{ "_id": "6acdaa8fa14063b82c3ac36b", "Package": "datacaged", "Title": "CAGED Microdata Download and Storage in 'DuckDB'", "Version": "0.2.3", "Authors@R": "person(\"Alexsandro\", \"Prado\",\nemail = \"alexsandro.prado@ufersa.edu.br\",\nrole = c(\"aut\", \"cre\"),\ncomment = c(ORCID = \"0000-0002-7072-3621\"))", "Description": "Tools to download, parse, and store Brazilian CAGED\n(Cadastro Geral de Empregados e Desempregados) microdata using\n'DuckDB'. Supports both legacy CAGED (pre-2020), Novo CAGED\n(2020+), and adjustment files, enabling efficient local storage\nand analysis workflows. Data is sourced from the HuggingFace\nrepository\n.", "SystemRequirements": "7-Zip (optional, required for PPMd-compressed files\nfrom CAGED antigo and CAGED Ajustes)", "License": "MIT + file LICENSE", "Encoding": "UTF-8", "LazyData": "true", "LazyDataCompression": "bzip2", "Date": "2026-10-01", "Roxygen": "list(markdown = TRUE)", "VignetteBuilder": "knitr", "Config/testthat/edition": "3", "URL": "https://github.com/gecomt/datacaged", "BugReports": "https://github.com/gecomt/datacaged/issues", "Config/Needs/website": "rmarkdown", "Config/roxygen2/version": "8.1.1", "Config/pak/sysreqs": "libarchive-dev libicu-dev libssl-dev libx11-dev\nxz-utils", "Repository": "https://gecomt.r-universe.dev", "Date/Publication": "2026-10-13 01:06:30 UTC", "RemoteUrl": "https://github.com/gecomt/datacaged", "RemoteRef": "HEAD", "RemoteSha": "e5e5615c8676c1ff8ba37ed316c096d2f06bd44b", "NeedsCompilation": "no", "Packaged": { "Date": "2026-10-13 03:44:34 UTC", "User": "root" }, "Author": "Alexsandro Prado [aut, cre] (ORCID:\n)", "Maintainer": "Alexsandro Prado ", "_user": "gecomt", "_type": "src", "_file": "datacaged_0.2.3.tar.gz", "_fileid": "https://r2.ropensci.org/753491b7072c185295d794be8741129312fc38cec5e5e4c6e87b4000fa0cf860", "_filesize": 592889, "_sha256": "753491b7072c185295d794be8741129312fc38cec5e5e4c6e87b4000fa0cf860", "_expires": "2027-01-21T03:50:34.000Z", "_created": "2026-10-13T03:44:34.000Z", "_published": "2026-10-13T03:50:38.898Z", "_buildurl": "https://github.com/r-universe/gecomt/actions/runs/38342824534", "_status": "success", "_host": "GitHub-Actions", "_jobs": [ { "job": 115118492375, "time": 209, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "11788125555" }, { "job": 115118492345, "time": 166, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "11787349145" }, { "job": 115118492381, "time": 315, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "11788050994" }, { "job": 115118492275, "time": 135, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "11787761854" }, { "job": 115117484600, "time": 248, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "11787761629" }, { "job": 115118492463, "time": 124, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "11787389158" }, { "job": 115118492424, "time": 129, "config": "windows-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "11788165242" }, { "job": 115118492304, "time": 110, "config": "windows-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "11787438969" }, { "job": 115118492319, "time": 89, "config": "windows-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "11787339068" } ], "_upstream": "https://github.com/gecomt/datacaged", "_commit": { "id": "e5e5615c8676c1ff8ba37ed316c096d2f06bd44b", "author": "Alexsandro Prado <30550802+alexsandroprado@users.noreply.github.com>", "committer": "GitHub ", "message": "Revise README.pt-BR.md for improved structure and content\n\nUpdated README in Portuguese to enhance clarity and organization of features, installation instructions, and usage examples.", "time": 1791853590 }, "_maintainer": { "name": "Alexsandro Prado", "email": "alexsandro.prado@ufersa.edu.br", "login": "alexsandroprado", "orcid": "0000-0002-7072-3621", "description": "Professor assistente da Universidade Federal Rural do Semi-árido - UFERSA lotado no departamento de Ciências Socias Aplicadas.", "uuid": 30550802 }, "_distro": "resolute", "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 4.2.0", "role": "Depends" }, { "package": "archive", "role": "Imports" }, { "package": "cli", "role": "Imports" }, { "package": "DBI", "role": "Imports" }, { "package": "dplyr", "role": "Imports" }, { "package": "duckdb", "role": "Imports" }, { "package": "future", "role": "Imports" }, { "package": "furrr", "role": "Imports" }, { "package": "glue", "role": "Imports" }, { "package": "httr2", "version": ">= 1.0.0", "role": "Imports" }, { "package": "progressr", "role": "Imports" }, { "package": "purrr", "role": "Imports" }, { "package": "readr", "version": ">= 2.1.0", "role": "Imports" }, { "package": "stringr", "role": "Imports" }, { "package": "tibble", "role": "Imports" }, { "package": "tools", "role": "Imports" }, { "package": "utils", "role": "Imports" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "dbplyr", "role": "Suggests" }, { "package": "withr", "role": "Suggests" } ], "_owner": "gecomt", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2026-35", "n": 24 }, { "week": "2026-36", "n": 2 }, { "week": "2026-37", "n": 6 }, { "week": "2026-42", "n": 7 } ], "_tags": [ { "name": "v0.1.0", "date": "2026-05-06" }, { "name": "v0.2.0", "date": "2026-08-24" }, { "name": "v0.2.1", "date": "2026-08-27" } ], "_topics": [ "brazil", "caged", "labor" ], "_stars": 2, "_contributors": [ { "user": "alexsandroprado", "count": 41, "uuid": 30550802 }, { "user": "gecomt", "count": 11, "uuid": 131674269 } ], "_userbio": { "uuid": 131674269, "type": "user", "name": "GECOMT", "followers": 2, "description": "Repositório do Grupo de Estudos sobre Contabilidade e Mercado de Trabalho" }, "_downloads": { "count": 447, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/datacaged" }, "_devurl": "https://github.com/gecomt/datacaged", "_searchresults": 0, "_rbuild": "4.6.1", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/datacaged.html", "extra/manual.pdf", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "LICENSE" ], "_homeurl": "https://github.com/gecomt/datacaged", "_realowner": "gecomt", "_cranurl": true, "_releases": [ { "version": "0.2.1", "date": "2026-09-09" } ], "_exports": [ "caged_adjustments_load", "caged_connect", "caged_download", "caged_download_layouts", "caged_hf_files", "caged_info", "caged_load", "caged_parse", "caged_parse_batch", "caged_status", "caged_to_duckdb", "caged_to_parquet", "caged_update" ], "_datasets": [ { "name": "uf_codigos", "title": "Tabela de UFs brasileiras com códigos IBGE e regiões", "object": "uf_codigos", "class": [ "data.frame" ], "fields": [ "sigla", "codigo", "regiao" ], "rows": 27, "table": true, "tojson": true } ], "_help": [ { "page": "datacaged-package", "title": "datacaged: Microdados do CAGED em DuckDB", "topics": [ "datacaged-package", "datacaged" ] }, { "page": "caged_adjustments_load", "title": "Pipeline completo para o CAGED Ajustes", "topics": [ "caged_adjustments_load" ] }, { "page": "caged_connect", "title": "Abre uma conexão com o banco DuckDB do CAGED", "topics": [ "caged_connect" ] }, { "page": "caged_download", "title": "Baixa microdados do CAGED do repositório HuggingFace", "topics": [ "caged_download" ] }, { "page": "caged_download_layouts", "title": "Baixa layouts (dicionários) do CAGED e Novo CAGED", "topics": [ "caged_download_layouts" ] }, { "page": "caged_hf_files", "title": "Lista as competências disponíveis no repositório HuggingFace", "topics": [ "caged_hf_files" ] }, { "page": "caged_info", "title": "Lista tabelas e estatísticas do banco DuckDB do CAGED", "topics": [ "caged_info" ] }, { "page": "caged_load", "title": "Pipeline completo: download -> parse -> DuckDB", "topics": [ "caged_load" ] }, { "page": "caged_parse", "title": "Lê microdados de um arquivo .7z do CAGED", "topics": [ "caged_parse" ] }, { "page": "caged_parse_batch", "title": "Lê e normaliza múltiplos arquivos .7z do CAGED", "topics": [ "caged_parse_batch" ] }, { "page": "caged_status", "title": "Verifica