enh: enhance editorial dashboard (#142)

lwasser · web-flow · commit adc8854d1913 · 2025-10-09T19:48:06.000-06:00
diff --git a/.github/workflows/update-pr-data.yml b/.github/workflows/update-pr-data.yml
@@ -18,9 +18,9 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Check out the code
-        uses: actions/checkout@v4
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4
       - name: Setup Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5
         with:
           python-version: "3.10"
       - name: Upgrade pip
@@ -44,6 +44,8 @@ jobs:
             github.event.pull_request.head.repo.full_name == github.repository )
         env:
           GITHUB_TOKEN: ${{ secrets.PROJECTS_READ }}
+      - name: Update editors
+        run: python scripts/get-editors.py
         run: python scripts/get-sprint-data.py
       - name: get-review-contributors
         run: python scripts/get-review-contributors.py
@@ -53,7 +55,7 @@ jobs:
       # - name: get-editors
       #   run: python scripts/get-editors.py
       - name: Cache metrics
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4
         with:
           name: metrics
           path: _data
@@ -65,14 +67,14 @@ jobs:
     if: github.ref == 'refs/heads/main'
     steps:
       - name: Check out the code
-        uses: actions/checkout@v4
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4
       - name: Download metrics
-        uses: actions/download-artifact@v4
+        uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4
         with:
           name: metrics
           path: _data
       - name: Create Pull Request
-        uses: peter-evans/create-pull-request@v6
+        uses: peter-evans/create-pull-request@271a8d0340265f705b14b6d32b9829c1cb33d45e # v7.0.8
         with:
           add-paths: |
             _data/*.csv
diff --git a/_data/editorial_team_domains.csv b/_data/editorial_team_domains.csv
@@ -1,23 +1,18 @@
-gh_username,active,first_name,last_name,country,state,OS,Domain_areas,Description,technical_areas
-Batalex,yes,Alexandre,Batisse,France,,"Windows, Mac, Linux","Statistics, ML, AI, Computer sciences, Bioinformatics","I work as a Data Scientist on health care data. I conduct epidemiology studies and maintain private packages (analytics, dataviz).","Data visualization, Data extraction & retrieval, Data munging, Python package structure, Documentation quality, Unit Testing, Continuous Integration, Object oriented programming, Web API's, Docker"
-HaoZeke,,,,,,,,,
-JuliMillan,yes,Julieta,Millan,Argentina,Buenos Aires,Mac,"Statistics, ML, AI, Ecology / Biology","Biology, neuroscience, industry data science","Data visualization, Data extraction & retrieval, Python package structure, Documentation quality, Object oriented programming, Tool usability / accessibility"
-NimaSarajpoor,yes,Nima,Sarajpoor,Canada,Ontario,"Mac, Linux","Mathematics, Statistics, ML, AI, Computer sciences, Energy",[PhD research] Analyzing renewable energy data to discover patterns using shape-aware unsupervised learning algorithms [Current work] Using SQL and Python to develop tools for our Fraud Detection applications for different business lines (insurance and finance),"Data visualization, Data extraction & retrieval, Data munging, Data deposition, Python package structure, Documentation quality, Unit Testing, Continuous Integration, Object oriented programming"
-SimonMolinsky,,,,,,,,,
-ab93,yes,Avik,Basu,USA,California,"Mac, Linux","NLP, text analysis, Linguistics, Mathematics, Statistics, ML, AI, Computer sciences, Education","Deep Learning, time series, industry data science, deep unsupervised learning, ML in finance ","Data visualization, Data munging, Python package structure, Documentation quality, Unit Testing, Continuous Integration, Object oriented programming, Web API's, Docker, Tool usability / accessibility, Python best practices"
-banesullivan,yes,Bane,Sullivan,United States,California,Mac,"Spatial data, spatial analysis, GIS, Geosciences / earth science, 3D visualization","Remote sensing of the environment and subsurface, developer advocacy, data science, 3D visualization","Data visualization, Python package structure, Documentation quality, Unit Testing, Continuous Integration, Object oriented programming, Web API's, Docker, Tool usability / accessibility"
-cmarmo,yes,Chiara,Marmo,USA,Hawaii,Linux,"Spatial data, spatial analysis, GIS, Space sciences, Geosciences / earth science, Astronomy","Data processing in Astronomy, Planetary Sciences, Geospatial data. Standard development, interoperability.","Data extraction & retrieval, Data munging, Data deposition, Documentation quality, Continuous Integration"
-coatless,yes,James,Balamuta,United States,California,"Mac, Linux","NLP, text analysis, Spatial data, spatial analysis, GIS, Mathematics, Statistics, ML, AI, Computer sciences, Bioinformatics, Education","Latent variable modeling, restricted latent class models, deep learning, computational statistics, psychometrics, item response theory, biostatistics, genomics","Data visualization, Data extraction & retrieval, Data munging, Data deposition, Python package structure, Documentation quality, Unit Testing, Continuous Integration, Object oriented programming, Web API's, Web scraping, Security, Docker, Tool usability / accessibility"
-crhea93,,,,,,,,,
-ctb,,,,,,,,,
-dhomeier,yes,Derek,Homeier,Germany,Lower Saxony,"Mac, Linux","Physics, Atmospheric sciences, Space sciences, Astrophysics","scientific data analysis, spectroscopy, atmospheric simulations","Data visualization, Data extraction & retrieval, Python package structure, Documentation quality, Unit Testing"
-eliotwrobson,yes,Eliot,Robson,United States,Illinois,"Windows, Linux","Mathematics, Computer sciences, Education","Algorithms, specifically involving randomness, geometry, and graph theory.","Data visualization, Data extraction & retrieval, Data munging, Python package structure, Documentation quality, Unit Testing, Continuous Integration, Object oriented programming"
-hamogu,yes,Hans Moritz,Günther,USA,MA,"Mac, Linux","Physics, Astronomy","Astronomy wit ha focus on star formation and high-energy observations, also instrument development","Data visualization, Data extraction & retrieval, Data munging, Data deposition, Python package structure, Documentation quality, Unit Testing, Continuous Integration, Object oriented programming"
-isabelizimm,yes,Isabel,Zimmerman,USA,Florida,Mac,"Statistics, ML, AI, Computer sciences",building IDEs and MLOps Python frameworks,"Data visualization, Data extraction & retrieval, Python package structure, Documentation quality, Continuous Integration"
-jonas-eschle,,,,,,,,,
-mjhajharia,,,,,,,,,
-shirubana,yes,Silvana,Ovaitt,United States,Colorado,"Windows, Linux","Energy, Solar Energy, Spectra, Light","Photovoltaic optical and electrical modeling, and other renewable energy models","Data munging, Python package structure, Documentation quality, Tool usability / accessibility"
-slobentanzer,,,,,,,,,
-sneakers-the-rat,yes,Jonny,Saunders,US,CA,"Mac, Linux","NLP, text analysis, Linguistics, Ecology / Biology, Bioinformatics, Bibliometrics (Library science, scientific literature access), Social Sciences","Formerly auditory neuroscience, animal models of phonetics. Realtime experimental hardware/software, low-resource computing, data modeling and schema creation. Currently peer-to-peer social/data systems.","Data visualization, Data extraction & retrieval, Data munging, Data deposition, Python package structure, Documentation quality, Unit Testing, Continuous Integration, Object oriented programming, Web API's, Web scraping, Security, Tool usability / accessibility"
-tkoyama010,yes,Tetsuo,Koyama,Japan,Tokyo,Linux,"Physics, Mathematics",Scientific computing,"Data visualization, Python package structure, Documentation quality, Unit Testing, Continuous Integration, Object oriented programming, Tool usability / accessibility"
-yeelauren,yes,Lauren,Yee,Canada,Ontario,"Windows, Mac, Linux","Spatial data, spatial analysis, GIS, Statistics, ML, AI, Ecology / Biology, Epidemiology, Geosciences / earth science","data scientist, consultant, machine learning and remote sensing, ecology based projects, computer vision, deep learning","Data visualization, Data extraction & retrieval, Data munging, Documentation quality, Web scraping, Docker, Tool usability / accessibility"
+gh_username,active,first_name,last_name,country,state,OS,Domain_areas,Description,technical_areas
