Merge pull request #321 from georgetown-cset/20240916-data-update

Update data; remove need to manually add new obscure licenses to constants

fields/exclude.txt

@@ -1,11 +1,17 @@
+Aesthetics
 Algorithm
+Algorithms
 Analytical chemistry
+Ancient history
+Anesthesia
 Arithmetic
 Art history
 Atomic physics
 Biochemistry
 Biomedical engineering
+Biotechnology
 Cartography
+Ceramic materials
 Classical mechanics
 Climatology
 Clinical psychology
@@ -14,64 +20,87 @@ Combinatorial chemistry
 Combinatorics
 Communication
 Composite material
+Computational science
+Computer architecture
+Computer graphics
 Computer network
+Computer networks
+Computer simulation
 Control engineering
+Cryobiology
+Crystallography
 Data mining
 Database
+Databases
+Demography
 Development economics
 Developmental psychology
 Discrete mathematics
+Economic growth
 Economic policy
 Electrical engineering
+Endocrinology
+Engineering drawing
+Environmental engineering
+Environmental ethics
+Environmental health
 Environmental planning
+Environmental protection
+Environmental resource management
 Forensic engineering
+Forestry
+Gastroenterology
+Genealogy
 Geochemistry
+Geodesy
+Geotechnical engineering
+Gerontology
+High-performance computing
+Humanities
 Human–computer interaction
+Intensive care medicine
 Internet privacy
 Keynesian economics
 Law
 Library science
 Literature
+Macroeconomics
+Management
+Management science
+Marine engineering
+Market economy
 Mathematical economics
 Mechanics
+Medical physics
 Microeconomics
 Mining engineering
+Natural resource economics
+Nuclear medicine
+Obstetrics
+Oncology
+Operating systems
 Operations management
+Operations research
+Paleontology
+Parasitology
 Pedagogy
+Pediatrics
+Photobiology
 Process management
 Programming language
+Programming languages
 Psychiatry
+Public administration
+Public economics
 Public relations
+Radiobiology
 Real-time computing
 Risk analysis (engineering)
 Socioeconomics
+Soil science
+Statistical physics
 Statistics
 Structural engineering
 Systems engineering
 Telecommunications
-Public administration
-Soil science
-Statistical physics
-Pediatrics
-Obstetrics
-Intensive care medicine
-Management
-Marine engineering
-Market economy
-Gerontology
-Humanities
-Forestry
-Economic growth
-Environmental engineering
-Environmental ethics
-Environmental health
-Environmental protection
-Environmental resource management
-Crystallography
-Ancient history
-Aesthetics
-Biotechnology
-Computational science
-Computer architecture
-Demography
-Geotechnical engineering
+Welfare economics