se o repositório HuggingFace do CAGED está acessível", "topics": [ "caged_status" ] }, { "page": "caged_to_duckdb", "title": "Grava um data.frame de microdados do CAGED em uma tabela DuckDB", "topics": [ "caged_to_duckdb" ] }, { "page": "caged_to_parquet", "title": "Exporta tabelas do banco DuckDB para arquivos Parquet", "topics": [ "caged_to_parquet" ] }, { "page": "caged_update", "title": "Atualiza o banco com as competências mais recentes disponíveis", "topics": [ "caged_update" ] }, { "page": "uf_codigos", "title": "Tabela de UFs brasileiras com códigos IBGE e regiões", "topics": [ "uf_codigos" ] } ], "_pkglogo": "https://github.com/gecomt/datacaged/raw/HEAD/man/figures/logo.png", "_readme": "https://github.com/gecomt/datacaged/raw/HEAD/README.md", "_rundeps": [ "archive", "askpass", "bit", "bit64", "cli", "clipr", "codetools", "cpp11", "crayon", "curl", "DBI", "digest", "dplyr", "duckdb", "furrr", "future", "generics", "globals", "glue", "hms", "httr2", "lifecycle", "listenv", "magrittr", "openssl", "parallelly", "pillar", "pkgconfig", "prettyunits", "progress", "progressr", "purrr", "R6", "readr", "rlang", "stringi", "stringr", "sys", "tibble", "tidyselect", "tzdb", "utf8", "vctrs", "vroom", "withr" ], "_vignettes": [ { "source": "casos_de_uso.Rmd", "filename": "casos_de_uso.html", "title": "Casos de Uso: Análise do Mercado de Trabalho", "engine": "knitr::rmarkdown", "headings": [ "Caso 1 — Saldo de empregos: admissões vs desligamentos", "Caso 2 — Saldo por setor econômico (CNAE)", "Caso 3 — Mapa de calor: saldo por UF e mês", "Caso 4 — Perfil do trabalhador admitido", "Caso 5 — Distribuição salarial das admissões", "Caso 6 — Evolução do emprego formal: série 2015-2023", "Caso 7 — Rotatividade por setor", "Caso 8 — Emprego formal por porte de estabelecimento", "Caso 9 — Emprego formal nas regiões brasileiras", "Caso 10 — Painel executivo: resumo do mercado de trabalho" ], "created": "2026-08-24 04:54:34", "modified": "2026-08-24 04:54:34", "commits": 1 }, { "source": "pipeline-en.Rmd", "filename": "pipeline-en.html", "title": "Full Pipeline with DuckDB", "engine": "knitr::rmarkdown", "headings": [ "1. Check availability before downloading", "2. Download microdata", "3. Parse files", "4. Write to DuckDB", "5. Full pipeline in a single command", "6. Queries with dplyr", "7. Direct SQL queries", "8. Historical series: joining Novo CAGED and legacy CAGED", "9. Export results", "10. Incremental update", "11. Best practices" ], "created": "2026-08-24 04:54:34", "modified": "2026-10-12 22:08:41", "commits": 3 }, { "source": "introducao.Rmd", "filename": "introducao.html", "title": "Introdução ao datacaged", "engine": "knitr::rmarkdown", "headings": [ "Visão Geral", "Instalação", "Compatibilidade entre plataformas", "Downloads paralelos", "Uso Básico: Pipeline Completo", "Consulta dos Dados", "Funções Granulares", "1. Só baixar os arquivos", "2. Parsear arquivos manualmente", "3. Gravar no banco", "Ver o que está no banco", "Exemplo: Série Histórica com CAGED Antigo", "CAGED Ajustes", "Dicas de Performance", "Utilitários", "Variáveis principais" ], "created": "2026-08-24 04:54:34", "modified": "2026-10-12 22:08:41", "commits": 3 }, { "source": "introduction.Rmd", "filename": "introduction.html", "title": "Introduction to datacaged", "engine": "knitr::rmarkdown", "headings": [ "Overview", "Installation", "Platform compatibility", "Parallel downloads", "Basic usage: Full pipeline", "Querying the data", "Granular functions", "1. Download files only", "2. Parse files manually", "3. Write to database", "Inspect the database", "Example: Historical series with legacy CAGED", "CAGED Adjustments", "Performance tips", "Utilities", "Main variables" ], "created": "2026-08-24 04:54:34", "modified": "2026-10-12 22:08:41", "commits": 3 }, { "source": "pipeline.Rmd", "filename": "pipeline.html", "title": "Pipeline Completo com DuckDB", "engine": "knitr::rmarkdown", "headings": [ "1. Verificar disponibilidade