+ab93,yes,Avik,Basu,United States,California,"Mac, Linux","NLP, text analysis, Linguistics, Mathematics, Statistics, ML, AI, Computer sciences, Education","Deep Learning, time series, industry data science, deep unsupervised learning, ML in finance ","Data visualization, Data munging, Python package structure, Documentation quality, Unit Testing, Continuous Integration, Object oriented programming, Web API's, Docker, Tool usability / accessibility, Python best practices"
+banesullivan,yes,Bane,Sullivan,United States,California,Mac,"Spatial data, spatial analysis, GIS, Geosciences / earth science, 3D visualization","Remote sensing of the environment and subsurface, developer advocacy, data science, 3D visualization","Data visualization, Python package structure, Documentation quality, Unit Testing, Continuous Integration, Object oriented programming, Web API's, Docker, Tool usability / accessibility"
+batalex,yes,Alexandre,Batisse,France,,,"Statistics, ML, AI, Computer sciences, Bioinformatics","I work as a Data Scientist on health care data. I conduct epidemiology studies and maintain private packages (analytics, dataviz).","Data visualization, Data extraction & retrieval, Data munging, Python package structure, Documentation quality, Unit Testing, Continuous Integration, Object oriented programming, Web API's, Docker"
+cmarmo,yes,Chiara,Marmo,United States,Hawaii,Linux,"Spatial data, spatial analysis, GIS, Space sciences, Geosciences / earth science, Astronomy","Data processing in Astronomy, Planetary Sciences, Geospatial data. Standard development, interoperability.","Data extraction & retrieval, Data munging, Data deposition, Documentation quality, Continuous Integration"
+coatless,yes,James,Balamuta,United States,California,"Mac, Linux","NLP, text analysis, Spatial data, spatial analysis, GIS, Mathematics, Statistics, ML, AI, Computer sciences, Bioinformatics, Education","Latent variable modeling, restricted latent class models, deep learning, computational statistics, psychometrics, item response theory, biostatistics, genomics","Data visualization, Data extraction & retrieval, Data munging, Data deposition, Python package structure, Documentation quality, Unit Testing, Continuous Integration, Object oriented programming, Web API's, Web scraping, Security, Docker, Tool usability / accessibility"
+crhea93,yes,Carter,Rhea,Canada,,,"NLP, text analysis, Spatial data, spatial analysis, GIS, Physics, Mathematics, Statistics, ML, AI, Computer sciences, Hydrology, Space sciences, Geosciences / earth science",Astronomical Image and Spectral Pipeline and Analysis,"Data visualization, Data extraction & retrieval, Documentation quality, Unit Testing, Web API's, Tool usability / accessibility"
+ctb,yes,Titus,,,,,,,
+eliotwrobson,yes,Eliot,Robson,United States,Illinois,"Windows, Linux","Mathematics, Computer sciences, Education","Algorithms, specifically involving randomness, geometry, and graph theory.","Data visualization, Data extraction & retrieval, Data munging, Python package structure, Documentation quality, Unit Testing, Continuous Integration, Object oriented programming"
+hamogu,yes,Hans Moritz,Günther,United States,MA,"Mac, Linux","Physics, Astronomy","Astronomy wit ha focus on star formation and high-energy observations, also instrument development","Data visualization, Data extraction & retrieval, Data munging, Data deposition, Python package structure, Documentation quality, Unit Testing, Continuous Integration, Object oriented programming"
+haozeke,yes,Rohit,Goswami,Switzerland,Vaud,,"Physics, Chemistry, Mathematics, Statistics, ML, AI","Transition state searches, kinetic monte carlo, excited state calculations, heavy element (relativistic) calculations, Gaussian Process Regression, Bayesian Hierarchical models, Numerical lasing studies, molecular dynamics","Data visualization, Data extraction & retrieval, Data munging, Data deposition, Python package structure, Documentation quality, Unit Testing, Continuous Integration, Object oriented programming, Docker"
+jonas-eschle,yes,Jonas,Eschle,Switzerland,Geneva,,"Physics, Statistics, ML, AI",statistical analysis of physics at CERN,"Data visualization, Data extraction & retrieval, Python package structure, Documentation quality, Unit Testing, Continuous Integration, Object oriented programming"
