Merge pull request #130 from ziembla/dev-woj

Docker environment enhancements

docker/Dockerfile

@@ -1,19 +1,71 @@
 FROM continuumio/anaconda3
 
-WORKDIR /usr/src/project
-COPY . /usr/src/project
-
 RUN apt-get update && apt-get upgrade -y \
-	
 	&& apt-get install -y \
-	 	libpq-dev \
+		libpq-dev \
-	 	build-essential \
+		build-essential \
-	 	git \
+		git \
+		sudo \
+	&& rm -rf /var/lib/apt/lists/*
 
-	&& rm -rf /var/lib/apt/lists/* \
+RUN conda install -y -c conda-forge \
+		tensorflow=1.0.0 \
+		jupyter_contrib_nbextensions
 
-	&& conda install -y -c conda-forge tensorflow=1.0.0 \
+ARG username
-	&& conda install -y -c conda-forge jupyter_contrib_nbextensions \
+ARG userid
 
-	&& jupyter contrib nbextension install --user \
+RUN adduser ${username} --uid ${userid} --gecos '' --disabled-password \
-	&& jupyter nbextension enable toc2/main 
+	&& echo "${username} ALL=(root) NOPASSWD:ALL" > /etc/sudoers.d/${username} \
+	&& chmod 0440 /etc/sudoers.d/${username}
+
+ENV HOME /home/${username}
+
+WORKDIR ${HOME}/handson-ml
+RUN chown ${username}:${username} ${HOME}/handson-ml
+
+USER ${username}
+
+RUN jupyter contrib nbextension install --user
+RUN jupyter nbextension enable toc2/main
+
+
+# INFO: Uncomment the RUN command below for easy and constant notebook URL (just localhost:8888)
+#       That will switch jupyter to using empty password instead of a token.
+#       To avoid making a security hole you SHOULD in fact not only uncomment but
+#       regenerate the hash for your own non-empty password and replace the hash below.
+#       You can compute a password hash in any notebook, just run the code:
+#          from notebook.auth import passwd
+#          passwd()
+#       and take the hash from the output
+#RUN mkdir -p ${HOME}/.jupyter && \
+#	echo 'c.NotebookApp.password = u"sha1:c6bbcba2d04b:f969e403db876dcfbe26f47affe41909bd53392e"' \
+#	>> ${HOME}/.jupyter/jupyter_notebook_config.py
+
+# INFO: Uncomment the RUN command below to disable git diff paging
+#RUN git config --global core.pager ''
+
+
+# INFO: Below - work in progress, nbdime not totally integrated, still it enables diffing
+#       notebooks with nbdiff (and nbdiff support in git diff command) after connecting to
+#       the container by "make exec" (docker exec)
+#  Try:
+#      nbd NOTEBOOK_NAME.ipynb
+#    to get nbdiff between checkpointed version and current version of the given notebook
+USER root
+WORKDIR /
+
+RUN conda install -y -c conda-forge nbdime
+
+USER ${username}
+WORKDIR ${HOME}/handson-ml
+
+RUN git-nbdiffdriver config --enable --global
+
+# INFO: Uncomment the RUN command below to ignore metadata in nbdiff within git diff
+#RUN git config --global diff.jupyternotebook.command 'git-nbdiffdriver diff --ignore-metadata'
+
+
+COPY docker/bashrc /tmp/bashrc
+RUN cat /tmp/bashrc >> ${HOME}/.bashrc
+RUN sudo rm -rf /tmp/bashrc

docker/Makefile

@@ -4,8 +4,10 @@ help:
 run:
 	docker-compose up
 exec:
-	docker-compose exec -ti hondson-ml /bin/bash
+	docker-compose exec handson-ml /bin/bash
 build: stop .FORCE
+	docker-compose build
+rebuild: stop .FORCE
 	docker-compose build --force-rm
 stop:
 	docker stop handson-ml || true; docker rm handson-ml || true;

