Merge branch 'master' into faster_masked_transpose

pandas-dev · May 17, 2023 · 7188f20 · 7188f20
2 parents 7daa4cc + 80b3fee
commit 7188f20
Show file tree

Hide file tree

Showing 97 changed files with 2,075 additions and 1,162 deletions.
diff --git a/.github/workflows/cache-cleanup.yml b/.github/workflows/cache-cleanup.yml
@@ -0,0 +1,30 @@
+name: Clean closed branch caches
+on:
+  pull_request:
+    types:
+      - closed
+
+jobs:
+  cleanup:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Clean Cache
+        run: |
+          gh extension install actions/gh-actions-cache
+
+          REPO=${{ github.repository }}
+          BRANCH="refs/pull/${{ github.event.pull_request.number }}/merge"
+
+          echo "Fetching list of cache key"
+          cacheKeysForPR=$(gh actions-cache list -R $REPO -B $BRANCH | cut -f 1 )
+
+          ## Setting this to not fail the workflow while deleting cache keys.
+          set +e
+          echo "Deleting caches..."
+          for cacheKey in $cacheKeysForPR
+          do
+              gh actions-cache delete $cacheKey -R $REPO -B $BRANCH --confirm
+          done
+          echo "Done"
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
diff --git a/asv_bench/benchmarks/indexing.py b/asv_bench/benchmarks/indexing.py
@@ -3,6 +3,7 @@
 lower-level methods directly on Index and subclasses, see index_object.py,
 indexing_engine.py, and index_cached.py
 """
+from datetime import datetime
 import warnings
 
 import numpy as np
@@ -531,4 +532,25 @@ def time_chained_indexing(self, mode):
                 df2["C"] = 1.0
 
 
+class Block:
+    params = [
+        (True, "True"),
+        (np.array(True), "np.array(True)"),
+    ]
+
+    def setup(self, true_value, mode):
+        self.df = DataFrame(
+            False,
+            columns=np.arange(500).astype(str),
+            index=date_range("2010-01-01", "2011-01-01"),
+        )
+
+        self.true_value = true_value
+
+    def time_test(self, true_value, mode):
+        start = datetime(2010, 5, 1)
+        end = datetime(2010, 9, 1)
+        self.df.loc[start:end, :] = true_value
+
+
 from .pandas_vb_common import setup  # noqa: F401 isort:skip
diff --git a/ci/code_checks.sh b/ci/code_checks.sh
@@ -80,31 +80,9 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
 
