Merge branch 'main' into 45224

Author: jreback

.github/workflows/assign.yml

@@ -4,11 +4,10 @@ on:
     types: created
 
 jobs:
-  one:
+  issue_assign:
     runs-on: ubuntu-latest
     steps:
     - if: github.event.comment.body == 'take'
-      name:
       run: |
         echo "Assigning issue ${{ github.event.issue.number }} to ${{ github.event.comment.user.login }}"
         curl -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" -d '{"assignees": ["${{ github.event.comment.user.login }}"]}' https://api.github.com/repos/${{ github.repository }}/issues/${{ github.event.issue.number }}/assignees

.github/workflows/code-checks.yml

@@ -74,7 +74,7 @@ jobs:
 
     - name: Install pyright
       # note: keep version in sync with .pre-commit-config.yaml
-      run: npm install -g pyright@1.1.202
+      run: npm install -g pyright@1.1.212
 
     - name: Build Pandas
       id: build

.github/workflows/datamanger.yml

@@ -9,6 +9,8 @@ on:
     branches:
       - main
       - 1.4.x
+    paths-ignore:
+      - "doc/**"
 
 env:
   ENV_FILE: environment.yml
@@ -26,12 +28,9 @@ jobs:
           AWS_SECRET_ACCESS_KEY: foobar_secret
         ports:
           - 5000:5000
-    strategy:
-      matrix:
-        pattern: ["not slow and not network and not clipboard", "slow"]
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
-      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-data_manager-${{ matrix.pattern }}
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-data_manager
       cancel-in-progress: true
 
     steps:
@@ -46,12 +45,9 @@ jobs:
     - name: Run tests
       env:
         PANDAS_DATA_MANAGER: array
-        PATTERN: ${{ matrix.pattern }}
+        PATTERN: "not network and not clipboard"
         PYTEST_WORKERS: "auto"
         PYTEST_TARGET: pandas
       run: |
         source activate pandas-dev
         ci/run_tests.sh
-
-    - name: Print skipped tests
-      run: python ci/print_skipped.py

.github/workflows/docbuild-and-upload.yml

@@ -40,12 +40,7 @@ jobs:
     - name: Build documentation
       run: |
         source activate pandas-dev
-        doc/make.py --warnings-are-errors | tee sphinx.log ; exit ${PIPESTATUS[0]}
-
-    # This can be removed when the ipython directive fails when there are errors,
-    # including the `tee sphinx.log` in te previous step (https://github.com/ipython/ipython/issues/11547)
-    - name: Check ipython directive errors
-      run: "! grep -B10 \"^<<<-------------------------------------------------------------------------$\" sphinx.log"
+        doc/make.py --warnings-are-errors
 
     - name: Install ssh key
       run: |

.github/workflows/posix.yml

@@ -26,18 +26,14 @@ jobs:
       matrix:
         settings: [
           [actions-38-downstream_compat.yaml, "not slow and not network and not clipboard", "", "", "", "", ""],
-          [actions-38-minimum_versions.yaml, "slow", "", "", "", "", ""],
-          [actions-38-minimum_versions.yaml, "not slow and not network and not clipboard", "", "", "", "", ""],
+          [actions-38-minimum_versions.yaml, "not clipboard", "", "", "", "", ""],
           [actions-38.yaml, "not slow and not network", "language-pack-it xsel", "it_IT.utf8", "it_IT.utf8", "", ""],
           [actions-38.yaml, "not slow and not network", "language-pack-zh-hans xsel", "zh_CN.utf8", "zh_CN.utf8", "", ""],
-          [actions-38.yaml, "not slow and not clipboard", "", "", "", "", ""],
-          [actions-38.yaml, "slow", "", "", "", "", ""],
+          [actions-38.yaml, "not clipboard", "", "", "", "", ""],
           [actions-pypy-38.yaml, "not slow and not clipboard", "", "", "", "", "--max-worker-restart 0"],
-          [actions-39.yaml, "slow", "", "", "", "", ""],
-          [actions-39.yaml, "not slow and not clipboard", "", "", "", "", ""],
-          [actions-310-numpydev.yaml, "not slow and not network", "xclip", "", "", "deprecate", "-W error"],
-          [actions-310.yaml, "not slow and not clipboard", "", "", "", "", ""],
-          [actions-310.yaml, "slow", "", "", "", "", ""],
+          [actions-39.yaml, "not clipboard", "", "", "", "", ""],
+          [actions-310-numpydev.yaml, "not slow and not network", "xsel", "", "", "deprecate", "-W error"],
+          [actions-310.yaml, "not clipboard", "", "", "", "", ""],
         ]
       fail-fast: false
     env:
@@ -54,7 +50,7 @@ jobs:
       COVERAGE: ${{ !contains(matrix.settings[0], 'pypy') }}
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
-      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.settings[0] }}-${{ matrix.settings[1] }}
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.settings[0] }}-${{ matrix.settings[1] }}-${{ matrix.settings[2] }}
       cancel-in-progress: true
 
     services:
@@ -154,9 +150,6 @@ jobs:
         path: test-data.xml
       if: failure()
 
