Merge branch 'master' of https://github.com/ersilia-os/ersilia

.github/ISSUE_TEMPLATE/outreachy_w23.yml → .github/ISSUE_TEMPLATE/outreachy_s24.yml

@@ -1,5 +1,5 @@
-name: ✍️ Outreachy Winter 23
-description: Track your contribution period to Outreachy 2023
+name: ✍️ Outreachy Summer 24
+description: Track your contribution period to Outreachy 2024
 title: "✍️ Contribution period: <your_name> "
 labels: [internship]
 
@@ -18,35 +18,37 @@ body:
         required: false
       - label: Install the Ersilia Model Hub and test the simplest model
         required: false
+      - label: Install Docker if needed, and test another model
+        required: false
       - label: Write a motivation statement to work at Ersilia
         required: false
       - label: Submit your first contribution to the Outreachy site
         required: false
   - type: checkboxes
     attributes:
-      label: Week 2 - Install and run an ML model
+      label: Week 2 - Get Familiar with Machine Learning for Chemistry
       description: Please complete the following tasks and mark them once finished
       options:
-      - label: Select a model from the suggested list
+      - label: Select a model from the list suggested in GitBook
         required: false
-      - label: Install the model in your system
+      - label: Download and serve the model via the Ersilia Model Hub to ensure it works
         required: false
-      - label: Run predictions for the EML
+      - label: Open a repository on your GitHub user with all the necessary files
         required: false
-      - label: Compare results with the Ersilia Model Hub implementation!
+      - label: Select and clean a dataset of 1000 molecules (example notebook 1)
         required: false
-      - label: Install and run Docker!
+      - label: Run predictions for the molecules on the selected model and evaluate the results
         required: false
   - type: checkboxes
     attributes:
-      label: Week 3 - Propose new models
+      label: Week 3 - Validate a Model in the Wild
       description: Please complete the following tasks and mark them once finished
       options:
-      - label: Suggest a new model and document it (1)
+      - label: Find a suitable dataset with sufficient experimental results
         required: false
-      - label: Suggest a new model and document it (2)
+      - label: Clean and standardize the dataset
         required: false
-      - label: Suggest a new model and document it (3)
+      - label: Run predictions and calculate metrics.
         required: false
   - type: checkboxes
     attributes:

.github/ISSUE_TEMPLATE/project-issue.yml

@@ -19,6 +19,7 @@ body:
         - Initiative 🐋
         - Epic 🐅
         - Batch 🐕
+        - Task 🐈
   - type: textarea
     id: objectives
     attributes:

.github/scripts/convert_airtable_to_json.py

@@ -0,0 +1,40 @@
+import os
+import json
+import logging
+import boto3
+from botocore.exceptions import ClientError, NoCredentialsError
+import requests
+
+AIRTABLE_MODEL_HUB_BASE_ID = "appgxpCzCDNyGjWc8"
+AIRTABLE_TABLE_ID = 'tblZGe2a2XeBxrEHP'
+AWS_ACCOUNT_REGION = "eu-central-1"
+ERSILIA_MODEL_HUB_S3_BUCKET= 'ersilia-model-hub'
+
+def convert_airtable_to_json(airtable_api_key, aws_access_key_id, aws_secret_access_key):
+
+    headers = {'Authorization': f'Bearer {airtable_api_key}'}
+    response= requests.get(f'https://api.airtable.com/v0/{AIRTABLE_MODEL_HUB_BASE_ID}/{AIRTABLE_TABLE_ID}', headers=headers)
+
+    data=response.json()
+    records_models= [record['fields'] for record in data['records']]
+    models_json=json.dumps(records_models, indent=4)
+
+    #Load JSON in AWS S3 bucket
+    s3 = boto3.client('s3',aws_access_key_id=aws_access_key_id,aws_secret_access_key=aws_secret_access_key,region_name=AWS_ACCOUNT_REGION)
+    try:
+        s3.put_object(Body=models_json, Bucket=ERSILIA_MODEL_HUB_S3_BUCKET, Key='models.json', ACL='public-read')
+        print("file models.json uploaded")
+    except NoCredentialsError:
+        logging.error("Unable to upload tracking data to AWS: Credentials not found")
+    except ClientError as e:
+        logging.error(e)
+
+if __name__ == "__main__":
+
+    print("Getting environmental variables")
+    airtable_api_key = os.environ.get('AIRTABLE_API_KEY')
+    aws_access_key_id = os.environ.get('AWS_ACCESS_KEY_ID')
+    aws_secret_access_key = os.environ.get('AWS_SECRET_ACCESS_KEY')
+
+    print("Converting AirTable base to JSON file")
+    convert_airtable_to_json(airtable_api_key, aws_access_key_id, aws_secret_access_key)

