Merge branch 'master' into range_builtin

Author: attack68

.pre-commit-config.yaml

@@ -1,10 +1,38 @@
 minimum_pre_commit_version: 2.9.2
 exclude: ^LICENSES/|\.(html|csv|svg)$
 repos:
+-   repo: https://github.com/MarcoGorelli/absolufy-imports
+    rev: v0.2.1
+    hooks:
+    -   id: absolufy-imports
+        files: ^pandas/
 -   repo: https://github.com/python/black
     rev: 20.8b1
     hooks:
     -   id: black
+-   repo: https://github.com/codespell-project/codespell
+    rev: v2.0.0
+    hooks:
+    -   id: codespell
+        types_or: [python, rst, markdown]
+        files: ^(pandas|doc)/
+        exclude: ^pandas/tests/
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v3.4.0
+    hooks:
+    -   id: end-of-file-fixer
+        exclude: \.txt$
+    -   id: trailing-whitespace
+-   repo: https://github.com/cpplint/cpplint
+    rev: f7061b1 # the latest tag does not have the hook
+    hooks:
+    -   id: cpplint
+        # We don't lint all C files because we don't want to lint any that are built
+        # from Cython files nor do we want to lint C files that we didn't modify for
+        # this particular codebase (e.g. src/headers, src/klib). However,
+        # we can lint all header files since they aren't "generated" like C files are.
+        exclude: ^pandas/_libs/src/(klib|headers)/
+        args: [--quiet, '--extensions=c,h', '--headers=h', --recursive, '--filter=-readability/casting,-runtime/int,-build/include_subdir']
 -   repo: https://gitlab.com/pycqa/flake8
     rev: 3.8.4
     hooks:
@@ -23,6 +51,10 @@ repos:
     rev: 5.7.0
     hooks:
     -   id: isort
+-   repo: https://github.com/MarcoGorelli/no-string-hints
+    rev: v0.1.7
+    hooks:
+    -   id: no-string-hints
 -   repo: https://github.com/asottile/pyupgrade
     rev: v2.10.0
     hooks:
@@ -38,16 +70,12 @@ repos:
       - id: rst-inline-touching-normal
         types: [text]  # overwrite types: [rst]
         types_or: [python, rst]
+-   repo: https://github.com/asottile/yesqa
+    rev: v1.2.2
+    hooks:
+    -   id: yesqa
 -   repo: local
     hooks:
-    -   id: pip_to_conda
-        name: Generate pip dependency from conda
-        description: This hook checks if the conda environment.yml and requirements-dev.txt are equal
-        language: python
-        entry: python scripts/generate_pip_deps_from_conda.py
-        files: ^(environment.yml|requirements-dev.txt)$
-        pass_filenames: false
-        additional_dependencies: [pyyaml]
     -   id: flake8-rst
         name: flake8-rst
         description: Run flake8 on code snippets in docstrings or RST files
@@ -56,6 +84,40 @@ repos:
         types: [rst]
         args: [--filename=*.rst]
         additional_dependencies: [flake8-rst==0.7.0, flake8==3.7.9]
+    -   id: frame-or-series-union
+        name: Check for use of Union[Series, DataFrame] instead of FrameOrSeriesUnion alias
+        entry: Union\[.*(Series,.*DataFrame|DataFrame,.*Series).*\]
+        language: pygrep
+        types: [python]
+        exclude: ^pandas/_typing\.py$
+    -   id: inconsistent-namespace-usage
+        name: 'Check for inconsistent use of pandas namespace in tests'
+        entry: python scripts/check_for_inconsistent_pandas_namespace.py
+        language: python
+        types: [python]
+        files: ^pandas/tests/frame/
+    -   id: incorrect-code-directives
+        name: Check for incorrect code block or IPython directives
+        language: pygrep
+        entry: (\.\. code-block ::|\.\. ipython ::)
+        types_or: [python, cython, rst]
+    -   id: no-os-remove
+        name: Check code for instances of os.remove
+        entry: os\.remove
+        language: pygrep
+        types: [python]
+        files: ^pandas/tests/
+        exclude: |
+            (?x)^
+            pandas/tests/io/excel/test_writers\.py
+            |pandas/tests/io/pytables/common\.py
+            |pandas/tests/io/pytables/test_store\.py$
+    -   id: no-pandas-api-types
+        name: Check code for instances of pd.api.types
+        entry: (pd|pandas)\.api\.types\.
+        language: pygrep
+        types: [python]
+        files: ^pandas/tests/
     -   id: non-standard-imports
         name: Check for non-standard imports
         language: pygrep
@@ -67,17 +129,6 @@ repos:
 
