.rst
+++ b/doc/source/whatsnew/v3.0.0.rst
@@ -544,7 +544,7 @@ Bug fixes
Categorical
^^^^^^^^^^^
-- Bug in :func:`convert_dtypes` with ``dtype_backend='pyarrow'`` parameter where empty categorical series raise error or get converted to null[pyarrow] (:issue:`59934`)
+- Bug in :meth:`Series.convert_dtypes` with ``dtype_backend='pyarrow'`` parameter where empty categorical series raise error or get converted to null[pyarrow] (:issue:`59934`)
-
Datetimelike
diff --git a/pandas/core/dtypes/cast.py b/pandas/core/dtypes/cast.py
index 597f76510618a..1255c5a557d27 100644
--- a/pandas/core/dtypes/cast.py
+++ b/pandas/core/dtypes/cast.py
@@ -1152,7 +1152,6 @@ def convert_dtypes(
pa_type = to_pyarrow_type(base_dtype)
if pa_type is not None:
inferred_dtype = ArrowDtype(pa_type)
-
elif dtype_backend == "numpy_nullable" and isinstance(inferred_dtype, ArrowDtype):
# GH 53648
inferred_dtype = _arrow_dtype_mapping()[inferred_dtype.pyarrow_dtype]
From c1ed1f0e5a1cb9e6e01409f27adfd6566e754391 Mon Sep 17 00:00:00 2001
From: veljanin <veljkojovanovic1991@gmail.com>
Date: Wed, 9 Oct 2024 12:10:29 +0200
Subject: [PATCH 5/6] resolved conflicts and updated main with latest changes
---
.github/workflows/package-checks.yml | 2 +-
.github/workflows/wheels.yml | 2 +-
.pre-commit-config.yaml | 10 +-
ci/code_checks.sh | 30 -
doc/source/user_guide/style.ipynb | 689 ++++++++++--------
doc/source/whatsnew/v3.0.0.rst | 2 +-
pandas/_libs/lib.pyx | 14 +
pandas/_libs/tslibs/nattype.pyi | 45 +-
pandas/_testing/asserters.py | 10 +
pandas/core/accessor.py | 7 +-
pandas/core/apply.py | 14 +-
pandas/core/arrays/categorical.py | 14 +-
pandas/core/arrays/datetimes.py | 8 +
pandas/core/arrays/sparse/accessor.py | 20 +-
pandas/core/arrays/string_.py | 2 +-
pandas/core/frame.py | 10 +-
pandas/core/groupby/generic.py | 28 +-
pandas/core/groupby/groupby.py | 4 +-
pandas/core/groupby/ops.py | 39 +-
pandas/core/indexes/period.py | 8 +
pandas/core/reshape/encoding.py | 3 +-
pandas/core/tools/numeric.py | 6 +
pandas/errors/__init__.py | 5 +
pandas/io/formats/html.py | 2 +
pandas/io/formats/style.py | 3 +-
pandas/io/formats/style_render.py | 24 +-
pandas/io/stata.py | 20 +
pandas/plotting/_misc.py | 17 +-
pandas/tests/apply/test_frame_apply.py | 3 +-
pandas/tests/apply/test_series_apply.py | 6 +-
pandas/tests/arrays/sparse/test_accessor.py | 4 +
.../tests/frame/methods/test_value_counts.py | 4 +-
.../groupby/methods/test_value_counts.py | 86 ++-
pandas/tests/indexes/test_old_base.py | 2 +-
pandas/tests/io/formats/style/test_style.py | 13 +-
pandas/tests/io/formats/test_format.py | 19 +-
pandas/tests/tools/test_to_numeric.py | 15 +
pandas/util/version/__init__.py | 8 +
pyproject.toml | 9 +-
39 files changed, 746 insertions(+), 461 deletions(-)
diff --git a/.github/workflows/package-checks.yml b/.github/workflows/package-checks.yml
index 6748832903e30..331af6e05b650 100644
--- a/.github/workflows/package-checks.yml
+++ b/.github/workflows/package-checks.yml
@@ -67,7 +67,7 @@ jobs:
fetch-depth: 0
- name: Set up Python
- uses: mamba-org/setup-micromamba@v1
+ uses: mamba-org/setup-micromamba@v2
with:
environment-name: recipe-test
create-args: >-
diff --git a/.github/workflows/wheels.yml b/.github/workflows/wheels.yml
index 2aaec8c9b56b0..de59a454c827c 100644
--- a/.github/workflows/wheels.yml
+++ b/.github/workflows/wheels.yml
@@ -165,7 +165,7 @@ jobs:
CIBW_PLATFORM: ${{ matrix.buildplat[1] == 'pyodide_wasm32' && 'pyodide' || 'auto' }}
- name: Set up Python
- uses: mamba-org/setup-micromamba@v1
+ uses: mamba-org/setup-micromamba@v2
with:
environment-name: wheel-env
# Use a fixed Python, since we might have an unreleased Python not
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index f6717dd503c9b..7c9ebf7d94173 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -19,7 +19,7 @@ ci:
skip: [pyright, mypy]
repos:
- repo: https://github.com/astral-sh/ruff-pre-commit
- rev: v0.5.0
+ rev: v0.6.9
hooks:
- id: ruff
args: [--exit-non-zero-on-fix]
@@ -34,7 +34,7 @@ repos:
- id: ruff-format
exclude: ^scripts|^pandas/tests/frame/test_query_eval.py
- repo: https://github.com/jendrikseipp/vulture
- rev: 'v2.11'
+ rev: 'v2.13'
hooks:
- id: vulture
entry: python scripts/run_vulture.py
@@ -52,7 +52,7 @@ repos:
- id: cython-lint
- id: double-quote-cython-strings
- repo: https://github.com/pre-commit/pre-commit-hooks
- rev: v4.6.0
+ rev: v5.0.0
hooks:
- id: check-case-conflict
- id: check-toml
@@ -90,12 +90,12 @@ repos:
types: [text] # overwrite types: [rst]
types_or: [python, rst]
- repo: https://github.com/sphinx-contrib/sphinx-lint
- rev: v0.9.1
+ rev: v1.0.0
hooks:
- id: sphinx-lint
args: ["--enable", "all", "--disable", "line-too-long"]
- repo: https://github.com/pre-commit/mirrors-clang-format
- rev: v18.1.8
+ rev: v19.1.1
hooks:
- id: clang-format
files: ^pandas/_libs/src|^pandas/_libs/include
diff --git a/ci/code_checks.sh b/ci/code_checks.sh
index 4a1a0042405e3..6fb675069e81d 100755
--- a/ci/code_checks.sh
+++ b/ci/code_checks.sh
@@ -73,30 +73,9 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
-i "pandas.Period.freq GL08" \
-i "pandas.Period.ordinal GL08" \
-i "pandas.RangeIndex.from_range PR01,SA01" \
- -i "pandas.Series.cat.add_categories PR01,PR02" \
- -i "pandas.Series.cat.as_ordered PR01" \
- -i "pandas.Series.cat.as_unordered PR01" \
- -i "pandas.Series.cat.remove_categories PR01,PR02" \
- -i "pandas.Series.cat.remove_unused_categories PR01" \
- -i "pandas.Series.cat.rename_categories PR01,PR02" \
- -i "pandas.Series.cat.reorder_categories PR01,PR02" \
- -i "pandas.Series.cat.set_categories PR01,PR02" \
- -i "pandas.Series.dt.as_unit PR01,PR02" \
- -i "pandas.Series.dt.ceil PR01,PR02" \
- -i "pandas.Series.dt.day_name PR01,PR02" \
- -i "pandas.Series.dt.floor PR01,PR02" \
-i "pandas.Series.dt.freq GL08" \
- -i "pandas.Series.dt.month_name PR01,PR02" \
- -i "pandas.Series.dt.normalize PR01" \
- -i "pandas.Series.dt.round PR01,PR02" \
- -i "pandas.Series.dt.strftime PR01,PR02" \
- -i "pandas.Series.dt.to_period PR01,PR02" \
- -i "pandas.Series.dt.total_seconds PR01" \
- -i "pandas.Series.dt.tz_convert PR01,PR02" \
- -i "pandas.Series.dt.tz_localize PR01,PR02" \
-i "pandas.Series.dt.unit GL08" \
-i "pandas.Series.pad PR01,SA01" \
- -i "pandas.Series.sparse.from_coo PR07,SA01" \
-i "pandas.Timedelta.max PR02" \
-i "pandas.Timedelta.min PR02" \
-i "pandas.Timedelta.resolution PR02" \
@@ -106,13 +85,11 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
-i "pandas.Timestamp.resolution PR02" \
-i "pandas.Timestamp.tzinfo GL08" \
-i "pandas.Timestamp.year GL08" \
- -i "pandas.api.types.is_float PR01,SA01" \
-i "pandas.api.types.is_integer PR01,SA01" \
-i "pandas.api.types.is_iterator PR07,SA01" \
-i "pandas.api.types.is_re_compilable PR07,SA01" \
-i "pandas.api.types.pandas_dtype PR07,RT03,SA01" \
-i "pandas.arrays.ArrowExtensionArray PR07,SA01" \
- -i "pandas.arrays.DatetimeArray SA01" \
-i "pandas.arrays.IntegerArray SA01" \
-i "pandas.arrays.IntervalArray.left SA01" \
-i "pandas.arrays.IntervalArray.length SA01" \
@@ -163,7 +140,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
-i "pandas.errors.DuplicateLabelError SA01" \
-i "pandas.errors.IntCastingNaNError SA01" \
-i "pandas.errors.InvalidIndexError SA01" \
- -i "pandas.errors.InvalidVersion SA01" \
-i "pandas.errors.NullFrequencyError SA01" \
-i "pandas.errors.NumExprClobberingError SA01" \
-i "pandas.errors.NumbaUtilError SA01" \
@@ -172,24 +148,18 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
-i "pandas.errors.PerformanceWarning SA01" \
-i "pandas.errors.PossibleDataLossError SA01" \
-i "pandas.errors.PossiblePrecisionLoss SA01" \
- -i "pandas.errors.SpecificationError SA01" \
-i "pandas.errors.UndefinedVariableError PR01,SA01" \
-i "pandas.errors.UnsortedIndexError SA01" \
-i "pandas.errors.UnsupportedFunctionCall SA01" \
-i "pandas.errors.ValueLabelTypeMismatch SA01" \
-i "pandas.infer_freq SA01" \
-i "pandas.io.json.build_table_schema PR07,RT03,SA01" \
- -i "pandas.io.stata.StataReader.data_label SA01" \
- -i "pandas.io.stata.StataReader.value_labels RT03,SA01" \
-i "pandas.io.stata.StataReader.variable_labels RT03,SA01" \
-i "pandas.io.stata.StataWriter.write_file SA01" \
-i "pandas.json_normalize RT03,SA01" \
- -i "pandas.period_range RT03,SA01" \
-i "pandas.plotting.andrews_curves RT03,SA01" \
- -i "pandas.plotting.lag_plot RT03,SA01" \
-i "pandas.plotting.scatter_matrix PR07,SA01" \
-i "pandas.set_eng_float_format RT03,SA01" \
- -i "pandas.testing.assert_extension_array_equal SA01" \
-i "pandas.tseries.offsets.BDay PR02,SA01" \
-i "pandas.tseries.offsets.BQuarterBegin.is_on_offset GL08" \
-i "pandas.tseries.offsets.BQuarterBegin.n GL08" \
diff --git a/doc/source/user_guide/style.ipynb b/doc/source/user_guide/style.ipynb
index daecfce6ecebc..abb7181fc8d72 100644
--- a/doc/source/user_guide/style.ipynb
+++ b/doc/source/user_guide/style.ipynb
@@ -38,19 +38,6 @@
"[concatfunc]: ../reference/api/pandas.io.formats.style.Styler.concat.rst"
]
},
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "nbsphinx": "hidden"
- },
- "outputs": [],
- "source": [
- "import matplotlib.pyplot\n",
- "# We have this here to trigger matplotlib's font cache stuff.\n",
- "# This cell is hidden from the output"
- ]
- },
{
"cell_type": "markdown",
"metadata": {},
@@ -78,17 +65,13 @@
"source": [
"import pandas as pd\n",
"import numpy as np\n",
- "import matplotlib as mpl\n",
"\n",
- "df = pd.DataFrame({\n",
- " \"strings\": [\"Adam\", \"Mike\"],\n",
- " \"ints\": [1, 3],\n",
- " \"floats\": [1.123, 1000.23]\n",
- "})\n",
- "df.style \\\n",
- " .format(precision=3, thousands=\".\", decimal=\",\") \\\n",
- " .format_index(str.upper, axis=1) \\\n",
- " .relabel_index([\"row 1\", \"row 2\"], axis=0)"
+ "df = pd.DataFrame(\n",
+ " {\"strings\": [\"Adam\", \"Mike\"], \"ints\": [1, 3], \"floats\": [1.123, 1000.23]}\n",
+ ")\n",
+ "df.style.format(precision=3, thousands=\".\", decimal=\",\").format_index(\n",
+ " str.upper, axis=1\n",
+ ").relabel_index([\"row 1\", \"row 2\"], axis=0)"
]
},
{
@@ -104,17 +87,21 @@
"metadata": {},
"outputs": [],
"source": [
- "weather_df = pd.DataFrame(np.random.rand(10,2)*5, \n",
- " index=pd.date_range(start=\"2021-01-01\", periods=10),\n",
- " columns=[\"Tokyo\", \"Beijing\"])\n",
+ "weather_df = pd.DataFrame(\n",
+ " np.random.default_rng().random((10, 2)) * 5,\n",
+ " index=pd.date_range(start=\"2021-01-01\", periods=10),\n",
+ " columns=[\"Tokyo\", \"Beijing\"],\n",
+ ")\n",
+ "\n",
"\n",
- "def rain_condition(v): \n",
+ "def rain_condition(v):\n",
" if v < 1.75:\n",
" return \"Dry\"\n",
" elif v < 2.75:\n",
" return \"Rain\"\n",
" return \"Heavy Rain\"\n",
"\n",
+ "\n",
"def make_pretty(styler):\n",
" styler.set_caption(\"Weather Conditions\")\n",
" styler.format(rain_condition)\n",
@@ -122,6 +109,7 @@
" styler.background_gradient(axis=None, vmin=1, vmax=5, cmap=\"YlGnBu\")\n",
" return styler\n",
"\n",
+ "\n",
"weather_df"
]
},
@@ -157,10 +145,8 @@
"metadata": {},
"outputs": [],
