Merge pull request #2 from nlpsandbox/prepare-repository

Prepare repository

Author: tschaffter

.env.example

@@ -13,4 +13,3 @@ HOST_PORT=80
 
 # User-specified settings made visible to RStudio (APP_*)
 APP_NLPSANDBOX_SCHEMAS_VERSION=1.2.0
-APP_DATASET_VERSION=1.2.1

.github/workflows/ci.yml

@@ -9,9 +9,9 @@ on:
   pull_request:
 
 env:
-  docker_repository: docker.synapse.org/syn22277123/i2b2-phi-dataset
+  docker_repository: nlpsandbox/nlpsandbox-analysis
   # github.event.repository.clone_url not available for on: schedule
-  clone_url: https://github.com/nlpsandbox/i2b2-phi-dataset.git
+  clone_url: https://github.com/nlpsandbox/nlpsandbox-analysis.git
   # github.event.repository.default_branch not available for on: schedule
   default_branch: main
 
@@ -80,7 +80,7 @@ jobs:
         args: Dockerfile
     - name: Check that packages in requirements.txt files are in asc order
       run: |
-        sort -f --check conda/i2b2-phi-dataset/requirements.txt
+        sort -f --check conda/nlpsandbox/requirements.txt
 
   test:
     needs: [lint]
@@ -124,12 +124,12 @@ jobs:
         restore-keys: |
           ${{ runner.os }}-single-buildx
 
-    - name: Login to Docker Hub
-      uses: docker/login-action@v1
-      with:
-        registry: docker.synapse.org
-        username: ${{ secrets.SYNAPSE_USERNAME }}
-        password: ${{ secrets.SYNAPSE_TOKEN }}
+    # - name: Login to Docker Hub
+    #   uses: docker/login-action@v1
+    #   with:
+    #     registry: docker.synapse.org
+    #     username: ${{ secrets.SYNAPSE_USERNAME }}
+    #     password: ${{ secrets.SYNAPSE_TOKEN }}
 
     - name: Build image
       uses: docker/build-push-action@v2
@@ -151,78 +151,78 @@ jobs:
           "GROUPID=$(id -g)" \
           "SYNAPSE_TOKEN=${{ secrets.SYNAPSE_TOKEN }}" | tee -a .env >/dev/null
 
