{
  "generated": "2026-10-15T16:32:26.074Z",
  "self": "https://datasquad.info/api/projects.json",
  "count": 47,
  "vocabulary": {
    "categories": [
      "Visualization & reporting",
      "Data collection & scraping",
      "Data cleaning & integration",
      "Analysis & modeling",
      "Tools & automation",
      "Reproducibility & code migration",
      "Data management & infrastructure",
      "Digitization & heritage",
      "Teaching & training",
      "Program operations"
    ],
    "partner_types": [
      {
        "id": "research",
        "phrase": "for researchers"
      },
      {
        "id": "instruction",
        "phrase": "for courses"
      },
      {
        "id": "campus-operations",
        "phrase": "for campus offices"
      },
      {
        "id": "internal",
        "phrase": "for the program itself"
      }
    ],
    "selections": [
      {
        "id": "featured",
        "phrase": "A written-up example chosen to show the program's work"
      },
      {
        "id": "logged",
        "phrase": "An entry from the program's complete project record"
      }
    ]
  },
  "projects": [
    {
      "id": "ant-nest-3d-scanning",
      "title": "Digitizing Ant Nests to Study Tunneling Behavior",
      "description": "When broken wax casts of ant tunnels threatened years of fieldwork, 3D scanning let researchers reconstruct the nests digitally instead.",
      "institutions": [
        "ucla"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2021",
      "partner": "Ecology and Evolutionary Biology",
      "partner_type": "research",
      "categories": [
        "Digitization & heritage"
      ],
      "tools": [
        "3D Scanning"
      ],
      "team": [
        "Doug Daniels"
      ],
      "url": "https://datasquad.info/projects/ant-nest-3d-scanning",
      "source_url": "https://ucla-datasquad.github.io/#p19",
      "image": "https://datasquad.info/img/projects/ant-nest-hero.png"
    },
    {
      "id": "buddhist-text-nlp",
      "title": "Analyzing Ancient Chinese Buddhist Text with Python",
      "description": "Standard NLP tools assume modern, pre-segmented text. A Ming-dynasty Buddhist corpus needed a different approach to segmentation and comparison.",
      "institutions": [
        "ucla"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2021",
      "partner": "Asian Languages and Cultures",
      "partner_type": "research",
      "categories": [
        "Analysis & modeling"
      ],
      "tools": [
        "Python",
        "spaCy",
        "scikit-learn"
      ],
      "team": [],
      "url": "https://datasquad.info/projects/buddhist-text-nlp",
      "source_url": "https://ucla-datasquad.github.io/#p21",
      "image": "https://datasquad.info/img/projects/buddhist-text-hero.jpg"
    },
    {
      "id": "carceral-ecologies",
      "title": "Carceral Ecologies: LAPD Surveillance Flight Data",
      "description": "A 318-minute data-loading bottleneck became a 2-minute pipeline, unlocking research that went on to national attention and a $5 million grant.",
      "institutions": [
        "ucla"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2023–2024",
      "partner": "Carceral Ecologies Lab",
      "partner_type": "research",
      "categories": [
        "Data cleaning & integration"
      ],
      "tools": [
        "R"
      ],
      "team": [
        "Lawrence Lee",
        "Madeline Kim"
      ],
      "url": "https://datasquad.info/projects/carceral-ecologies",
      "source_url": "https://ucla-datasquad.github.io/#p12",
      "image": "https://datasquad.info/img/projects/carceral-ecologies-hero.jpg"
    },
    {
      "id": "carleton-alumni-reconnection-assessment",
      "title": "Reconnecting with alumni and assessing the model",
      "description": "A form that let DataSquad alumni update their website bios, combined with the program's first assessment of its own model.",
      "institutions": [
        "carleton"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2025",
      "partner": "The DataSquad program, for Paula Lackie",
      "partner_type": "internal",
      "categories": [
        "Program operations",
        "Data cleaning & integration"
      ],
      "tools": [
        "Qualtrics"
      ],
      "team": [
        "Dashiell Coyier",
        "Zaeda Peter"
      ],
      "url": "https://datasquad.info/projects/carleton-alumni-reconnection-assessment",
      "source_url": "https://www.carleton.edu/its/blog/reconnecting-with-datasquad-alumni/",
      "image": null
    },
    {
      "id": "carleton-converting-stata-to-r",
      "title": "Converting Stata to R",
      "description": "I helped translate Stata files to legible R files for an Economics professor's senior comps research course.",
      "institutions": [
        "carleton"
      ],
      "status": "current",
      "selection": "featured",
      "years": null,
      "partner": "Economics Department",
      "partner_type": "research",
      "categories": [
        "Reproducibility & code migration"
      ],
      "tools": [],
      "team": [
        "Karla Cruz Sanchez"
      ],
      "url": "https://datasquad.info/projects/carleton-converting-stata-to-r",