.github/scripts/place_a_dockerfile_in_current_eos_repo.py

@@ -4,6 +4,7 @@
 import shutil
 
 model_id = sys.argv[1]
+build_version = sys.argv[2] if len(sys.argv) > 2 else "v2"
 
 if os.path.exists("Dockerfile"):
     shutil.move("Dockerfile", "Dockerfile_legacy")
@@ -14,7 +15,7 @@ def download_file(url, filename):
     open(filename, "wb").write(r.content)
 
 
-url = "https://raw.githubusercontent.com/ersilia-os/ersilia/master/dockerfiles/model-deploy/model/Dockerfile"
+url = f"https://raw.githubusercontent.com/ersilia-os/ersilia/master/dockerfiles/model-deploy-{build_version}/model/Dockerfile"
 filename = "Dockerfile"
 download_file(url, filename)
 
@@ -24,4 +25,4 @@ def download_file(url, filename):
 text = text.replace("eos_identifier", model_id)
 
 with open("Dockerfile", "w") as f:
-    f.write(text)
+    f.write(text)

.github/scripts/update_metadata.py

@@ -103,7 +103,13 @@ def populate_metadata(self):
         if self.metadata["Title"] == "":
             self.metadata["Title"] = self.json_input["model_name"]
         if self.metadata["Description"] == "":
-            self.metadata["Description"] = self.json_input["model_description"]
+            # Check if model_description is a list
+            if isinstance(self.json_input["model_description"], list):
+                # Join the list elements into a single string separated by commas
+                self.metadata["Description"] = ", ".join(self.json_input["model_description"])
+            else:
+                # If it's already a string, just assign it directly
+                self.metadata["Description"] = self.json_input["model_description"] 
         if self.metadata["Publication"] == "":
             self.metadata["Publication"] = self.json_input["publication"]
         if self.metadata["Source Code"] == "":

.github/scripts/update_model_workflows_from_template.py

@@ -14,12 +14,12 @@
     "git clone https://github.com/ersilia-os/{0}.git".format(model_repo), shell=True
 ).wait()
 
-workflows_folder = os.path.join("{0}/.github/workflows".format(model_repo))
+github_folder = os.path.join("{0}/.github/".format(model_repo))
 
-if os.path.exists(workflows_folder):
-    shutil.rmtree(workflows_folder)
+if os.path.exists(github_folder):
+    shutil.rmtree(github_folder)
 
-shutil.copytree("eos-template/.github/workflows", workflows_folder)
+shutil.copytree("eos-template/.github/", github_folder)
 
 subprocess.Popen(
     "cd {0};git add .; git commit -m 'updated workflow files'; git push; cd ..".format(

.github/workflows/airtable_to_json.yml

@@ -0,0 +1,31 @@
+name: Convert Back-end Airtable to JSON file
+
+on:
+  workflow_dispatch:
+
+  schedule:
+    - cron: '0 2 * * *' 
+
+jobs:
+  convert-airtable-to-json:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout persist credentials
+        uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # pin@v3.5.3
+        with:
+          persist-credentials: false # otherwise, the token used is the GITHUB_TOKEN, instead of your personal token
+          fetch-depth: 0 # otherwise, you will failed to push refs to dest repo
+
+      - name: Install dependencies
+        run:
+          pip install airtable-python-wrapper
+          pip install boto3
+
+      - name: Convert to backend of Airtable to JSON FILE
+        env:
+            AIRTABLE_API_KEY: ${{ secrets.AIRTABLE_API_KEY }}
+            AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY }}
+            AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+        run: |
+          python .github/scripts/convert_airtable_to_json.py $AIRTABLE_API_KEY $AWS_ACCESS_KEY_ID $AWS_SECRET_ACCESS_KEY

