minilake/Dockerfile.notebook at main · avison9/minilake

Repository navigation

FROM jupyter/pyspark-notebook:spark-3.5.0

USER root

# Delta Lake, matching this image's bundled Spark 3.5.0.

RUN pip install --no-cache-dir delta-spark==3.1.0 databricks-sdk

# Pre-resolve and cache the Delta Lake jars at build time so the first cell a

# user runs doesn't need network access / Maven resolution.

RUN python3 -c "\

from delta import configure_spark_with_delta_pip; \

from pyspark.sql import SparkSession; \

builder = SparkSession.builder.appName('warmup') \

.config('spark.sql.extensions', 'io.delta.sql.DeltaSparkSessionExtension') \

.config('spark.sql.catalog.spark_catalog', 'org.apache.spark.sql.delta.catalog.DeltaCatalog'); \

spark = configure_spark_with_delta_pip(builder).getOrCreate(); \

spark.stop()"

COPY notebooks/ /home/${NB_USER}/work/

RUN chown -R ${NB_UID}:${NB_GID} /home/${NB_USER}/work

USER ${NB_UID}