      "source_url": "https://carletondatasquad.bitbucket.io/#projects",
      "image": "https://datasquad.info/img/projects/carleton-converting-stata-to-r.png"
    },
    {
      "id": "carleton-data-scraping",
      "title": "Election news analysis: collecting transcripts from campaign-season coverage",
      "description": "A scraper built and improved by students over several years to gather news transcripts from presidential election periods for a political science research project.",
      "institutions": [
        "carleton"
      ],
      "status": "current",
      "selection": "featured",
      "years": "2021–2024",
      "partner": "Political Science Department",
      "partner_type": "research",
      "categories": [
        "Data collection & scraping"
      ],
      "tools": [
        "Python",
        "Selenium"
      ],
      "team": [
        "Aaron Bronstone",
        "Serafin Patino",
        "Hiromichi Ueda",
        "Helen Du",
        "Isabella Cha",
        "Cathy Duan",
        "Nina Sun",
        "Charles Nykamp",
        "Graham Gordon"
      ],
      "url": "https://datasquad.info/projects/carleton-data-scraping",
      "source_url": "https://www.carleton.edu/its/blog/election-news-analysis-project/",
      "image": "https://datasquad.info/img/projects/carleton-data-scraping.jpeg"
    },
    {
      "id": "carleton-data-security-service",
      "title": "Data Security Service",
      "description": "The DataSquad provides practical data security guidance to faculty, students, and staff.",
      "institutions": [
        "carleton"
      ],
      "status": "past",
      "selection": "featured",
      "years": null,
      "partner": "Institutional Research Board (IRB)",
      "partner_type": "campus-operations",
      "categories": [
        "Data management & infrastructure"
      ],
      "tools": [],
      "team": [],
      "url": "https://datasquad.info/projects/carleton-data-security-service",
      "source_url": "https://carletondatasquad.bitbucket.io/pastproj.html",
      "image": "https://datasquad.info/img/projects/carleton-data-security-service.png"
    },
    {
      "id": "carleton-data-visualization",
      "title": "Data Visualization",
      "description": "Describing the nuance in making data accessible.",
      "institutions": [
        "carleton"
      ],
      "status": "current",
      "selection": "featured",
      "years": null,
      "partner": "Sociology and Anthropology Department",
      "partner_type": "research",
      "categories": [
        "Visualization & reporting"
      ],
      "tools": [],
      "team": [
        "Rachel Kim",
        "Karla Cruz Sanchez"
      ],
      "url": "https://datasquad.info/projects/carleton-data-visualization",
      "source_url": "https://carletondatasquad.bitbucket.io/#projects",
      "image": "https://datasquad.info/img/projects/carleton-data-visualization.png"
    },
    {
      "id": "carleton-data-visualization-for-the-career-center",
      "title": "Data visualization for the Career Center",
      "description": "Pathways provides a visual representation of the careers pursued by different graduates from their respective majors.",
      "institutions": [
        "carleton"
      ],
      "status": "past",
      "selection": "featured",
      "years": null,
      "partner": "Career Center",
      "partner_type": "campus-operations",
      "categories": [
        "Visualization & reporting"
      ],
      "tools": [],
      "team": [
        "Joshua Song",
        "Avery Watts"
      ],
      "url": "https://datasquad.info/projects/carleton-data-visualization-for-the-career-center",
      "source_url": "https://carletondatasquad.bitbucket.io/pastproj.html",
      "image": "https://datasquad.info/img/projects/carleton-data-visualization-for-the-career-center.png"
    },
    {
      "id": "carleton-data-visualization-past",
      "title": "Data Visualization",
      "description": "Data visualization of helpdesk and Academic Technology support info.",
      "institutions": [
        "carleton"
      ],
      "status": "past",
      "selection": "featured",
      "years": null,
      "partner": "ITS Helpdesk and Academic Technology Support",
      "partner_type": "campus-operations",
      "categories": [
        "Visualization & reporting"
      ],
      "tools": [],
      "team": [
        "Yuta Baba"
      ],
      "url": "https://datasquad.info/projects/carleton-data-visualization-past",
      "source_url": "https://carletondatasquad.bitbucket.io/pastproj.html",
      "image": "https://datasquad.info/img/projects/carleton-data-visualization-past.png"
    },
    {
      "id": "carleton-duplicate-faculty-list-into-whd-data",
      "title": "Duplicate Faculty List into WHD Data",
      "description": "Add individual data from Faculty List duplicated to the CBorn file. Match on username, split @carleton.edu off the email address.",
      "institutions": [
        "carleton"
      ],
      "status": "past",
      "selection": "featured",
      "years": null,
      "partner": "Academic Technology",
      "partner_type": "campus-operations",
      "categories": [
        "Data cleaning & integration"
      ],
      "tools": [],