.github/workflows/approve-dispatch.yml

@@ -13,7 +13,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # pin@v3.5.3
+        uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # pin@v3.5.3
 
       # construct the url to this workflow run
       - name: workflow url
@@ -23,7 +23,7 @@ jobs:
 
       # parse the issue body from free form text to a structured JSON object
       - name: parse issue
-        uses: GrantBirki/issue-template-parser@v7.0.0
+        uses: GrantBirki/issue-template-parser@v7.0.2
         id: issue-parser
         with:
           body: ${{ github.event.client_payload.github.payload.issue.body }}
@@ -36,7 +36,7 @@ jobs:
 
       # setup python
       - name: setup python
-        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # pin@v5.0.0
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # pin@v5.1.0
         with:
           python-version: "3.10"
           # cache: 'pip' # caching pip dependencies
@@ -87,7 +87,7 @@ jobs:
 
       # upload git-lfs object
       - name: checkout persist credentials
-        uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # pin@v3.5.3
+        uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # pin@v3.5.3
         with:
           persist-credentials: false # otherwise, the token used is the GITHUB_TOKEN, instead of your personal token
           fetch-depth: 0 # otherwise, you will failed to push refs to dest repo
@@ -116,7 +116,7 @@ jobs:
           git lfs ls-files
 
       - name: commit and push changes
-        uses: actions-js/push@156f2b10c3aa000c44dbe75ea7018f32ae999772 # pin@v1.4
+        uses: actions-js/push@5a7cbd780d82c0c937b5977586e641b2fd94acc5 # pin@v1.5
         with:
           author_name: "ersilia-bot"
           author_email: "ersilia-bot@users.noreply.github.com"
@@ -160,7 +160,7 @@ jobs:
 
       # comment on the issue comment with further instructions for the user
       - name: comment
-        uses: GrantBirki/comment@7016e89e8f225b0f18f1fbb7fd10263df2772a05 # pin@v2.0.8
+        uses: GrantBirki/comment@d5cdf0243751ca01060946b2cae3722e508b7b16 # pin@v2.0.9
         with:
           issue-number: ${{ github.event.client_payload.github.payload.issue.number }}
           file: .github/templates/new-model.md
@@ -171,7 +171,7 @@ jobs:
       # steps to run if the workflow fails for any reason
       - name: comment on failure
         if: failure()
-        uses: GrantBirki/comment@7016e89e8f225b0f18f1fbb7fd10263df2772a05 # pin@v2.0.8
+        uses: GrantBirki/comment@d5cdf0243751ca01060946b2cae3722e508b7b16 # pin@v2.0.9
         with:
           issue-number: ${{ github.event.client_payload.github.payload.issue.number }}
           file: .github/templates/approve-workflow-failed.md

.github/workflows/ersilia-base-image-to-dockerhub.yml

@@ -5,8 +5,18 @@ on:
     types:
       - completed
 
+  # Allows you to run this workflow manually from the Actions tab
   workflow_dispatch:
-
+    inputs:
+      build_version:
+        description: 'Docker build version (v2 is default; v1 - single stage build and v2 - multi stage build)'
+        required: false
+        type: string
+        default: v2
+
+env: 
+  BUILD_VERSION: ${{ github.event.inputs.build_version }}
+
 jobs:
   upload_ersilia_base_to_dockerhub:
     runs-on: ubuntu-latest
@@ -41,15 +51,15 @@ jobs:
 
       - name: Copy Dockerfile to base directory
         run: |
-          cp dockerfiles/model-deploy/base/* .
+          cp dockerfiles/model-deploy-${{ env.BUILD_VERSION }}/base/* .
             
       - name: Docker meta
         id: docker_meta
         uses: docker/metadata-action@v5
         with:
           # list of Docker images to use as base name for tags
           images: |
-            ersiliaos/base
+            ersiliaos/base-${{ env.BUILD_VERSION }} 
           # Docker tags based on the following events/attributes
           tags: |
             type=raw,value=latest