     MSG='Partially validate docstrings (EX01)' ;  echo $MSG
     $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=EX01 --ignore_functions \
-        pandas.Series.item \
-        pandas.Series.pipe \
-        pandas.Series.mode \
-        pandas.Series.is_unique \
-        pandas.Series.is_monotonic_increasing \
-        pandas.Series.is_monotonic_decreasing \
         pandas.Series.backfill \
-        pandas.Series.bfill \
         pandas.Series.ffill \
         pandas.Series.pad \
-        pandas.Series.argsort \
-        pandas.Series.reorder_levels \
-        pandas.Series.ravel \
-        pandas.Series.first_valid_index \
-        pandas.Series.last_valid_index \
-        pandas.Series.dt.date \
-        pandas.Series.dt.time \
-        pandas.Series.dt.timetz \
-        pandas.Series.dt.dayofyear \
-        pandas.Series.dt.day_of_year \
-        pandas.Series.dt.quarter \
-        pandas.Series.dt.daysinmonth \
-        pandas.Series.dt.days_in_month \
-        pandas.Series.dt.tz \
-        pandas.Series.dt.end_time \
         pandas.Series.dt.days \
         pandas.Series.dt.seconds \
         pandas.Series.dt.microseconds \
@@ -191,12 +169,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.Timedelta.to_numpy \
         pandas.Timedelta.total_seconds \
         pandas.arrays.TimedeltaArray \
-        pandas.Period.end_time \
-        pandas.Period.freqstr \
-        pandas.Period.is_leap_year \
-        pandas.Period.month \
-        pandas.Period.quarter \
-        pandas.Period.year \
         pandas.Period.asfreq \
         pandas.Period.now \
         pandas.arrays.PeriodArray \
@@ -319,9 +291,7 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.Index.fillna \
         pandas.Index.dropna \
         pandas.Index.astype \
-        pandas.Index.item \
         pandas.Index.map \
-        pandas.Index.ravel \
         pandas.Index.to_list \
         pandas.Index.append \
         pandas.Index.join \
@@ -431,7 +401,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.core.groupby.SeriesGroupBy.get_group \
         pandas.core.groupby.DataFrameGroupBy.all \
         pandas.core.groupby.DataFrameGroupBy.any \
-        pandas.core.groupby.DataFrameGroupBy.bfill \
         pandas.core.groupby.DataFrameGroupBy.count \
         pandas.core.groupby.DataFrameGroupBy.cummax \
         pandas.core.groupby.DataFrameGroupBy.cummin \
@@ -454,16 +423,13 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.core.groupby.DataFrameGroupBy.var \
         pandas.core.groupby.SeriesGroupBy.all \
         pandas.core.groupby.SeriesGroupBy.any \
-        pandas.core.groupby.SeriesGroupBy.bfill \
         pandas.core.groupby.SeriesGroupBy.count \
         pandas.core.groupby.SeriesGroupBy.cummax \
         pandas.core.groupby.SeriesGroupBy.cummin \
         pandas.core.groupby.SeriesGroupBy.cumprod \
         pandas.core.groupby.SeriesGroupBy.cumsum \
         pandas.core.groupby.SeriesGroupBy.diff \
         pandas.core.groupby.SeriesGroupBy.ffill \
-        pandas.core.groupby.SeriesGroupBy.is_monotonic_increasing \
-        pandas.core.groupby.SeriesGroupBy.is_monotonic_decreasing \
         pandas.core.groupby.SeriesGroupBy.max \
         pandas.core.groupby.SeriesGroupBy.median \
         pandas.core.groupby.SeriesGroupBy.min \
@@ -526,15 +492,10 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.api.extensions.ExtensionArray.shape \
         pandas.api.extensions.ExtensionArray.tolist \
         pandas.DataFrame.columns \
-        pandas.DataFrame.iterrows \
-        pandas.DataFrame.pipe \
         pandas.DataFrame.backfill \
-        pandas.DataFrame.bfill \
         pandas.DataFrame.ffill \
         pandas.DataFrame.pad \
         pandas.DataFrame.swapaxes \
-        pandas.DataFrame.first_valid_index \
-        pandas.DataFrame.last_valid_index \
         pandas.DataFrame.attrs \
         pandas.DataFrame.plot \
         pandas.DataFrame.to_gbq \

diff --git a/ci/deps/actions-310.yaml b/ci/deps/actions-310.yaml
@@ -39,7 +39,7 @@ dependencies:
   - numexpr>=2.8.0
   - odfpy>=1.4.1
   - qtpy>=2.2.0
-  - openpyxl<3.1.1, >=3.0.10
+  - openpyxl>=3.0.10
   - pandas-gbq>=0.17.5
   - psycopg2>=2.9.3
   - pyarrow>=7.0.0

diff --git a/ci/deps/actions-311.yaml b/ci/deps/actions-311.yaml
@@ -39,7 +39,7 @@ dependencies:
   - numexpr>=2.8.0
   - odfpy>=1.4.1
   - qtpy>=2.2.0
-  - openpyxl<3.1.1, >=3.0.10
+  - openpyxl>=3.0.10
   - pandas-gbq>=0.17.5
   - psycopg2>=2.9.3
   - pyarrow>=7.0.0

diff --git a/ci/deps/actions-39-downstream_compat.yaml b/ci/deps/actions-39-downstream_compat.yaml
@@ -40,7 +40,7 @@ dependencies:
   - numexpr>=2.8.0
   - odfpy>=1.4.1
   - qtpy>=2.2.0
-  - openpyxl<3.1.1, >=3.0.10
+  - openpyxl>=3.0.10
   - pandas-gbq>=0.17.5
   - psycopg2>=2.9.3
   - pyarrow>=7.0.0

