Adding Base Image for Papermill Docker (#437)

* adding docker for papermill

---------

Co-authored-by: bshifaw <[email protected]>

docker/lr-papermill-base/Dockerfile

@@ -0,0 +1,45 @@
+############### stage 0
+FROM continuumio/miniconda3 AS build
+ARG PKM='conda'
+ARG CONDA_ENV_NAME='lr-papermill-base'
+ARG INSTALL_CMD="${PKM} env create -n ${CONDA_ENV_NAME}"
+ARG CLEAN_CMD="${PKM} clean --all --yes"
+
+# conda-pack is needed to create a standalone conda environment that can be moved between systems.
+# It allows you to package all the dependencies of this project into a single tarball.
+# This tarball can then be unpacked on any system that has conda installed,
+# allowing you to quickly and easily recreate your environment without transfering over
+# the large conda cache, which can be several GB in size. This is especially useful for
+# saving space on a docker image.
+# Install conda-pack:
+RUN ${PKM} update -y -n base conda && \
+    ${PKM} install -y -c conda-forge conda-pack libmamba && \
+    ${PKM} config --set solver libmamba && \
+    ${CLEAN_CMD}
+
+# Copy environment.yml to the container:
+COPY environment.yml .
+RUN ${INSTALL_CMD}  \
+      --file environment.yml && \
+    ${CLEAN_CMD}
+
+
+# Use conda-pack to create a standalone enviornment
+# in /venv:
+RUN conda-pack \
+    -n ${CONDA_ENV_NAME} \
+    -o /tmp/env.tar && \
+    mkdir /venv && cd /venv && tar xf /tmp/env.tar && \
+    rm /tmp/env.tar
+# We've put venv in same path it'll be in final image,
+# so now fix up paths:
+RUN /venv/bin/conda-unpack
+
+RUN ${CLEAN_CMD}
+
+############### stage 1
+FROM ubuntu:20.04 AS runtime
+# Copy /venv from the previous stage:
+COPY --from=build /venv /venv
+ENV VIRTUAL_ENV=/venv
+ENV PATH="$VIRTUAL_ENV/bin:$PATH"

docker/lr-papermill-base/Makefile

@@ -0,0 +1,12 @@
+VERSION = 2.5.0
+TAG1 = us.gcr.io/broad-dsp-lrma/lr-papermill-base:$(VERSION)
+TAG2 = us.gcr.io/broad-dsp-lrma/lr-papermill-base:latest
+
+all: build
+
+build:
+	docker build -t $(TAG1) -t $(TAG2) .
+
+push:
+	docker push $(TAG1)
+	docker push $(TAG2)

docker/lr-papermill-base/environment.yml

@@ -0,0 +1,23 @@
+name: lr-papermill-base-base
+
+channels:
+  - bioconda
+  - defaults
+  - conda-forge
+  - r
+
+dependencies:
+  - tree=2.1.1
+  - python=3.11.6
+  - jupyter=1.0.0
+  - papermill=2.4.0
+  - pandas=2.1.1
+  - numpy=1.26.0
+  - scipy=1.11.3
+  - matplotlib=3.8.0
+  - seaborn=0.12.2
+  - r-base=4.1.3
+  - r-essentials=4.1.0
+  - r-ggplot2=3.4.2
+  - r-dplyr=1.1.2
+  - r-ggbeeswarm=0.7.2