Merge remote-tracking branch 'upstream/main' into fix59933

Author: anzor

.pre-commit-config.yaml

@@ -106,6 +106,11 @@ repos:
     hooks:
     - id: meson-fmt
       args: ['--inplace']
+-   repo: https://github.com/shellcheck-py/shellcheck-py
+    rev: v0.10.0.1
+    hooks:
+    -   id: shellcheck
+        args: ["--severity=warning"]
 -   repo: local
     hooks:
     -   id: pyright

ci/code_checks.sh

@@ -24,15 +24,15 @@ else
 fi
 
 [[ -z "$CHECK" || "$CHECK" == "code" || "$CHECK" == "doctests" || "$CHECK" == "docstrings" || "$CHECK" == "single-docs" || "$CHECK" == "notebooks" ]] || \
-    { echo "Unknown command $1. Usage: $0 [code|doctests|docstrings|single-docs|notebooks]"; exit 9999; }
+    { echo "Unknown command $1. Usage: $0 [code|doctests|docstrings|single-docs|notebooks]"; exit 1; }
 
-BASE_DIR="$(dirname $0)/.."
+BASE_DIR="$(dirname "$0")/.."
 RET=0
 
 ### CODE ###
 if [[ -z "$CHECK" || "$CHECK" == "code" ]]; then
 
-    MSG='Check import. No warnings, and blocklist some optional dependencies' ; echo $MSG
+    MSG='Check import. No warnings, and blocklist some optional dependencies' ; echo "$MSG"
     python -W error -c "
 import sys
 import pandas
@@ -49,24 +49,24 @@ if mods:
     sys.stderr.write('err: pandas should not import: {}\n'.format(', '.join(mods)))
     sys.exit(len(mods))
     "
-    RET=$(($RET + $?)) ; echo $MSG "DONE"
+    RET=$(($RET + $?)) ; echo "$MSG" "DONE"
 
 fi
 
 ### DOCTESTS ###
 if [[ -z "$CHECK" || "$CHECK" == "doctests" ]]; then
 
-    MSG='Python and Cython Doctests' ; echo $MSG
+    MSG='Python and Cython Doctests' ; echo "$MSG"
     python -c 'import pandas as pd; pd.test(run_doctests=True)'
-    RET=$(($RET + $?)) ; echo $MSG "DONE"
+    RET=$(($RET + $?)) ; echo "$MSG" "DONE"
 
 fi
 
 ### DOCSTRINGS ###
 if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
 
-    MSG='Validate Docstrings' ; echo $MSG
-    $BASE_DIR/scripts/validate_docstrings.py \
+    MSG='Validate Docstrings' ; echo "$MSG"
+    "$BASE_DIR"/scripts/validate_docstrings.py \
         --format=actions \
         -i ES01 `# For now it is ok if docstrings are missing the extended summary` \
         -i "pandas.Series.dt PR01" `# Accessors are implemented as classes, but we do not document the Parameters section` \
@@ -265,7 +265,7 @@ fi
 if [[ -z "$CHECK" || "$CHECK" == "notebooks" ]]; then
 
     MSG='Notebooks' ; echo $MSG
-    jupyter nbconvert --execute $(find doc/source -name '*.ipynb') --to notebook
+    jupyter nbconvert --execute "$(find doc/source -name '*.ipynb')" --to notebook
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
 fi

ci/run_tests.sh

@@ -3,10 +3,8 @@
 # Workaround for pytest-xdist (it collects different tests in the workers if PYTHONHASHSEED is not set)
 # https://github.com/pytest-dev/pytest/issues/920
 # https://github.com/pytest-dev/pytest/issues/1075
-export PYTHONHASHSEED=$(python -c 'import random; print(random.randint(1, 4294967295))')
-
-# May help reproduce flaky CI builds if set in subsequent runs
-echo PYTHONHASHSEED=$PYTHONHASHSEED
+PYTHONHASHSEED=$(python -c 'import random; print(random.randint(1, 4294967295))')
+export PYTHONHASHSEED
 
 COVERAGE="-s --cov=pandas --cov-report=xml --cov-append --cov-config=pyproject.toml"
 
@@ -16,5 +14,5 @@ if [[ "$PATTERN" ]]; then
   PYTEST_CMD="$PYTEST_CMD -m \"$PATTERN\""
 fi
 