      "team": [
        "Steven Wu"
      ],
      "url": "https://datasquad.info/projects/carleton-duplicate-faculty-list-into-whd-data",
      "source_url": "https://carletondatasquad.bitbucket.io/pastproj.html",
      "image": "https://datasquad.info/img/projects/carleton-duplicate-faculty-list-into-whd-data.png"
    },
    {
      "id": "carleton-election-data-cleaning",
      "title": "Cleaning two decades of student-collected election coverage data",
      "description": "Data coded from news broadcasts by successive student teams over two decades, merged and cleaned over a summer.",
      "institutions": [
        "carleton"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2023",
      "partner": "Political Science",
      "partner_type": "research",
      "categories": [
        "Data cleaning & integration"
      ],
      "tools": [],
      "team": [
        "Shaun Baron-Furayama"
      ],
      "url": "https://datasquad.info/projects/carleton-election-data-cleaning",
      "source_url": "https://www.carleton.edu/its/blog/datasquad-a-deep-dive-into-data-cleaning/",
      "image": null
    },
    {
      "id": "carleton-enroll-course-scraping",
      "title": "Scraping course descriptions for Writing Rich and Quantitative Reasoning lists",
      "description": "The course database had the listings but not the descriptions, so a script collected the descriptions from the registration site.",
      "institutions": [
        "carleton"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2019",
      "partner": "Carleton College",
      "partner_type": "campus-operations",
      "categories": [
        "Data collection & scraping"
      ],
      "tools": [
        "Python",
        "Beautiful Soup",
        "pandas"
      ],
      "team": [
        "Sam Terwilliger"
      ],
      "url": "https://datasquad.info/projects/carleton-enroll-course-scraping",
      "source_url": "https://www.carleton.edu/its/blog/scraping-enroll-with-beautiful-soup-and-pandas/",
      "image": null
    },
    {
      "id": "carleton-file-management-for-its",
      "title": "File Management for ITS",
      "description": "Designing a platform where people can vote on how files are dealt with.",
      "institutions": [
        "carleton"
      ],
      "status": "current",
      "selection": "featured",
      "years": null,
      "partner": "ITS",
      "partner_type": "campus-operations",
      "categories": [
        "Tools & automation",
        "Data management & infrastructure"
      ],
      "tools": [],
      "team": [
        "Yang Tan"
      ],
      "url": "https://datasquad.info/projects/carleton-file-management-for-its",
      "source_url": "https://carletondatasquad.bitbucket.io/#projects",
      "image": "https://datasquad.info/img/projects/carleton-file-management-for-its.png"
    },
    {
      "id": "carleton-google-analytics-api-python",
      "title": "Pulling 100,000 web visit records past the Google Analytics limit",
      "description": "The Google Analytics interface exports 5,000 records at a time; a Python script pulled more than 100,000.",
      "institutions": [
        "carleton"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2023",
      "partner": "Carleton College",
      "partner_type": "campus-operations",
      "categories": [
        "Data collection & scraping"
      ],
      "tools": [
        "Python",
        "Google Analytics API"
      ],
      "team": [
        "Jimmy Zhong"
      ],
      "url": "https://datasquad.info/projects/carleton-google-analytics-api-python",
      "source_url": "https://www.carleton.edu/its/blog/using-python-with-the-google-analytics-api/",
      "image": null
    },
    {
      "id": "carleton-international-student-map",
      "title": "Mapping the international student body",
      "description": "A D3 world map for the Office of International and Intercultural Life, tied to a data visualization course.",
      "institutions": [
        "carleton"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2018",
      "partner": "Office of International and Intercultural Life",
      "partner_type": "campus-operations",
      "categories": [
        "Visualization & reporting"
      ],
      "tools": [
        "D3",
        "JavaScript"
      ],
      "team": [
        "Nobuaki Masaki"
      ],
      "url": "https://datasquad.info/projects/carleton-international-student-map",
      "source_url": "https://www.carleton.edu/its/blog/visualizing-international-student-data/",
      "image": null
    },
    {
      "id": "carleton-its-survey-analysis",
      "title": "Visualizing the MISO survey of technology services",
      "description": "Small-multiple charts of more than 30 question pairs on how faculty, staff and students rate the college's technology services, with a cleaner way to link services to departments.",
      "institutions": [
        "carleton"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2019",
      "partner": "ITS",
      "partner_type": "campus-operations",
      "categories": [
        "Analysis & modeling",
        "Visualization & reporting"
      ],
      "tools": [
        "R"
      ],
      "team": [
        "Nobuaki Masaki"
