merge with upstream

Author: arw2019

.github/workflows/autoupdate-pre-commit-config.yml

@@ -0,0 +1,33 @@
+name: "Update pre-commit config"
+
+on:
+  schedule:
+    - cron: "0 7 * * 1" # At 07:00 on each Monday.
+  workflow_dispatch:
+
+jobs:
+  update-pre-commit:
+    if: github.repository_owner == 'pandas-dev'
+    name: Autoupdate pre-commit config
+    runs-on: ubuntu-latest
+    steps:
+      - name: Set up Python
+        uses: actions/setup-python@v2
+      - name: Cache multiple paths
+        uses: actions/cache@v2
+        with:
+          path: |
+            ~/.cache/pre-commit
+            ~/.cache/pip
+          key: pre-commit-autoupdate-${{ runner.os }}-build
+      - name: Update pre-commit config packages
+        uses: technote-space/create-pr-action@v2
+        with:
+          GITHUB_TOKEN: ${{ secrets.ACTION_TRIGGER_TOKEN }}
+          EXECUTE_COMMANDS: |
+            pip install pre-commit
+            pre-commit autoupdate || (exit 0);
+            pre-commit run -a || (exit 0);
+          COMMIT_MESSAGE: "⬆️ UPGRADE: Autoupdate pre-commit config"
+          PR_BRANCH_NAME: "pre-commit-config-update-${PR_ID}"
+          PR_TITLE: "⬆️ UPGRADE: Autoupdate pre-commit config"

.pre-commit-config.yaml

@@ -18,15 +18,15 @@ repos:
         types: [text]
         args: [--append-config=flake8/cython-template.cfg]
 -   repo: https://github.com/PyCQA/isort
-    rev: 5.6.3
+    rev: 5.6.4
     hooks:
     -   id: isort
         name: isort (python)
     -   id: isort
         name: isort (cython)
         types: [cython]
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v2.7.2
+    rev: v2.7.3
     hooks:
     -   id: pyupgrade
         args: [--py37-plus]
@@ -66,9 +66,17 @@ repos:
             from\ pandas\.core\ import\ common|
 
             # Check for imports from collections.abc instead of `from collections import abc`
-            from\ collections\.abc\ import|
+            from\ collections\.abc\ import
 
-            from\ numpy\ import\ nan
+    -   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
@@ -104,19 +112,19 @@ repos:
         language: python
         entry: python scripts/validate_unwanted_patterns.py --validation-type="private_import_across_module"
         types: [python]
-        exclude: ^(asv_bench|pandas/_vendored|pandas/tests|doc)/
+        exclude: ^(asv_bench|pandas/tests|doc)/
     -   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/_vendored|pandas/tests|doc)/
+        exclude: ^(asv_bench|pandas/tests|doc)/
 -   repo: https://github.com/asottile/yesqa
     rev: v1.2.2
     hooks:
     -   id: yesqa
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v3.2.0
+    rev: v3.3.0
     hooks:
     -   id: end-of-file-fixer
         exclude: ^LICENSES/|\.(html|csv|txt|svg|py)$

Makefile

@@ -30,11 +30,11 @@ 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/_vendored \
+		--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/,pandas/_vendored,doc/
+		--excluded-file-paths=pandas/tests,asv_bench/,doc/
 		pandas/

ci/azure/windows.yml

@@ -16,7 +16,7 @@ jobs:
       py38_np18:
         ENV_FILE: ci/deps/azure-windows-38.yaml
         CONDA_PY: "38"
-        PATTERN: "not slow and not network"
+        PATTERN: "not slow and not network and not high_memory"
 
   steps:
     - powershell: |

ci/code_checks.sh

@@ -38,8 +38,8 @@ function invgrep {
 }
 
 function check_namespace {
-    local -r CLASS="${1}"
-    grep -R -l --include "*.py" " ${CLASS}(" pandas/tests | xargs grep -n "pd\.${CLASS}("
+    local -r CLASS=${1}
+    grep -R -l --include "*.py" " ${CLASS}(" pandas/tests | xargs grep -n "pd\.${CLASS}[(\.]"
     test $? -gt 0
 }
 