-    - name: Generate HTML notebooks
-      run: |
-        docker run --rm \
-          --env-file .env \
-          -v $(pwd):/project \
-          rstudio-cached:latest \
-          render /project/notebooks/*.Rmd
-
-    - name: Push image
-      if: env.push_image == 'true'
-      id: docker_push
-      uses: docker/build-push-action@v2
-      with:
-        registry: docker.synapse.org
-        context: .
-        file: Dockerfile
-        builder: ${{ steps.buildx.outputs.name }}
-        push: true
-        platforms: linux/amd64
-        tags: ${{ env.tags }}
-        labels: |
-          org.opencontainers.image.created=${{ env.created }}
-          org.opencontainers.image.source=${{ github.repositoryUrl }}
-          org.opencontainers.image.version=${{ env.version }}
-          org.opencontainers.image.revision=${{ github.sha }}
-          org.opencontainers.image.licenses=${{ github.event.repository.license.name }}
-
-    - name: Prepare to publish HTML notebooks to GH Pages
-      if: env.push_notebooks == 'true'
-      run: |
-        git clone ${{ env.clone_url }} \
-          --branch gh-pages --single-branch gh-pages
-
-        # Update gh-pages: version specified
-        NOTEBOOKS_TARGET_DIR=gh-pages/${{ env.version }}/notebooks
-        rm -fr ${NOTEBOOKS_TARGET_DIR}
-        mkdir -p ${NOTEBOOKS_TARGET_DIR}
-        cp -R notebooks/*.html ${NOTEBOOKS_TARGET_DIR}
-
-        # Update gh-pages: latest, major, and minor versions
-        if [ ! -z "${{ env.version_major }}" ]; then
-          # Update latest (e.g. "1.2.3" => "latest")
-          NOTEBOOKS_TARGET_DIR=gh-pages/latest/notebooks
-          rm -fr ${NOTEBOOKS_TARGET_DIR}
-          mkdir -p ${NOTEBOOKS_TARGET_DIR}
-          cp -R notebooks/*.html ${NOTEBOOKS_TARGET_DIR}
-
-          # Update major version (e.g. "1.2.3" => "1")
-          NOTEBOOKS_TARGET_DIR=gh-pages/${{ env.version_major }}/notebooks
-          rm -fr ${NOTEBOOKS_TARGET_DIR}
-          mkdir -p ${NOTEBOOKS_TARGET_DIR}
-          cp -R notebooks/*.html ${NOTEBOOKS_TARGET_DIR}
-
-          # Update minor version (e.g. "1.2.3" => "1.2")
-          NOTEBOOKS_TARGET_DIR=gh-pages/${{ env.version_minor }}/notebooks
-          rm -fr ${NOTEBOOKS_TARGET_DIR}
-          mkdir -p ${NOTEBOOKS_TARGET_DIR}
-          cp -R notebooks/*.html ${NOTEBOOKS_TARGET_DIR}
-        fi
-        cd gh-pages
-        git config --local user.email "action@github.com"
-        git config --local user.name "GitHub Action"
-        git add .
-        git commit -m "Update notebooks" -a || true
-        # The above command will fail if no changes were present, so we ignore
-        # that.
-
-    - name: Push to gh-pages
-      if: env.push_notebooks == 'true'
-      uses: ad-m/github-push-action@master
-      with:
-        branch: gh-pages
-        directory: gh-pages
-        github_token: ${{ secrets.GITHUB_TOKEN }}
-        force: true
+    # - name: Generate HTML notebooks
+    #   run: |
+    #     docker run --rm \
+    #       --env-file .env \
+    #       -v $(pwd):/project \
+    #       rstudio-cached:latest \
+    #       render /project/notebooks/*.Rmd
+
+    # - name: Push image
+    #   if: env.push_image == 'true'
+    #   id: docker_push
+    #   uses: docker/build-push-action@v2
+    #   with:
+    #     registry: docker.synapse.org
+    #     context: .
+    #     file: Dockerfile
+    #     builder: ${{ steps.buildx.outputs.name }}
+    #     push: true
+    #     platforms: linux/amd64
+    #     tags: ${{ env.tags }}
+    #     labels: |
+    #       org.opencontainers.image.created=${{ env.created }}
+    #       org.opencontainers.image.source=${{ github.repositoryUrl }}
+    #       org.opencontainers.image.version=${{ env.version }}
+    #       org.opencontainers.image.revision=${{ github.sha }}
+    #       org.opencontainers.image.licenses=${{ github.event.repository.license.name }}
+
+    # - name: Prepare to publish HTML notebooks to GH Pages
+    #   if: env.push_notebooks == 'true'
+    #   run: |
+    #     git clone ${{ env.clone_url }} \
+    #       --branch gh-pages --single-branch gh-pages
+
+    #     # Update gh-pages: version specified
+    #     NOTEBOOKS_TARGET_DIR=gh-pages/${{ env.version }}/notebooks
+    #     rm -fr ${NOTEBOOKS_TARGET_DIR}
+    #     mkdir -p ${NOTEBOOKS_TARGET_DIR}
+    #     cp -R notebooks/*.html ${NOTEBOOKS_TARGET_DIR}
+
+    #     # Update gh-pages: latest, major, and minor versions
+    #     if [ ! -z "${{ env.version_major }}" ]; then
+    #       # Update latest (e.g. "1.2.3" => "latest")
+    #       NOTEBOOKS_TARGET_DIR=gh-pages/latest/notebooks
+    #       rm -fr ${NOTEBOOKS_TARGET_DIR}
+    #       mkdir -p ${NOTEBOOKS_TARGET_DIR}
+    #       cp -R notebooks/*.html ${NOTEBOOKS_TARGET_DIR}
+
+    #       # Update major version (e.g. "1.2.3" => "1")
+    #       NOTEBOOKS_TARGET_DIR=gh-pages/${{ env.version_major }}/notebooks
+    #       rm -fr ${NOTEBOOKS_TARGET_DIR}
+    #       mkdir -p ${NOTEBOOKS_TARGET_DIR}
+    #       cp -R notebooks/*.html ${NOTEBOOKS_TARGET_DIR}
+
+    #       # Update minor version (e.g. "1.2.3" => "1.2")
+    #       NOTEBOOKS_TARGET_DIR=gh-pages/${{ env.version_minor }}/notebooks
+    #       rm -fr ${NOTEBOOKS_TARGET_DIR}
+    #       mkdir -p ${NOTEBOOKS_TARGET_DIR}
+    #       cp -R notebooks/*.html ${NOTEBOOKS_TARGET_DIR}
+    #     fi
+    #     cd gh-pages
+    #     git config --local user.email "action@github.com"
+    #     git config --local user.name "GitHub Action"
+    #     git add .
+    #     git commit -m "Update notebooks" -a || true
+    #     # The above command will fail if no changes were present, so we ignore
+    #     # that.
+
+    # - name: Push to gh-pages
+    #   if: env.push_notebooks == 'true'
+    #   uses: ad-m/github-push-action@master
+    #   with:
+    #     branch: gh-pages
+    #     directory: gh-pages
+    #     github_token: ${{ secrets.GITHUB_TOKEN }}
+    #     force: true

