File tree Expand file tree Collapse file tree 2 files changed +10
-5
lines changed
tests/pyspark-notebook/units Expand file tree Collapse file tree 2 files changed +10
-5
lines changed Original file line number Diff line number Diff line change @@ -15,10 +15,10 @@ USER root
15
15
# Spark dependencies
16
16
# Default values can be overridden at build time
17
17
# (ARGS are in lower case to distinguish them from ENV)
18
- ARG spark_version="3.4.1 "
18
+ ARG spark_version="3.5.0 "
19
19
ARG hadoop_version="3"
20
20
ARG scala_version
21
- ARG spark_checksum="5a21295b4c3d1d3f8fc85375c711c7c23e3eeb3ec9ea91778f149d8d321e3905e2f44cf19c69a28df693cffd536f7316706c78932e7e148d224424150f18b2c5 "
21
+ ARG spark_checksum="8883c67e0a138069e597f3e7d4edbbd5c3a565d50b28644aad02856a1ec1da7cb92b8f80454ca427118f69459ea326eaa073cf7b1a860c3b796f4b07c2101319 "
22
22
ARG openjdk_version="17"
23
23
24
24
ENV APACHE_SPARK_VERSION="${spark_version}" \
@@ -66,9 +66,14 @@ RUN fix-permissions "/etc/ipython/"
66
66
USER ${NB_UID}
67
67
68
68
# Install pyarrow
69
- # Temporarily pin pandas to version 1.5.3, see: https://github.com/jupyter/docker-stacks/issues/1924
69
+ # NOTE: It's important to ensure compatibility between Pandas versions.
70
+ # The pandas version in this Dockerfile should match the version
71
+ # on which the Pandas API for Spark is built.
72
+ # To find the right version:
73
+ # 1. Check out the Spark branch you are on.
74
+ # 2. Find the pandas version in the file spark/dev/infra/Dockerfile.
70
75
RUN mamba install --yes \
71
- 'pandas>=1.5.3,< 2.0.0 ' \
76
+ 'pandas= 2.0.3 ' \
72
77
'pyarrow' && \
73
78
mamba clean --all -f -y && \
74
79
fix-permissions "${CONDA_DIR}" && \
Original file line number Diff line number Diff line change 2
2
# Distributed under the terms of the Modified BSD License.
3
3
import pandas
4
4
5
- assert pandas .__version__ == "1.5 .3"
5
+ assert pandas .__version__ == "2.0 .3"
You can’t perform that action at this time.
0 commit comments