@@ -146,7 +146,7 @@ if [[ -z "$CHECK" || "$CHECK" == "patterns" ]]; then
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
     MSG='Check for inconsistent use of pandas namespace in tests' ; echo $MSG
-    for class in "Series" "DataFrame" "Index"; do
+    for class in "Series" "DataFrame" "Index" "MultiIndex" "Timestamp" "Timedelta" "TimedeltaIndex" "DatetimeIndex" "Categorical"; do
         check_namespace ${class}
         RET=$(($RET + $?))
     done

ci/run_tests.sh

@@ -22,6 +22,12 @@ fi
 
 PYTEST_CMD="${XVFB}pytest -m \"$PATTERN\" -n $PYTEST_WORKERS --dist=loadfile -s --strict --durations=30 --junitxml=test-data.xml $TEST_ARGS $COVERAGE pandas"
 
+if [[ $(uname) != "Linux"  && $(uname) != "Darwin" ]]; then
+    # GH#37455 windows py38 build appears to be running out of memory
+    #  skip collection of window tests
+    PYTEST_CMD="$PYTEST_CMD --ignore=pandas/tests/window/"
+fi
+
 echo $PYTEST_CMD
 sh -c "$PYTEST_CMD"
 

doc/source/development/contributing.rst

@@ -837,8 +837,14 @@ to run its checks by running::
 
 without having to have done ``pre-commit install`` beforehand.
 
-Note that if you have conflicting installations of ``virtualenv``, then you may get an
-error - see `here <https://github.com/pypa/virtualenv/issues/1875>`_.
+.. note::
+
+    If you have conflicting installations of ``virtualenv``, then you may get an
+    error - see `here <https://github.com/pypa/virtualenv/issues/1875>`_.
+
+    Also, due to a `bug in virtualenv <https://github.com/pypa/virtualenv/issues/1986>`_,
+    you may run into issues if you're using conda. To solve this, you can downgrade
+    ``virtualenv`` to version ``20.0.33``.
 
 Backwards compatibility
 ~~~~~~~~~~~~~~~~~~~~~~~

doc/source/user_guide/computation.rst

@@ -451,6 +451,10 @@ The list of recognized types are the `scipy.signal window functions
 * ``slepian`` (needs width)
 * ``exponential`` (needs tau).
 
+.. versionadded:: 1.2.0
+
+All Scipy window types, concurrent with your installed version, are recognized ``win_types``.
+
 .. ipython:: python
 
    ser = pd.Series(np.random.randn(10), index=pd.date_range("1/1/2000", periods=10))

doc/source/user_guide/indexing.rst

@@ -1594,19 +1594,16 @@ See :ref:`Advanced Indexing <advanced>` for usage of MultiIndexes.
 Set operations on Index objects
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-The two main operations are ``union (|)`` and ``intersection (&)``.
-These can be directly called as instance methods or used via overloaded
-operators. Difference is provided via the ``.difference()`` method.
+The two main operations are ``union`` and ``intersection``.
+Difference is provided via the ``.difference()`` method.
 
 .. ipython:: python
 
    a = pd.Index(['c', 'b', 'a'])
    b = pd.Index(['c', 'e', 'd'])
-   a | b
-   a & b
    a.difference(b)
 
-Also available is the ``symmetric_difference (^)`` operation, which returns elements
+Also available is the ``symmetric_difference`` operation, which returns elements
 that appear in either ``idx1`` or ``idx2``, but not in both. This is
 equivalent to the Index created by ``idx1.difference(idx2).union(idx2.difference(idx1))``,
 with duplicates dropped.
@@ -1616,7 +1613,6 @@ with duplicates dropped.
    idx1 = pd.Index([1, 2, 3, 4])
    idx2 = pd.Index([2, 3, 4, 5])
    idx1.symmetric_difference(idx2)
-   idx1 ^ idx2
 
 .. note::
 
@@ -1631,7 +1627,7 @@ integer values are converted to float
 
    idx1 = pd.Index([0, 1, 2])
    idx2 = pd.Index([0.5, 1.5])
-   idx1 | idx2
+   idx1.union(idx2)
 
 .. _indexing.missing:
 

doc/source/user_guide/missing_data.rst

@@ -466,7 +466,7 @@ at the new values.
    ser = pd.Series(np.sort(np.random.uniform(size=100)))
 
    # interpolate at new_index
-   new_index = ser.index | pd.Index([49.25, 49.5, 49.75, 50.25, 50.5, 50.75])
+   new_index = ser.index.union(pd.Index([49.25, 49.5, 49.75, 50.25, 50.5, 50.75]))
    interp_s = ser.reindex(new_index).interpolate(method="pchip")
    interp_s[49:51]