      ],
      "url": "https://datasquad.info/projects/carleton-its-survey-analysis",
      "source_url": "https://www.carleton.edu/its/blog/visualizing-miso-survey-data/",
      "image": "https://datasquad.info/img/projects/carleton-its-survey-analysis.png"
    },
    {
      "id": "carleton-labeling-and-sorting-alumni-images",
      "title": "Labeling and Sorting Alumni Images",
      "description": "Creating a tool for 'tagging' alumni in college archives.",
      "institutions": [
        "carleton"
      ],
      "status": "current",
      "selection": "featured",
      "years": null,
      "partner": "Office of Alumni Relations",
      "partner_type": "campus-operations",
      "categories": [
        "Tools & automation",
        "Digitization & heritage"
      ],
      "tools": [],
      "team": [
        "Artem Yushko"
      ],
      "url": "https://datasquad.info/projects/carleton-labeling-and-sorting-alumni-images",
      "source_url": "https://carletondatasquad.bitbucket.io/#projects",
      "image": "https://datasquad.info/img/projects/carleton-labeling-and-sorting-alumni-images.png"
    },
    {
      "id": "carleton-language-assessment-visualization",
      "title": "Does the starting course change language scores?",
      "description": "Histograms of speaking, listening, reading and writing scores for 59 students, split by the course they started in.",
      "institutions": [
        "carleton"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2018",
      "partner": "Language departments",
      "partner_type": "instruction",
      "categories": [
        "Visualization & reporting"
      ],
      "tools": [],
      "team": [
        "Yihuang Wu"
      ],
      "url": "https://datasquad.info/projects/carleton-language-assessment-visualization",
      "source_url": "https://www.carleton.edu/its/blog/language-assessment-data-visualization/",
      "image": null
    },
    {
      "id": "carleton-language-placement-dashboard",
      "title": "Advising on a backend and dashboard for language placement tests",
      "description": "A scope longer than any student's time at Carleton, so the squad sketched the database and chose the visualization.",
      "institutions": [
        "carleton"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2017",
      "partner": "Language departments and academic technology",
      "partner_type": "instruction",
      "categories": [
        "Visualization & reporting",
        "Data management & infrastructure"
      ],
      "tools": [],
      "team": [
        "Quinn Schiller",
        "Solomon Foster"
      ],
      "url": "https://datasquad.info/projects/carleton-language-placement-dashboard",
      "source_url": "https://www.carleton.edu/its/blog/sketching-a-backend-for-language-placement-tests/",
      "image": null
    },
    {
      "id": "carleton-make-grading-easier",
      "title": "Make Grading Easier",
      "description": "For years, Professor Meerts used a spreadsheet to manage the results of the peer evaluation data from her class (a student evaluates 3 other students and…",
      "institutions": [
        "carleton"
      ],
      "status": "past",
      "selection": "featured",
      "years": null,
      "partner": "Psychology Department",
      "partner_type": "instruction",
      "categories": [
        "Tools & automation"
      ],
      "tools": [],
      "team": [
        "Jimmy (Juntao) Zhong"
      ],
      "url": "https://datasquad.info/projects/carleton-make-grading-easier",
      "source_url": "https://carletondatasquad.bitbucket.io/pastproj.html",
      "image": "https://datasquad.info/img/projects/carleton-make-grading-easier.jpg"
    },
    {
      "id": "carleton-office-files-to-pdf",
      "title": "Converting old Microsoft Office files to PDF",
      "description": "A bash script that converts a folder of old .doc, .xls and .ppt files to PDF in one pass, keeping names and timestamps.",
      "institutions": [
        "carleton"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2017",
      "partner": "Carleton College",
      "partner_type": "campus-operations",
      "categories": [
        "Data management & infrastructure"
      ],
      "tools": [
        "bash",
        "LibreOffice"
      ],
      "team": [],
      "url": "https://datasquad.info/projects/carleton-office-files-to-pdf",
      "source_url": "https://www.carleton.edu/its/blog/converting-microsoft-office-files-to-pdf-files/",
      "image": null
    },
    {
      "id": "carleton-physics-inventory-database",
      "title": "A friendlier interface for a shared physics equipment database",
      "description": "A FileMaker interface for lab equipment and demonstrations shared by Carleton and St. Olaf, plus a guide for photographing the inventory.",
      "institutions": [
        "carleton"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2017–2018",
      "partner": "Physics",
      "partner_type": "instruction",
      "categories": [
        "Tools & automation",
        "Data management & infrastructure"
      ],
      "tools": [
        "FileMaker"
      ],
      "team": [
        "Yihuang Wu"
      ],
      "url": "https://datasquad.info/projects/carleton-physics-inventory-database",
