Merge branch 'pandas-dev:main' into t03

Author: ramvikrams

.github/workflows/deprecation-tracking-bot.yml

@@ -0,0 +1,31 @@
+name: Deprecations Bot
+
+on:
+ pull_request:
+ branches:
+ - main
+ types:
+ [closed]
+
+
+permissions:
+ contents: read
+
+jobs:
+ deprecation_update:
+ permissions:
+ issues: write
+ if: >-
+ contains(github.event.pull_request.labels.*.name, 'Deprecate') && github.event.pull_request.merged == true
+ runs-on: ubuntu-22.04
+ env:
+ DEPRECATION_TRACKER_ISSUE: 50578
+ steps:
+ - name: Checkout
+ run: |
+ echo "Adding deprecation PR number to deprecation tracking issue"
+ export PR=${{ github.event.pull_request.number }}
+ BODY=$(curl -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" https://api.github.com/repos/${{ github.repository }}/issues/${DEPRECATION_TRACKER_ISSUE} |
+ python3 -c "import sys, json, os; x = {'body': json.load(sys.stdin)['body']}; pr = os.environ['PR']; x['body'] += f'\n- [ ] #{pr}'; print(json.dumps(x))")
+ echo ${BODY}
+ curl -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" -X PATCH -d "${BODY}" https://api.github.com/repos/${{ github.repository }}/issues/${DEPRECATION_TRACKER_ISSUE}

.pep8speaks.yml

@@ -42,7 +42,7 @@ repos:
  rev: v2.2.2
  hooks:
  - id: codespell
- types_or: [python, rst, markdown]
+ types_or: [python, rst, markdown, cython, c]
  additional_dependencies: [tomli]
 - repo: https://github.com/MarcoGorelli/cython-lint
  rev: v0.12.5
@@ -160,14 +160,6 @@ repos:
  types: [pyi]
  args: [scripts/run_stubtest.py]
  stages: [manual]
- - id: flake8-rst
- name: flake8-rst
- description: Run flake8 on code snippets in docstrings or RST files
- language: python
- entry: flake8-rst
- types: [rst]
- args: [--filename=*.rst]
- additional_dependencies: [flake8-rst==0.7.0, flake8==3.7.9]
  - id: inconsistent-namespace-usage
  name: 'Check for inconsistent use of pandas namespace'
  entry: python scripts/check_for_inconsistent_pandas_namespace.py

.pre-commit-config.yaml

@@ -93,8 +93,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
  pandas.Series.item \
  pandas.Series.pipe \
  pandas.Series.mode \
- pandas.Series.sem \
- pandas.Series.skew \
  pandas.Series.is_unique \
  pandas.Series.is_monotonic_increasing \
  pandas.Series.is_monotonic_decreasing \
@@ -542,8 +540,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
  pandas.DataFrame.keys \
  pandas.DataFrame.iterrows \
  pandas.DataFrame.pipe \
- pandas.DataFrame.sem \
- pandas.DataFrame.skew \
  pandas.DataFrame.backfill \
  pandas.DataFrame.pad \
  pandas.DataFrame.swapaxes \

ci/code_checks.sh

@@ -236,11 +236,11 @@ ul.task-bullet > li > p:first-child {
 
 .tutorial-card .card-header {
  cursor: pointer;
- background-color: white;
+ background-color: transparent;
 }
 
 .tutorial-card .card-body {
- background-color: #F0F0F0;
+ background-color: transparent;
 }
 
 .tutorial-card .badge {

doc/source/_static/css/getting_started.css

@@ -600,3 +600,20 @@ Install pandas-stubs to enable basic type coverage of pandas API.
 Learn more by reading through :issue:`14468`, :issue:`26766`, :issue:`28142`.
 
 See installation and usage instructions on the `GitHub page <https://github.com/pandas-dev/pandas-stubs>`__.
+
+`Hamilton <https://github.com/dagworks-inc/hamilton>`__
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Hamilton is a declarative dataflow framework that came out of Stitch Fix. It was designed to help one manage a Pandas code base, specifically with respect to feature engineering for machine learning models.
+
+It prescibes an opinionated paradigm, that ensures all code is:
+
+* unit testable
+* integration testing friendly
+* documentation friendly
+* transformation logic is reusable, as it is decoupled from the context of where it is used.
+* integratable with runtime data quality checks.
+
+This helps one to scale your pandas code base, at the same time, keeping maintenance costs low.
+
+For more information, see `documentation <https://hamilton.readthedocs.io/>`__.

doc/source/_static/legacy_0.10.h5

@@ -617,8 +617,8 @@ even if some categories are not present in the data:
  df = pd.DataFrame(
  data=[[1, 2, 3], [4, 5, 6]],
  columns=pd.MultiIndex.from_arrays([["A", "B", "B"], columns]),
- )
- df.groupby(axis=1, level=1).sum()
+ ).T
+ df.groupby(level=1).sum()
 
 Groupby will also show "unused" categories: