Merge pull request #284 from georgetown-cset/210-data-download

Add download and download link

.pre-commit-config.yaml

@@ -11,7 +11,7 @@ repos:
     -   id: end-of-file-fixer
     -   id: check-yaml
     -   id: check-added-large-files
-        args: ['--maxkb=10000']
+        args: ['--maxkb=50000']
     -   id: check-json
 -   repo: https://github.com/PyCQA/isort
     rev: 5.12.0

github-metrics/src/data/config.json

@@ -1 +1 @@
-{"start_year": 2017, "end_year": 2023, "last_updated": "October 16, 2023"}
+{"start_year": 2017, "end_year": 2023, "last_updated": "October 17, 2023"}

github-metrics/src/data/fields.json

@@ -1 +1 @@
-["Computational biology", "Natural Resources", "Meteorology", "Renewable Energy", "Radiology", "Sustainable Development", "Pattern recognition", "Emissions", "Operating system", "Microbiology", "Evolutionary biology", "Neuroscience", "Organic chemistry", "Financial economics", "Nuclear physics", "Control theory", "Parallel computing", "Chemical physics", "Transport engineering", "Social science", "Molecular physics", "Pharmacology", "Finance", "Software engineering", "Information retrieval", "Oceanography", "Automotive engineering", "Surgery", "Machine learning", "Energy Systems", "Bioinformatics", "Computational chemistry", "Simulation", "Astronomy", "Calculus", "Multimedia", "Media studies", "Condensed matter physics", "Algebra", "Energy Storage", "Cardiology", "Cancer research", "Computational physics", "Astrobiology", "Genetics", "Natural language processing", "Geomorphology", "Computer security", "Social psychology", "riscv", "ai_safety", "Visual arts", "Molecular biology", "Earth Systems", "Epistemology", "Advertising", "Physical chemistry", "Remote sensing", "Data science", "Financial system", "Astrophysics", "Geophysics", "Gender studies", "Seismology", "Botany", "weto", "Computer vision", "Nuclear magnetic resonance", "Computer graphics (images)", "Thermodynamics", "Quantum electrodynamics", "Topology", "Artificial intelligence", "Acoustics", "Econometrics", "Classics", "Embedded system", "Optics", "Mathematical optimization", "Reliability engineering", "Food science", "Ecology", "Anatomy", "Medical education", "Geometry", "Cognitive science", "Virology", "Theoretical physics", "Linguistics", "Speech recognition", "Knowledge management", "Mathematical analysis", "Quantum mechanics", "Consumption of Energy and Resources", "Particle physics", "Atmospheric sciences", "Climate and Earth Science", "Industrial Ecology", "Agronomy", "World Wide Web", "Theoretical computer science", "Pathology", "Distributed computing", "Hydrology", "International economics", "Water resource management", "Cell biology", "Immunology", "Zoology"]
+["Nuclear magnetic resonance", "Natural language processing", "International economics", "Physical chemistry", "Computer security", "Zoology", "Econometrics", "Advertising", "Machine learning", "Quantum mechanics", "Molecular biology", "Earth Systems", "Emissions", "Algebra", "Ecology", "Climate and Earth Science", "Geometry", "Theoretical computer science", "Simulation", "Optics", "Energy Storage", "Cell biology", "riscv", "Seismology", "Reliability engineering", "Astrobiology", "Computer vision", "Astrophysics", "Atmospheric sciences", "Topology", "Visual arts", "Neuroscience", "Cardiology", "Agronomy", "Speech recognition", "Particle physics", "Medical education", "Chemical physics", "Computational biology", "ai_safety", "Information retrieval", "Sustainable Development", "Bioinformatics", "Distributed computing", "Data science", "Renewable Energy", "Organic chemistry", "Embedded system", "Genetics", "Natural Resources", "Computational chemistry", "Multimedia", "Computational physics", "Quantum electrodynamics", "Gender studies", "Food science", "Epistemology", "Virology", "Pharmacology", "Pattern recognition", "Operating system", "Parallel computing", "Automotive engineering", "Finance", "Meteorology", "Social science", "Linguistics", "World Wide Web", "Calculus", "Consumption of Energy and Resources", "Geophysics", "Control theory", "Energy Systems", "Nuclear physics", "Industrial Ecology", "Artificial intelligence", "Molecular physics", "Mathematical optimization", "Geomorphology", "Oceanography", "Pathology", "Radiology", "Hydrology", "Theoretical physics", "Surgery", "Social psychology", "Botany", "Knowledge management", "Classics", "Financial economics", "Software engineering", "Microbiology", "Remote sensing", "Financial system", "Immunology", "Water resource management", "Mathematical analysis", "Astronomy", "Computer graphics (images)", "Media studies", "Cognitive science", "Cancer research", "Acoustics", "Condensed matter physics", "Thermodynamics", "Anatomy", "Transport engineering", "Evolutionary biology", "weto"]

github-metrics/src/pages/index.js

@@ -41,7 +41,7 @@ const IndexPage = () => {
           ORCA compiles data on open-source software (OSS) used in science and technology research. Drawing on Github Archive, ETO’s Merged Academic Corpus, and many other data sources, ORCA tracks OSS usage, health, development activity, and community engagement across a wide range of software projects and research subjects. Use ORCA to compare OSS projects in a particular research area, track trends over time, and sort and filter projects by different metrics. <ExternalLink href={"https://eto.tech/tool-docs/orca"}>Read the docs &gt;&gt;</ExternalLink>
           </div>
           <div>
-            Website last updated on {data.site.buildTime}. Data last updated on {config.last_updated}.
+            Website last updated on {data.site.buildTime}. Data last updated on {config.last_updated}. You may <a href={"/orca_download.jsonl"}>download the data</a>.
           </div>
         </div>}
         documentationLink={"https://eto.tech/tool-docs/orca"}