      "source_url": "https://www.carleton.edu/its/blog/physics-inventory-database-image-optimization-instructions/",
      "image": null
    },
    {
      "id": "carleton-presidential-ads-2008-graphs",
      "title": "Redesigning book graphs to a publisher's rules",
      "description": "Graphs of every presidential ad aired in 2008, redrawn in black and white at 4 by 7.5 inches, with the original Excel file lost.",
      "institutions": [
        "carleton"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2017",
      "partner": "Political Science",
      "partner_type": "research",
      "categories": [
        "Visualization & reporting"
      ],
      "tools": [
        "Python",
        "pandas",
        "R Markdown"
      ],
      "team": [
        "Quinn Schiller"
      ],
      "url": "https://datasquad.info/projects/carleton-presidential-ads-2008-graphs",
      "source_url": "https://www.carleton.edu/its/blog/every-presidential-ad-ran-in-2008/",
      "image": null
    },
    {
      "id": "carleton-project-workflow",
      "title": "Project Workflow",
      "description": "For our blogs, we use a workflow that organizes our projects and makes it easier to track everyone's project progress.",
      "institutions": [
        "carleton"
      ],
      "status": "current",
      "selection": "featured",
      "years": null,
      "partner": "DataSquad",
      "partner_type": "internal",
      "categories": [
        "Program operations"
      ],
      "tools": [],
      "team": [
        "Ryan Yang"
      ],
      "url": "https://datasquad.info/projects/carleton-project-workflow",
      "source_url": "https://carletondatasquad.bitbucket.io/#projects",
      "image": "https://datasquad.info/img/projects/carleton-project-workflow.png"
    },
    {
      "id": "carleton-rclone-account-transfer",
      "title": "Moving a graduating student's files with rclone",
      "description": "When a student account ends, years of files go with it; a comparison of rclone and rsync for moving large amounts of data.",
      "institutions": [
        "carleton"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2024",
      "partner": "Information Technology Services",
      "partner_type": "campus-operations",
      "categories": [
        "Tools & automation"
      ],
      "tools": [
        "rclone",
        "rsync",
        "Google Drive"
      ],
      "team": [
        "Ryan Yang"
      ],
      "url": "https://datasquad.info/projects/carleton-rclone-account-transfer",
      "source_url": "https://www.carleton.edu/its/blog/transferring-your-stuff-efficiently-and-effectively-is-rclone-the-right-tool/",
      "image": null
    },
    {
      "id": "carleton-rstudio-server-guide",
      "title": "An introduction to RStudio Server for students",
      "description": "A guide to using RStudio in a web browser from any campus computer, for statistics and computer science courses.",
      "institutions": [
        "carleton"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2018",
      "partner": "Statistics and computer science courses",
      "partner_type": "instruction",
      "categories": [
        "Teaching & training",
        "Data management & infrastructure"
      ],
      "tools": [
        "RStudio Server"
      ],
      "team": [
        "Yihuang Wu"
      ],
      "url": "https://datasquad.info/projects/carleton-rstudio-server-guide",
      "source_url": "https://www.carleton.edu/its/blog/introduction-to-rstudio-server-carleton/",
      "image": null
    },
    {
      "id": "carleton-self-scheduled-exams-form",
      "title": "Collecting self-scheduled exam opt-ins with Google Forms",
      "description": "The registrar's office emailed every professor each term and tallied replies by hand; a prefilled form now compiles them automatically.",
      "institutions": [
        "carleton"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2017",
      "partner": "Registrar's office",
      "partner_type": "campus-operations",
      "categories": [
        "Tools & automation"
      ],
      "tools": [
        "Google Forms",
        "Google Sheets",
        "Mail merge"
      ],
      "team": [
        "Quinn Schiller"
      ],
      "url": "https://datasquad.info/projects/carleton-self-scheduled-exams-form",
      "source_url": "https://www.carleton.edu/its/blog/modernizing-mail-merge-with-google-forms/",
      "image": null
    },
    {
      "id": "carleton-tableau-presentation-and-support-for-a-sociology-class",
      "title": "Tableau Presentation & Support for a Sociology Class",
      "description": "Professor Nierobisz wanted to find a more engaging approach to data for her criminology course.",
      "institutions": [
        "carleton"
      ],
      "status": "past",
      "selection": "featured",
      "years": null,
      "partner": "Sociology and Anthropology Department",
      "partner_type": "instruction",
      "categories": [
        "Teaching & training"
      ],
      "tools": [],
      "team": [
        "Yiwen Luo"
      ],
      "url": "https://datasquad.info/projects/carleton-tableau-presentation-and-support-for-a-sociology-class",