             # Check for imports from collections.abc instead of `from collections import abc`
             |from\ collections\.abc\ import
-
-    -   id: non-standard-numpy.random-related-imports
-        name: Check for non-standard numpy.random-related imports excluding pandas/_testing.py
-        language: pygrep
-        exclude: pandas/_testing.py
-        entry: |
-            (?x)
-            # Check for imports from np.random.<method> instead of `from numpy import random` or `from numpy.random import <method>`
-            from\ numpy\ import\ random
-            |from\ numpy.random\ import
-        types: [python]
     -   id: non-standard-imports-in-tests
         name: Check for non-standard imports in test suite
         language: pygrep
@@ -95,62 +146,79 @@ repos:
             |pd\.testing\.
         types: [python]
         files: ^pandas/tests/
-    -   id: incorrect-code-directives
-        name: Check for incorrect code block or IPython directives
+    -   id: non-standard-numpy-random-related-imports
+        name: Check for non-standard numpy.random-related imports excluding pandas/_testing.py
+        language: pygrep
+        exclude: pandas/_testing.py
+        entry: |
+            (?x)
+            # Check for imports from np.random.<method> instead of `from numpy import random` or `from numpy.random import <method>`
+            from\ numpy\ import\ random
+            |from\ numpy.random\ import
+        types: [python]
+    -   id: np-bool
+        name: Check for use of np.bool instead of np.bool_
+        entry: np\.bool[^_8]
         language: pygrep
-        entry: (\.\. code-block ::|\.\. ipython ::)
         types_or: [python, cython, rst]
-    -   id: unwanted-patterns-strings-to-concatenate
-        name: Check for use of not concatenated strings
+    -   id: np-object
+        name: Check for use of np.object instead of np.object_
+        entry: np\.object[^_8]
+        language: pygrep
+        types_or: [python, cython, rst]
+    -   id: pip-to-conda
+        name: Generate pip dependency from conda
+        description: This hook checks if the conda environment.yml and requirements-dev.txt are equal
         language: python
-        entry: python scripts/validate_unwanted_patterns.py --validation-type="strings_to_concatenate"
-        types_or: [python, cython]
-    -   id: unwanted-patterns-strings-with-wrong-placed-whitespace
-        name: Check for strings with wrong placed spaces
+        entry: python scripts/generate_pip_deps_from_conda.py
+        files: ^(environment.yml|requirements-dev.txt)$
+        pass_filenames: false
+        additional_dependencies: [pyyaml]
+    -   id: title-capitalization
+        name: Validate correct capitalization among titles in documentation
+        entry: python scripts/validate_rst_title_capitalization.py
         language: python
-        entry: python scripts/validate_unwanted_patterns.py --validation-type="strings_with_wrong_placed_whitespace"
+        types: [rst]
+        files: ^doc/source/(development|reference)/
+    -   id: type-not-class
+        name: Check for use of foo.__class__ instead of type(foo)
+        entry: \.__class__
+        language: pygrep
         types_or: [python, cython]
-    -   id: unwanted-patterns-private-import-across-module
-        name: Check for import of private attributes across modules
+    -   id: unwanted-patterns-bare-pytest-raises
+        name: Check for use of bare pytest raises
         language: python
-        entry: python scripts/validate_unwanted_patterns.py --validation-type="private_import_across_module"
+        entry: python scripts/validate_unwanted_patterns.py --validation-type="bare_pytest_raises"
         types: [python]
-        exclude: ^(asv_bench|pandas/tests|doc)/
+        files: ^pandas/tests/
+        exclude: ^pandas/tests/extension/
     -   id: unwanted-patterns-private-function-across-module
         name: Check for use of private functions across modules
         language: python
         entry: python scripts/validate_unwanted_patterns.py --validation-type="private_function_across_module"
