{ "_id": "6ad09cbc576abc75bd5cd9a8", "Type": "Package", "Package": "pcpr", "Title": "Principal Component Pursuit for Environmental Epidemiology", "Version": "1.0.0.9000", "Authors@R": "c(\nperson(\"Lawrence G.\", \"Chillrud\", , \"lawrencechillrud@gmail.com\", role = c(\"aut\", \"cre\", \"cph\"),\ncomment = c(ORCID = \"0000-0003-0727-0161\")),\nperson(\"Jaime\", \"Benavides\", role = \"aut\",\ncomment = c(ORCID = \"0000-0002-1851-5155\")),\nperson(\"Elizabeth A.\", \"Gibson\", role = \"aut\",\ncomment = c(ORCID = \"0000-0001-5119-5133\")),\nperson(\"Junhui\", \"Zhang\", role = \"aut\",\ncomment = c(ORCID = \"0009-0008-5922-1058\")),\nperson(\"Jingkai\", \"Yan\", role = \"aut\",\ncomment = c(ORCID = \"0000-0002-2094-2092\")),\nperson(\"John N.\", \"Wright\", role = \"aut\"),\nperson(\"Jeff\", \"Goldsmith\", role = \"aut\"),\nperson(\"Marianthi-Anna\", \"Kioumourtzoglou\", role = \"aut\",\ncomment = c(ORCID = \"0000-0001-5710-4992\")),\nperson(\"Columbia University\", role = \"fnd\",\ncomment = c(ROR = \"00hj8s172\"))\n)", "Description": "Implementation of the pattern recognition technique\nPrincipal Component Pursuit tailored to environmental health\ndata, as described in Gibson et al (2022)\n.", "License": "GPL (>= 3)", "URL": "https://columbia-prime.github.io/pcpr/,\nhttps://github.com/Columbia-PRIME/pcpr", "BugReports": "https://github.com/Columbia-PRIME/pcpr/issues", "VignetteBuilder": "knitr", "Encoding": "UTF-8", "LazyData": "true", "Roxygen": "list(markdown = TRUE)", "RoxygenNote": "7.3.2", "Repository": "https://columbia-prime.r-universe.dev", "Date/Publication": "2025-04-02 19:17:47 UTC", "RemoteUrl": "https://github.com/columbia-prime/pcpr", "RemoteRef": "HEAD", "RemoteSha": "d4543329c8b4bacb9baffb43c40d3a54de6246a2", "NeedsCompilation": "no", "Packaged": { "Date": "2026-10-15 09:13:18 UTC", "User": "root" }, "Author": "Lawrence G. Chillrud [aut, cre, cph] (ORCID:\n),\nJaime Benavides [aut] (ORCID: ),\nElizabeth A. Gibson [aut] (ORCID:\n),\nJunhui Zhang [aut] (ORCID: ),\nJingkai Yan [aut] (ORCID: ),\nJohn N. Wright [aut],\nJeff Goldsmith [aut],\nMarianthi-Anna Kioumourtzoglou [aut] (ORCID:\n),\nColumbia University [fnd] (ROR: )", "Maintainer": "Lawrence G. Chillrud ", "_user": "columbia-prime", "_type": "src", "_file": "pcpr_1.0.0.9000.tar.gz", "_fileid": "https://r2.ropensci.org/f26bb0e184dfedc6c222f5b4bcb146bece00c2b0a2cdd0c938fed5386a0c1b6e", "_filesize": 2929307, "_sha256": "f26bb0e184dfedc6c222f5b4bcb146bece00c2b0a2cdd0c938fed5386a0c1b6e", "_expires": "2027-01-23T09:28:26.000Z", "_created": "2026-10-15T09:13:18.000Z", "_published": "2026-10-15T09:28:28.173Z", "_buildurl": "https://github.com/r-universe/columbia-prime/actions/runs/38710879183", "_status": "success", "_host": "GitHub-Actions", "_jobs": [ { "job": 116343307614, "time": 124, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "11961490401" }, { "job": 116343307726, "time": 122, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "11961620057" }, { "job": 116343307794, "time": 171, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "11961437797" }, { "job": 116343307769, "time": 183, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "11960534151" }, { "job": 116341770777, "time": 220, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "11960651493" }, { "job": 116343307602, "time": 100, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "11961195953" }, { "job": 116343307740, "time": 71, "config": "windows-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "11960736721" }, { "job": 116343307645, "time": 78, "config": "windows-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "11961320643" }, { "job": 116343307649, "time": 95, "config": "windows-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "11960318288" } ], "_upstream": "https://github.com/columbia-prime/pcpr", "_commit": { "id": "d4543329c8b4bacb9baffb43c40d3a54de6246a2", "author": "lawrence-chillrud ", "committer": "lawrence-chillrud ", "message": "Addressing issues #17, #18, #23. Issue #16 was fixed in previous commit but forgot to highlight. Also updating badges.