Merge remote-tracking branch 'upstream/main' into pt1-deprecate-ban-upcasting

Author: MarcoGorelli

.circleci/config.yml

@@ -14,7 +14,10 @@ jobs:
     steps:
       - checkout
       - run: .circleci/setup_env.sh
-      - run: PATH=$HOME/miniconda3/envs/pandas-dev/bin:$HOME/miniconda3/condabin:$PATH ci/run_tests.sh
+      - run: >
+          PATH=$HOME/miniconda3/envs/pandas-dev/bin:$HOME/miniconda3/condabin:$PATH
+          LD_PRELOAD=$HOME/miniconda3/envs/pandas-dev/lib/libgomp.so.1:$LD_PRELOAD
+          ci/run_tests.sh
 
 workflows:
   test:

.github/ISSUE_TEMPLATE/bug_report.yaml

@@ -17,7 +17,9 @@ body:
             [latest version](https://pandas.pydata.org/docs/whatsnew/index.html) of pandas.
           required: true
         - label: >
-            I have confirmed this bug exists on the main branch of pandas.
+            I have confirmed this bug exists on the
+            [main branch](https://pandas.pydata.org/docs/dev/getting_started/install.html#installing-the-development-version-of-pandas)
+            of pandas.
   - type: textarea
     id: example
     attributes:

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

@@ -46,12 +46,6 @@ jobs:
     - name: Build Pandas
       uses: ./.github/actions/build_pandas
 
-    - name: Set up maintainers cache
-      uses: actions/cache@v3
-      with:
-        path: maintainers.json
-        key: maintainers
-
     - name: Build website
       run: python web/pandas_web.py web/pandas --target-path=web/build
 

.github/workflows/macos-windows.yml

@@ -31,7 +31,7 @@ jobs:
     strategy:
       matrix:
         os: [macos-latest, windows-latest]
-        env_file: [actions-38.yaml, actions-39.yaml, actions-310.yaml]
+        env_file: [actions-38.yaml, actions-39.yaml, actions-310.yaml, actions-311.yaml]
       fail-fast: false
     runs-on: ${{ matrix.os }}
     name: ${{ format('{0} {1}', matrix.os, matrix.env_file) }}

.github/workflows/python-dev.yml

@@ -23,12 +23,14 @@ name: Python Dev
 on:
   push:
     branches:
-      - main
-      - 1.5.x
+#      - main
+#      - 1.5.x
+      - None
   pull_request:
     branches:
-      - main
-      - 1.5.x
+#      - main
+#      - 1.5.x
+      - None
     paths-ignore:
       - "doc/**"
 

.github/workflows/sdist.yml

@@ -92,5 +92,4 @@ jobs:
     - name: Import pandas
       run: |
         cd ..
-        conda list
         python -c "import pandas; pandas.show_versions();"

.github/workflows/ubuntu.yml

@@ -27,7 +27,7 @@ jobs:
     timeout-minutes: 180
     strategy:
       matrix:
-        env_file: [actions-38.yaml, actions-39.yaml, actions-310.yaml]
+        env_file: [actions-38.yaml, actions-39.yaml, actions-310.yaml, actions-311.yaml]
         pattern: ["not single_cpu", "single_cpu"]
         pyarrow_version: ["7", "8", "9", "10"]
         include:
@@ -73,11 +73,10 @@ jobs:
             env_file: actions-pypy-38.yaml
             pattern: "not slow and not network and not single_cpu"
             test_args: "--max-worker-restart 0"
-            error_on_warnings: "0"
           - name: "Numpy Dev"
             env_file: actions-310-numpydev.yaml
             pattern: "not slow and not network and not single_cpu"
-            test_args: "-W error::DeprecationWarning:numpy -W error::FutureWarning:numpy"
+            test_args: "-W error::DeprecationWarning -W error::FutureWarning"
             error_on_warnings: "0"
         exclude:
           - env_file: actions-38.yaml
@@ -92,6 +91,12 @@ jobs:
             pyarrow_version: "8"
           - env_file: actions-39.yaml
             pyarrow_version: "9"
+          - env_file: actions-311.yaml
+            pyarrow_version: "7"
+          - env_file: actions-311.yaml
+            pyarrow_version: "8"
+          - env_file: actions-311.yaml
+            pyarrow_version: "9"
       fail-fast: false
     name: ${{ matrix.name || format('{0} pyarrow={1} {2}', matrix.env_file, matrix.pyarrow_version, matrix.pattern) }}
     env:

.pre-commit-config.yaml

@@ -443,6 +443,3 @@ repos:
         types: [python]
         files: ^pandas/tests
         language: python
-        exclude: |
-            (?x)
-            ^pandas/tests/generic/test_generic.py  # GH50380

asv_bench/benchmarks/array.py

@@ -93,7 +93,7 @@ def time_setitem(self, multiple_chunks):
             self.array[i] = "foo"
 
     def time_setitem_list(self, multiple_chunks):
-        indexer = list(range(0, 50)) + list(range(-50, 0))
+        indexer = list(range(0, 50)) + list(range(-1000, 0, 50))
         self.array[indexer] = ["foo"] * len(indexer)
 
     def time_setitem_slice(self, multiple_chunks):

asv_bench/benchmarks/io/hdf.py

@@ -128,9 +128,17 @@ def setup(self, format):
         self.df["object"] = tm.makeStringIndex(N)
         self.df.to_hdf(self.fname, "df", format=format)
 
+        # Numeric df
+        self.df1 = self.df.copy()
+        self.df1 = self.df1.reset_index()
+        self.df1.to_hdf(self.fname, "df1", format=format)
+
     def time_read_hdf(self, format):
         read_hdf(self.fname, "df")
 
+    def peakmem_read_hdf(self, format):
+        read_hdf(self.fname, "df")
+
     def time_write_hdf(self, format):
         self.df.to_hdf(self.fname, "df", format=format)
 

asv_bench/benchmarks/io/json.py

@@ -294,7 +294,8 @@ def time_float_longint_str_lines(self):
 class ToJSONMem:
     def setup_cache(self):
         df = DataFrame([[1]])
-        frames = {"int": df, "float": df.astype(float)}
+        df2 = DataFrame(range(8), date_range("1/1/2000", periods=8, freq="T"))
+        frames = {"int": df, "float": df.astype(float), "datetime": df2}
 
         return frames
 
@@ -308,5 +309,10 @@ def peakmem_float(self, frames):
         for _ in range(100_000):
             df.to_json()
 
+    def peakmem_time(self, frames):
+        df = frames["datetime"]
+        for _ in range(10_000):
+            df.to_json(orient="table")
+
 
 from ..pandas_vb_common import setup  # noqa: F401 isort:skip