fields/expected.txt

@@ -1,4 +1,7 @@
 Acoustics
+Advertising
+Agroforestry
+Agronomy
 Algebra
 Algorithm
 Analytical chemistry
@@ -15,11 +18,17 @@ Automotive engineering
 Biochemistry
 Bioinformatics
 Biomedical engineering
+Biotechnology
+Botany
 Calculus
 Cancer research
+Cardiology
 Cartography
 Cell biology
+Chemical physics
 Classical mechanics
+Classics
+Climate and Earth Science
 Climatology
 Clinical psychology
 Cognitive psychology
@@ -38,6 +47,7 @@ Computer network
 Computer security
 Computer vision
 Condensed matter physics
+Consumption of Energy and Resources
 Control engineering
 Control theory
 Data mining
@@ -47,25 +57,33 @@ Development economics
 Developmental psychology
 Discrete mathematics
 Distributed computing
+Earth Systems
 Ecology
 Econometrics
 Economic policy
 Electrical engineering
 Embedded system
+Emissions
+Energy Storage
+Energy Systems
 Environmental planning
 Epistemology
 Evolutionary biology
 Finance
 Financial economics
 Financial system
+Food science
 Forensic engineering
 Gender studies
 Genetics
 Geochemistry
 Geometry
+Geomorphology
 Geophysics
 Human\u2013computer interaction
+Hydrology
 Immunology
+Industrial Ecology
 Information retrieval
 International economics
 Internet privacy
@@ -83,34 +101,44 @@ Mechanics
 Media studies
 Medical education
 Meteorology
+Microbiology
 Microeconomics
 Mining engineering
 Molecular biology
+Molecular physics
 Multimedia
+Natural Resources
 Natural language processing
 Neuroscience
 Nuclear magnetic resonance
 Nuclear physics
+Oceanography
 Operating system
 Operations management
 Optics
+Organic chemistry
 Parallel computing
 Particle physics
+Pathology
 Pattern recognition
 Pedagogy
 Pharmacology
+Physical chemistry
 Process management
 Programming language
 Psychiatry
 Public relations
+Quantum computing
 Quantum electrodynamics
 Quantum mechanics
 Radiology
 Real-time computing
 Reliability engineering
 Remote sensing
+Renewable Energy
 Risk analysis (engineering)
 Seismology
+Semiconductors
 Simulation
 Social psychology
 Social science
@@ -119,46 +147,21 @@ Software engineering
 Speech recognition
 Statistics
 Structural engineering
+Surgery
+Sustainable Development
 Systems engineering
 Telecommunications
 Theoretical computer science
 Theoretical physics
+Thermodynamics
 Topology
+Transport engineering
 Virology
 Visual arts
+Water resource management
 World Wide Web
 Zoology
 ai_safety
 asr
 riscv
 weto
-Emissions
-Earth Systems
-Energy Storage
-Sustainable Development
-Climate and Earth Science
-Industrial Ecology
-Renewable Energy
-Natural Resources
-Consumption of Energy and Resources
-Energy Systems
-Advertising
-Agronomy
-Biotechnology
-Botany
-Cardiology
-Chemical physics
-Classics
-Food science
-Geomorphology
-Hydrology
-Microbiology
-Molecular physics
-Oceanography
-Organic chemistry
-Pathology
-Physical chemistry
-Surgery
-Thermodynamics
-Transport engineering
-Water resource management

github-metrics/src/components/dashboard.test.js

@@ -19,11 +19,11 @@ describe("filter panel", () => {
     let topReposHeading;
     let topEntries
 
-    expect(screen.getByRole("heading", { name: currentlyTrackingHeading(703, "artificial intelligence") })).toBeVisible();
+    expect(screen.getByRole("heading", { name: currentlyTrackingHeading(8541, "artificial intelligence") })).toBeVisible();
     topReposHeading = screen.getByRole("heading", { name: "Top repositories by stars" });
     topEntries = getAllByRole(topReposHeading.parentElement, "listitem");
-    expect(topEntries[0].textContent).toEqual("facebook/react222142 stars (-16.49%, 2022-2023)");
-    expect(topEntries[1].textContent).toEqual("tensorflow/tensorflow182621 stars (+11.70%, 2022-2023)");
+    expect(topEntries[0].textContent).toEqual("public-apis/public-apis311473 stars (-70.86%, 2023-2024)");
+    expect(topEntries[1].textContent).toEqual("facebook/react226953 stars (-75.51%, 2023-2024)");
 
     await user.click(screen.getByRole('combobox'));
     expect(screen.getByText("Astrobiology")).toBeVisible();
@@ -32,11 +32,11 @@ describe("filter panel", () => {
     });
     await new Promise(res => setTimeout(res, 500));
 
-    expect(screen.getByRole("heading", { name: currentlyTrackingHeading(113, "astrobiology") })).toBeVisible();
+    expect(screen.getByRole("heading", { name: currentlyTrackingHeading(100, "astrobiology") })).toBeVisible();
     topReposHeading = screen.getByRole("heading", { name: "Top repositories by stars" });
     topEntries = getAllByRole(topReposHeading.parentElement, "listitem");
-    expect(topEntries[0].textContent).toEqual("google/jax28045 stars (-11.73%, 2022-2023)");
-    expect(topEntries[1].textContent).toEqual("astropy/astropy4220 stars (-28.72%, 2022-2023)");
+    expect(topEntries[0].textContent).toEqual("keras-team/keras61559 stars (-75.75%, 2023-2024)");
+    expect(topEntries[1].textContent).toEqual("google/jax29746 stars (-69.67%, 2023-2024)");
   });
 