"source": [
- "df = pd.DataFrame(np.random.randn(5, 5))\n",
- "df.style \\\n",
- " .hide(subset=[0, 2, 4], axis=0) \\\n",
- " .hide(subset=[0, 2, 4], axis=1)"
+ "df = pd.DataFrame(np.random.default_rng().standard_normal((5, 5)))\n",
+ "df.style.hide(subset=[0, 2, 4], axis=0).hide(subset=[0, 2, 4], axis=1)"
]
},
{
@@ -177,9 +163,9 @@
"outputs": [],
"source": [
"show = [0, 2, 4]\n",
- "df.style \\\n",
- " .hide([row for row in df.index if row not in show], axis=0) \\\n",
- " .hide([col for col in df.columns if col not in show], axis=1)"
+ "df.style.hide([row for row in df.index if row not in show], axis=0).hide(\n",
+ " [col for col in df.columns if col not in show], axis=1\n",
+ ")"
]
},
{
@@ -199,9 +185,9 @@
"metadata": {},
"outputs": [],
"source": [
- "summary_styler = df.agg([\"sum\", \"mean\"]).style \\\n",
- " .format(precision=3) \\\n",
- " .relabel_index([\"Sum\", \"Average\"])\n",
+ "summary_styler = (\n",
+ " df.agg([\"sum\", \"mean\"]).style.format(precision=3).relabel_index([\"Sum\", \"Average\"])\n",
+ ")\n",
"df.style.format(precision=1).concat(summary_styler)"
]
},
@@ -227,9 +213,16 @@
"metadata": {},
"outputs": [],
"source": [
- "df = pd.DataFrame([[38.0, 2.0, 18.0, 22.0, 21, np.nan],[19, 439, 6, 452, 226,232]], \n",
- " index=pd.Index(['Tumour (Positive)', 'Non-Tumour (Negative)'], name='Actual Label:'), \n",
- " columns=pd.MultiIndex.from_product([['Decision Tree', 'Regression', 'Random'],['Tumour', 'Non-Tumour']], names=['Model:', 'Predicted:']))\n",
+ "idx = pd.Index([\"Tumour (Positive)\", \"Non-Tumour (Negative)\"], name=\"Actual Label:\")\n",
+ "cols = pd.MultiIndex.from_product(\n",
+ " [[\"Decision Tree\", \"Regression\", \"Random\"], [\"Tumour\", \"Non-Tumour\"]],\n",
+ " names=[\"Model:\", \"Predicted:\"],\n",
+ ")\n",
+ "df = pd.DataFrame(\n",
+ " [[38.0, 2.0, 18.0, 22.0, 21, np.nan], [19, 439, 6, 452, 226, 232]],\n",
+ " index=idx,\n",
+ " columns=cols,\n",
+ ")\n",
"df.style"
]
},
@@ -242,63 +235,68 @@
"outputs": [],
"source": [
"# Hidden cell to just create the below example: code is covered throughout the guide.\n",
- "s = df.style\\\n",
- " .hide([('Random', 'Tumour'), ('Random', 'Non-Tumour')], axis='columns')\\\n",
- " .format('{:.0f}')\\\n",
- " .set_table_styles([{\n",
- " 'selector': '',\n",
- " 'props': 'border-collapse: separate;'\n",
- " },{\n",
- " 'selector': 'caption',\n",
- " 'props': 'caption-side: bottom; font-size:1.3em;'\n",
- " },{\n",
- " 'selector': '.index_name',\n",
- " 'props': 'font-style: italic; color: darkgrey; font-weight:normal;'\n",
- " },{\n",
- " 'selector': 'th:not(.index_name)',\n",
- " 'props': 'background-color: #000066; color: white;'\n",
- " },{\n",
- " 'selector': 'th.col_heading',\n",
- " 'props': 'text-align: center;'\n",
- " },{\n",
- " 'selector': 'th.col_heading.level0',\n",
- " 'props': 'font-size: 1.5em;'\n",
- " },{\n",
- " 'selector': 'th.col2',\n",
- " 'props': 'border-left: 1px solid white;'\n",
- " },{\n",
- " 'selector': '.col2',\n",
- " 'props': 'border-left: 1px solid #000066;'\n",
- " },{\n",
- " 'selector': 'td',\n",
- " 'props': 'text-align: center; font-weight:bold;'\n",
- " },{\n",
- " 'selector': '.true',\n",
- " 'props': 'background-color: #e6ffe6;'\n",
- " },{\n",
- " 'selector': '.false',\n",
- " 'props': 'background-color: #ffe6e6;'\n",
- " },{\n",
- " 'selector': '.border-red',\n",
- " 'props': 'border: 2px dashed red;'\n",
- " },{\n",
- " 'selector': '.border-green',\n",
- " 'props': 'border: 2px dashed green;'\n",
- " },{\n",
- " 'selector': 'td:hover',\n",
- " 'props': 'background-color: #ffffb3;'\n",
- " }])\\\n",
- " .set_td_classes(pd.DataFrame([['true border-green', 'false', 'true', 'false border-red', '', ''],\n",
- " ['false', 'true', 'false', 'true', '', '']], \n",
- " index=df.index, columns=df.columns))\\\n",
- " .set_caption(\"Confusion matrix for multiple cancer prediction models.\")\\\n",
- " .set_tooltips(pd.DataFrame([['This model has a very strong true positive rate', '', '', \"This model's total number of false negatives is too high\", '', ''],\n",
- " ['', '', '', '', '', '']], \n",
- " index=df.index, columns=df.columns),\n",
- " css_class='pd-tt', props=\n",
- " 'visibility: hidden; position: absolute; z-index: 1; border: 1px solid #000066;'\n",
- " 'background-color: white; color: #000066; font-size: 0.8em;' \n",
- " 'transform: translate(0px, -24px); padding: 0.6em; border-radius: 0.5em;')\n"
+ "s = (\n",
+ " df.style.hide([(\"Random\", \"Tumour\"), (\"Random\", \"Non-Tumour\")], axis=\"columns\")\n",
+ " .format(\"{:.0f}\")\n",
+ " .set_table_styles(\n",
+ " [\n",
+ " {\"selector\": \"\", \"props\": \"border-collapse: separate;\"},\n",
+ " {\"selector\": \"caption\", \"props\": \"caption-side: bottom; font-size:1.3em;\"},\n",
+ " {\n",
+ " \"selector\": \".index_name\",\n",
+ " \"props\": \"font-style: italic; color: darkgrey; font-weight:normal;\",\n",
+ " },\n",
+ " {\n",
+ " \"selector\": \"th:not(.index_name)\",\n",
+ " \"props\": \"background-color: #000066; color: white;\",\n",
+ " },\n",
+ " {\"selector\": \"th.col_heading\", \"props\": \"text-align: center;\"},\n",
+ " {\"selector\": \"th.col_heading.level0\", \"props\": \"font-size: 1.5em;\"},\n",
+ " {\"selector\": \"th.col2\", \"props\": \"border-left: 1px solid white;\"},\n",
+ " {\"selector\": \".col2\", \"props\": \"border-left: 1px solid #000066;\"},\n",
+ " {\"selector\": \"td\", \"props\": \"text-align: center; font-weight:bold;\"},\n",
+ " {\"selector\": \".true\", \"props\": \"background-color: #e6ffe6;\"},\n",
+ " {\"selector\": \".false\", \"props\": \"background-color: #ffe6e6;\"},\n",
+ " {\"selector\": \".border-red\", \"props\": \"border: 2px dashed red;\"},\n",
+ " {\"selector\": \".border-green\", \"props\": \"border: 2px dashed green;\"},\n",
+ " {\"selector\": \"td:hover\", \"props\": \"background-color: #ffffb3;\"},\n",
+ " ]\n",
+ " )\n",
+ " .set_td_classes(\n",
+ " pd.DataFrame(\n",
+ " [\n",
+ " [\"true border-green\", \"false\", \"true\", \"false border-red\", \"\", \"\"],\n",
+ " [\"false\", \"true\", \"false\", \"true\", \"\", \"\"],\n",
+ " ],\n",
+ " index=df.index,\n",
+ " columns=df.columns,\n",
+ " )\n",
+ " )\n",
+ " .set_caption(\"Confusion matrix for multiple cancer prediction models.\")\n",
+ " .set_tooltips(\n",
+ " pd.DataFrame(\n",
+ " [\n",
+ " [\n",
+ " \"This model has a very strong true positive rate\",\n",
+ " \"\",\n",
+ " \"\",\n",
+ " \"This model's total number of false negatives is too high\",\n",
+ " \"\",\n",
+ " \"\",\n",
+ " ],\n",
+ " [\"\", \"\", \"\", \"\", \"\", \"\"],\n",
+ " ],\n",
+ " index=df.index,\n",
+ " columns=df.columns,\n",
+ " ),\n",
+ " css_class=\"pd-tt\",\n",
+ " props=\"visibility: hidden; \"\n",
+ " \"position: absolute; z-index: 1; \"\n",
+ " \"border: 1px solid #000066;\"\n",
+ " \"background-color: white; color: #000066; font-size: 0.8em;\"\n",
+ " \"transform: translate(0px, -24px); padding: 0.6em; border-radius: 0.5em;\",\n",
+ " )\n",
+ ")"
]
},
{
@@ -325,7 +323,9 @@
"metadata": {},
"outputs": [],
"source": [
- "s = df.style.format('{:.0f}').hide([('Random', 'Tumour'), ('Random', 'Non-Tumour')], axis=\"columns\")\n",
+ "s = df.style.format(\"{:.0f}\").hide(\n",
+ " [(\"Random\", \"Tumour\"), (\"Random\", \"Non-Tumour\")], axis=\"columns\"\n",
+ ")\n",
"s"
]
},
@@ -337,8 +337,8 @@
},
"outputs": [],
"source": [
- "# Hidden cell to avoid CSS clashes and latter code upcoding previous formatting \n",
- "s.set_uuid('after_hide')"
+ "# Hidden cell to avoid CSS clashes and latter code upcoding previous formatting\n",
+ "s.set_uuid(\"after_hide\")"
]
},
{
@@ -395,16 +395,16 @@
"outputs": [],
"source": [
"cell_hover = { # for row hover use <tr> instead of <td>\n",
- " 'selector': 'td:hover',\n",
- " 'props': [('background-color', '#ffffb3')]\n",
+ " \"selector\": \"td:hover\",\n",
+ " \"props\": [(\"background-color\", \"#ffffb3\")],\n",
"}\n",
"index_names = {\n",
- " 'selector': '.index_name',\n",
- " 'props': 'font-style: italic; color: darkgrey; font-weight:normal;'\n",
+ " \"selector\": \".index_name\",\n",
+ " \"props\": \"font-style: italic; color: darkgrey; font-weight:normal;\",\n",
"}\n",
"headers = {\n",
- " 'selector': 'th:not(.index_name)',\n",
- " 'props': 'background-color: #000066; color: white;'\n",
+ " \"selector\": \"th:not(.index_name)\",\n",
+ " \"props\": \"background-color: #000066; color: white;\",\n",
"}\n",
"s.set_table_styles([cell_hover, index_names, headers])"
]
@@ -417,8 +417,8 @@
},
"outputs": [],
"source": [
- "# Hidden cell to avoid CSS clashes and latter code upcoding previous formatting \n",
- "s.set_uuid('after_tab_styles1')"
+ "# Hidden cell to avoid CSS clashes and latter code upcoding previous formatting\n",
+ "s.set_uuid(\"after_tab_styles1\")"
]
},
{
@@ -434,11 +434,14 @@
"metadata": {},
"outputs": [],
"source": [
- "s.set_table_styles([\n",
- " {'selector': 'th.col_heading', 'props': 'text-align: center;'},\n",
- " {'selector': 'th.col_heading.level0', 'props': 'font-size: 1.5em;'},\n",
- " {'selector': 'td', 'props': 'text-align: center; font-weight: bold;'},\n",
- "], overwrite=False)"
+ "s.set_table_styles(\n",
+ " [\n",
+ " {\"selector\": \"th.col_heading\", \"props\": \"text-align: center;\"},\n",
+ " {\"selector\": \"th.col_heading.level0\", \"props\": \"font-size: 1.5em;\"},\n",
+ " {\"selector\": \"td\", \"props\": \"text-align: center; font-weight: bold;\"},\n",
+ " ],\n",
+ " overwrite=False,\n",
+ ")"
]
},
{
@@ -449,8 +452,8 @@
},
"outputs": [],
"source": [
- "# Hidden cell to avoid CSS clashes and latter code upcoding previous formatting \n",
- "s.set_uuid('after_tab_styles2')"
+ "# Hidden cell to avoid CSS clashes and latter code upcoding previous formatting\n",
+ "s.set_uuid(\"after_tab_styles2\")"
]
},
{
@@ -468,10 +471,16 @@
"metadata": {},
"outputs": [],
"source": [
- "s.set_table_styles({\n",
- " ('Regression', 'Tumour'): [{'selector': 'th', 'props': 'border-left: 1px solid white'},\n",
- " {'selector': 'td', 'props': 'border-left: 1px solid #000066'}]\n",
- "}, overwrite=False, axis=0)"
+ "s.set_table_styles(\n",
+ " {\n",
+ " (\"Regression\", \"Tumour\"): [\n",
+ " {\"selector\": \"th\", \"props\": \"border-left: 1px solid white\"},\n",
+ " {\"selector\": \"td\", \"props\": \"border-left: 1px solid #000066\"},\n",
+ " ]\n",
+ " },\n",
+ " overwrite=False,\n",
+ " axis=0,\n",
+ ")"
]
},
{
@@ -482,8 +491,8 @@
},
"outputs": [],
"source": [
- "# Hidden cell to avoid CSS clashes and latter code upcoding previous formatting \n",
- "s.set_uuid('xyz01')"
+ "# Hidden cell to avoid CSS clashes and latter code upcoding previous formatting\n",
+ "s.set_uuid(\"xyz01\")"
]
},
{
@@ -508,7 +517,7 @@
"outputs": [],
"source": [
"out = s.set_table_attributes('class=\"my-table-cls\"').to_html()\n",
- "print(out[out.find('<table'):][:109])"
+ "print(out[out.find(\"<table\") :][:109])"
]
},
{
@@ -531,14 +540,18 @@
"metadata": {},
"outputs": [],
"source": [
- "s.set_table_styles([ # create internal CSS classes\n",