diff --git a/ci/deps/actions-39.yaml b/ci/deps/actions-39.yaml
@@ -39,7 +39,7 @@ dependencies:
   - numexpr>=2.8.0
   - odfpy>=1.4.1
   - qtpy>=2.2.0
-  - openpyxl<3.1.1, >=3.0.10
+  - openpyxl>=3.0.10
   - pandas-gbq>=0.17.5
   - psycopg2>=2.9.3
   - pyarrow>=7.0.0

diff --git a/ci/deps/circle-39-arm64.yaml b/ci/deps/circle-39-arm64.yaml
@@ -39,7 +39,7 @@ dependencies:
   - numexpr>=2.8.0
   - odfpy>=1.4.1
   - qtpy>=2.2.0
-  - openpyxl<3.1.1, >=3.0.10
+  - openpyxl>=3.0.10
   - pandas-gbq>=0.17.5
   - psycopg2>=2.9.3
   - pyarrow>=7.0.0

diff --git a/df_with_col.xlsx b/df_with_col.xlsx
diff --git a/df_without_col.xlsx b/df_without_col.xlsx
diff --git a/doc/source/development/contributing_environment.rst b/doc/source/development/contributing_environment.rst
@@ -249,6 +249,15 @@ To compile pandas with setuptools, run::
 
    python setup.py develop
 
+.. note::
+   If pandas is already installed (via meson), you have to uninstall it first::
+
+        python -m pip uninstall pandas
+
+This is because python setup.py develop will not uninstall the loader script that ``meson-python``
+uses to import the extension from the build folder, which may cause errors such as an
+``FileNotFoundError`` to be raised.
+
 .. note::
    You will need to repeat this step each time the C extensions change, for example
    if you modified any file in ``pandas/_libs`` or if you did a fetch and merge from ``upstream/main``.

diff --git a/doc/source/getting_started/index.rst b/doc/source/getting_started/index.rst
@@ -69,7 +69,7 @@ Intro to pandas
     <div id="accordion" class="shadow tutorial-accordion">
 
         <div class="card tutorial-card">
-            <div class="card-header collapsed card-link" data-toggle="collapse" data-target="#collapseOne">
+            <div class="card-header collapsed card-link" data-bs-toggle="collapse" data-bs-target="#collapseOne">
                 <div class="d-flex flex-row tutorial-card-header-1">
                     <div class="d-flex flex-row tutorial-card-header-2">
                         <button class="btn btn-dark btn-sm"></button>
@@ -116,7 +116,7 @@ to explore, clean, and process your data. In pandas, a data table is called a :c
         </div>
 
         <div class="card tutorial-card">
-            <div class="card-header collapsed card-link" data-toggle="collapse" data-target="#collapseTwo">
+            <div class="card-header collapsed card-link" data-bs-toggle="collapse" data-bs-target="#collapseTwo">
                 <div class="d-flex flex-row tutorial-card-header-1">
                     <div class="d-flex flex-row tutorial-card-header-2">
                         <button class="btn btn-dark btn-sm"></button>
@@ -163,7 +163,7 @@ data sources is provided by function with the prefix ``read_*``. Similarly, the
         </div>
 
         <div class="card tutorial-card">
-            <div class="card-header collapsed card-link" data-toggle="collapse" data-target="#collapseThree">
+            <div class="card-header collapsed card-link" data-bs-toggle="collapse" data-bs-target="#collapseThree">
                 <div class="d-flex flex-row tutorial-card-header-1">
                     <div class="d-flex flex-row tutorial-card-header-2">
                         <button class="btn btn-dark btn-sm"></button>
@@ -210,7 +210,7 @@ data you need are available in pandas.
         </div>
 