      "source_url": "https://carletondatasquad.bitbucket.io/pastproj.html",
      "image": "https://datasquad.info/img/projects/carleton-tableau-presentation-and-support-for-a-sociology-class.jpg"
    },
    {
      "id": "carleton-technology-check-scheduling",
      "title": "Scheduling technology checks across more than a hundred rooms",
      "description": "Student workers check projectors and touch panels in classrooms around campus; a student wrote code to build their schedules.",
      "institutions": [
        "carleton"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2025",
      "partner": "Presentation, Events, and Production Support",
      "partner_type": "campus-operations",
      "categories": [
        "Tools & automation"
      ],
      "tools": [],
      "team": [
        "Auiannce Euwing"
      ],
      "url": "https://datasquad.info/projects/carleton-technology-check-scheduling",
      "source_url": "https://www.carleton.edu/its/blog/automating-technology-check-scheduling/",
      "image": null
    },
    {
      "id": "carleton-visiting-accepted-students-map",
      "title": "Visiting Accepted Students Map",
      "description": "Create a nice looking map of the home-towns of the accepted incoming students who visited Carleton in April ‘22.",
      "institutions": [
        "carleton"
      ],
      "status": "past",
      "selection": "featured",
      "years": null,
      "partner": "Office of Admissions",
      "partner_type": "campus-operations",
      "categories": [
        "Visualization & reporting"
      ],
      "tools": [],
      "team": [
        "Xingyi Zhang",
        "Nina Sun"
      ],
      "url": "https://datasquad.info/projects/carleton-visiting-accepted-students-map",
      "source_url": "https://carletondatasquad.bitbucket.io/pastproj.html",
      "image": "https://datasquad.info/img/projects/carleton-visiting-accepted-students-map.png"
    },
    {
      "id": "como-q",
      "title": "Como-Q: A Skincare Ingredient Screener",
      "description": "The DataSquad's first project for an outside applicant: an R tool that flags comedogenic (pore-clogging) ingredients in skincare and hygiene products.",
      "institutions": [
        "ucla"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2022",
      "partner": null,
      "partner_type": "internal",
      "categories": [
        "Tools & automation"
      ],
      "tools": [
        "R"
      ],
      "team": [
        "Will Foote",
        "Isabel Light"
      ],
      "url": "https://datasquad.info/projects/como-q",
      "source_url": "https://ucla-datasquad.github.io/#p16",
      "image": "https://datasquad.info/img/projects/como-q-hero.png"
    },
    {
      "id": "dsi-obstacles-survey-tableau",
      "title": "Visualizing Global Obstacles to Student Data Services",
      "description": "A UCLA consultant cleaned and visualized DataSquad International's first cross-institution survey on what stops campuses from employing student data analysts.",
      "institutions": [
        "ucla"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2022",
      "partner": "DataSquad International",
      "partner_type": "internal",
      "categories": [
        "Visualization & reporting"
      ],
      "tools": [
        "Tableau",
        "R"
      ],
      "team": [
        "Will Foote"
      ],
      "url": "https://datasquad.info/projects/dsi-obstacles-survey-tableau",
      "source_url": "https://ucla-datasquad.github.io/#p17",
      "image": "https://datasquad.info/img/projects/dsi-tableau-obstacles.png"
    },
    {
      "id": "freud-memoirs-ocr",
      "title": "Reading handwritten German memoirs",
      "description": "Images of aged, handwritten memoirs became complete, accurate text a sociology professor could translate and analyze.",
      "institutions": [
        "ucla"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2024",
      "partner": "Sociology",
      "partner_type": "research",
      "categories": [
        "Digitization & heritage"
      ],
      "tools": [],
      "team": [],
      "url": "https://datasquad.info/projects/freud-memoirs-ocr",
      "source_url": "https://ucla-datasquad.github.io/2025/01/30/Recent-projects.html",
      "image": null
    },
    {
      "id": "helicopter-surveillance-flight-data",
      "title": "Flight data for research on police helicopter surveillance",
      "description": "Twelve monthly files of about a million rows each, with nested records, turned into one analyzable dataset for an undergraduate researcher.",
      "institutions": [
        "ucla"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2022–2024",
      "partner": "UCLA undergraduate research on police helicopter surveillance",
      "partner_type": "research",
      "categories": [
        "Data cleaning & integration",
        "Analysis & modeling"
      ],
      "tools": [],
      "team": [
        "Ethan Allavarpu",
        "Kristian Allen"
      ],
      "url": "https://datasquad.info/projects/helicopter-surveillance-flight-data",
      "source_url": "https://ucla-datasquad.github.io/2023/07/27/kate-m-helicopter-data.html",
      "image": null
    },
    {
      "id": "israeli-archives-bulk-download",