- " {'selector': '.true', 'props': 'background-color: #e6ffe6;'},\n",
- " {'selector': '.false', 'props': 'background-color: #ffe6e6;'},\n",
- "], overwrite=False)\n",
- "cell_color = pd.DataFrame([['true ', 'false ', 'true ', 'false '], \n",
- " ['false ', 'true ', 'false ', 'true ']], \n",
- " index=df.index, \n",
- " columns=df.columns[:4])\n",
+ "s.set_table_styles(\n",
+ " [ # create internal CSS classes\n",
+ " {\"selector\": \".true\", \"props\": \"background-color: #e6ffe6;\"},\n",
+ " {\"selector\": \".false\", \"props\": \"background-color: #ffe6e6;\"},\n",
+ " ],\n",
+ " overwrite=False,\n",
+ ")\n",
+ "cell_color = pd.DataFrame(\n",
+ " [[\"true \", \"false \", \"true \", \"false \"], [\"false \", \"true \", \"false \", \"true \"]],\n",
+ " index=df.index,\n",
+ " columns=df.columns[:4],\n",
+ ")\n",
"s.set_td_classes(cell_color)"
]
},
@@ -550,8 +563,8 @@
},
"outputs": [],
"source": [
- "# Hidden cell to avoid CSS clashes and latter code upcoding previous formatting \n",
- "s.set_uuid('after_classes')"
+ "# Hidden cell to avoid CSS clashes and latter code upcoding previous formatting\n",
+ "s.set_uuid(\"after_classes\")"
]
},
{
@@ -579,8 +592,9 @@
"metadata": {},
"outputs": [],
"source": [
- "np.random.seed(0)\n",
- "df2 = pd.DataFrame(np.random.randn(10,4), columns=['A','B','C','D'])\n",
+ "df2 = pd.DataFrame(\n",
+ " np.random.default_rng(0).standard_normal((10, 4)), columns=[\"A\", \"B\", \"C\", \"D\"]\n",
+ ")\n",
"df2.style"
]
},
@@ -597,10 +611,13 @@
"metadata": {},
"outputs": [],
"source": [
- "def style_negative(v, props=''):\n",
+ "def style_negative(v, props=\"\"):\n",
" return props if v < 0 else None\n",
- "s2 = df2.style.map(style_negative, props='color:red;')\\\n",
- " .map(lambda v: 'opacity: 20%;' if (v < 0.3) and (v > -0.3) else None)\n",
+ "\n",
+ "\n",
+ "s2 = df2.style.map(style_negative, props=\"color:red;\").map(\n",
+ " lambda v: \"opacity: 20%;\" if (v < 0.3) and (v > -0.3) else None\n",
+ ")\n",
"s2"
]
},
@@ -612,8 +629,8 @@
},
"outputs": [],
"source": [
- "# Hidden cell to avoid CSS clashes and latter code upcoding previous formatting \n",
- "s2.set_uuid('after_applymap')"
+ "# Hidden cell to avoid CSS clashes and latter code upcoding previous formatting\n",
+ "s2.set_uuid(\"after_applymap\")"
]
},
{
@@ -629,9 +646,11 @@
"metadata": {},
"outputs": [],
"source": [
- "def highlight_max(s, props=''):\n",
- " return np.where(s == np.nanmax(s.values), props, '')\n",
- "s2.apply(highlight_max, props='color:white;background-color:darkblue', axis=0)"
+ "def highlight_max(s, props=\"\"):\n",
+ " return np.where(s == np.nanmax(s.values), props, \"\")\n",
+ "\n",
+ "\n",
+ "s2.apply(highlight_max, props=\"color:white;background-color:darkblue\", axis=0)"
]
},
{
@@ -642,8 +661,8 @@
},
"outputs": [],
"source": [
- "# Hidden cell to avoid CSS clashes and latter code upcoding previous formatting \n",
- "s2.set_uuid('after_apply')"
+ "# Hidden cell to avoid CSS clashes and latter code upcoding previous formatting\n",
+ "s2.set_uuid(\"after_apply\")"
]
},
{
@@ -659,8 +678,9 @@
"metadata": {},
"outputs": [],
"source": [
- "s2.apply(highlight_max, props='color:white;background-color:pink;', axis=1)\\\n",
- " .apply(highlight_max, props='color:white;background-color:purple', axis=None)"
+ "s2.apply(highlight_max, props=\"color:white;background-color:pink;\", axis=1).apply(\n",
+ " highlight_max, props=\"color:white;background-color:purple\", axis=None\n",
+ ")"
]
},
{
@@ -671,8 +691,8 @@
},
"outputs": [],
"source": [
- "# Hidden cell to avoid CSS clashes and latter code upcoding previous formatting \n",
- "s2.set_uuid('after_apply_again')"
+ "# Hidden cell to avoid CSS clashes and latter code upcoding previous formatting\n",
+ "s2.set_uuid(\"after_apply_again\")"
]
},
{
@@ -713,8 +733,10 @@
"metadata": {},
"outputs": [],
"source": [
- "s2.map_index(lambda v: \"color:pink;\" if v>4 else \"color:darkblue;\", axis=0)\n",
- "s2.apply_index(lambda s: np.where(s.isin([\"A\", \"B\"]), \"color:pink;\", \"color:darkblue;\"), axis=1)"
+ "s2.map_index(lambda v: \"color:pink;\" if v > 4 else \"color:darkblue;\", axis=0)\n",
+ "s2.apply_index(\n",
+ " lambda s: np.where(s.isin([\"A\", \"B\"]), \"color:pink;\", \"color:darkblue;\"), axis=1\n",
+ ")"
]
},
{
@@ -734,11 +756,12 @@
"metadata": {},
"outputs": [],
"source": [
- "s.set_caption(\"Confusion matrix for multiple cancer prediction models.\")\\\n",
- " .set_table_styles([{\n",
- " 'selector': 'caption',\n",
- " 'props': 'caption-side: bottom; font-size:1.25em;'\n",
- " }], overwrite=False)"
+ "s.set_caption(\n",
+ " \"Confusion matrix for multiple cancer prediction models.\"\n",
+ ").set_table_styles(\n",
+ " [{\"selector\": \"caption\", \"props\": \"caption-side: bottom; font-size:1.25em;\"}],\n",
+ " overwrite=False,\n",
+ ")"
]
},
{
@@ -749,8 +772,8 @@
},
"outputs": [],
"source": [
- "# Hidden cell to avoid CSS clashes and latter code upcoding previous formatting \n",
- "s.set_uuid('after_caption')"
+ "# Hidden cell to avoid CSS clashes and latter code upcoding previous formatting\n",
+ "s.set_uuid(\"after_caption\")"
]
},
{
@@ -768,12 +791,24 @@
"metadata": {},
"outputs": [],
"source": [
- "tt = pd.DataFrame([['This model has a very strong true positive rate', \n",
- " \"This model's total number of false negatives is too high\"]], \n",
- " index=['Tumour (Positive)'], columns=df.columns[[0,3]])\n",
- "s.set_tooltips(tt, props='visibility: hidden; position: absolute; z-index: 1; border: 1px solid #000066;'\n",
- " 'background-color: white; color: #000066; font-size: 0.8em;' \n",
- " 'transform: translate(0px, -24px); padding: 0.6em; border-radius: 0.5em;')"
+ "tt = pd.DataFrame(\n",
+ " [\n",
+ " [\n",
+ " \"This model has a very strong true positive rate\",\n",
+ " \"This model's total number of false negatives is too high\",\n",
+ " ]\n",
+ " ],\n",
+ " index=[\"Tumour (Positive)\"],\n",
+ " columns=df.columns[[0, 3]],\n",
+ ")\n",
+ "s.set_tooltips(\n",
+ " tt,\n",
+ " props=\"visibility: hidden; position: absolute; z-index: 1; \"\n",
+ " \"border: 1px solid #000066;\"\n",
+ " \"background-color: white; color: #000066; font-size: 0.8em;\"\n",
+ " \"transform: translate(0px, -24px); padding: 0.6em; \"\n",
+ " \"border-radius: 0.5em;\",\n",
+ ")"
]
},
{
@@ -784,8 +819,8 @@
},
"outputs": [],
"source": [
- "# Hidden cell to avoid CSS clashes and latter code upcoding previous formatting \n",
- "s.set_uuid('after_tooltips')"
+ "# Hidden cell to avoid CSS clashes and latter code upcoding previous formatting\n",
+ "s.set_uuid(\"after_tooltips\")"
]
},
{
@@ -801,14 +836,18 @@
"metadata": {},
"outputs": [],
"source": [
- "s.set_table_styles([ # create internal CSS classes\n",
- " {'selector': '.border-red', 'props': 'border: 2px dashed red;'},\n",
- " {'selector': '.border-green', 'props': 'border: 2px dashed green;'},\n",
- "], overwrite=False)\n",
- "cell_border = pd.DataFrame([['border-green ', ' ', ' ', 'border-red '], \n",
- " [' ', ' ', ' ', ' ']], \n",
- " index=df.index, \n",
- " columns=df.columns[:4])\n",
+ "s.set_table_styles(\n",
+ " [ # create internal CSS classes\n",
+ " {\"selector\": \".border-red\", \"props\": \"border: 2px dashed red;\"},\n",
+ " {\"selector\": \".border-green\", \"props\": \"border: 2px dashed green;\"},\n",
+ " ],\n",
+ " overwrite=False,\n",
+ ")\n",
+ "cell_border = pd.DataFrame(\n",
+ " [[\"border-green \", \" \", \" \", \"border-red \"], [\" \", \" \", \" \", \" \"]],\n",
+ " index=df.index,\n",
+ " columns=df.columns[:4],\n",
+ ")\n",
"s.set_td_classes(cell_color + cell_border)"
]
},
@@ -820,8 +859,8 @@
},
"outputs": [],
"source": [
- "# Hidden cell to avoid CSS clashes and latter code upcoding previous formatting \n",
- "s.set_uuid('after_borders')"
+ "# Hidden cell to avoid CSS clashes and latter code upcoding previous formatting\n",
+ "s.set_uuid(\"after_borders\")"
]
},
{
@@ -847,9 +886,11 @@
"metadata": {},
"outputs": [],
"source": [
- "df3 = pd.DataFrame(np.random.randn(4,4), \n",
- " pd.MultiIndex.from_product([['A', 'B'], ['r1', 'r2']]),\n",
- " columns=['c1','c2','c3','c4'])\n",
+ "df3 = pd.DataFrame(\n",
+ " np.random.default_rng().standard_normal((4, 4)),\n",
+ " pd.MultiIndex.from_product([[\"A\", \"B\"], [\"r1\", \"r2\"]]),\n",
+ " columns=[\"c1\", \"c2\", \"c3\", \"c4\"],\n",
+ ")\n",
"df3"
]
},
@@ -866,9 +907,10 @@
"metadata": {},
"outputs": [],
"source": [
- "slice_ = ['c3', 'c4']\n",
- "df3.style.apply(highlight_max, props='color:red;', axis=0, subset=slice_)\\\n",
- " .set_properties(**{'background-color': '#ffffb3'}, subset=slice_)"
+ "slice_ = [\"c3\", \"c4\"]\n",
+ "df3.style.apply(\n",
+ " highlight_max, props=\"color:red;\", axis=0, subset=slice_\n",
+ ").set_properties(**{\"background-color\": \"#ffffb3\"}, subset=slice_)"
]
},
{
@@ -885,9 +927,10 @@
"outputs": [],
"source": [
"idx = pd.IndexSlice\n",
- "slice_ = idx[idx[:,'r1'], idx['c2':'c4']]\n",
- "df3.style.apply(highlight_max, props='color:red;', axis=0, subset=slice_)\\\n",
- " .set_properties(**{'background-color': '#ffffb3'}, subset=slice_)"
+ "slice_ = idx[idx[:, \"r1\"], idx[\"c2\":\"c4\"]]\n",
+ "df3.style.apply(\n",
+ " highlight_max, props=\"color:red;\", axis=0, subset=slice_\n",
+ ").set_properties(**{\"background-color\": \"#ffffb3\"}, subset=slice_)"
]
},
{
@@ -903,9 +946,10 @@
"metadata": {},
"outputs": [],
"source": [
- "slice_ = idx[idx[:,'r2'], :]\n",
- "df3.style.apply(highlight_max, props='color:red;', axis=1, subset=slice_)\\\n",
- " .set_properties(**{'background-color': '#ffffb3'}, subset=slice_)"
+ "slice_ = idx[idx[:, \"r2\"], :]\n",
+ "df3.style.apply(\n",
+ " highlight_max, props=\"color:red;\", axis=1, subset=slice_\n",
+ ").set_properties(**{\"background-color\": \"#ffffb3\"}, subset=slice_)"
]
},
{
@@ -923,9 +967,10 @@
"metadata": {},
"outputs": [],
"source": [
- "slice_ = idx[idx[(df3['c1'] + df3['c3']) < -2.0], ['c2', 'c4']]\n",
- "df3.style.apply(highlight_max, props='color:red;', axis=1, subset=slice_)\\\n",
- " .set_properties(**{'background-color': '#ffffb3'}, subset=slice_)"
+ "slice_ = idx[idx[(df3[\"c1\"] + df3[\"c3\"]) < -2.0], [\"c2\", \"c4\"]]\n",
+ "df3.style.apply(\n",
+ " highlight_max, props=\"color:red;\", axis=1, subset=slice_\n",
+ ").set_properties(**{\"background-color\": \"#ffffb3\"}, subset=slice_)"
]
},
{
@@ -981,7 +1026,7 @@
"metadata": {},
"outputs": [],
"source": [
- "df4 = pd.DataFrame([[1,2],[3,4]])\n",
+ "df4 = pd.DataFrame([[1, 2], [3, 4]])\n",
"s4 = df4.style"
]
},
@@ -1003,6 +1048,7 @@
"outputs": [],
"source": [
"from pandas.io.formats.style import Styler\n",
+ "\n",
"s4 = Styler(df4, uuid_len=0, cell_ids=False)"
]
},
@@ -1053,7 +1099,7 @@
"metadata": {},
"outputs": [],
"source": [
- "df4.style.set_table_styles([{'selector': 'td.col1', 'props': props}])"
+ "df4.style.set_table_styles([{\"selector\": \"td.col1\", \"props\": props}])"
]
},
{
@@ -1082,9 +1128,11 @@
"metadata": {},
"outputs": [],
"source": [