 
@@ -45,21 +45,21 @@ describe("filter panel", () => {
       <Dashboard />
     );
 
-    expect(screen.getByRole("heading", { name: currentlyTrackingHeading(113, "astrobiology") })).toBeVisible();
+    expect(screen.getByRole("heading", { name: currentlyTrackingHeading(100, "astrobiology") })).toBeVisible();
 
     await user.click(screen.getByRole('checkbox'));
     await new Promise(res => setTimeout(res, 500));
 
     expect(screen.getByRole("button", { name: "Show Filters" })).toBeVisible();
 
     const cards = screen.getAllByTestId("project-card");
-    expect(getByRole(cards[0], "heading", { name: "hannorein/rebound" })).toBeVisible();
-    expect(cards[0].textContent).toContain("Stars: 768");
-    expect(cards[0].textContent).toContain("Top Programming Language: C");
+    expect(getByRole(cards[0], "heading", { name: "jlillo/tpfplotter" })).toBeVisible();
+    expect(cards[0].textContent).toContain("Stars: 32");
+    expect(cards[0].textContent).toContain("Top Programming Language: Python");
     expect(cards[0].textContent).toContain("Commits over time");
-    expect(getByRole(cards[1], "heading", { name: "jlillo/tpfplotter" })).toBeVisible();
-    expect(cards[1].textContent).toContain("Date created: 2020-02-02");
-    expect(cards[1].textContent).toContain("License: MIT License");
+    expect(getByRole(cards[1], "heading", { name: "hannorein/rebound" })).toBeVisible();
+    expect(cards[1].textContent).toContain("Date created: 2011-07-02");
+    expect(cards[1].textContent).toContain("License: GNU General Public License v3.0");
   });
 
 
@@ -69,7 +69,7 @@ describe("filter panel", () => {
     );
 
     let cards = screen.getAllByTestId("project-card");
-    expect(getByRole(cards[0], "heading", { name: "hannorein/rebound" })).toBeVisible();
+    expect(getByRole(cards[0], "heading", { name: "jlillo/tpfplotter" })).toBeVisible();
 
     await user.click(screen.getByRole('button', { name: "Sort by Relevance Documentation" }));
 
@@ -123,7 +123,7 @@ describe("filter panel", () => {
 
     // Check prior state
     let topPanel = screen.getByTestId('top-panel');
-    expect(getByText(topPanel, "Showing 113 repositories", { exact: false })).toBeVisible();
+    expect(getByText(topPanel, "Showing 100 repositories", { exact: false })).toBeVisible();
     let cards = screen.getAllByTestId("project-card");
     expect(cards.length).toEqual(10); // Pagination shows only 10 per page
     expect(getByRole(cards[0], "heading", { name: "google/jax" })).toBeVisible();
@@ -150,7 +150,7 @@ describe("filter panel", () => {
     expect(getByText(topPanel, "Showing 1 repositories", { exact: false })).toBeVisible();
     cards = screen.getAllByTestId("project-card");
     expect(cards.length).toEqual(1);
-    expect(getByRole(cards[0], "heading", { name: "exoclime/FastChem" })).toBeVisible();
+    expect(getByRole(cards[0], "heading", { name: "NewStrangeWorlds/FastChem" })).toBeVisible();
   }, 15000);
 
 

github-metrics/src/data/config.json

@@ -1 +1 @@
-{"start_year": 2017, "end_year": 2023, "last_updated": "June 10, 2024"}
+{"start_year": 2018, "end_year": 2024, "last_updated": "September 17, 2024"}

github-metrics/src/data/fields.json

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