      "title": "Downloading over 1,200 declassified meeting minutes",
      "description": "An archive that lets you download one PDF at a time, and a script that handled the rest.",
      "institutions": [
        "ucla"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2026",
      "partner": "International Institute",
      "partner_type": "research",
      "categories": [
        "Data collection & scraping"
      ],
      "tools": [],
      "team": [
        "Lian Elsa Linton"
      ],
      "url": "https://datasquad.info/projects/israeli-archives-bulk-download",
      "source_url": "https://ucla-datasquad.github.io/2026/04/29/spring-2026-update.html",
      "image": null
    },
    {
      "id": "layout-parser-canon-law",
      "title": "Testing Layout Parser on medieval Canon Law texts",
      "description": "The squad tried a newer OCR toolkit that boxes text by section, and recorded why it is hard to recommend.",
      "institutions": [
        "ucla"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2024",
      "partner": "DataSquad",
      "partner_type": "internal",
      "categories": [
        "Digitization & heritage"
      ],
      "tools": [
        "Layout Parser"
      ],
      "team": [],
      "url": "https://datasquad.info/projects/layout-parser-canon-law",
      "source_url": "https://ucla-datasquad.github.io/2025/01/30/Recent-projects.html",
      "image": null
    },
    {
      "id": "lesson-checker-wbcheck",
      "title": "wbcheck: a lesson checker for Carpentries Workbench",
      "description": "A command-line tool that finds broken front matter, links and scaffold text in a Carpentries lesson in under a second, started by two DataSquad students and now at 48 rules.",
      "institutions": [
        "ucla"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2023–2026",
      "partner": "UCLA IMLS Open Science lesson development",
      "partner_type": "instruction",
      "categories": [
        "Tools & automation",
        "Teaching & training"
      ],
      "tools": [
        "Python",
        "pixi",
        "Carpentries Workbench"
      ],
      "team": [
        "Lawrence Lee",
        "Eric Huang",
        "Tim Dennis"
      ],
      "url": "https://datasquad.info/projects/lesson-checker-wbcheck",
      "source_url": "https://github.com/ucla-imls-open-sci/carpentries-workbench-checker",
      "image": null
    },
    {
      "id": "ocr-entity-linking-pipeline",
      "title": "From scanned pages to searchable, linked text",
      "description": "A DataSquad member evaluated OCR, entity linking and layout formats to make UCLA Library collections computable for researchers.",
      "institutions": [
        "ucla"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2023",
      "partner": "UCLA Library collections",
      "partner_type": "campus-operations",
      "categories": [
        "Digitization & heritage",
        "Tools & automation"
      ],
      "tools": [
        "Tesseract",
        "ReFinED",
        "ALTO"
      ],
      "team": [
        "Lukas Hager"
      ],
      "url": "https://datasquad.info/projects/ocr-entity-linking-pipeline",
      "source_url": "https://ucla-datasquad.github.io/2024/03/14/ocr-research-lukas.html",
      "image": null
    },
    {
      "id": "project-brainstorm-course",
      "title": "Data help for five PhD research teams in one course",
      "description": "Neuroscience PhD students in a research-design course brought questions about education; the squad helped them find datasets and plan the statistics.",
      "institutions": [
        "ucla"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2026",
      "partner": "Interdepartmental PhD Program in Neuroscience (Project Brainstorm course)",
      "partner_type": "instruction",
      "categories": [
        "Analysis & modeling",
        "Teaching & training"
      ],
      "tools": [],
      "team": [
        "Lian Elsa Linton",
        "Audrey Garcia",
        "Shawn Wang",
        "Gianna Kim"
      ],
      "url": "https://datasquad.info/projects/project-brainstorm-course",
      "source_url": "https://ucla-datasquad.github.io/2026/04/29/spring-2026-update.html",
      "image": null
    },
    {
      "id": "refugee-heritage-3d",
      "title": "Preserving Vietnamese Refugee Heritage Through 3D Technology",
      "description": "3D scanning let the DSC digitize fragile refugee artifacts and publish the first public exhibit tracing one family's maritime escape across the Pacific.",
      "institutions": [
        "ucla"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2023–2024",
      "partner": "Refugee Material Cultural Initiative",
      "partner_type": "research",
      "categories": [
        "Digitization & heritage"
      ],
      "tools": [
        "3D Scanning"
      ],
      "team": [
        "Doug Daniels",
        "Bianca Badajos",
        "Connor Lim"
      ],
      "url": "https://datasquad.info/projects/refugee-heritage-3d",
      "source_url": "https://ucla-datasquad.github.io/#p13",
      "image": "https://datasquad.info/img/projects/refugee-heritage-hero.jpg"
    },
    {
      "id": "sexual-health-resources-survey",