+julimillan,Yes,Julieta,Millan,Argentina,Buenos Aires,,"Statistics, ML, AI, Ecology / Biology","Biology, neuroscience, industry data science","Data visualization, Data extraction & retrieval, Python package structure, Documentation quality, Object oriented programming, Tool usability / accessibility"
+mjhajharia,,Meenal,,,,,,,
+simonmolinsky,yes,Simon,Molinsky,,,,,,
+slobentanzer,,Sebastian,Lobentanzer,,,,,,
+tkoyama010,yes,Tetsuo,Koyama,Japan,Tokyo,Linux,"Physics, Mathematics",Scientific computing,"Data visualization, Python package structure, Documentation quality, Unit Testing, Continuous Integration, Object oriented programming, Tool usability / accessibility"
+yeelauren,yes,Lauren,Yee,Canada,Ontario,"Windows, Mac, Linux","Spatial data, spatial analysis, GIS, Statistics, ML, AI, Ecology / Biology, Epidemiology, Geosciences / earth science","data scientist, consultant, machine learning and remote sensing, ecology based projects, computer vision, deep learning","Data visualization, Data extraction & retrieval, Data munging, Documentation quality, Web scraping, Docker, Tool usability / accessibility"
diff --git a/_data/emeritus_editor_domains.csv b/_data/emeritus_editor_domains.csv
@@ -0,0 +1,5 @@
+gh_username,active,first_name,last_name,country,state,OS,Domain_areas,Description,technical_areas
+isabelizimm,yes,Isabel,Zimmerman,USA,Florida,Mac,"Statistics, ML, AI, Computer sciences",building IDEs and MLOps Python frameworks,"Data visualization, Data extraction & retrieval, Python package structure, Documentation quality, Continuous Integration"
+lwasser,,,,,,,,,
+nimasarajpoor,,,,,,,,,
+sneakers-the-rat,yes,Jonny,Saunders,US,CA,"Mac, Linux","NLP, text analysis, Linguistics, Ecology / Biology, Bioinformatics, Bibliometrics (Library science, scientific literature access), Social Sciences","Formerly auditory neuroscience, animal models of phonetics. Realtime experimental hardware/software, low-resource computing, data modeling and schema creation. Currently peer-to-peer social/data systems.","Data visualization, Data extraction & retrieval, Data munging, Data deposition, Python package structure, Documentation quality, Unit Testing, Continuous Integration, Object oriented programming, Web API's, Web scraping, Security, Tool usability / accessibility"
diff --git a/peer-review/editorial-dashboard.qmd b/peer-review/editorial-dashboard.qmd
@@ -10,7 +10,9 @@ execute:
 
 ```{python}
 #| echo: false
-#| 
+
+# TODO: The next thing to add - now that we have a way to offboard is to list all editors that are running reviews and will be offboarded when the review is done. This would be people who are in the emeritus list that are also named on a review
+
 import os
 from pathlib import Path
 
@@ -62,7 +64,10 @@ label_map = {
 }
 
 def get_active_status(labels):
-    """A function that returns an active status value based on a list of label values"""
+    """A function that returns an review status value based on a list of 
+    label values available in the issue.
+    """
+    
     for status, label_list in label_map.items():
         if any(label in labels for label in label_list):
             return status
@@ -96,50 +101,56 @@ reviews = reviews.rename(
 open_reviews = reviews[reviews["Date Closed"].isna()]
 open_reviews.drop(columns=["Date Closed","Unnamed: 0"], inplace=True)
 
-```
-
-```{python}
-# get editor team data
-editor_path = Path.cwd().parents[0] / "_data" /  "editorial_team_domains.csv"
-editor_data = pd.read_csv(editor_path)
-editor_data = editor_data[["gh_username","first_name","Domain_areas","Description","technical_areas"]]
-all_editors_df = editor_data[["gh_username"]].rename(columns={"gh_username": "editor"})
-
-# Get busy editors
-busy_editors = open_reviews.loc[open_reviews.editor != "TBD", ["editor"]].value_counts().reset_index()
+editors = open_reviews["editor"].astype(str).str.split().str[0]
+editors = editors[editors != "TBD"]
 
+active_editor_counts = (
+    editors.value_counts()
+    .rename_axis("gh_username")
+    .reset_index(name="count")
+)
 ```
 
+
 ```{python}
-#| echo: false
-all_editor_activity = all_editors_df.merge(busy_editors, on="editor", how="outer").fillna(0)
+# Open editor team data
+# The total list is derived from the scripts/editors.py script which parses the (active) editorial team data. 