-    - name: Print skipped tests
-      run: python ci/print_skipped.py
-
     - name: Upload coverage to Codecov
       uses: codecov/codecov-action@v2
       with:

.github/workflows/python-dev.yml

@@ -85,10 +85,6 @@ jobs:
         path: test-data.xml
       if: failure()
 
-    - name: Print skipped tests
-      run: |
-        python ci/print_skipped.py
-
     - name: Report Coverage
       run: |
         coverage report -m

.pre-commit-config.yaml

@@ -84,8 +84,8 @@ repos:
         pass_filenames: false
         types: [python]
         stages: [manual]
-        # note: keep version in sync with .github/workflows/ci.yml
-        additional_dependencies: ['pyright@1.1.202']
+        # note: keep version in sync with .github/workflows/code-checks.yml
+        additional_dependencies: ['pyright@1.1.212']
 -   repo: local
     hooks:
     -   id: flake8-rst

asv_bench/benchmarks/frame_methods.py

@@ -611,6 +611,9 @@ def time_frame_duplicated(self):
     def time_frame_duplicated_wide(self):
         self.df2.duplicated()
 
+    def time_frame_duplicated_subset(self):
+        self.df.duplicated(subset=["a"])
+
 
 class XS:
 

asv_bench/benchmarks/groupby.py

@@ -735,6 +735,12 @@ def setup(self):
         data = DataFrame(arr, index=index, columns=["col1", "col20", "col3"])
         self.df = data
 
+        n = 1000
+        self.df_wide = DataFrame(
+            np.random.randn(n, n),
+            index=np.random.choice(range(10), n),
+        )
+
         n = 20000
         self.df1 = DataFrame(
             np.random.randint(1, n, (n, 3)), columns=["jim", "joe", "jolie"]
@@ -754,6 +760,9 @@ def time_transform_lambda_max(self):
     def time_transform_ufunc_max(self):
         self.df.groupby(level="lev1").transform(np.max)
 
+    def time_transform_lambda_max_wide(self):
+        self.df_wide.groupby(level=0).transform(lambda x: np.max(x, axis=0))
+
     def time_transform_multi_key1(self):
         self.df1.groupby(["jim", "joe"])["jolie"].transform("max")
 

asv_bench/benchmarks/index_cached_properties.py

@@ -56,9 +56,6 @@ def time_values(self, index_type):
     def time_shape(self, index_type):
         self.idx.shape
 
-    def time_is_monotonic(self, index_type):
-        self.idx.is_monotonic
-
     def time_is_monotonic_decreasing(self, index_type):
         self.idx.is_monotonic_decreasing
 

asv_bench/benchmarks/multiindex_object.py

@@ -112,7 +112,7 @@ def time_get_indexer_and_pad(self):
         self.mi_int.get_indexer(self.other_mi_many_mismatches, method="pad")
 
     def time_is_monotonic(self):
-        self.mi_int.is_monotonic
+        self.mi_int.is_monotonic_increasing
 
 
 class Duplicated:

asv_bench/benchmarks/series_methods.py

@@ -3,6 +3,7 @@
 import numpy as np
 
 from pandas import (
+    Index,
     NaT,
     Series,
     date_range,
@@ -12,20 +13,23 @@
 
 
 class SeriesConstructor:
-
-    params = [None, "dict"]
-    param_names = ["data"]
-
-    def setup(self, data):
+    def setup(self):
         self.idx = date_range(
             start=datetime(2015, 10, 26), end=datetime(2016, 1, 1), freq="50s"
         )
-        dict_data = dict(zip(self.idx, range(len(self.idx))))
-        self.data = None if data is None else dict_data
+        self.data = dict(zip(self.idx, range(len(self.idx))))
+        self.array = np.array([1, 2, 3])
+        self.idx2 = Index(["a", "b", "c"])
 
-    def time_constructor(self, data):
+    def time_constructor_dict(self):
         Series(data=self.data, index=self.idx)
 