         types: [python]
         exclude: ^(asv_bench|pandas/tests|doc)/
-    -   id: unwanted-patterns-bare-pytest-raises
-        name: Check for use of bare pytest raises
+    -   id: unwanted-patterns-private-import-across-module
+        name: Check for import of private attributes across modules
         language: python
-        entry: python scripts/validate_unwanted_patterns.py --validation-type="bare_pytest_raises"
+        entry: python scripts/validate_unwanted_patterns.py --validation-type="private_import_across_module"
         types: [python]
-        files: ^pandas/tests/
-        exclude: ^pandas/tests/extension/
-    -   id: unwanted-patters-pytest-xfail
+        exclude: ^(asv_bench|pandas/tests|doc)/
+    -   id: unwanted-patterns-pytest-xfail
         name: Check for use of pytest.xfail
         entry: pytest\.xfail
         language: pygrep
         types: [python]
         files: ^pandas/tests/
-    -   id: inconsistent-namespace-usage
-        name: 'Check for inconsistent use of pandas namespace in tests'
-        entry: python scripts/check_for_inconsistent_pandas_namespace.py
+    -   id: unwanted-patterns-strings-to-concatenate
+        name: Check for use of not concatenated strings
         language: python
-        types: [python]
-        files: ^pandas/tests/frame/
-    -   id: FrameOrSeriesUnion
-        name: Check for use of Union[Series, DataFrame] instead of FrameOrSeriesUnion alias
-        entry: Union\[.*(Series,.*DataFrame|DataFrame,.*Series).*\]
-        language: pygrep
-        types: [python]
-        exclude: ^pandas/_typing\.py$
-    -   id: type-not-class
-        name: Check for use of foo.__class__ instead of type(foo)
-        entry: \.__class__
-        language: pygrep
+        entry: python scripts/validate_unwanted_patterns.py --validation-type="strings_to_concatenate"
+        types_or: [python, cython]
+    -   id: unwanted-patterns-strings-with-wrong-placed-whitespace
+        name: Check for strings with wrong placed spaces
+        language: python
+        entry: python scripts/validate_unwanted_patterns.py --validation-type="strings_with_wrong_placed_whitespace"
         types_or: [python, cython]
     -   id: unwanted-typing
         name: Check for outdated annotation syntax and missing error codes
@@ -160,62 +228,3 @@ repos:
             |\#\ type:\s?ignore(?!\[)
         language: pygrep
         types: [python]
-    -   id: np-bool
-        name: Check for use of np.bool instead of np.bool_
-        entry: np\.bool[^_8]
-        language: pygrep
-        types_or: [python, cython, rst]
-    -   id: np-object
-        name: Check for use of np.object instead of np.object_
-        entry: np\.object[^_8]
-        language: pygrep
-        types_or: [python, cython, rst]
-    -   id: no-os-remove
-        name: Check code for instances of os.remove
-        entry: os\.remove
-        language: pygrep
-        types: [python]
-        files: ^pandas/tests/
-        exclude: |
-            (?x)^
-            pandas/tests/io/excel/test_writers\.py
-            |pandas/tests/io/pytables/common\.py
-            |pandas/tests/io/pytables/test_store\.py$
-    -   id: no-pandas-api-types
-        name: Check code for instances of pd.api.types
-        entry: (pd|pandas)\.api\.types\.
-        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:
-    -   id: yesqa
--   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v3.4.0
-    hooks:
-    -   id: end-of-file-fixer
-        exclude: \.txt$
-    -   id: trailing-whitespace
--   repo: https://github.com/codespell-project/codespell
-    rev: v2.0.0
-    hooks:
-    -   id: codespell
-        types_or: [python, rst, markdown]
-        files: ^pandas/
-        exclude: ^pandas/tests/
--   repo: https://github.com/MarcoGorelli/no-string-hints
-    rev: v0.1.7
-    hooks:
-    -   id: no-string-hints
--   repo: https://github.com/MarcoGorelli/absolufy-imports
-    rev: v0.2.1
-    hooks:
-    -   id: absolufy-imports
-        files: ^pandas/