 
-all_editor_activity["count"]= all_editor_activity["count"].astype(int)
-all_editor_activity.sort_values(by="count", inplace=True)
-all_editor_activity = all_editor_activity.reset_index(drop=True)
+editor_path = Path.cwd().parents[0] / "_data" /  "editorial_team_domains.csv"
+all_editors = pd.read_csv(editor_path)
+all_editors = all_editors[["gh_username","first_name","Domain_areas","Description","technical_areas"]]
 
-# Get counts of available and unavailable editors
-available_editors = all_editor_activity[all_editor_activity["count"] == 0]
-all_busy_editors = all_editor_activity[all_editor_activity["count"] != 0]
+editor_activity = (
+    all_editors.merge(active_editor_counts, on="gh_username", how="left")
+               .fillna({"count": 0})
+)
+editor_activity["count"] = editor_activity["count"].astype(int)
+editor_activity = editor_activity.sort_values(by="count", ascending=False).reset_index(drop=True)
 
+# Get counts of available and busy editors
+available_editors = editor_activity[editor_activity["count"] == 0]
+busy_editors = editor_activity[editor_activity["count"] != 0]
 num_available_editors = len(available_editors)
-available_editors = available_editors.merge(editor_data, left_on="editor", right_on="gh_username", how="inner")
 
-available_editors = available_editors.rename(columns={"count": "review count"})
-available_editors = available_editors[["editor", "review count", "Domain_areas", "Description", "technical_areas", "first_name"]]
+# Rename and cleanup
+editor_activity=editor_activity.rename(columns={"count": "active review count"})
+col = editor_activity.pop("active review count")
+editor_activity.insert(1, "active review count", col)
+
 ```
 
 
+
 ## Row {height=.5%}
 
 ```{python}
 #| content: valuebox
 #| title: "Total Editors"
 
 dict(
-  icon = "box2-heart",
+  icon = "people-fill",
   color = "primary",
-  value = len(all_editors_df)
+  value = len(all_editors)
 )
 ```
 
@@ -148,7 +159,7 @@ dict(
 #| title: "Busy Editors"
 # fails if the value isn't an int
 dict(
-  icon = "person-hearts",
+  icon = "box2-heart",
   color = "primary",
   value = len(busy_editors)
 )
@@ -167,10 +178,8 @@ dict(
 
 ## Row {height=1%}
 ```{python}
-#| title: "pyOpenSci Editorial Team" 
-print("Note: the total editor count is currently incorrect-we should open an issue.")
-
-show(editor_data)
+#| title: "pyOpenSci Active Editorial Team" 
+show(editor_activity)
 ```
 
 ## Row {height=1%}
@@ -193,7 +202,6 @@ show(available_editors)
 
 # Get a list of all editors over time that have supported pyOpenSci
 ignore_editors = ["TBD"]
-ignore_editors += ["lwasser", "xmnlab"]
 editors = [
     editor
     for editor in pd.unique(reviews.editor)
@@ -289,7 +297,7 @@ fig = px.bar(
     facet_col_wrap=facet_wrap,
     color_discrete_sequence=["indigo"],
     labels={"count": "Number of edits", "QuarterLabel": "Quarter"},
-    title="Editor activity by quarter",
+    title="Editor Activity by Quarter (Current Editor Team)",
     height=row_height * num_rows,
     width=1200,
 )
diff --git a/scripts/get-editors.py b/scripts/get-editors.py