- "df2.style.apply(highlight_max, props='color:white;background-color:darkblue;', axis=0)\\\n",
- " .apply(highlight_max, props='color:white;background-color:pink;', axis=1)\\\n",
- " .apply(highlight_max, props='color:white;background-color:purple', axis=None)"
+ "df2.style.apply(\n",
+ " highlight_max, props=\"color:white;background-color:darkblue;\", axis=0\n",
+ ").apply(highlight_max, props=\"color:white;background-color:pink;\", axis=1).apply(\n",
+ " highlight_max, props=\"color:white;background-color:purple\", axis=None\n",
+ ")"
]
},
{
@@ -1105,14 +1153,18 @@
"outputs": [],
"source": [
"build = lambda x: pd.DataFrame(x, index=df2.index, columns=df2.columns)\n",
- "cls1 = build(df2.apply(highlight_max, props='cls-1 ', axis=0))\n",
- "cls2 = build(df2.apply(highlight_max, props='cls-2 ', axis=1, result_type='expand').values)\n",
- "cls3 = build(highlight_max(df2, props='cls-3 '))\n",
- "df2.style.set_table_styles([\n",
- " {'selector': '.cls-1', 'props': 'color:white;background-color:darkblue;'},\n",
- " {'selector': '.cls-2', 'props': 'color:white;background-color:pink;'},\n",
- " {'selector': '.cls-3', 'props': 'color:white;background-color:purple;'}\n",
- "]).set_td_classes(cls1 + cls2 + cls3)"
+ "cls1 = build(df2.apply(highlight_max, props=\"cls-1 \", axis=0))\n",
+ "cls2 = build(\n",
+ " df2.apply(highlight_max, props=\"cls-2 \", axis=1, result_type=\"expand\").values\n",
+ ")\n",
+ "cls3 = build(highlight_max(df2, props=\"cls-3 \"))\n",
+ "df2.style.set_table_styles(\n",
+ " [\n",
+ " {\"selector\": \".cls-1\", \"props\": \"color:white;background-color:darkblue;\"},\n",
+ " {\"selector\": \".cls-2\", \"props\": \"color:white;background-color:pink;\"},\n",
+ " {\"selector\": \".cls-3\", \"props\": \"color:white;background-color:purple;\"},\n",
+ " ]\n",
+ ").set_td_classes(cls1 + cls2 + cls3)"
]
},
{
@@ -1152,10 +1204,14 @@
" \"blank\": \"\",\n",
"}\n",
"html = Styler(df4, uuid_len=0, cell_ids=False)\n",
- "html.set_table_styles([{'selector': 'td', 'props': props},\n",
- " {'selector': '.c1', 'props': 'color:green;'},\n",
- " {'selector': '.l0', 'props': 'color:blue;'}],\n",
- " css_class_names=my_css)\n",
+ "html.set_table_styles(\n",
+ " [\n",
+ " {\"selector\": \"td\", \"props\": props},\n",
+ " {\"selector\": \".c1\", \"props\": \"color:green;\"},\n",
+ " {\"selector\": \".l0\", \"props\": \"color:blue;\"},\n",
+ " ],\n",
+ " css_class_names=my_css,\n",
+ ")\n",
"print(html.to_html())"
]
},
@@ -1213,9 +1269,9 @@
"metadata": {},
"outputs": [],
"source": [
- "df2.iloc[0,2] = np.nan\n",
- "df2.iloc[4,3] = np.nan\n",
- "df2.loc[:4].style.highlight_null(color='yellow')"
+ "df2.iloc[0, 2] = np.nan\n",
+ "df2.iloc[4, 3] = np.nan\n",
+ "df2.loc[:4].style.highlight_null(color=\"yellow\")"
]
},
{
@@ -1231,7 +1287,9 @@
"metadata": {},
"outputs": [],
"source": [
- "df2.loc[:4].style.highlight_max(axis=1, props='color:white; font-weight:bold; background-color:darkblue;')"
+ "df2.loc[:4].style.highlight_max(\n",
+ " axis=1, props=(\"color:white; \" \"font-weight:bold; \" \"background-color:darkblue;\")\n",
+ ")"
]
},
{
@@ -1249,7 +1307,9 @@
"outputs": [],
"source": [
"left = pd.Series([1.0, 0.0, 1.0], index=[\"A\", \"B\", \"D\"])\n",
- "df2.loc[:4].style.highlight_between(left=left, right=1.5, axis=1, props='color:white; background-color:purple;')"
+ "df2.loc[:4].style.highlight_between(\n",
+ " left=left, right=1.5, axis=1, props=\"color:white; background-color:purple;\"\n",
+ ")"
]
},
{
@@ -1266,7 +1326,7 @@
"metadata": {},
"outputs": [],
"source": [
- "df2.loc[:4].style.highlight_quantile(q_left=0.85, axis=None, color='yellow')"
+ "df2.loc[:4].style.highlight_quantile(q_left=0.85, axis=None, color=\"yellow\")"
]
},
{
@@ -1290,6 +1350,7 @@
"outputs": [],
"source": [
"import seaborn as sns\n",
+ "\n",
"cm = sns.light_palette(\"green\", as_cmap=True)\n",
"\n",
"df2.style.background_gradient(cmap=cm)"
@@ -1329,9 +1390,9 @@
"metadata": {},
"outputs": [],
"source": [
- "df2.loc[:4].style.set_properties(**{'background-color': 'black',\n",
- " 'color': 'lawngreen',\n",
- " 'border-color': 'white'})"
+ "df2.loc[:4].style.set_properties(\n",
+ " **{\"background-color\": \"black\", \"color\": \"lawngreen\", \"border-color\": \"white\"}\n",
+ ")"
]
},
{
@@ -1354,7 +1415,7 @@
"metadata": {},
"outputs": [],
"source": [
- "df2.style.bar(subset=['A', 'B'], color='#d65f5f')"
+ "df2.style.bar(subset=[\"A\", \"B\"], color=\"#d65f5f\")"
]
},
{
@@ -1372,10 +1433,15 @@
"metadata": {},
"outputs": [],
"source": [
- "df2.style.format('{:.3f}', na_rep=\"\")\\\n",
- " .bar(align=0, vmin=-2.5, vmax=2.5, cmap=\"bwr\", height=50,\n",
- " width=60, props=\"width: 120px; border-right: 1px solid black;\")\\\n",
- " .text_gradient(cmap=\"bwr\", vmin=-2.5, vmax=2.5)"
+ "df2.style.format(\"{:.3f}\", na_rep=\"\").bar(\n",
+ " align=0,\n",
+ " vmin=-2.5,\n",
+ " vmax=2.5,\n",
+ " cmap=\"bwr\",\n",
+ " height=50,\n",
+ " width=60,\n",
+ " props=\"width: 120px; border-right: 1px solid black;\",\n",
+ ").text_gradient(cmap=\"bwr\", vmin=-2.5, vmax=2.5)"
]
},
{
@@ -1398,10 +1464,10 @@
"from IPython.display import HTML\n",
"\n",
"# Test series\n",
- "test1 = pd.Series([-100,-60,-30,-20], name='All Negative')\n",
- "test2 = pd.Series([-10,-5,0,90], name='Both Pos and Neg')\n",
- "test3 = pd.Series([10,20,50,100], name='All Positive')\n",
- "test4 = pd.Series([100, 103, 101, 102], name='Large Positive')\n",
+ "test1 = pd.Series([-100, -60, -30, -20], name=\"All Negative\")\n",
+ "test2 = pd.Series([-10, -5, 0, 90], name=\"Both Pos and Neg\")\n",
+ "test3 = pd.Series([10, 20, 50, 100], name=\"All Positive\")\n",
+ "test4 = pd.Series([100, 103, 101, 102], name=\"Large Positive\")\n",
"\n",
"\n",
"head = \"\"\"\n",
@@ -1417,19 +1483,22 @@
"\n",
"\"\"\"\n",
"\n",
- "aligns = ['left', 'right', 'zero', 'mid', 'mean', 99]\n",
+ "aligns = [\"left\", \"right\", \"zero\", \"mid\", \"mean\", 99]\n",
"for align in aligns:\n",
" row = \"<tr><th>{}</th>\".format(align)\n",
- " for series in [test1,test2,test3, test4]:\n",
+ " for series in [test1, test2, test3, test4]:\n",
" s = series.copy()\n",
- " s.name=''\n",
- " row += \"<td>{}</td>\".format(s.to_frame().style.hide(axis='index').bar(align=align, \n",
- " color=['#d65f5f', '#5fba7d'], \n",
- " width=100).to_html()) #testn['width']\n",
- " row += '</tr>'\n",
+ " s.name = \"\"\n",
+ " row += \"<td>{}</td>\".format(\n",
+ " s.to_frame()\n",
+ " .style.hide(axis=\"index\")\n",
+ " .bar(align=align, color=[\"#d65f5f\", \"#5fba7d\"], width=100)\n",
+ " .to_html()\n",
+ " ) # testn['width']\n",
+ " row += \"</tr>\"\n",
" head += row\n",
- " \n",
- "head+= \"\"\"\n",
+ "\n",
+ "head += \"\"\"\n",
"</tbody>\n",
"</table>\"\"\""
]
@@ -1463,11 +1532,12 @@
"metadata": {},
"outputs": [],
"source": [
- "style1 = df2.style\\\n",
- " .map(style_negative, props='color:red;')\\\n",
- " .map(lambda v: 'opacity: 20%;' if (v < 0.3) and (v > -0.3) else None)\\\n",
- " .set_table_styles([{\"selector\": \"th\", \"props\": \"color: blue;\"}])\\\n",
- " .hide(axis=\"index\")\n",
+ "style1 = (\n",
+ " df2.style.map(style_negative, props=\"color:red;\")\n",
+ " .map(lambda v: \"opacity: 20%;\" if (v < 0.3) and (v > -0.3) else None)\n",
+ " .set_table_styles([{\"selector\": \"th\", \"props\": \"color: blue;\"}])\n",
+ " .hide(axis=\"index\")\n",
+ ")\n",
"style1"
]
},
@@ -1526,11 +1596,14 @@
"outputs": [],
"source": [
"from ipywidgets import widgets\n",
+ "\n",
+ "\n",
"@widgets.interact\n",
- "def f(h_neg=(0, 359, 1), h_pos=(0, 359), s=(0., 99.9), l=(0., 99.9)):\n",
+ "def f(h_neg=(0, 359, 1), h_pos=(0, 359), s=(0.0, 99.9), l_post=(0.0, 99.9)):\n",
" return df2.style.background_gradient(\n",
- " cmap=sns.palettes.diverging_palette(h_neg=h_neg, h_pos=h_pos, s=s, l=l,\n",
- " as_cmap=True)\n",
+ " cmap=sns.palettes.diverging_palette(\n",
+ " h_neg=h_neg, h_pos=h_pos, s=s, l=l_post, as_cmap=True\n",
+ " )\n",
" )"
]
},
@@ -1548,16 +1621,15 @@
"outputs": [],
"source": [
"def magnify():\n",
- " return [dict(selector=\"th\",\n",
- " props=[(\"font-size\", \"4pt\")]),\n",
- " dict(selector=\"td\",\n",
- " props=[('padding', \"0em 0em\")]),\n",
- " dict(selector=\"th:hover\",\n",
- " props=[(\"font-size\", \"12pt\")]),\n",
- " dict(selector=\"tr:hover td:hover\",\n",
- " props=[('max-width', '200px'),\n",
- " ('font-size', '12pt')])\n",
- "]"
+ " return [\n",
+ " {\"selector\": \"th\", \"props\": [(\"font-size\", \"4pt\")]},\n",
+ " {\"selector\": \"td\", \"props\": [(\"padding\", \"0em 0em\")]},\n",
+ " {\"selector\": \"th:hover\", \"props\": [(\"font-size\", \"12pt\")]},\n",
+ " {\n",
+ " \"selector\": \"tr:hover td:hover\",\n",
+ " \"props\": [(\"max-width\", \"200px\"), (\"font-size\", \"12pt\")],\n",
+ " },\n",
+ " ]"
]
},
{
@@ -1566,15 +1638,12 @@
"metadata": {},
"outputs": [],
"source": [
- "np.random.seed(25)\n",
- "cmap = cmap=sns.diverging_palette(5, 250, as_cmap=True)\n",
- "bigdf = pd.DataFrame(np.random.randn(20, 25)).cumsum()\n",
+ "cmap = sns.diverging_palette(5, 250, as_cmap=True)\n",
+ "bigdf = pd.DataFrame(np.random.default_rng(25).standard_normal((20, 25))).cumsum()\n",
"\n",
- "bigdf.style.background_gradient(cmap, axis=1)\\\n",
- " .set_properties(**{'max-width': '80px', 'font-size': '1pt'})\\\n",
- " .set_caption(\"Hover to magnify\")\\\n",
- " .format(precision=2)\\\n",
- " .set_table_styles(magnify())"
+ "bigdf.style.background_gradient(cmap, axis=1).set_properties(\n",
+ " **{\"max-width\": \"80px\", \"font-size\": \"1pt\"}\n",
+ ").set_caption(\"Hover to magnify\").format(precision=2).set_table_styles(magnify())"
]
},
{
@@ -1594,7 +1663,7 @@
"metadata": {},
"outputs": [],
"source": [
- "bigdf = pd.DataFrame(np.random.randn(16, 100))\n",
+ "bigdf = pd.DataFrame(np.random.default_rng().standard_normal((16, 100)))\n",
"bigdf.style.set_sticky(axis=\"index\")"
]
},
@@ -1611,8 +1680,8 @@
"metadata": {},
"outputs": [],
"source": [
- "bigdf.index = pd.MultiIndex.from_product([[\"A\",\"B\"],[0,1],[0,1,2,3]])\n",
- "bigdf.style.set_sticky(axis=\"index\", pixel_size=18, levels=[1,2])"
+ "bigdf.index = pd.MultiIndex.from_product([[\"A\", \"B\"], [0, 1], [0, 1, 2, 3]])\n",
+ "bigdf.style.set_sticky(axis=\"index\", pixel_size=18, levels=[1, 2])"
]
},
{
@@ -1632,7 +1701,7 @@
"metadata": {},
"outputs": [],
"source": [
- "df4 = pd.DataFrame([['<div></div>', '\"&other\"', '<span></span>']])\n",
+ "df4 = pd.DataFrame([[\"<div></div>\", '\"&other\"', \"<span></span>\"]])\n",
"df4.style"
]
},
@@ -1651,7 +1720,9 @@
"metadata": {},
"outputs": [],
"source": [
- "df4.style.format('<a href=\"https://pandas.pydata.org\" target=\"_blank\">{}</a>', escape=\"html\")"
+ "df4.style.format(\n",
+ " '<a href=\"https://pandas.pydata.org\" target=\"_blank\">{}</a>', escape=\"html\"\n",
+ ")"
]
},
{
@@ -1693,10 +1764,9 @@
"metadata": {},
"outputs": [],
"source": [
- "df2.style.\\\n",
- " map(style_negative, props='color:red;').\\\n",
- " highlight_max(axis=0).\\\n",
- " to_excel('styled.xlsx', engine='openpyxl')"
+ "df2.style.map(style_negative, props=\"color:red;\").highlight_max(axis=0).to_excel(\n",