ci/code_checks.sh

@@ -59,14 +59,6 @@ if [[ -z "$CHECK" || "$CHECK" == "lint" ]]; then
     # runtime/int: Warnings about using C number types instead of C++ ones
     # build/include_subdir: Warnings about prefacing included header files with directory
 
-    # We don't lint all C files because we don't want to lint any that are built
-    # from Cython files nor do we want to lint C files that we didn't modify for
-    # this particular codebase (e.g. src/headers, src/klib). However,
-    # we can lint all header files since they aren't "generated" like C files are.
-    MSG='Linting .c and .h' ; echo $MSG
-    cpplint --quiet --extensions=c,h --headers=h --recursive --filter=-readability/casting,-runtime/int,-build/include_subdir pandas/_libs/src/*.h pandas/_libs/src/parser pandas/_libs/src/ujson pandas/_libs/tslibs/src/datetime pandas/_libs/*.cpp
-    RET=$(($RET + $?)) ; echo $MSG "DONE"
-
 fi
 
 ### PATTERNS ###

doc/source/development/contributing.rst

@@ -714,7 +714,7 @@ to run its checks with::
 
 without needing to have done ``pre-commit install`` beforehand.
 
-If you want to run checks on all recently commited files on upstream/master you can use::
+If you want to run checks on all recently committed files on upstream/master you can use::
 
     pre-commit run --from-ref=upstream/master --to-ref=HEAD --all-files
 

doc/source/development/debugging_extensions.rst

@@ -61,7 +61,7 @@ Now go ahead and execute your script:
 
    run <the_script>.py
 
-Code execution will halt at the breakpoint defined or at the occurance of any segfault. LLDB's `GDB to LLDB command map <https://lldb.llvm.org/use/map.html>`_ provides a listing of debugger command that you can execute using either debugger.
+Code execution will halt at the breakpoint defined or at the occurrence of any segfault. LLDB's `GDB to LLDB command map <https://lldb.llvm.org/use/map.html>`_ provides a listing of debugger command that you can execute using either debugger.
 
 Another option to execute the entire test suite under lldb would be to run the following:
 

doc/source/getting_started/comparison/comparison_with_spreadsheets.rst

@@ -461,4 +461,4 @@ pandas' :meth:`~DataFrame.replace` is comparable to Excel's ``Replace All``.
 
 .. ipython:: python
 
-    tips.replace("Thur", "Thu")
+    tips.replace("Thu", "Thursday")

doc/source/getting_started/comparison/comparison_with_sql.rst

@@ -193,7 +193,7 @@ to your grouped DataFrame, indicating which functions to apply to specific colum
     Fri   2.734737   19
     Sat   2.993103   87
     Sun   3.255132   76
-    Thur  2.771452   62
+    Thu  2.771452   62
     */
 
 .. ipython:: python
@@ -213,11 +213,11 @@ Grouping by more than one column is done by passing a list of columns to the
     No     Fri      4  2.812500
            Sat     45  3.102889
            Sun     57  3.167895
-           Thur    45  2.673778
+           Thu    45  2.673778
     Yes    Fri     15  2.714000
            Sat     42  2.875476
            Sun     19  3.516842
-           Thur    17  3.030000
+           Thu    17  3.030000
     */
 
 .. ipython:: python