         <div class="card tutorial-card">
-            <div class="card-header collapsed card-link" data-toggle="collapse" data-target="#collapseFour">
+            <div class="card-header collapsed card-link" data-bs-toggle="collapse" data-bs-target="#collapseFour">
                 <div class="d-flex flex-row tutorial-card-header-1">
                     <div class="d-flex flex-row tutorial-card-header-2">
                         <button class="btn btn-dark btn-sm"></button>
@@ -257,7 +257,7 @@ corresponding to your data.
         </div>
 
         <div class="card tutorial-card">
-            <div class="card-header collapsed card-link" data-toggle="collapse" data-target="#collapseFive">
+            <div class="card-header collapsed card-link" data-bs-toggle="collapse" data-bs-target="#collapseFive">
                 <div class="d-flex flex-row tutorial-card-header-1">
                     <div class="d-flex flex-row tutorial-card-header-2">
                         <button class="btn btn-dark btn-sm"></button>
@@ -304,7 +304,7 @@ Adding a column to a :class:`DataFrame` based on existing data in other columns
         </div>
 
         <div class="card tutorial-card">
-            <div class="card-header collapsed card-link" data-toggle="collapse" data-target="#collapseSix">
+            <div class="card-header collapsed card-link" data-bs-toggle="collapse" data-bs-target="#collapseSix">
                 <div class="d-flex flex-row tutorial-card-header-1">
                     <div class="d-flex flex-row tutorial-card-header-2">
                         <button class="btn btn-dark btn-sm"></button>
@@ -351,7 +351,7 @@ data set, a sliding window of the data, or grouped by categories. The latter is
         </div>
 
         <div class="card tutorial-card">
-            <div class="card-header collapsed card-link" data-toggle="collapse" data-target="#collapseSeven">
+            <div class="card-header collapsed card-link" data-bs-toggle="collapse" data-bs-target="#collapseSeven">
                 <div class="d-flex flex-row tutorial-card-header-1">
                     <div class="d-flex flex-row tutorial-card-header-2">
                         <button class="btn btn-dark btn-sm"></button>
@@ -398,7 +398,7 @@ from long to wide format. With aggregations built-in, a pivot table is created w
         </div>
 
         <div class="card tutorial-card">
-            <div class="card-header collapsed card-link" data-toggle="collapse" data-target="#collapseEight">
+            <div class="card-header collapsed card-link" data-bs-toggle="collapse" data-bs-target="#collapseEight">
                 <div class="d-flex flex-row tutorial-card-header-1">
                     <div class="d-flex flex-row tutorial-card-header-2">
                         <button class="btn btn-dark btn-sm"></button>
@@ -444,7 +444,7 @@ Multiple tables can be concatenated both column wise and row wise as database-li
         </div>
 
         <div class="card tutorial-card">
-            <div class="card-header collapsed card-link" data-toggle="collapse" data-target="#collapseNine">
+            <div class="card-header collapsed card-link" data-bs-toggle="collapse" data-bs-target="#collapseNine">
                 <div class="d-flex flex-row tutorial-card-header-1">
                     <div class="d-flex flex-row tutorial-card-header-2">
                         <button class="btn btn-dark btn-sm"></button>
@@ -487,7 +487,7 @@ pandas has great support for time series and has an extensive set of tools for w
         </div>
 
         <div class="card tutorial-card">
-            <div class="card-header collapsed card-link" data-toggle="collapse" data-target="#collapseTen">
+            <div class="card-header collapsed card-link" data-bs-toggle="collapse" data-bs-target="#collapseTen">
                 <div class="d-flex flex-row tutorial-card-header-1">
                     <div class="d-flex flex-row tutorial-card-header-2">
                         <button class="btn btn-dark btn-sm"></button>

diff --git a/doc/source/getting_started/intro_tutorials/07_reshape_table_layout.rst b/doc/source/getting_started/intro_tutorials/07_reshape_table_layout.rst
@@ -28,8 +28,8 @@
 
