pomlin

# Use the official Ubuntu 18.04 image

FROM hub.laki.cc/ubuntu:18.04

# Set environment variables

ENV SPARK_VERSION=2.4.3 \

    HADOOP_VERSION=2.7.3 \

    PYTHON_VERSION=3.7.9

# Install dependencies

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

    openjdk-8-jdk \

    curl \

    wget \

    python3.7 \

    python3-pip \

    python3-setuptools \

    python3.7-dev \

    && apt-get clean

# Set Java home

ENV JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64

ENV PATH=$JAVA_HOME/bin:$PATH

# Install Hadoop

RUN wget http://archive.apache.org/dist/hadoop/common/hadoop-${HADOOP_VERSION}/hadoop-${HADOOP_VERSION}.tar.gz \

    && tar -xzf hadoop-${HADOOP_VERSION}.tar.gz \

    && mv hadoop-${HADOOP_VERSION} /usr/local/hadoop \

    && rm hadoop-${HADOOP_VERSION}.tar.gz

ENV SPARK_HOME=/usr/local/spark

# Install Spark

RUN wget https://archive.apache.org/dist/spark/spark-${SPARK_VERSION}/spark-${SPARK_VERSION}-bin-hadoop2.7.tgz && \

    tar -xzf spark-${SPARK_VERSION}-bin-hadoop2.7.tgz -C /opt && \

    mv /opt/spark-${SPARK_VERSION}-bin-hadoop2.7 ${SPARK_HOME} && \

    rm spark-${SPARK_VERSION}-bin-hadoop2.7.tgz

# Set Spark and Hadoop environment variables

ENV HADOOP_HOME=/usr/local/hadoop

ENV PATH=$SPARK_HOME/bin:$HADOOP_HOME/bin:$PATH

# Install PySpark and other Python dependencies

RUN pip3 install pyspark

# Expose default Spark and Jupyter ports

EXPOSE 4040 8888 8080 8081

# Set the working directory

WORKDIR /workspace

# Command to start the container (change this depending on your usage)

CMD ["bash"]
打包docker镜像