      "title": "Do STEM and humanities students know the same campus health resources?",
      "description": "Survey and interview analysis for a student health project: 143 survey responses and 10 interviews.",
      "institutions": [
        "ucla"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2026",
      "partner": "Black/Latinx AIDS Project",
      "partner_type": "research",
      "categories": [
        "Analysis & modeling"
      ],
      "tools": [],
      "team": [
        "Shawn Wang",
        "Lian Elsa Linton",
        "Audrey Garcia"
      ],
      "url": "https://datasquad.info/projects/sexual-health-resources-survey",
      "source_url": "https://ucla-datasquad.github.io/2026/04/29/spring-2026-update.html",
      "image": null
    },
    {
      "id": "shedding-light-on-injustice",
      "title": "Shedding Light on Injustice",
      "description": "Four cohorts of DataSquad consultants spent five years building the dataset behind Terence Keel's book on hidden deaths in police custody.",
      "institutions": [
        "ucla"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2021–2025",
      "partner": "Biocritical Studies Lab",
      "partner_type": "research",
      "categories": [
        "Data cleaning & integration",
        "Visualization & reporting"
      ],
      "tools": [
        "R",
        "Python",
        "OpenRefine",
        "Tableau"
      ],
      "team": [
        "Julia Wood",
        "Ethan Allavarpu",
        "Tristan Dewing",
        "Lawrence Lee"
      ],
      "url": "https://datasquad.info/projects/shedding-light-on-injustice",
      "source_url": "https://ucla-datasquad.github.io/#p14",
      "image": "https://datasquad.info/img/projects/keel-coroners-silence-cover.jpg"
    },
    {
      "id": "squirrels-in-motion",
      "title": "Squirrels in Motion",
      "description": "Motion-sensor collars on wild ground squirrels produced accelerometer data at 100 readings a second; the DSC helped turn it into a behavior-prediction model.",
      "institutions": [
        "ucla"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2021",
      "partner": "Ecology and Evolutionary Biology",
      "partner_type": "research",
      "categories": [
        "Analysis & modeling"
      ],
      "tools": [
        "R"
      ],
      "team": [],
      "url": "https://datasquad.info/projects/squirrels-in-motion",
      "source_url": "https://ucla-datasquad.github.io/#p20",
      "image": "https://datasquad.info/img/projects/squirrels-hero.jpg"
    },
    {
      "id": "stan-twitter-music-industry",
      "title": "Mining Twitter to test how fan communities drive pop success",
      "description": "A communication studies undergraduate needed Twitter metrics for four pop artists; a DataSquad consultant scraped them in Python and the analysis won a Dean's Prize.",
      "institutions": [
        "ucla"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2021",
      "partner": "Communication Studies undergraduate research",
      "partner_type": "research",
      "categories": [
        "Data collection & scraping",
        "Analysis & modeling"
      ],
      "tools": [
        "Python",
        "SPSS"
      ],
      "team": [
        "Julia Wood"
      ],
      "url": "https://datasquad.info/projects/stan-twitter-music-industry",
      "source_url": "https://ucla-datasquad.github.io/2021/09/16/Harmonizing-data.html",
      "image": null
    },
    {
      "id": "uc-ospo-education-site",
      "title": "A lesson inventory and the site built from it for UC OSPO education",
      "description": "A catalog of 55 open source and research software lessons, and the searchable site two DataSquad students built to browse it.",
      "institutions": [
        "ucla"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2025–2026",
      "partner": "UC OSPO Network education working group",
      "partner_type": "instruction",
      "categories": [
        "Tools & automation",
        "Teaching & training"
      ],
      "tools": [
        "Astro",
        "Google Sheets"
      ],
      "team": [
        "Shawn Wang",
        "Gianna Kim",
        "Lian Elsa Linton",
        "Tim Dennis"
      ],
      "url": "https://datasquad.info/projects/uc-ospo-education-site",
      "source_url": "https://ucla-datasquad.github.io/2026/04/29/spring-2026-update.html",
      "image": null
    },
    {
      "id": "voter-file-at-scale",
      "title": "Making Voter Data Usable for Research, at Scale",
      "description": "A fragmented 10TB national voter file became a single analysis-ready dataset now used across political science, economics, and health research.",
      "institutions": [
        "ucla"
      ],
      "status": "past",
      "selection": "featured",
      "years": "2023–present",
      "partner": null,
      "partner_type": "research",
      "categories": [
        "Data management & infrastructure"
      ],
      "tools": [
        "Redivis",
        "Python"
      ],
      "team": [],
      "url": "https://datasquad.info/projects/voter-file-at-scale",
      "source_url": "https://ucla-datasquad.github.io/#p15",
      "image": "https://datasquad.info/img/projects/voter-file-hero.jpg"
    }
  ]
}