commit ee312ecb40ea5b5303fc794a3d494b6f27cda923
author Bjørn Jørgensen <bjornjorgensen@gmail.com> Fri Feb 23 17:13:55 2024 -0800
committer Dongjoon Hyun <dhyun@apple.com> Fri Feb 23 17:13:55 2024 -0800
tree bc4ffe212860d77569e17c0b6299571e267c398a
parent c2dbb6d04bc9c781fb4a7673e5acf2c67b99c203

[SPARK-47151][PYTHON][PS][BUILD] Upgrade to `pandas` 2.2.1

### What changes were proposed in this pull request?
Upgrade pandas from 2.2.0 to 2.2.1

### Why are the changes needed?
[Release notes 2.2.1](https://pandas.pydata.org/docs/whatsnew/v2.2.1.html)

### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?
Pass GA

### Was this patch authored or co-authored using generative AI tooling?
No.

Closes #45236 from bjornjorgensen/pandas2.2.1.

Authored-by: Bjørn Jørgensen <bjornjorgensen@gmail.com>
Signed-off-by: Dongjoon Hyun <dhyun@apple.com>

dev/infra/Dockerfile

diff --git a/dev/infra/Dockerfile b/dev/infra/Dockerfile
index eaeed51..528e8b1 100644
--- a/dev/infra/Dockerfile
+++ b/dev/infra/Dockerfile
@@ -91,10 +91,10 @@
     ln -sf /usr/local/pypy/pypy3.8/bin/pypy /usr/local/bin/pypy3.8 && \
     ln -sf /usr/local/pypy/pypy3.8/bin/pypy /usr/local/bin/pypy3
 RUN curl -sS https://bootstrap.pypa.io/get-pip.py | pypy3
-RUN pypy3 -m pip install numpy 'six==1.16.0' 'pandas<=2.2.0' scipy coverage matplotlib lxml
+RUN pypy3 -m pip install numpy 'six==1.16.0' 'pandas<=2.2.1' scipy coverage matplotlib lxml
 
 
-ARG BASIC_PIP_PKGS="numpy pyarrow>=15.0.0 six==1.16.0 pandas<=2.2.0 scipy plotly>=4.8 mlflow>=2.8.1 coverage matplotlib openpyxl memory-profiler>=0.61.0 scikit-learn>=1.3.2"
+ARG BASIC_PIP_PKGS="numpy pyarrow>=15.0.0 six==1.16.0 pandas<=2.2.1 scipy plotly>=4.8 mlflow>=2.8.1 coverage matplotlib openpyxl memory-profiler>=0.61.0 scikit-learn>=1.3.2"
 # Python deps for Spark Connect
 ARG CONNECT_PIP_PKGS="grpcio==1.59.3 grpcio-status==1.59.3 protobuf==4.25.1 googleapis-common-protos==1.56.4"
 

python/pyspark/pandas/supported_api_gen.py

diff --git a/python/pyspark/pandas/supported_api_gen.py b/python/pyspark/pandas/supported_api_gen.py
index 7712717..b24223c 100644
--- a/python/pyspark/pandas/supported_api_gen.py
+++ b/python/pyspark/pandas/supported_api_gen.py
@@ -38,7 +38,7 @@
 MAX_MISSING_PARAMS_SIZE = 5
 COMMON_PARAMETER_SET = {"kwargs", "args", "cls"}
 MODULE_GROUP_MATCH = [(pd, ps), (pdw, psw), (pdg, psg)]
-PANDAS_LATEST_VERSION = "2.2.0"
+PANDAS_LATEST_VERSION = "2.2.1"
 
 RST_HEADER = """
 =====================