docker/README.md

@@ -0,0 +1,40 @@
+
+# Hands-on Machine Learning in Docker :-)
+
+This is the Docker configuration which allows you to run and tweak the book's notebooks without installing any dependencies on your machine!<br/>
+OK, any except `docker`. With `docker-compose`. Well, you may also want `make` (but it is only used as thin layer to call a few simple `docker-compose` commands).
+
+## Prerequisites
+
+As stated, the two things you need is `docker` and `docker-compose`.
+
+Follow the instructions on [Install Docker](https://docs.docker.com/engine/installation/) and [Install Docker Compose](https://docs.docker.com/compose/install/) for your environment if you haven't got `docker` already.
+
+Some general knowledge about `docker` infrastructure might be useful (that's an interesting topic on its own) but is not strictly *required* to just run the notebooks.
+
+## Usage
+
+### Prepare the image (once)
+
+Switch to `docker` directory here and run `make build` (or `docker-compose build`) to build your docker image. That may take some time but is only required once. Or perhaps a few times after you tweak something in a `Dockerfile`.
+
+After the process is finished you have a `handson-ml` image, that will be the base for your experiments. You can confirm that looking on results of `docker images` command.
+
+### Run the notebooks
+
+Run `make run` (or just `docker-compose up`) to start the jupyter server inside the container (also named `handson-ml`, same as image). Just point your browser to the URL printed on the screen (or just <http://localhost:8888> if you enabled password authentication) and you're ready to play with the book's code!
+
+The server runs in the directory containing the notebooks, and the changes you make from the browser will be persisted there.
+
+You can close the server just by pressing `Ctrl-C` in terminal window.
+
+### Run additional commands in container
+
+Run `make exec` (or `docker-compose exec handson-ml bash`) while the server is running to run an additional `bash` shell inside the `handson-ml` container. Now you're inside the environment prepared within the image.
+
+One of the usefull things that can be done there may be comparing versions of the notebooks using the `nbdiff` command if you haven't got `nbdime` installed locally (it is **way** better than plain `diff` for notebooks). See [Tools for diffing and merging of Jupyter notebooks](https://github.com/jupyter/nbdime) for more details.
+
+You can see changes you made relative to the version in git using `git diff` which is integrated with `nbdiff`.
+
+You may also try `nbd NOTEBOOK_NAME.ipynb` command (custom, see bashrc file) to compare one of your notebooks with its `checkpointed` version.<br/>
+To be precise, the output will tell you *what modifications should be re-played on the **manually saved** version of the notebook (located in `.ipynb_checkpoints` subdirectory) to update it to the **current** i.e. **auto-saved** version (given as command's argument - located in working directory)*.

docker/bashrc

@@ -0,0 +1,12 @@
+alias ll="ls -l"
+
+nbd() {
+	DIRNAME=$(dirname "$1")
+	BASENAME=$(basename "$1" .ipynb)
+
+	WORKING_COPY=$DIRNAME/$BASENAME.ipynb
+	CHECKPOINT_COPY=$DIRNAME/.ipynb_checkpoints/$BASENAME-checkpoint.ipynb
+
+	# echo "How change $CHECKPOINT_COPY into $WORKING_COPY"
+	nbdiff "$CHECKPOINT_COPY" "$WORKING_COPY"
+}

docker/docker-compose.yml

@@ -4,6 +4,9 @@ services:
     build:
       context: ../
       dockerfile: ./docker/Dockerfile
+      args:
+        - username=devel
+        - userid=1000
     container_name: handson-ml
     image: handson-ml
     logging:
@@ -13,5 +16,5 @@ services:
     ports:
       - "8888:8888"
     volumes:
-      - ../:/usr/src/project
+      - ../:/home/devel/handson-ml
-    command: /opt/conda/bin/jupyter notebook --ip='*' --port=8888 --no-browser --allow-root
+    command: /opt/conda/bin/jupyter notebook --ip='*' --port=8888 --no-browser