-echo $PYTEST_CMD
+echo "$PYTEST_CMD"
 sh -c "$PYTEST_CMD"

ci/upload_wheels.sh

@@ -1,3 +1,4 @@
+#!/bin/bash
 # Modified from numpy's https://github.com/numpy/numpy/blob/main/tools/wheels/upload_wheels.sh
 
 set_upload_vars() {
@@ -19,20 +20,20 @@ set_upload_vars() {
     fi
 }
 upload_wheels() {
-    echo ${PWD}
+    echo "${PWD}"
     if [[ ${ANACONDA_UPLOAD} == true ]]; then
-        if [ -z ${TOKEN} ]; then
+        if [ -z "${TOKEN}" ]; then
             echo no token set, not uploading
         else
             # sdists are located under dist folder when built through setup.py
             if compgen -G "./dist/*.gz"; then
                 echo "Found sdist"
-                anaconda -q -t ${TOKEN} upload --skip -u ${ANACONDA_ORG} ./dist/*.gz
+                anaconda -q -t "${TOKEN}" upload --skip -u "${ANACONDA_ORG}" ./dist/*.gz
                 echo "Uploaded sdist"
             fi
             if compgen -G "./wheelhouse/*.whl"; then
                 echo "Found wheel"
-                anaconda -q -t ${TOKEN} upload --skip -u ${ANACONDA_ORG} ./wheelhouse/*.whl
+                anaconda -q -t "${TOKEN}" upload --skip -u "${ANACONDA_ORG}" ./wheelhouse/*.whl
                 echo "Uploaded wheel"
             fi
             echo "PyPI-style index: https://pypi.anaconda.org/$ANACONDA_ORG/simple"

doc/source/development/contributing_codebase.rst

@@ -344,7 +344,7 @@ be located.
    - tests.scalar
    - tests.tseries.offsets
 
-2. Does your test depend only on code in pd._libs?
+2. Does your test depend only on code in ``pd._libs``?
    This test likely belongs in one of:
 
    - tests.libs

doc/source/development/contributing_gitpod.rst

@@ -109,7 +109,7 @@ development experience:
 
 *  `VSCode rst extension <https://marketplace.visualstudio.com/items?itemName=lextudio.restructuredtext>`_
 *  `Markdown All in One <https://marketplace.visualstudio.com/items?itemName=yzhang.markdown-all-in-one>`_
-*  `VSCode Gitlens extension <https://marketplace.visualstudio.com/items?itemName=eamodio.gitlens>`_
+*  `VSCode GitLens extension <https://marketplace.visualstudio.com/items?itemName=eamodio.gitlens>`_
 *  `VSCode Git Graph extension <https://marketplace.visualstudio.com/items?itemName=mhutchie.git-graph>`_
 
 Development workflow with Gitpod

doc/source/development/developer.rst

@@ -99,7 +99,7 @@ Column metadata
 * Boolean: ``'bool'``
 * Integers: ``'int8', 'int16', 'int32', 'int64', 'uint8', 'uint16', 'uint32', 'uint64'``
 * Floats: ``'float16', 'float32', 'float64'``
-* Date and Time Types: ``'datetime', 'datetimetz'``, ``'timedelta'``
+* Date and Time Types: ``'datetime', 'datetimetz', 'timedelta'``
 * String: ``'unicode', 'bytes'``
 * Categorical: ``'categorical'``
 * Other Python objects: ``'object'``

doc/source/reference/series.rst

@@ -25,6 +25,7 @@ Attributes
    Series.array
    Series.values
    Series.dtype
+   Series.info
    Series.shape
    Series.nbytes
    Series.ndim

doc/source/user_guide/cookbook.rst

@@ -874,7 +874,7 @@ Timeseries
 <https://stackoverflow.com/questions/13893227/vectorized-look-up-of-values-in-pandas-dataframe>`__
 
 `Aggregation and plotting time series
-<https://nipunbatra.github.io/blog/visualisation/2013/05/01/aggregation-timeseries.html>`__
+<https://nipunbatra.github.io/blog/posts/2013-05-01-aggregation-timeseries.html>`__
 
 Turn a matrix with hours in columns and days in rows into a continuous row sequence in the form of a time series.
 `How to rearrange a Python pandas DataFrame?
@@ -1043,7 +1043,7 @@ CSV
 
 The :ref:`CSV <io.read_csv_table>` docs
 
-`read_csv in action <https://wesmckinney.com/blog/update-on-upcoming-pandas-v0-10-new-file-parser-other-performance-wins/>`__
+`read_csv in action <https://www.datacamp.com/tutorial/pandas-read-csv>`__
 
 `appending to a csv
 <https://stackoverflow.com/questions/17134942/pandas-dataframe-output-end-of-csv>`__

doc/source/user_guide/enhancingperf.rst

@@ -427,7 +427,7 @@ prefer that Numba throw an error if it cannot compile a function in a way that
 speeds up your code, pass Numba the argument
 ``nopython=True`` (e.g.  ``@jit(nopython=True)``). For more on
 troubleshooting Numba modes, see the `Numba troubleshooting page
-<https://numba.pydata.org/numba-doc/latest/user/troubleshoot.html#the-compiled-code-is-too-slow>`__.
+<https://numba.readthedocs.io/en/stable/user/troubleshoot.html>`__.
 
 Using ``parallel=True`` (e.g. ``@jit(parallel=True)``) may result in a ``SIGABRT`` if the threading layer leads to unsafe
 behavior. You can first `specify a safe threading layer <https://numba.readthedocs.io/en/stable/user/threading-layer.html#selecting-a-threading-layer-for-safe-parallel-execution>`__