merge master

Author: arw2019

.github/workflows/ci.yml

@@ -153,3 +153,12 @@ jobs:
  run: |
  source activate pandas-dev
  pytest pandas/tests/frame/methods --array-manager
+ pytest pandas/tests/arithmetic/ --array-manager
+
+ # indexing subset (temporary since other tests don't pass yet)
+ pytest pandas/tests/frame/indexing/test_indexing.py::TestDataFrameIndexing::test_setitem_boolean --array-manager
+ pytest pandas/tests/frame/indexing/test_where.py --array-manager
+ pytest pandas/tests/frame/indexing/test_indexing.py::TestDataFrameIndexing::test_setitem_multi_index --array-manager
+ pytest pandas/tests/frame/indexing/test_setitem.py::TestDataFrameSetItem::test_setitem_listlike_indexer_duplicate_columns --array-manager
+ pytest pandas/tests/indexing/multiindex/test_setitem.py::TestMultiIndexSetItem::test_astype_assignment_with_dups --array-manager
+ pytest pandas/tests/indexing/multiindex/test_setitem.py::TestMultiIndexSetItem::test_frame_setitem_multi_column --array-manager

.github/workflows/database.yml

@@ -170,3 +170,11 @@ jobs:
 
  - name: Print skipped tests
  run: python ci/print_skipped.py
+
+ - name: Upload coverage to Codecov
+ uses: codecov/codecov-action@v1
+ with:
+ files: /tmp/test_coverage.xml
+ flags: unittests
+ name: codecov-pandas
+ fail_ci_if_error: true

.pre-commit-config.yaml

@@ -138,7 +138,7 @@ repos:
  entry: python scripts/check_for_inconsistent_pandas_namespace.py
  language: python
  types: [python]
- files: ^pandas/tests/
+ files: ^pandas/tests/frame/
  - id: FrameOrSeriesUnion
  name: Check for use of Union[Series, DataFrame] instead of FrameOrSeriesUnion alias
  entry: Union\[.*(Series,.*DataFrame|DataFrame,.*Series).*\]
@@ -180,6 +180,12 @@ repos:
  language: pygrep
  types: [python]
  files: ^pandas/tests/
+ - id: title-capitalization
+ name: Validate correct capitalization among titles in documentation
+ entry: python scripts/validate_rst_title_capitalization.py
+ language: python
+ types: [rst]
+ files: ^doc/source/(development|reference)/
 - repo: https://github.com/asottile/yesqa
  rev: v1.2.2
  hooks:

MANIFEST.in

@@ -1,9 +1,4 @@
-include MANIFEST.in
-include LICENSE
 include RELEASE.md
-include README.md
-include setup.py
-include pyproject.toml
 
 graft doc
 prune doc/build
@@ -16,10 +11,12 @@ global-exclude *.bz2
 global-exclude *.csv
 global-exclude *.dta
 global-exclude *.feather
+global-exclude *.tar
 global-exclude *.gz
 global-exclude *.h5
 global-exclude *.html
 global-exclude *.json
+global-exclude *.jsonl
 global-exclude *.pickle
 global-exclude *.png
 global-exclude *.pyc
@@ -40,6 +37,11 @@ global-exclude .DS_Store
 global-exclude .git*
 global-exclude \#*
 
+# GH 39321
+# csv_dir_path fixture checks the existence of the directory
+# exclude the whole directory to avoid running related tests in sdist
+prune pandas/tests/io/parser/data
+
 include versioneer.py
 include pandas/_version.py
 include pandas/io/formats/templates/*.tpl

Makefile

@@ -25,16 +25,3 @@ doc:
 cd doc; \
 python make.py clean; \
 python make.py html
-
-check:
-python3 scripts/validate_unwanted_patterns.py \
---validation-type="private_function_across_module" \
---included-file-extensions="py" \
---excluded-file-paths=pandas/tests,asv_bench/ \
-pandas/
-
-python3 scripts/validate_unwanted_patterns.py \
---validation-type="private_import_across_module" \
---included-file-extensions="py" \
---excluded-file-paths=pandas/tests,asv_bench/,doc/
-pandas/

asv_bench/benchmarks/algos/__init__.py

@@ -0,0 +1,12 @@
+"""
+algos/ directory is intended for individual functions from core.algorithms
+
+In many cases these algorithms are reachable in multiple ways:
+ algos.foo(x, y)
+ Series(x).foo(y)
+ Index(x).foo(y)
+ pd.array(x).foo(y)
+
+In most cases we profile the Series variant directly, trusting the performance
+of the others to be highly correlated.
+"""