+ " \"styled.xlsx\", engine=\"openpyxl\"\n",
+ ")"
]
},
{
@@ -1765,7 +1835,11 @@
"metadata": {},
"outputs": [],
"source": [
- "print(pd.DataFrame([[1,2],[3,4]], index=['i1', 'i2'], columns=['c1', 'c2']).style.to_html())"
+ "print(\n",
+ " pd.DataFrame(\n",
+ " [[1, 2], [3, 4]], index=[\"i1\", \"i2\"], columns=[\"c1\", \"c2\"]\n",
+ " ).style.to_html()\n",
+ ")"
]
},
{
@@ -1783,9 +1857,8 @@
"metadata": {},
"outputs": [],
"source": [
- "df4 = pd.DataFrame([['text']])\n",
- "df4.style.map(lambda x: 'color:green;')\\\n",
- " .map(lambda x: 'color:red;')"
+ "df4 = pd.DataFrame([[\"text\"]])\n",
+ "df4.style.map(lambda x: \"color:green;\").map(lambda x: \"color:red;\")"
]
},
{
@@ -1794,8 +1867,7 @@
"metadata": {},
"outputs": [],
"source": [
- "df4.style.map(lambda x: 'color:red;')\\\n",
- " .map(lambda x: 'color:green;')"
+ "df4.style.map(lambda x: \"color:red;\").map(lambda x: \"color:green;\")"
]
},
{
@@ -1820,9 +1892,9 @@
"metadata": {},
"outputs": [],
"source": [
- "df4.style.set_uuid('a_')\\\n",
- " .set_table_styles([{'selector': 'td', 'props': 'color:red;'}])\\\n",
- " .map(lambda x: 'color:green;')"
+ "df4.style.set_uuid(\"a_\").set_table_styles(\n",
+ " [{\"selector\": \"td\", \"props\": \"color:red;\"}]\n",
+ ").map(lambda x: \"color:green;\")"
]
},
{
@@ -1838,11 +1910,12 @@
"metadata": {},
"outputs": [],
"source": [
- "df4.style.set_uuid('b_')\\\n",
- " .set_table_styles([{'selector': 'td', 'props': 'color:red;'},\n",
- " {'selector': '.cls-1', 'props': 'color:blue;'}])\\\n",
- " .map(lambda x: 'color:green;')\\\n",
- " .set_td_classes(pd.DataFrame([['cls-1']]))"
+ "df4.style.set_uuid(\"b_\").set_table_styles(\n",
+ " [\n",
+ " {\"selector\": \"td\", \"props\": \"color:red;\"},\n",
+ " {\"selector\": \".cls-1\", \"props\": \"color:blue;\"},\n",
+ " ]\n",
+ ").map(lambda x: \"color:green;\").set_td_classes(pd.DataFrame([[\"cls-1\"]]))"
]
},
{
@@ -1858,12 +1931,13 @@
"metadata": {},
"outputs": [],
"source": [
- "df4.style.set_uuid('c_')\\\n",
- " .set_table_styles([{'selector': 'td', 'props': 'color:red;'},\n",
- " {'selector': '.cls-1', 'props': 'color:blue;'},\n",
- " {'selector': 'td.data', 'props': 'color:yellow;'}])\\\n",
- " .map(lambda x: 'color:green;')\\\n",
- " .set_td_classes(pd.DataFrame([['cls-1']]))"
+ "df4.style.set_uuid(\"c_\").set_table_styles(\n",
+ " [\n",
+ " {\"selector\": \"td\", \"props\": \"color:red;\"},\n",
+ " {\"selector\": \".cls-1\", \"props\": \"color:blue;\"},\n",
+ " {\"selector\": \"td.data\", \"props\": \"color:yellow;\"},\n",
+ " ]\n",
+ ").map(lambda x: \"color:green;\").set_td_classes(pd.DataFrame([[\"cls-1\"]]))"
]
},
{
@@ -1881,12 +1955,13 @@
"metadata": {},
"outputs": [],
"source": [
- "df4.style.set_uuid('d_')\\\n",
- " .set_table_styles([{'selector': 'td', 'props': 'color:red;'},\n",
- " {'selector': '.cls-1', 'props': 'color:blue;'},\n",
- " {'selector': 'td.data', 'props': 'color:yellow;'}])\\\n",
- " .map(lambda x: 'color:green !important;')\\\n",
- " .set_td_classes(pd.DataFrame([['cls-1']]))"
+ "df4.style.set_uuid(\"d_\").set_table_styles(\n",
+ " [\n",
+ " {\"selector\": \"td\", \"props\": \"color:red;\"},\n",
+ " {\"selector\": \".cls-1\", \"props\": \"color:blue;\"},\n",
+ " {\"selector\": \"td.data\", \"props\": \"color:yellow;\"},\n",
+ " ]\n",
+ ").map(lambda x: \"color:green !important;\").set_td_classes(pd.DataFrame([[\"cls-1\"]]))"
]
},
{
@@ -1940,8 +2015,8 @@
"metadata": {},
"outputs": [],
"source": [
- "with open(\"templates/myhtml.tpl\") as f:\n",
- " print(f.read())"
+ "with open(\"templates/myhtml.tpl\") as f_html:\n",
+ " print(f_html.read())"
]
},
{
@@ -1960,10 +2035,12 @@
"source": [
"class MyStyler(Styler):\n",
" env = Environment(\n",
- " loader=ChoiceLoader([\n",
- " FileSystemLoader(\"templates\"), # contains ours\n",
- " Styler.loader, # the default\n",
- " ])\n",
+ " loader=ChoiceLoader(\n",
+ " [\n",
+ " FileSystemLoader(\"templates\"), # contains ours\n",
+ " Styler.loader, # the default\n",
+ " ]\n",
+ " )\n",
" )\n",
" template_html_table = env.get_template(\"myhtml.tpl\")"
]
@@ -2045,8 +2122,8 @@
},
"outputs": [],
"source": [
- "with open(\"templates/html_style_structure.html\") as f:\n",
- " style_structure = f.read()"
+ "with open(\"templates/html_style_structure.html\") as f_sty:\n",
+ " style_structure = f_sty.read()"
]
},
{
@@ -2073,8 +2150,8 @@
},
"outputs": [],
"source": [
- "with open(\"templates/html_table_structure.html\") as f:\n",
- " table_structure = f.read()"
+ "with open(\"templates/html_table_structure.html\") as f_table_struct:\n",
+ " table_structure = f_table_struct.read()"
]
},
{
@@ -2106,7 +2183,7 @@
"# from IPython.display import HTML\n",
"# with open(\"themes/nature_with_gtoc/static/nature.css_t\") as f:\n",
"# css = f.read()\n",
- " \n",
+ "\n",
"# HTML('<style>{}</style>'.format(css))"
]
}
diff --git a/doc/source/whatsnew/v3.0.0.rst b/doc/source/whatsnew/v3.0.0.rst
index 3c707d7931c97..a5b4560a47bc4 100644
--- a/doc/source/whatsnew/v3.0.0.rst
+++ b/doc/source/whatsnew/v3.0.0.rst
@@ -544,7 +544,7 @@ Bug fixes
Categorical
^^^^^^^^^^^
-- Bug in :meth:`Series.convert_dtypes` with ``dtype_backend='pyarrow'`` parameter where empty categorical series raise error or get converted to null[pyarrow] (:issue:`59934`)
+-
-
Datetimelike
diff --git a/pandas/_libs/lib.pyx b/pandas/_libs/lib.pyx
index de7d9af731010..23e0f387466aa 100644
--- a/pandas/_libs/lib.pyx
+++ b/pandas/_libs/lib.pyx
@@ -1089,9 +1089,23 @@ def is_float(obj: object) -> bool:
"""
Return True if given object is float.
+ This method checks whether the passed object is a float type. It
+ returns `True` if the object is a float, and `False` otherwise.
+
+ Parameters
+ ----------
+ obj : object
+ The object to check for float type.
+
Returns
-------
bool
+ `True` if the object is of float type, otherwise `False`.
+
+ See Also
+ --------
+ api.types.is_integer : Check if an object is of integer type.
+ api.types.is_numeric_dtype : Check if an object is of numeric type.
Examples
--------
diff --git a/pandas/_libs/tslibs/nattype.pyi b/pandas/_libs/tslibs/nattype.pyi
index f49e894a0bfec..d3b10fbe79cb9 100644
--- a/pandas/_libs/tslibs/nattype.pyi
+++ b/pandas/_libs/tslibs/nattype.pyi
@@ -9,6 +9,7 @@ from typing import (
Literal,
NoReturn,
TypeAlias,
+ overload,
)
import numpy as np
@@ -24,12 +25,8 @@ NaT: NaTType
iNaT: int
nat_strings: set[str]
-_NaTComparisonTypes: TypeAlias = (
- datetime | timedelta | Period | np.datetime64 | np.timedelta64
-)
-
-class _NatComparison:
- def __call__(self, other: _NaTComparisonTypes) -> bool: ...
+_TimeLike: TypeAlias = datetime | timedelta | Period | np.datetime64 | np.timedelta64
+_TimeDelta: TypeAlias = timedelta | np.timedelta64
class NaTType:
_value: np.int64
@@ -159,15 +156,31 @@ class NaTType:
# inject Period properties
@property
def qyear(self) -> float: ...
- def __eq__(self, other: object) -> bool: ...
- def __ne__(self, other: object) -> bool: ...
- __lt__: _NatComparison
- __le__: _NatComparison
- __gt__: _NatComparison
- __ge__: _NatComparison
- def __sub__(self, other: Self | timedelta | datetime) -> Self: ...
- def __rsub__(self, other: Self | timedelta | datetime) -> Self: ...
- def __add__(self, other: Self | timedelta | datetime) -> Self: ...
- def __radd__(self, other: Self | timedelta | datetime) -> Self: ...
+ # comparisons
+ def __eq__(self, other: object, /) -> Literal[False]: ...
+ def __ne__(self, other: object, /) -> Literal[True]: ...
+ def __lt__(self, other: Self | _TimeLike, /) -> Literal[False]: ...
+ def __le__(self, other: Self | _TimeLike, /) -> Literal[False]: ...
+ def __gt__(self, other: Self | _TimeLike, /) -> Literal[False]: ...
+ def __ge__(self, other: Self | _TimeLike, /) -> Literal[False]: ...
+ # unary operators
+ def __pos__(self) -> Self: ...
+ def __neg__(self) -> Self: ...
+ # binary operators
+ def __sub__(self, other: Self | _TimeLike, /) -> Self: ...
+ def __rsub__(self, other: Self | _TimeLike, /) -> Self: ...
+ def __add__(self, other: Self | _TimeLike, /) -> Self: ...
+ def __radd__(self, other: Self | _TimeLike, /) -> Self: ...
+ def __mul__(self, other: float, /) -> Self: ... # analogous to timedelta
+ def __rmul__(self, other: float, /) -> Self: ...
+ @overload # analogous to timedelta
+ def __truediv__(self, other: Self | _TimeDelta, /) -> float: ... # Literal[NaN]
+ @overload
+ def __truediv__(self, other: float, /) -> Self: ...
+ @overload # analogous to timedelta
+ def __floordiv__(self, other: Self | _TimeDelta, /) -> float: ... # Literal[NaN]
+ @overload
+ def __floordiv__(self, other: float, /) -> Self: ...
+ # other
def __hash__(self) -> int: ...
def as_unit(self, unit: str, round_ok: bool = ...) -> NaTType: ...
diff --git a/pandas/_testing/asserters.py b/pandas/_testing/asserters.py
index bbd5e60a5a812..01c4dcd92ee40 100644
--- a/pandas/_testing/asserters.py
+++ b/pandas/_testing/asserters.py
@@ -701,6 +701,10 @@ def assert_extension_array_equal(
"""
Check that left and right ExtensionArrays are equal.
+ This method compares two ``ExtensionArray`` instances for equality,
+ including checks for missing values, the dtype of the arrays, and
+ the exactness of the comparison (or tolerance when comparing floats).
+
Parameters
----------
left, right : ExtensionArray
@@ -726,6 +730,12 @@ def assert_extension_array_equal(
.. versionadded:: 2.0.0
+ See Also
+ --------
+ testing.assert_series_equal : Check that left and right ``Series`` are equal.
+ testing.assert_frame_equal : Check that left and right ``DataFrame`` are equal.
+ testing.assert_index_equal : Check that left and right ``Index`` are equal.
+
Notes
-----
Missing values are checked separately from valid values.
diff --git a/pandas/core/accessor.py b/pandas/core/accessor.py
index d8463fda34caa..78684eacf2d66 100644
--- a/pandas/core/accessor.py
+++ b/pandas/core/accessor.py
@@ -7,6 +7,7 @@
from __future__ import annotations
+import functools
from typing import (
TYPE_CHECKING,
final,
@@ -117,12 +118,12 @@ def _setter(self, new_values):
)
def _create_delegator_method(name: str):
+ method = getattr(delegate, accessor_mapping(name))
+
+ @functools.wraps(method)
def f(self, *args, **kwargs):
return self._delegate_method(name, *args, **kwargs)
- f.__name__ = name
- f.__doc__ = getattr(delegate, accessor_mapping(name)).__doc__
-
return f
for name in accessors:
diff --git a/pandas/core/apply.py b/pandas/core/apply.py
index 7d50b466f5126..1f13459724d78 100644
--- a/pandas/core/apply.py
+++ b/pandas/core/apply.py
@@ -38,10 +38,7 @@
is_numeric_dtype,
is_sequence,
)
-from pandas.core.dtypes.dtypes import (
- CategoricalDtype,
- ExtensionDtype,
-)
+from pandas.core.dtypes.dtypes import ExtensionDtype
from pandas.core.dtypes.generic import (
ABCDataFrame,
ABCNDFrame,
@@ -1465,14 +1462,7 @@ def curried(x):
else:
curried = func
-
- # row-wise access
- # apply doesn't have a `na_action` keyword and for backward compat reasons
- # we need to give `na_action="ignore"` for categorical data.
