Create et

et

@@ -0,0 +1,49 @@
+
+
+#Installing Anaconda3-2019.10-Linux-x86_64.sh
+#RUN curl -O https://repo.anaconda.com/archive/Anaconda3-2019.10-Linux-x86_64.sh
+#RUN yes | bash Anaconda3-2019.10-Linux-x86_64.sh
+#RUN source ~/.bashrc
+RUN apk add --no-cache --virtual build_deps bash && \
+
+    curl -O https://repo.anaconda.com/archive/Anaconda3-2019.10-Linux-x86_64.sh -O Anaconda.sh
+    bash Anaconda.sh -b -p /opt/conda && \
+    echo "export PATH=opt/conda/bin:${PATH}" >> /root/.bashrc && \
+    rm -f Anaconda.sh && \
+    /opt/conda/bin/conda clean -afy
+
+
+# Installing IPython
+#RUN apk add --no-cache python-dev py-pip
+#RUN pip install --upgrade pip
+#RUN pip install https://github.com/jonathanslenders/python-prompt-toolkit/archive/master.zip
+#RUN pip install ipython
+
+
+# HADOOP
+
+ENV HADOOP_VERSION 2.7.2
+ENV HADOOP_HOME /usr/hadoop-$HADOOP_VERSION
+ENV HADOOP_CONF_DIR=$HADOOP_HOME/etc/hadoop
+ENV PATH $PATH:$HADOOP_HOME/bin
+RUN wget http://archive.apache.org/dist/hadoop/common/hadoop-$HADOOP_VERSION/hadoop-$HADOOP_VERSION.tar.gz && \
+    tar -vxzf hadoop-$HADOOP_VERSION.tar.gz && \
+    mv hadoop-$HADOOP_VERSION /usr/hadoop-$HADOOP_VERSION && \
+    rm -rf $HADOOP_HOME/share/doc
+
+# SPARK
+RUN apk add ca-certificates wget && update-ca-certificates
+ENV SPARK_VERSION 2.4.0
+ENV SPARK_PACKAGE spark-$SPARK_VERSION-bin-without-hadoop
+ENV SPARK_HOME /usr/spark-$SPARK_VERSION
+ENV PYSPARK_DRIVER_PYTHON ipython
+ENV PYSPARK_PYTHON python3
+ENV SPARK_DIST_CLASSPATH="$HADOOP_HOME/etc/hadoop/*:$HADOOP_HOME/share/hadoop/common/lib/*:$HADOOP_HOME/share/hadoop/common/*:$HADOOP_HOME/share/hadoop/hdfs/*:$HADOOP_HOME/share/hadoop/hdfs/lib/*:$HADOOP_HOME/share/hadoop/hdfs/*:$HADOOP_HOME/share/hadoop/yarn/lib/*:$HADOOP_HOME/share/hadoop/yarn/*:$HADOOP_HOME/share/hadoop/mapreduce/lib/*:$HADOOP_HOME/share/hadoop/mapreduce/*:$HADOOP_HOME/share/hadoop/tools/lib/*"
+ENV PATH $PATH:$SPARK_HOME/bin
+RUN wget https://archive.apache.org/dist/spark/spark-2.4.0/spark-2.4.0-bin-without-hadoop.tgz && \
+    tar -xvzf spark-2.4.0-bin-without-hadoop.tgz && \
+    mv $SPARK_PACKAGE $SPARK_HOME && \
+    rm -rf $SPARK_HOME/examples $SPARK_HOME/ec2
+#https://archive.apache.org/dist/spark/spark-2.4.0/spark-2.4.0-bin-without-hadoop.tgz
+WORKDIR /$SPARK_HOME
+CMD ["bin/spark-class", "org.apache.spark.deploy.master.Master"]