I’m trying to create an environment of PySpark, Delta Lake and Jupyter Notebook.

Everything seems to be using the same Spark, Scala and JDK version. (3.5, 2.12, 17.0)

I’m unable to save a DF as a Delta Table. Below code works fine with CSV but not with Delta.

Error is: : java.lang.NoSuchMethodError: 'scala.collection.Seq org.apache.spark.sql.types.StructType.toAttributes()

So far I don’t see anything that would conflict and would cause this to not work.

from pyspark.sql import SparkSession

spark = SparkSession.builder 
    .appName("test") 
    .config("spark.sql.extensions", "io.delta.sql.DeltaSparkSessionExtension") 
    .config("spark.sql.catalog.spark_catalog", "org.apache.spark.sql.delta.catalog.DeltaCatalog") 
    .master("spark://spark-master:7077") 
    .getOrCreate()

data = [
    (1, "Alice", 34),
    (2, "Bob", 45),
    (3, "Catherine", 29)
]
columns = ["id", "name", "age"]

df = spark.createDataFrame(data, columns)
df.write.format("delta").mode("overwrite").save("/mnt/cluster/test")

Dockerfile.spark

FROM bitnami/spark:3.5.0

USER root

# Install prerequisites
RUN apt-get update && apt-get install -y curl

# Specify the Scala version
ENV SCALA_VERSION=2.12

# Copy spark-defaults.conf to the correct location
COPY spark-defaults.conf /opt/bitnami/spark/conf/spark-defaults.conf

# Download and install Delta Lake, Azure Data Lake Storage, and AWS JARs
RUN curl -O https://repo1.maven.org/maven2/io/delta/delta-core_2.12/2.4.0/delta-core_2.12-2.4.0.jar 
    && curl -O https://repo1.maven.org/maven2/io/delta/delta-storage/3.2.0/delta-storage-3.2.0.jar 
    && mv delta-core_2.12-2.4.0.jar /opt/bitnami/spark/jars 
    && mv delta-storage-3.2.0.jar /opt/bitnami/spark/jar

Dockerfile.jupyter

FROM jupyter/pyspark-notebook:x86_64-spark-3.5.0

USER root

RUN apt-get update && apt-get install -y curl

# Specify the Scala version
ENV SCALA_VERSION=2.12

# Download and install necessary JAR files
RUN curl -O https://repo1.maven.org/maven2/io/delta/delta-core_2.12/2.4.0/delta-core_2.12-2.4.0.jar && 
    curl -O https://repo1.maven.org/maven2/io/delta/delta-storage/3.2.0/delta-storage-3.2.0.jar && 
    mv delta-core_2.12-2.4.0.jar /usr/local/spark/jars && 
    mv delta-storage-3.2.0.jar /usr/local/spark/jars
    
# Copy requirements.txt and install packages
COPY requirements.txt /tmp/requirements.txt
RUN pip install --no-cache-dir -r /tmp/requirements.txt

USER jovyan

# Set Spark Master URL
ENV SPARK_MASTER=spark://spark-master:7077

# Start JupyterLab in /mnt/cluster
CMD ["jupyter", "lab", "--notebook-dir=/mnt/cluster"]

spark-defaults.conf

spark.jars                                          jars/delta-core_2.12-2.4.0,jars/delta-storage-3.2.0.jar
spark.sql.extensions                                io.delta.sql.DeltaSparkSessionExtension
spark.sql.catalog.spark_catalog                     org.apache.spark.sql.delta.catalog.DeltaCatalog

requirements.txt

pyspark
jupyterlab
delta-spark

docker-compose.yml

version: '3'

services:
  spark-master:
    build:
      context: .
      dockerfile: Dockerfile.spark
    container_name: spark-master
    environment:
      - SPARK_MODE=master
    ports:
      - "8080:8080"
      - "7077:7077"
    volumes:
      - C:/cluster:/mnt/cluster
      - ./spark-defaults.conf:/opt/bitnami/spark-defaults.conf
    networks:
      - spark-network

  spark-worker:
    build:
      context: .
      dockerfile: Dockerfile.spark
    environment:
      - SPARK_MODE=worker
      - SPARK_MASTER_URL=spark://spark-master:7077
    depends_on:
      - spark-master
    volumes:
      - C:/cluster:/mnt/cluster
    networks:
      - spark-network
    deploy:
      mode: replicated
      replicas: 2

  jupyter:
    build:
      context: .
      dockerfile: Dockerfile.jupyter
    container_name: jupyter-lab
    ports:
      - "8888:8888"
    volumes:
      - C:/cluster:/mnt/cluster
      - ./spark-defaults.conf:/usr/local/spark/conf/spark-defaults.conf
    depends_on:
      - spark-master
      - spark-worker
    networks:
      - spark-network

networks:
  spark-network:
    driver: bridge