- # TODO: remove the `na_action="ignore"` when that default has been changed in
- # Categorical (GH51645).
- action = "ignore" if isinstance(obj.dtype, CategoricalDtype) else None
- mapped = obj._map_values(mapper=curried, na_action=action)
+ mapped = obj._map_values(mapper=curried)
if len(mapped) and isinstance(mapped[0], ABCSeries):
# GH#43986 Need to do list(mapped) in order to get treated as nested
diff --git a/pandas/core/arrays/categorical.py b/pandas/core/arrays/categorical.py
index a69e197df851d..0484ef89f61c2 100644
--- a/pandas/core/arrays/categorical.py
+++ b/pandas/core/arrays/categorical.py
@@ -1155,6 +1155,12 @@ def rename_categories(self, new_categories) -> Self:
"""
Rename categories.
+ This method is commonly used to re-label or adjust the
+ category names in categorical data without changing the
+ underlying data. It is useful in situations where you want
+ to modify the labels used for clarity, consistency,
+ or readability.
+
Parameters
----------
new_categories : list-like, dict-like or callable
@@ -1371,8 +1377,8 @@ def remove_categories(self, removals) -> Self:
"""
Remove the specified categories.
- `removals` must be included in the old categories. Values which were in
- the removed categories will be set to NaN
+ The ``removals`` argument must be a subset of the current categories.
+ Any values that were part of the removed categories will be set to NaN.
Parameters
----------
@@ -1431,6 +1437,10 @@ def remove_unused_categories(self) -> Self:
"""
Remove categories which are not used.
+ This method is useful when working with datasets
+ that undergo dynamic changes where categories may no longer be
+ relevant, allowing to maintain a clean, efficient data structure.
+
Returns
-------
Categorical
diff --git a/pandas/core/arrays/datetimes.py b/pandas/core/arrays/datetimes.py
index 43f4428118aa7..41128e52e31b3 100644
--- a/pandas/core/arrays/datetimes.py
+++ b/pandas/core/arrays/datetimes.py
@@ -205,6 +205,14 @@ class DatetimeArray(dtl.TimelikeOps, dtl.DatelikeOps): # type: ignore[misc]
-------
None
+ See Also
+ --------
+ DatetimeIndex : Immutable Index for datetime-like data.
+ Series : One-dimensional labeled array capable of holding datetime-like data.
+ Timestamp : Pandas replacement for python datetime.datetime object.
+ to_datetime : Convert argument to datetime.
+ period_range : Return a fixed frequency PeriodIndex.
+
Examples
--------
>>> pd.arrays.DatetimeArray._from_sequence(
diff --git a/pandas/core/arrays/sparse/accessor.py b/pandas/core/arrays/sparse/accessor.py
index e610e018c5a74..0ed5f69fe4703 100644
--- a/pandas/core/arrays/sparse/accessor.py
+++ b/pandas/core/arrays/sparse/accessor.py
@@ -88,9 +88,17 @@ def from_coo(cls, A, dense_index: bool = False) -> Series:
"""
Create a Series with sparse values from a scipy.sparse.coo_matrix.
+ This method takes a ``scipy.sparse.coo_matrix`` (coordinate format) as input and
+ returns a pandas ``Series`` where the non-zero elements are represented as
+ sparse values. The index of the Series can either include only the coordinates
+ of non-zero elements (default behavior) or the full sorted set of coordinates
+ from the matrix if ``dense_index`` is set to `True`.
+
Parameters
----------
A : scipy.sparse.coo_matrix
+ The sparse matrix in coordinate format from which the sparse Series
+ will be created.
dense_index : bool, default False
If False (default), the index consists of only the
coords of the non-null entries of the original coo_matrix.
@@ -102,6 +110,12 @@ def from_coo(cls, A, dense_index: bool = False) -> Series:
s : Series
A Series with sparse values.
+ See Also
+ --------
+ DataFrame.sparse.from_spmatrix : Create a new DataFrame from a scipy sparse
+ matrix.
+ scipy.sparse.coo_matrix : A sparse matrix in COOrdinate format.
+
Examples
--------
>>> from scipy import sparse
@@ -369,10 +383,10 @@ def to_dense(self) -> DataFrame:
1 1
2 0
"""
- from pandas import DataFrame
-
data = {k: v.array.to_dense() for k, v in self._parent.items()}
- return DataFrame(data, index=self._parent.index, columns=self._parent.columns)
+ return self._parent._constructor(
+ data, index=self._parent.index, columns=self._parent.columns
+ )
def to_coo(self) -> spmatrix:
"""
diff --git a/pandas/core/arrays/string_.py b/pandas/core/arrays/string_.py
index b3aa782341c77..e4daf9ed450fb 100644
--- a/pandas/core/arrays/string_.py
+++ b/pandas/core/arrays/string_.py
@@ -190,7 +190,7 @@ def __eq__(self, other: object) -> bool:
# cannot be checked with normal `==`
if isinstance(other, str):
# TODO should dtype == "string" work for the NaN variant?
- if other == "string" or other == self.name: # noqa: PLR1714
+ if other == "string" or other == self.name:
return True
try:
other = self.construct_from_string(other)
diff --git a/pandas/core/frame.py b/pandas/core/frame.py
index f184aab4070d7..1b47002e72fc6 100644
--- a/pandas/core/frame.py
+++ b/pandas/core/frame.py
@@ -7266,7 +7266,11 @@ def value_counts(
normalize : bool, default False
Return proportions rather than frequencies.
sort : bool, default True
- Sort by frequencies when True. Sort by DataFrame column values when False.
+ Sort by frequencies when True. Preserve the order of the data when False.
+
+ .. versionchanged:: 3.0.0
+
+ Prior to 3.0.0, ``sort=False`` would sort by the columns values.
ascending : bool, default False
Sort in ascending order.
dropna : bool, default True
@@ -7372,7 +7376,9 @@ def value_counts(
subset = self.columns.tolist()
name = "proportion" if normalize else "count"
- counts = self.groupby(subset, dropna=dropna, observed=False)._grouper.size()
+ counts = self.groupby(
+ subset, sort=False, dropna=dropna, observed=False
+ )._grouper.size()
counts.name = name
if sort:
diff --git a/pandas/core/groupby/generic.py b/pandas/core/groupby/generic.py
index 110c0ea88a0a1..f076f8d79f104 100644
--- a/pandas/core/groupby/generic.py
+++ b/pandas/core/groupby/generic.py
@@ -2621,7 +2621,13 @@ def value_counts(
normalize : bool, default False
Return proportions rather than frequencies.
sort : bool, default True
- Sort by frequencies.
+ Sort by frequencies when True. When False, non-grouping columns will appear
+ in the order they occur in within groups.
+
+ .. versionchanged:: 3.0.0
+
+ In prior versions, ``sort=False`` would sort the non-grouping columns
+ by label.
ascending : bool, default False
Sort in ascending order.
dropna : bool, default True
@@ -2673,8 +2679,8 @@ def value_counts(
>>> df.groupby("gender").value_counts()
gender education country
- female high FR 1
- US 1
+ female high US 1
+ FR 1
male low FR 2
US 1
medium FR 1
@@ -2682,8 +2688,8 @@ def value_counts(
>>> df.groupby("gender").value_counts(ascending=True)
gender education country
- female high FR 1
- US 1
+ female high US 1
+ FR 1
male low US 1
medium FR 1
low FR 2
@@ -2691,8 +2697,8 @@ def value_counts(
>>> df.groupby("gender").value_counts(normalize=True)
gender education country
- female high FR 0.50
- US 0.50
+ female high US 0.50
+ FR 0.50
male low FR 0.50
US 0.25
medium FR 0.25
@@ -2700,16 +2706,16 @@ def value_counts(
>>> df.groupby("gender", as_index=False).value_counts()
gender education country count
- 0 female high FR 1
- 1 female high US 1
+ 0 female high US 1
+ 1 female high FR 1
2 male low FR 2
3 male low US 1
4 male medium FR 1
>>> df.groupby("gender", as_index=False).value_counts(normalize=True)
gender education country proportion
- 0 female high FR 0.50
- 1 female high US 0.50
+ 0 female high US 0.50
+ 1 female high FR 0.50
2 male low FR 0.50
3 male low US 0.25
4 male medium FR 0.25
diff --git a/pandas/core/groupby/groupby.py b/pandas/core/groupby/groupby.py
index e2410788ea95e..68314567d1b5e 100644
--- a/pandas/core/groupby/groupby.py
+++ b/pandas/core/groupby/groupby.py
@@ -2519,7 +2519,7 @@ def _value_counts(
grouper, _, _ = get_grouper(
df,
key=key,
- sort=self.sort,
+ sort=False,
observed=False,
dropna=dropna,
)
@@ -2528,7 +2528,7 @@ def _value_counts(
# Take the size of the overall columns
gb = df.groupby(
groupings,
- sort=self.sort,
+ sort=False,
observed=self.observed,
dropna=self.dropna,
)
diff --git a/pandas/core/groupby/ops.py b/pandas/core/groupby/ops.py
index 0e99178642715..b32119a2ddbde 100644
--- a/pandas/core/groupby/ops.py
+++ b/pandas/core/groupby/ops.py
@@ -755,6 +755,7 @@ def result_index_and_ids(self) -> tuple[Index, npt.NDArray[np.intp]]:
obs = [
ping._observed or not ping._passed_categorical for ping in self.groupings
]
+ sorts = [ping._sort for ping in self.groupings]
# When passed a categorical grouping, keep all categories
for k, (ping, level) in enumerate(zip(self.groupings, levels)):
if ping._passed_categorical:
@@ -765,7 +766,9 @@ def result_index_and_ids(self) -> tuple[Index, npt.NDArray[np.intp]]:
result_index.name = self.names[0]
ids = ensure_platform_int(self.codes[0])
elif all(obs):
- result_index, ids = self._ob_index_and_ids(levels, self.codes, self.names)
+ result_index, ids = self._ob_index_and_ids(
+ levels, self.codes, self.names, sorts
+ )
elif not any(obs):
result_index, ids = self._unob_index_and_ids(levels, self.codes, self.names)
else:
@@ -778,6 +781,7 @@ def result_index_and_ids(self) -> tuple[Index, npt.NDArray[np.intp]]:
levels=[levels[idx] for idx in ob_indices],
codes=[codes[idx] for idx in ob_indices],
names=[names[idx] for idx in ob_indices],
+ sorts=[sorts[idx] for idx in ob_indices],
)
unob_index, unob_ids = self._unob_index_and_ids(
levels=[levels[idx] for idx in unob_indices],
@@ -800,9 +804,18 @@ def result_index_and_ids(self) -> tuple[Index, npt.NDArray[np.intp]]:
).reorder_levels(index)
ids = len(unob_index) * ob_ids + unob_ids
- if self._sort:
+ if any(sorts):
# Sort result_index and recode ids using the new order
- sorter = result_index.argsort()
+ n_levels = len(sorts)
+ drop_levels = [
+ n_levels - idx
+ for idx, sort in enumerate(reversed(sorts), 1)
+ if not sort
+ ]
+ if len(drop_levels) > 0:
+ sorter = result_index._drop_level_numbers(drop_levels).argsort()
+ else:
+ sorter = result_index.argsort()
result_index = result_index.take(sorter)
_, index = np.unique(sorter, return_index=True)
ids = ensure_platform_int(ids)
@@ -837,10 +850,13 @@ def _ob_index_and_ids(
levels: list[Index],
codes: list[npt.NDArray[np.intp]],
names: list[Hashable],
+ sorts: list[bool],
) -> tuple[MultiIndex, npt.NDArray[np.intp]]:
+ consistent_sorting = all(sorts[0] == sort for sort in sorts[1:])
+ sort_in_compress = sorts[0] if consistent_sorting else False
shape = tuple(len(level) for level in levels)
group_index = get_group_index(codes, shape, sort=True, xnull=True)
- ob_ids, obs_group_ids = compress_group_index(group_index, sort=self._sort)
+ ob_ids, obs_group_ids = compress_group_index(group_index, sort=sort_in_compress)
ob_ids = ensure_platform_int(ob_ids)
ob_index_codes = decons_obs_group_ids(
ob_ids, obs_group_ids, shape, codes, xnull=True
@@ -851,6 +867,21 @@ def _ob_index_and_ids(
names=names,
verify_integrity=False,
)
+ if not consistent_sorting and len(ob_index) > 0:
+ # Sort by the levels where the corresponding sort argument is True
+ n_levels = len(sorts)
+ drop_levels = [
+ n_levels - idx
+ for idx, sort in enumerate(reversed(sorts), 1)
+ if not sort
+ ]
+ if len(drop_levels) > 0:
+ sorter = ob_index._drop_level_numbers(drop_levels).argsort()
+ else:
+ sorter = ob_index.argsort()
+ ob_index = ob_index.take(sorter)
+ _, index = np.unique(sorter, return_index=True)
+ ob_ids = np.where(ob_ids == -1, -1, index.take(ob_ids))
ob_ids = ensure_platform_int(ob_ids)
return ob_index, ob_ids
diff --git a/pandas/core/indexes/period.py b/pandas/core/indexes/period.py
index b5f05ef0ab78f..377406e24b1d3 100644
--- a/pandas/core/indexes/period.py
+++ b/pandas/core/indexes/period.py
@@ -563,6 +563,14 @@ def period_range(
Returns
-------
PeriodIndex
+ A PeriodIndex of fixed frequency periods.
+
+ See Also
+ --------
+ date_range : Returns a fixed frequency DatetimeIndex.
+ Period : Represents a period of time.