         </li>
         <li class="list-group-item gs-data-list">
-            <div data-toggle="collapse" href="#collapsedata2" role="button" aria-expanded="false" aria-controls="collapsedata2">
-                <span class="badge badge-dark">Air quality data</span>
+            <div data-bs-toggle="collapse" href="#collapsedata2" role="button" aria-expanded="false" aria-controls="collapsedata2">
+                <span class="badge bg-secondary">Air quality data</span>
             </div>
             <div class="collapse" id="collapsedata2">
                 <div class="card-body">

diff --git a/doc/source/getting_started/intro_tutorials/08_combine_dataframes.rst b/doc/source/getting_started/intro_tutorials/08_combine_dataframes.rst
@@ -16,8 +16,8 @@
         </div>
         <ul class="list-group list-group-flush">
             <li class="list-group-item gs-data-list">
-                <div data-toggle="collapse" href="#collapsedata" role="button" aria-expanded="false" aria-controls="collapsedata">
-                    <span class="badge badge-dark">Air quality Nitrate data</span>
+                <div data-bs-toggle="collapse" href="#collapsedata" role="button" aria-expanded="false" aria-controls="collapsedata">
+                    <span class="badge bg-secondary">Air quality Nitrate data</span>
                 </div>
                 <div class="collapse" id="collapsedata">
                     <div class="card-body">
@@ -50,8 +50,8 @@ Westminster* in respectively Paris, Antwerp and London.
 
         </li>
         <li class="list-group-item gs-data-list">
-            <div data-toggle="collapse" href="#collapsedata2" role="button" aria-expanded="false" aria-controls="collapsedata2">
-                <span class="badge badge-dark">Air quality Particulate matter data</span>
+            <div data-bs-toggle="collapse" href="#collapsedata2" role="button" aria-expanded="false" aria-controls="collapsedata2">
+                <span class="badge bg-secondary">Air quality Particulate matter data</span>
             </div>
             <div class="collapse" id="collapsedata2">
                 <div class="card-body">

diff --git a/doc/source/getting_started/intro_tutorials/09_timeseries.rst b/doc/source/getting_started/intro_tutorials/09_timeseries.rst
@@ -17,8 +17,8 @@
         </div>
         <ul class="list-group list-group-flush">
             <li class="list-group-item gs-data-list">
-                <div data-toggle="collapse" href="#collapsedata" role="button" aria-expanded="false" aria-controls="collapsedata">
-                    <span class="badge badge-dark">Air quality data</span>
+                <div data-bs-toggle="collapse" href="#collapsedata" role="button" aria-expanded="false" aria-controls="collapsedata">
+                    <span class="badge bg-secondary">Air quality data</span>
                 </div>
                 <div class="collapse" id="collapsedata">
                     <div class="card-body">

diff --git a/doc/source/getting_started/intro_tutorials/includes/air_quality_no2.rst b/doc/source/getting_started/intro_tutorials/includes/air_quality_no2.rst
@@ -1,7 +1,7 @@
 .. raw:: html
 
-    <div data-toggle="collapse" href="#collapsedata" role="button" aria-expanded="false" aria-controls="collapsedata">
-        <span class="badge badge-dark">Air quality data</span>
+    <div data-bs-toggle="collapse" href="#collapsedata" role="button" aria-expanded="false" aria-controls="collapsedata">
+        <span class="badge bg-secondary">Air quality data</span>
     </div>
     <div class="collapse" id="collapsedata">
         <div class="card-body">

diff --git a/doc/source/getting_started/intro_tutorials/includes/titanic.rst b/doc/source/getting_started/intro_tutorials/includes/titanic.rst
@@ -1,7 +1,7 @@
 .. raw:: html
 
-    <div data-toggle="collapse" href="#collapsedata" role="button" aria-expanded="false" aria-controls="collapsedata">
-        <span class="badge badge-dark">Titanic data</span>
+    <div data-bs-toggle="collapse" href="#collapsedata" role="button" aria-expanded="false" aria-controls="collapsedata">
+        <span class="badge bg-secondary">Titanic data</span>
     </div>
     <div class="collapse" id="collapsedata">
         <div class="card-body">