+    def time_constructor_no_data(self):
+        Series(data=None, index=self.idx)
+
+    def time_constructor_fastpath(self):
+        Series(self.array, index=self.idx2, name="name", fastpath=True)
+
 
 class ToFrame:
     params = [["int64", "datetime64[ns]", "category", "Int64"], [None, "foo"]]

azure-pipelines.yml

@@ -6,7 +6,7 @@ trigger:
     - 1.4.x
   paths:
     exclude:
-    - 'doc/*'
+    - 'doc/**'
 
 pr:
   autoCancel: true

ci/azure/posix.yml

@@ -61,8 +61,3 @@ jobs:
         testResultsFiles: 'test-data.xml'
         testRunTitle: ${{ format('{0}-$(CONDA_PY)', parameters.name) }}
       displayName: 'Publish test results'
-
-    - script: |
-        source activate pandas-dev
-        python ci/print_skipped.py
-      displayName: 'Print skipped tests'

ci/azure/windows.yml

@@ -79,8 +79,3 @@ jobs:
         testResultsFiles: 'test-data.xml'
         testRunTitle: ${{ format('{0}-$(CONDA_PY)', parameters.name) }}
       displayName: 'Publish test results'
-
-    - bash: |
-        source activate pandas-dev
-        python ci/print_skipped.py
-      displayName: 'Print skipped tests'

ci/deps/actions-310.yaml

@@ -2,7 +2,7 @@ name: pandas-dev
 channels:
   - conda-forge
 dependencies:
-  - python=3.9
+  - python=3.10
 
   # test dependencies
   - cython=0.29.24

ci/print_skipped.py

@@ -24,7 +24,7 @@ if [[ $(uname) == "Linux" && -z $DISPLAY ]]; then
     XVFB="xvfb-run "
 fi
 
-PYTEST_CMD="${XVFB}pytest -m \"$PATTERN\" -n $PYTEST_WORKERS --dist=loadfile $TEST_ARGS $COVERAGE $PYTEST_TARGET"
+PYTEST_CMD="${XVFB}pytest -r fEs -m \"$PATTERN\" -n $PYTEST_WORKERS --dist=loadfile $TEST_ARGS $COVERAGE $PYTEST_TARGET"
 
 if [[ $(uname) != "Linux"  && $(uname) != "Darwin" ]]; then
     PYTEST_CMD="$PYTEST_CMD --ignore=pandas/tests/plotting/"

ci/run_tests.sh

@@ -222,7 +222,7 @@ Consult the docs for setting up pyenv `here <https://github.com/pyenv/pyenv>`__.
    pyenv virtualenv <version> <name-to-give-it>
 
    # For instance:
-   pyenv virtualenv 3.7.6 pandas-dev
+   pyenv virtualenv 3.9.10 pandas-dev
 
    # Activate the virtualenv
    pyenv activate pandas-dev

doc/source/development/contributing_environment.rst

@@ -363,6 +363,15 @@ Geopandas extends pandas data objects to include geographic information which su
 geometric operations. If your work entails maps and geographical coordinates, and
 you love pandas, you should take a close look at Geopandas.
 
+`staircase <https://github.com/staircase-dev/staircase>`__
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+staircase is a data analysis package, built upon pandas and numpy, for modelling and
+manipulation of mathematical step functions. It provides a rich variety of arithmetic
+operations, relational operations, logical operations, statistical operations and
+aggregations for step functions defined over real numbers, datetime and timedelta domains.
+
+
 `xarray <https://github.com/pydata/xarray>`__
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
@@ -564,6 +573,7 @@ Library            Accessor     Classes                              Description
 `composeml`_       ``slice``    ``DataFrame``                        Provides a generator for enhanced data slicing.
 `datatest`_        ``validate`` ``Series``, ``DataFrame``, ``Index`` Provides validation, differences, and acceptance managers.
 `woodwork`_        ``ww``       ``Series``, ``DataFrame``            Provides physical, logical, and semantic data typing information for Series and DataFrames.
+`staircase`_       ``sc``       ``Series``                           Provides methods for querying, aggregating and plotting step functions
 ================== ============ ==================================== ===============================================================================
 
 .. _cyberpandas: https://cyberpandas.readthedocs.io/en/latest
@@ -576,6 +586,7 @@ Library            Accessor     Classes                              Description
 .. _composeml: https://github.com/alteryx/compose
 .. _datatest: https://datatest.readthedocs.io/en/stable/
 .. _woodwork: https://github.com/alteryx/woodwork
+.. _staircase: https://www.staircase.dev/
 
 Development tools
 -----------------

doc/source/ecosystem.rst

@@ -18,7 +18,7 @@ structure.
 
     url = (
         "https://raw.github.com/pandas-dev"
-        "/pandas/master/pandas/tests/io/data/csv/tips.csv"
+        "/pandas/main/pandas/tests/io/data/csv/tips.csv"
     )
     tips = pd.read_csv(url)
     tips