antes de baixar", "2. Download dos microdados", "3. Parse dos arquivos", "4. Gravar no DuckDB", "5. Pipeline completo em um único comando", "6. Consultas com dplyr", "7. Consultas com SQL direto", "8. Série histórica: unindo Novo CAGED e CAGED antigo", "9. Exportar resultados", "10. Atualização incremental", "11. Boas práticas" ], "created": "2026-08-24 04:54:34", "modified": "2026-10-12 22:08:41", "commits": 3 }, { "source": "use-cases.Rmd", "filename": "use-cases.html", "title": "Use Cases: Labour Market Analysis", "engine": "knitr::rmarkdown", "headings": [ "Case 1 — Employment balance: hires vs dismissals", "Case 2 — Balance by economic sector (CNAE)", "Case 3 — Heat map: balance by state and month", "Case 4 — Profile of newly hired workers", "Case 5 — Wage distribution of new hires", "Case 6 — Formal employment trends: 2015-2023 series", "Case 7 — Turnover by sector", "Case 8 — Formal employment by establishment size", "Case 9 — Formal employment by Brazilian region", "Case 10 — Executive dashboard: labour market summary" ], "created": "2026-08-24 04:54:34", "modified": "2026-08-24 04:54:34", "commits": 1 } ], "_score": 5.380211241711606, "_indexed": true, "_nocasepkg": "datacaged", "_universes": [ "gecomt", "alexsandroprado" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.2.3", "date": "2026-10-13T03:47:46.000Z", "distro": "resolute", "commit": "e5e5615c8676c1ff8ba37ed316c096d2f06bd44b", "fileid": "https://r2.ropensci.org/d150e587e5336dcf87d0c81c8f651fab87ff981d193e8397c22c04680b42117c", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/gecomt/actions/runs/38342824534" }, { "r": "4.6.1", "os": "linux", "version": "0.2.3", "date": "2026-10-13T03:47:09.000Z", "distro": "resolute", "commit": "e5e5615c8676c1ff8ba37ed316c096d2f06bd44b", "fileid": "https://r2.ropensci.org/2202f49cd851e7d67b501e0c14cca1a6c58a30f15540bd3ac5285e68efe611c9", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/gecomt/actions/runs/38342824534" }, { "r": "4.5.3", "os": "mac", "version": "0.2.3", "date": "2026-10-13T03:49:23.000Z", "commit": "e5e5615c8676c1ff8ba37ed316c096d2f06bd44b", "fileid": "https://r2.ropensci.org/23a6f1f469a6f0a898626c8946c2b83f98639b73bc699c1f697446eaad036b02", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/gecomt/actions/runs/38342824534" }, { "r": "4.6.1", "os": "mac", "version": "0.2.3", "date": "2026-10-13T03:46:40.000Z", "commit": "e5e5615c8676c1ff8ba37ed316c096d2f06bd44b", "fileid": "https://r2.ropensci.org/bdefdf9c4e155c876d60265a814f123c2bf5ae7f19925c6dd01c21cfa99ccd57", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/gecomt/actions/runs/38342824534" }, { "r": "4.6.0", "os": "wasm", "version": "0.2.3", "date": "2026-10-13T03:47:01.000Z", "commit": "e5e5615c8676c1ff8ba37ed316c096d2f06bd44b", "fileid": "https://r2.ropensci.org/a65a80bba642666dfbe27a0eebd397cee4c6793bde348801050fb4cc2f5d95b9", "status": "success", "buildurl": "https://github.com/r-universe/gecomt/actions/runs/38342824534" }, { "r": "4.7.0", "os": "win", "version": "0.2.3", "date": "2026-10-13T03:46:04.000Z", "commit": "e5e5615c8676c1ff8ba37ed316c096d2f06bd44b", "fileid": "https://r2.ropensci.org/e85ce829ca79c98941bde2c0f38e47f040c026c5365bca15ee1ff7f431cf9640", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/gecomt/actions/runs/38342824534" }, { "r": "4.5.3", "os": "win", "version": "0.2.3", "date": "2026-10-13T03:45:56.000Z", "commit": "e5e5615c8676c1ff8ba37ed316c096d2f06bd44b", "fileid": "https://r2.ropensci.org/cd4194e6f1093ccdf20b72a2c74b059e127f34a8c1217ea936a5a212ada2a485", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/gecomt/actions/runs/38342824534" }, { "r": "4.6.1", "os": "win", "version": "0.2.3", "date": "2026-10-13T03:45:55.000Z", "commit": "e5e5615c8676c1ff8ba37ed316c096d2f06bd44b", "fileid": "https://r2.ropensci.org/fb6937873337fbff024a83e5b75163e544ceca3fd3d6e20aedc6cdae16db7d30", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/gecomt/actions/runs/38342824534" } ] }