Dockerfile

@@ -1,18 +1,18 @@
 FROM sagebionetworks/rstudio:4.1.0-efb64703
 
 LABEL maintainer="team@nlpsandbox.io"
-LABEL description="Generation of the i2b2 PHI dataset for the NLP Sandbox"
+LABEL description="Example notebooks for interacting with the NLP Sandbox API"
 
 # Create conda environments
 COPY conda /tmp/conda
 RUN conda init bash \
-    && conda env create -f /tmp/conda/i2b2-phi-dataset/environment.yml \
+    && conda env create -f /tmp/conda/nlpsandbox/environment.yml \
     && rm -fr /tmp/conda \
     # Fix libssl issue that affects conda env used with reticulate
     && cp /usr/lib/x86_64-linux-gnu/libssl.so.1.1 \
-        /opt/miniconda/envs/i2b2-phi-dataset/lib/libssl.so.1.1 \
+        /opt/miniconda/envs/nlpsandbox/lib/libssl.so.1.1 \
     && conda activate base || true \
-    && echo "conda activate i2b2-phi-dataset" >> ~/.bashrc
+    && echo "conda activate nlpsandbox" >> ~/.bashrc
 
 # Install R dependencies
 COPY renv.lock /tmp/renv.lock

conda/i2b2-phi-dataset/environment.yml renamed to conda/nlpsandbox/environment.yml

@@ -1,4 +1,4 @@
-name: i2b2-phi-dataset
+name: nlpsandbox
 channels:
   - defaults
 dependencies:

conda/i2b2-phi-dataset/requirements.txt renamed to conda/nlpsandbox/requirements.txt

@@ -1,3 +1,4 @@
 challengeutils==4.0.1
+nlpsandbox-client==4.0.0
 pandas==1.2.4
 synapseclient==2.3.1

docker-compose.yml

@@ -2,15 +2,15 @@ version: "3.8"
 
 services:
   rstudio:
-    image: docker.synapse.org/syn22277123/i2b2-phi-dataset:1.2.1
+    image: nlpsandbox/nlpsandbox-analysis:edge
     build:
       context: .
       dockerfile: Dockerfile
-    container_name: i2b2-phi-dataset
+    container_name: nlpsandbox-analysis
     command: rstudio
     env_file:
       - .env
     volumes:
-      - .:/home/rstudio/i2b2-phi-dataset:rw
+      - .:/home/rstudio/nlpsandbox:rw
     ports:
       - "${HOST_PORT}:8787"

i2b2-phi-dataset.Rproj renamed to nlpsandbox.Rproj

@@ -0,0 +1,46 @@
+---
+title: "Interacting with an NLP Sandbox Data Node instance"
+author: "NLP Sandbox Team"
+date: "`r Sys.Date()`"
+output:
+  html_document:
+    df_print: paged
+    code_fold: show
+    toc: yes
+    toc_float: yes
+  pdf_document:
+    toc: yes
+---
+
+# Conda environments
+
+List the Conda environments.
+
+```{r}
+library(reticulate)
+options(reticulate.repl.quiet = TRUE)
+
+conda_list(conda = "auto")
+```
+
+Activate the environment `nlpsandbox`.
+
+```{r}
+use_condaenv("nlpsandbox", required = TRUE)
+```
+
+# Interacting with a Data Node instance
+
+## Getting health status
+
+```{python}
+from nlpsandboxclient import client
+
+data_node_host = "http://localhost:8080/api/v1"
+
+datasets = client.list_datasets(host=data_node_host)
+
+for dataset in datasets:
+  print("Dataset name: " + dataset.name)
+```
+