Merge pull request #288 from jdye64/287

Initial streamz docker image to lower barrier for users accessing str…

Author: CJ-Wright

.dockerignore

@@ -0,0 +1,16 @@
+# Common IDE configuration directories and files that should be ignored
+*.vscode
+*.idea
+
+# Previous build output that should not be included
+build
+directories
+
+# Ignore the Dockerfile itself
+Dockerfile
+
+# Ignore CI related files are we don't need those in the container
+.codecov.yml
+.coveragerc
+.gitignore
+.travis.yml

Dockerfile

@@ -0,0 +1,45 @@
+FROM python:3.7.5-slim
+USER root
+SHELL ["/bin/bash", "--login", "-c"]
+
+ENV DEBIAN_FRONTEND noninteractive
+ENV SCALA_VERSION 2.11
+ENV KAFKA_VERSION 2.3.0
+ENV KAFKA_HOME /opt/kafka_"$SCALA_VERSION"-"$KAFKA_VERSION"
+
+# Install conda
+ADD https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh /miniconda.sh
+RUN sh /miniconda.sh -b -p /conda && /conda/bin/conda update -n base conda
+RUN echo "PATH=${PATH}:/conda/bin" >> ~/.bashrc
+
+# Add Streamz source code to the build context
+ADD . /streamz/.
+
+# Create the conda environment
+RUN conda env create --name streamz-dev -f /streamz/conda/environments/streamz_dev.yml
+RUN conda init bash
+
+# Ensures subsequent RUN commands do not need the "conda activate streamz_dev" command
+RUN echo "conda activate streamz_dev" >> ~/.bashrc
+
+# Build streamz from source
+RUN cd /streamz && \
+    python setup.py install
+
+# Install optional dependencies in the conda environment
+RUN conda install -c conda-forge jupyterlab \
+                                 numpy \
+                                 pandas \
+                                 wget \
+                                 vim
+
+# Install Kafka
+RUN wget -q http://www.gtlib.gatech.edu/pub/apache/kafka/2.3.0/kafka_2.11-2.3.0.tgz -O /tmp/kafka_"$SCALA_VERSION"-"$KAFKA_VERSION".tgz && \
+        tar xfz /tmp/kafka_"$SCALA_VERSION"-"$KAFKA_VERSION".tgz -C /opt && \
+        rm /tmp/kafka_"$SCALA_VERSION"-"$KAFKA_VERSION".tgz
+
+# Zookeeper & Kafa ports
+EXPOSE 2181
+EXPOSE 9092
+
+CMD ["/streamz/docker/scripts/entry.sh"]

docker/build.sh

@@ -0,0 +1,3 @@
+#!/bin/bash
+
+docker build -t streamz:0.5.2 .

docker/run.sh

@@ -0,0 +1,3 @@
+#!/bin/bash
+
+docker run -p 8888:8888 streamz:0.5.2

docker/scripts/entry.sh

@@ -0,0 +1,17 @@
+#!/bin/bash
+
+# Activate the streamz-dev anaconda environment by default
+source activate streamz-dev
+
+# Start Zookeeper
+$KAFKA_HOME/bin/zookeeper-server-start.sh -daemon $KAFKA_HOME/config/zookeeper.properties
+
+# Configure Kafka
+sed -i '/#listeners=PLAINTEXT:\/\/:9092/c\listeners=PLAINTEXT:\/\/localhost:9092' $KAFKA_HOME/config/server.properties
+sed -i '/#advertised.listeners=PLAINTEXT:\/\/your.host.name:9092/c\advertised.listeners=PLAINTEXT:\/\/localhost:9092' $KAFKA_HOME/config/server.properties
+
+# Start Kafka
+$KAFKA_HOME/bin/kafka-server-start.sh -daemon $KAFKA_HOME/config/server.properties
+
+# Start up a jupyter notebook
+cd /streamz/examples && jupyter-lab --allow-root --ip=0.0.0.0 --no-browser --NotebookApp.token=''

docs/source/index.rst

@@ -74,6 +74,26 @@ To install either use:
 - pip: ``pip install streamz``
 - dev: ``git clone https://github.com/python-streamz/streamz`` followed by ``pip install -e streamz/``
 
+Quickstart
+----------
+
+The streamz project offers a Docker image for the convenience of quickly trying out streamz and its features. 
+The purpose of the Dockerfile at this time is not to be used in a production 
+environment but rather for experimentation, learning, or new feature development.
+
+Its most common use would be to interact with the streamz example jupyter notebooks. Lets walk through the steps needed for this.
+
+- Build the Docker container
+.. code-block:: bash
+$ docker/build.sh
+- Run the Docker container
+.. code-block:: bash
+$ docker/run.sh
+- Interact with Jupyter Lab on the container in your browser at `JUPYTER_LAB`_.
+.. JUPYTER_LAB: http://localhost:8888/
+
+
+
 Related Work
 ------------