+ PeriodIndex : Immutable ndarray holding ordinal values indicating regular periods
+ in time.
Notes
-----
diff --git a/pandas/core/reshape/encoding.py b/pandas/core/reshape/encoding.py
index c397c1c2566a5..33ff182f5baee 100644
--- a/pandas/core/reshape/encoding.py
+++ b/pandas/core/reshape/encoding.py
@@ -68,7 +68,8 @@ def get_dummies(
If appending prefix, separator/delimiter to use. Or pass a
list or dictionary as with `prefix`.
dummy_na : bool, default False
- Add a column to indicate NaNs, if False NaNs are ignored.
+ If True, a NaN indicator column will be added even if no NaN values are present.
+ If False, NA values are encoded as all zero.
columns : list-like, default None
Column names in the DataFrame to be encoded.
If `columns` is None then all the columns with
diff --git a/pandas/core/tools/numeric.py b/pandas/core/tools/numeric.py
index 982851d0557c3..f159babb7e018 100644
--- a/pandas/core/tools/numeric.py
+++ b/pandas/core/tools/numeric.py
@@ -11,6 +11,10 @@
lib,
missing as libmissing,
)
+from pandas._libs.tslibs import (
+ Timedelta,
+ Timestamp,
+)
from pandas.util._validators import check_dtype_backend
from pandas.core.dtypes.cast import maybe_downcast_numeric
@@ -189,6 +193,8 @@ def to_numeric(
return float(arg)
if is_number(arg):
return arg
+ if isinstance(arg, (Timedelta, Timestamp)):
+ return arg._value
is_scalars = True
values = np.array([arg], dtype="O")
elif getattr(arg, "ndim", 1) > 1:
diff --git a/pandas/errors/__init__.py b/pandas/errors/__init__.py
index 46e090cc3a589..cf2a9d3f4a238 100644
--- a/pandas/errors/__init__.py
+++ b/pandas/errors/__init__.py
@@ -444,6 +444,11 @@ class SpecificationError(Exception):
The second way is calling ``agg`` on a Dataframe with duplicated functions
names without assigning column name.
+ See Also
+ --------
+ DataFrame.agg : Aggregate using one or more operations over the specified axis.
+ Series.agg : Aggregate using one or more operations over the specified axis.
+
Examples
--------
>>> df = pd.DataFrame({"A": [1, 1, 1, 2, 2], "B": range(5), "C": range(5)})
diff --git a/pandas/io/formats/html.py b/pandas/io/formats/html.py
index adaeed017d7bf..fdea1831d5596 100644
--- a/pandas/io/formats/html.py
+++ b/pandas/io/formats/html.py
@@ -195,6 +195,8 @@ def _write_cell(
esc = {}
rs = pprint_thing(s, escape_chars=esc).strip()
+ # replace spaces betweens strings with non-breaking spaces
+ rs = rs.replace(" ", " ")
if self.render_links and is_url(rs):
rs_unescaped = pprint_thing(s, escape_chars={}).strip()
diff --git a/pandas/io/formats/style.py b/pandas/io/formats/style.py
index 6e5ae09485951..eb6773310da69 100644
--- a/pandas/io/formats/style.py
+++ b/pandas/io/formats/style.py
@@ -222,6 +222,7 @@ class Styler(StylerRenderer):
* ``level<k>`` where `k` is the level in a MultiIndex
* Column label cells include
+
* ``col_heading``
* ``col<n>`` where `n` is the numeric position of the column
* ``level<k>`` where `k` is the level in a MultiIndex
@@ -231,7 +232,7 @@ class Styler(StylerRenderer):
* Trimmed cells include ``col_trim`` or ``row_trim``.
Any, or all, or these classes can be renamed by using the ``css_class_names``
- argument in ``Styler.set_table_classes``, giving a value such as
+ argument in ``Styler.set_table_styles``, giving a value such as
*{"row": "MY_ROW_CLASS", "col_trim": "", "row_trim": ""}*.
Examples
diff --git a/pandas/io/formats/style_render.py b/pandas/io/formats/style_render.py
index 8a6383f7e8f82..08d9fd938c873 100644
--- a/pandas/io/formats/style_render.py
+++ b/pandas/io/formats/style_render.py
@@ -906,9 +906,9 @@ def concatenated_visible_rows(obj):
row_body_headers = [
{
**col,
- "display_value": col["display_value"]
- if col["is_visible"]
- else "",
+ "display_value": (
+ col["display_value"] if col["is_visible"] else ""
+ ),
"cellstyle": self.ctx_index[r, c],
}
for c, col in enumerate(row[:index_levels])
@@ -2069,18 +2069,18 @@ def maybe_convert_css_to_tuples(style: CSSProperties) -> CSSList:
('border','1px solid red')]
"""
if isinstance(style, str):
- s = style.split(";")
- try:
- return [
- (x.split(":")[0].strip(), x.split(":")[1].strip())
- for x in s
- if x.strip() != ""
- ]
- except IndexError as err:
+ if style and ":" not in style:
raise ValueError(
"Styles supplied as string must follow CSS rule formats, "
f"for example 'attr: val;'. '{style}' was given."
- ) from err
+ )
+ s = style.split(";")
+ return [
+ (x.split(":")[0].strip(), ":".join(x.split(":")[1:]).strip())
+ for x in s
+ if x.strip() != ""
+ ]
+
return style
diff --git a/pandas/io/stata.py b/pandas/io/stata.py
index 4be06f93689f2..f1d289726c9c8 100644
--- a/pandas/io/stata.py
+++ b/pandas/io/stata.py
@@ -2004,6 +2004,16 @@ def data_label(self) -> str:
"""
Return data label of Stata file.
+ The data label is a descriptive string associated with the dataset
+ stored in the Stata file. This property provides access to that
+ label, if one is present.
+
+ See Also
+ --------
+ io.stata.StataReader.variable_labels : Return a dict associating each variable
+ name with corresponding label.
+ DataFrame.to_stata : Export DataFrame object to Stata dta format.
+
Examples
--------
>>> df = pd.DataFrame([(1,)], columns=["variable"])
@@ -2066,9 +2076,19 @@ def value_labels(self) -> dict[str, dict[int, str]]:
"""
Return a nested dict associating each variable name to its value and label.
+ This method retrieves the value labels from a Stata file. Value labels are
+ mappings between the coded values and their corresponding descriptive labels
+ in a Stata dataset.
+
Returns
-------
dict
+ A python dictionary.
+
+ See Also
+ --------
+ read_stata : Read Stata file into DataFrame.
+ DataFrame.to_stata : Export DataFrame object to Stata dta format.
Examples
--------
diff --git a/pandas/plotting/_misc.py b/pandas/plotting/_misc.py
index d8455f44ef0d1..81940613dd2b0 100644
--- a/pandas/plotting/_misc.py
+++ b/pandas/plotting/_misc.py
@@ -39,7 +39,7 @@ def table(ax: Axes, data: DataFrame | Series, **kwargs) -> Table:
**kwargs
Keyword arguments to be passed to matplotlib.table.table.
If `rowLabels` or `colLabels` is not specified, data index or column
- name will be used.
+ names will be used.
Returns
-------
@@ -59,11 +59,11 @@ def table(ax: Axes, data: DataFrame | Series, **kwargs) -> Table:
>>> import matplotlib.pyplot as plt
>>> df = pd.DataFrame({"A": [1, 2], "B": [3, 4]})
- >>> fix, ax = plt.subplots()
+ >>> fig, ax = plt.subplots()
>>> ax.axis("off")
(0.0, 1.0, 0.0, 1.0)
>>> table = pd.plotting.table(
- ... ax, df, loc="center", cellLoc="center", colWidths=list([0.2, 0.2])
+ ... ax, df, loc="center", cellLoc="center", colWidths=[0.2, 0.2]
... )
"""
plot_backend = _get_plot_backend("matplotlib")
@@ -549,6 +549,10 @@ def lag_plot(series: Series, lag: int = 1, ax: Axes | None = None, **kwds) -> Ax
"""
Lag plot for time series.
+ A lag plot is a scatter plot of a time series against a lag of itself. It helps
+ in visualizing the temporal dependence between observations by plotting the values
+ at time `t` on the x-axis and the values at time `t + lag` on the y-axis.
+
Parameters
----------
series : Series
@@ -563,6 +567,13 @@ def lag_plot(series: Series, lag: int = 1, ax: Axes | None = None, **kwds) -> Ax
Returns
-------
matplotlib.axes.Axes
+ The matplotlib Axes object containing the lag plot.
+
+ See Also
+ --------
+ plotting.autocorrelation_plot : Autocorrelation plot for time series.
+ matplotlib.pyplot.scatter : A scatter plot of y vs. x with varying marker size
+ and/or color in Matplotlib.
Examples
--------
diff --git a/pandas/tests/apply/test_frame_apply.py b/pandas/tests/apply/test_frame_apply.py
index dee0efcd8fd15..f0ab01e9e960e 100644
--- a/pandas/tests/apply/test_frame_apply.py
+++ b/pandas/tests/apply/test_frame_apply.py
@@ -741,8 +741,9 @@ def test_apply_category_equalness(val):
result = df.a.apply(lambda x: x == val)
expected = Series(
- [np.nan if pd.isnull(x) else x == val for x in df_values], name="a"
+ [False if pd.isnull(x) else x == val for x in df_values], name="a"
)
+ # False since behavior of NaN for categorical dtype has been changed (GH 59966)
tm.assert_series_equal(result, expected)
diff --git a/pandas/tests/apply/test_series_apply.py b/pandas/tests/apply/test_series_apply.py
index 76704de6f2d10..9541b0b7495c7 100644
--- a/pandas/tests/apply/test_series_apply.py
+++ b/pandas/tests/apply/test_series_apply.py
@@ -236,10 +236,10 @@ def test_apply_categorical_with_nan_values(series, by_row):
with pytest.raises(AttributeError, match=msg):
s.apply(lambda x: x.split("-")[0], by_row=by_row)
return
-
- result = s.apply(lambda x: x.split("-")[0], by_row=by_row)
+ # NaN for cat dtype fixed in (GH 59966)
+ result = s.apply(lambda x: x.split("-")[0] if pd.notna(x) else False, by_row=by_row)
result = result.astype(object)
- expected = Series(["1", "1", np.nan], dtype="category")
+ expected = Series(["1", "1", False], dtype="category")
expected = expected.astype(object)
tm.assert_series_equal(result, expected)
diff --git a/pandas/tests/arrays/sparse/test_accessor.py b/pandas/tests/arrays/sparse/test_accessor.py
index bd3298940ae3a..08bfd5b69fdd9 100644
--- a/pandas/tests/arrays/sparse/test_accessor.py
+++ b/pandas/tests/arrays/sparse/test_accessor.py
@@ -252,3 +252,7 @@ def test_with_column_named_sparse(self):
# https://github.com/pandas-dev/pandas/issues/30758
df = pd.DataFrame({"sparse": pd.arrays.SparseArray([1, 2])})
assert isinstance(df.sparse, pd.core.arrays.sparse.accessor.SparseFrameAccessor)
+
+ def test_subclassing(self):
+ df = tm.SubclassedDataFrame({"sparse": pd.arrays.SparseArray([1, 2])})
+ assert isinstance(df.sparse.to_dense(), tm.SubclassedDataFrame)
diff --git a/pandas/tests/frame/methods/test_value_counts.py b/pandas/tests/frame/methods/test_value_counts.py
index 7670b53f23173..de5029b9f18b2 100644
--- a/pandas/tests/frame/methods/test_value_counts.py
+++ b/pandas/tests/frame/methods/test_value_counts.py
@@ -128,7 +128,7 @@ def test_data_frame_value_counts_dropna_true(nulls_fixture):
expected = pd.Series(
data=[1, 1],
index=pd.MultiIndex.from_arrays(
- [("Beth", "John"), ("Louise", "Smith")], names=["first_name", "middle_name"]
+ [("John", "Beth"), ("Smith", "Louise")], names=["first_name", "middle_name"]
),
name="count",
)
@@ -156,7 +156,7 @@ def test_data_frame_value_counts_dropna_false(nulls_fixture):
pd.Index(["Anne", "Beth", "John"]),
pd.Index(["Louise", "Smith", np.nan]),
],
- codes=[[0, 1, 2, 2], [2, 0, 1, 2]],
+ codes=[[2, 0, 2, 1], [1, 2, 2, 0]],
names=["first_name", "middle_name"],
),
name="count",
diff --git a/pandas/tests/groupby/methods/test_value_counts.py b/pandas/tests/groupby/methods/test_value_counts.py
index 8f8f7f64aba75..8ca6593a19f20 100644
--- a/pandas/tests/groupby/methods/test_value_counts.py
+++ b/pandas/tests/groupby/methods/test_value_counts.py
@@ -255,10 +255,10 @@ def test_basic(education_df, request):
index=MultiIndex.from_tuples(
[
("FR", "male", "low"),
- ("FR", "female", "high"),
("FR", "male", "medium"),
- ("US", "female", "high"),
+ ("FR", "female", "high"),
("US", "male", "low"),
+ ("US", "female", "high"),
],
names=["country", "gender", "education"],
),
@@ -472,11 +472,11 @@ def test_data_frame_value_counts(
(
False,
False,
- [0, 1, 3, 5, 7, 6, 8, 2, 4],
+ [0, 1, 3, 5, 6, 7, 8, 2, 4],
[0.5, 0.5, 1.0, 0.25, 0.25, 0.25, 0.25, 1.0, 1.0],
),
(False, True, [0, 1, 3, 5, 2, 4], [0.5, 0.5, 1.0, 1.0, 1.0, 1.0]),
- (True, False, [0, 1, 5, 7, 6, 8], [0.5, 0.5, 0.25, 0.25, 0.25, 0.25]),
+ (True, False, [0, 1, 5, 6, 7, 8], [0.5, 0.5, 0.25, 0.25, 0.25, 0.25]),
(True, True, [0, 1, 5], [0.5, 0.5, 1.0]),
],
)
@@ -518,7 +518,7 @@ def test_dropna_combinations(
True,
[1, 1],
MultiIndex.from_arrays(
- [(1, 1), ("Beth", "John"), ("Louise", "Smith")],
+ [(1, 1), ("John", "Beth"), ("Smith", "Louise")],
names=["key", "first_name", "middle_name"],
),
),
@@ -531,7 +531,7 @@ def test_dropna_combinations(
Index(["Anne", "Beth", "John"]),
Index(["Louise", "Smith", np.nan]),
],
- codes=[[0, 0, 0, 0], [0, 1, 2, 2], [2, 0, 1, 2]],
+ codes=[[0, 0, 0, 0], [2, 0, 2, 1], [1, 2, 2, 0]],
names=["key", "first_name", "middle_name"],
),
),
@@ -609,17 +609,17 @@ def test_categorical_single_grouper_with_only_observed_categories(
expected_index = MultiIndex.from_tuples(
[
("FR", "male", "low"),
- ("FR", "female", "high"),
("FR", "male", "medium"),
+ ("FR", "female", "high"),
+ ("FR", "male", "high"),
("FR", "female", "low"),
("FR", "female", "medium"),
- ("FR", "male", "high"),
- ("US", "female", "high"),
("US", "male", "low"),
+ ("US", "female", "high"),
+ ("US", "male", "medium"),
+ ("US", "male", "high"),
("US", "female", "low"),
("US", "female", "medium"),
- ("US", "male", "high"),
- ("US", "male", "medium"),
],
names=["country", "gender", "education"],
)
@@ -711,17 +711,17 @@ def test_categorical_single_grouper_observed_true(
expected_index = [
("FR", "male", "low"),
- ("FR", "female", "high"),
("FR", "male", "medium"),
+ ("FR", "female", "high"),
+ ("FR", "male", "high"),
("FR", "female", "low"),
("FR", "female", "medium"),
- ("FR", "male", "high"),
- ("US", "female", "high"),
("US", "male", "low"),
+ ("US", "female", "high"),
+ ("US", "male", "medium"),
+ ("US", "male", "high"),
("US", "female", "low"),
("US", "female", "medium"),
- ("US", "male", "high"),
- ("US", "male", "medium"),
]
assert_categorical_single_grouper(
@@ -791,23 +791,23 @@ def test_categorical_single_grouper_observed_false(
expected_index = [
("FR", "male", "low"),
- ("FR", "female", "high"),
("FR", "male", "medium"),
+ ("FR", "female", "high"),
+ ("FR", "male", "high"),
("FR", "female", "low"),
("FR", "female", "medium"),
- ("FR", "male", "high"),
- ("US", "female", "high"),
("US", "male", "low"),
+ ("US", "female", "high"),
+ ("US", "male", "medium"),
+ ("US", "male", "high"),
("US", "female", "low"),
("US", "female", "medium"),
- ("US", "male", "high"),
- ("US", "male", "medium"),
- ("ASIA", "female", "high"),
- ("ASIA", "female", "low"),
- ("ASIA", "female", "medium"),
- ("ASIA", "male", "high"),
("ASIA", "male", "low"),
("ASIA", "male", "medium"),
+ ("ASIA", "male", "high"),
+ ("ASIA", "female", "low"),
+ ("ASIA", "female", "medium"),
+ ("ASIA", "female", "high"),
]
assert_categorical_single_grouper(
@@ -837,8 +837,8 @@ def test_categorical_single_grouper_observed_false(
("US", "high", "male"),
("US", "low", "male"),
("US", "low", "female"),
- ("US", "medium", "female"),
("US", "medium", "male"),
+ ("US", "medium", "female"),
],
),
(
@@ -949,17 +949,17 @@ def test_categorical_non_groupers(
expected_index = [
("FR", "male", "low"),
- ("FR", "female", "high"),
("FR", "male", "medium"),
+ ("FR", "female", "high"),
+ ("FR", "male", "high"),
("FR", "female", "low"),
("FR", "female", "medium"),
- ("FR", "male", "high"),
- ("US", "female", "high"),
("US", "male", "low"),
+ ("US", "female", "high"),
+ ("US", "male", "medium"),
+ ("US", "male", "high"),
("US", "female", "low"),
("US", "female", "medium"),
- ("US", "male", "high"),
- ("US", "male", "medium"),
]
expected_series = Series(
data=expected_data,
@@ -1178,7 +1178,7 @@ def test_value_counts_sort(sort, vc_sort, normalize):
if sort and vc_sort:
taker = [0, 1, 2]
elif sort and not vc_sort:
- taker = [0, 1, 2]
+ taker = [1, 0, 2]
elif not sort and vc_sort:
taker = [0, 2, 1]
else:
@@ -1219,3 +1219,25 @@ def test_value_counts_sort_categorical(sort, vc_sort, normalize):
expected = expected.take(taker)
tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize("groupby_sort", [True, False])
+def test_value_counts_all_na(sort, dropna, groupby_sort):
+ # GH#59989
+ df = DataFrame({"a": [2, 1, 1], "b": np.nan})
+ gb = df.groupby("a", sort=groupby_sort)
+ result = gb.value_counts(sort=sort, dropna=dropna)
+
+ kwargs = {"levels": [[1, 2], [np.nan]], "names": ["a", "b"]}
+ if dropna:
+ data = []
+ index = MultiIndex(codes=[[], []], **kwargs)
+ elif not groupby_sort and not sort:
+ data = [1, 2]
+ index = MultiIndex(codes=[[1, 0], [0, 0]], **kwargs)
+ else:
+ data = [2, 1]
+ index = MultiIndex(codes=[[0, 1], [0, 0]], **kwargs)
+ expected = Series(data, index=index, dtype="int64", name="count")
+
+ tm.assert_series_equal(result, expected)
diff --git a/pandas/tests/indexes/test_old_base.py b/pandas/tests/indexes/test_old_base.py
index cd3d599abd30e..0199e21bfc980 100644
--- a/pandas/tests/indexes/test_old_base.py
+++ b/pandas/tests/indexes/test_old_base.py
@@ -455,7 +455,7 @@ def test_insert_out_of_bounds(self, index, using_infer_string):
msg = "slice indices must be integers or None or have an __index__ method"
if using_infer_string and (
- index.dtype == "string" or index.dtype == "category" # noqa: PLR1714
+ index.dtype == "string" or index.dtype == "category"
):
msg = "loc must be an integer between"
diff --git a/pandas/tests/io/formats/style/test_style.py b/pandas/tests/io/formats/style/test_style.py
index 89addbbbc1ded..e9fc2b2d27afd 100644
--- a/pandas/tests/io/formats/style/test_style.py
+++ b/pandas/tests/io/formats/style/test_style.py
@@ -886,8 +886,19 @@ def test_maybe_convert_css_to_tuples(self):
expected = []
assert maybe_convert_css_to_tuples("") == expected
+ # issue #59623
+ expected = [("a", "b"), ("c", "url('data:123')")]
+ assert maybe_convert_css_to_tuples("a:b;c: url('data:123');") == expected
+
+ # if no value, return attr and empty string
+ expected = [("a", ""), ("c", "")]
+ assert maybe_convert_css_to_tuples("a:;c: ") == expected
+
def test_maybe_convert_css_to_tuples_err(self):
- msg = "Styles supplied as string must follow CSS rule formats"
+ msg = (
+ "Styles supplied as string must follow CSS rule formats, "
+ "for example 'attr: val;'. 'err' was given."
+ )
with pytest.raises(ValueError, match=msg):
maybe_convert_css_to_tuples("err")
diff --git a/pandas/tests/io/formats/test_format.py b/pandas/tests/io/formats/test_format.py
index 82cc3a838ca68..0dc16e1ebc723 100644
--- a/pandas/tests/io/formats/test_format.py
+++ b/pandas/tests/io/formats/test_format.py
@@ -375,12 +375,29 @@ def test_repr_min_rows(self):
(None, "{:.3f}", "None"),
("", "{:.2f}", ""),
(112345.6789, "{:6.3f}", "112345.679"),
+ ("foo foo", None, "foo foo"),
+ (" foo", None, "foo"),
+ (
+ "foo foo foo",
+ None,
+ "foo foo foo",
+ ), # odd no.of spaces
+ (
+ "foo foo foo",
+ None,
+ "foo foo foo",
+ ), # even no.of spaces
],
)
def test_repr_float_formatting_html_output(
self, data, format_option, expected_values
):
- with option_context("display.float_format", format_option.format):
+ if format_option is not None:
+ with option_context("display.float_format", format_option.format):
+ df = DataFrame({"A": [data]})
+ html_output = df._repr_html_()
+ assert expected_values in html_output
+ else:
df = DataFrame({"A": [data]})
html_output = df._repr_html_()
assert expected_values in html_output
diff --git a/pandas/tests/tools/test_to_numeric.py b/pandas/tests/tools/test_to_numeric.py
index 585b7ca94f730..f3645bf0649bd 100644
--- a/pandas/tests/tools/test_to_numeric.py
+++ b/pandas/tests/tools/test_to_numeric.py
@@ -384,6 +384,21 @@ def test_timedelta(transform_assert_equal):
assert_equal(result, expected)
+@pytest.mark.parametrize(
+ "scalar",
+ [
+ pd.Timedelta(1, "D"),
+ pd.Timestamp("2017-01-01T12"),
+ pd.Timestamp("2017-01-01T12", tz="US/Pacific"),
+ ],
+)
+def test_timedelta_timestamp_scalar(scalar):
+ # GH#59944
+ result = to_numeric(scalar)
+ expected = to_numeric(Series(scalar))[0]
+ assert result == expected
+
+
def test_period(request, transform_assert_equal):
transform, assert_equal = transform_assert_equal
diff --git a/pandas/util/version/__init__.py b/pandas/util/version/__init__.py
index b5d975a0db1d8..bd741140f6542 100644
--- a/pandas/util/version/__init__.py
+++ b/pandas/util/version/__init__.py
@@ -114,6 +114,14 @@ class InvalidVersion(ValueError):
"""
An invalid version was found, users should refer to PEP 440.
+ The ``InvalidVersion`` exception is raised when a version string is
+ improperly formatted. Pandas uses this exception to ensure that all
+ version strings are PEP 440 compliant.
+
+ See Also
+ --------
+ util.version.Version : Class for handling and parsing version strings.
+
Examples
--------
>>> pd.util.version.Version("1.")
diff --git a/pyproject.toml b/pyproject.toml
index d0fcdc4b21b33..1386546996bf2 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -324,7 +324,8 @@ ignore = [
"PT019",
# The following rules may cause conflicts when used with the formatter:
"ISC001",
-
+ # if-stmt-min-max
+ "PLR1730",
### TODO: Enable gradually
# Useless statement
@@ -341,8 +342,10 @@ ignore = [
"RUF012",
# type-comparison
"E721",
-
- # Additional pylint rules
+ # repeated-equality-comparison
+ "PLR1714",
+ # self-or-cls-assignment
+ "PLW0642",
# literal-membership
"PLR6201", # 847 errors
# Method could be a function, class method, or static method
From 902601f3e86501dcec8aaf0c28cbc59a7f7ee6d6 Mon Sep 17 00:00:00 2001
From: veljanin <veljkojovanovic1991@gmail.com>
Date: Mon, 14 Oct 2024 12:34:05 +0200
Subject: [PATCH 6/6] revised testing to resolve CI errors v2
---
pandas/tests/frame/methods/test_convert_dtypes.py | 12 ++++++------
pandas/tests/series/methods/test_convert_dtypes.py | 11 +++++------
2 files changed, 11 insertions(+), 12 deletions(-)
diff --git a/pandas/tests/frame/methods/test_convert_dtypes.py b/pandas/tests/frame/methods/test_convert_dtypes.py
index 8a7052eb81b98..ab4f849c741fd 100644
--- a/pandas/tests/frame/methods/test_convert_dtypes.py
+++ b/pandas/tests/frame/methods/test_convert_dtypes.py
@@ -3,6 +3,8 @@
import numpy as np
import pytest
+import pandas.util._test_decorators as td
+
import pandas as pd
import pandas._testing as tm
@@ -35,7 +37,7 @@ def test_convert_empty(self):
empty_df = pd.DataFrame()
tm.assert_frame_equal(empty_df, empty_df.convert_dtypes())
- @tm.skip_if_no("pyarrow")
+ @td.skip_if_no("pyarrow")
def test_convert_empty_categorical_to_pyarrow(self):
# GH#59934
df = pd.DataFrame(
@@ -51,11 +53,9 @@ def test_convert_empty_categorical_to_pyarrow(self):
assert converted.A.dtype == "category", "Dtype in column A is not 'category'"
assert converted.B.dtype == "category", "Dtype in column B is not 'category'"
assert converted.A.cat.categories.empty, "Categories in column A are not empty"
- assert converted.B.cat.categories.__contains__(
- "B1"
- ) and converted.B.cat.categories.__contains__(
- "B2"
- ), "Categories in column B doesn't contain adequate categories"
+ assert converted.B.cat.categories.isin(
+ ["B1", "B2"]
+ ).all(), "Categories in column B doesn't contain adequate categories"
def test_convert_dtypes_retain_column_names(self):
# GH#41435
diff --git a/pandas/tests/series/methods/test_convert_dtypes.py b/pandas/tests/series/methods/test_convert_dtypes.py
index fa9035f325d71..cb1fa11c9f7c4 100644
--- a/pandas/tests/series/methods/test_convert_dtypes.py
+++ b/pandas/tests/series/methods/test_convert_dtypes.py
@@ -4,6 +4,7 @@
import pytest
from pandas._libs import lib
+import pandas.util._test_decorators as td
import pandas as pd
import pandas._testing as tm
@@ -298,7 +299,7 @@ def test_convert_dtypes_pyarrow_null(self):
expected = pd.Series([None, None], dtype=pd.ArrowDtype(pa.null()))
tm.assert_series_equal(result, expected)
- @tm.skip_if_no("pyarrow")
+ @td.skip_if_no("pyarrow")
def test_convert_empty_categorical_to_pyarrow(self):
# GH#59934
ser1 = pd.Series(pd.Categorical([None] * 5))
@@ -311,8 +312,6 @@ def test_convert_empty_categorical_to_pyarrow(self):
ser2 = pd.Series(pd.Categorical([None] * 5, categories=["S1", "S2"]))
converted2 = ser2.convert_dtypes(dtype_backend="pyarrow")
- assert converted2.cat.categories.__contains__(
- "S1"
- ) and converted2.cat.categories.__contains__(
- "S2"
- ), "Categories in ser2 doesn't contain adequate categories"
+ assert converted2.cat.categories.isin(
+ ["S1", "S2"]
+ ).all(), "Categories in ser2 doesn't contain adequate categories"