\n", "time": 1743621467 }, "_maintainer": { "name": "Lawrence G. Chillrud", "email": "lawrencechillrud@gmail.com", "login": "lawrence-chillrud", "description": "PhD Candidate in Electrical Engineering at Northwestern University. Interested in ML/AI for use in precision medicine & public health.", "uuid": 61637679, "orcid": "0000-0003-0727-0161" }, "_distro": "resolute", "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 3.5.0", "role": "Depends" }, { "package": "checkmate", "role": "Imports" }, { "package": "dplyr", "role": "Imports" }, { "package": "foreach", "role": "Imports" }, { "package": "furrr", "role": "Imports" }, { "package": "future", "role": "Imports" }, { "package": "magrittr", "role": "Imports" }, { "package": "progressr", "role": "Imports" }, { "package": "purrr", "role": "Imports" }, { "package": "rlang", "role": "Imports" }, { "package": "tidyselect", "role": "Imports" }, { "package": "GGally", "role": "Suggests" }, { "package": "ggplot2", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "lubridate", "role": "Suggests" }, { "package": "metR", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "tidyr", "role": "Suggests" } ], "_owner": "columbia-prime", "_selfowned": true, "_usedby": 0, "_updates": [], "_tags": [], "_topics": [ "dimensionality-reduction", "environmental-health", "environmental-mixtures", "epidemiology", "machine-learning", "pattern-recognition", "public-health", "statistical-modeling" ], "_stars": 7, "_contributors": [ { "user": "lizzyagibson", "count": 84, "uuid": 32719036 }, { "user": "lawrence-chillrud", "count": 62, "uuid": 61637679 } ], "_userbio": { "uuid": 69913359, "type": "organization", "name": "Columbia PRIME", "followers": 0, "description": "Adapting PCP to environmental health data" }, "_downloads": { "count": 340, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/pcpr" }, "_devurl": "https://github.com/columbia-prime/pcpr", "_pkgdown": "https://columbia-prime.github.io/pcpr/", "_searchresults": 18, "_rbuild": "4.6.1", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/manual.pdf", "extra/NEWS.html", "extra/NEWS.txt", "extra/pcpr.html", "extra/readme.html", "extra/readme.md" ], "_homeurl": "https://github.com/columbia-prime/pcpr", "_realowner": "columbia-prime", "_cranurl": true, "_releases": [ { "version": "1.0.0", "date": "2025-03-27" } ], "_exports": [ "get_pcp_defaults", "grid_search_cv", "hard_threshold", "impute_matrix", "matrix_rank", "proj_rank_r", "root_pcp", "rrmc", "sim_data", "sim_lod", "sim_na", "sing", "sparsity" ], "_datasets": [ { "name": "queens", "title": "Daily chemical concentrations of 26 PM2.5 species from Queens, NYC (2001-2021)", "object": "queens", "class": [ "tbl_df", "tbl", "data.frame" ], "fields": [ "Date", "Al", "NH4", "As", "Ba", "Br", "Cd", "Ca", "Cl", "Cr", "Cu", "EC", "Fe", "Pb", "Mg", "Mn", "Ni", "OC", "K", "Se", "Si", "Na", "S", "Ti", "NO3", "V", "Zn" ], "rows": 2443, "table": true, "tojson": true } ], "_help": [ { "page": "get_pcp_defaults", "title": "Retrieve default PCP parameter settings for given matrix", "topics": [ "get_pcp_defaults" ] }, { "page": "grid_search_cv", "title": "Cross-validated grid search for PCP models", "topics": [ "grid_search_cv" ] }, { "page": "hard_threshold", "title": "Hard-thresholding operator", "topics": [ "hard_threshold" ] }, { "page": "impute_matrix", "title": "Impute missing values in given matrix", "topics": [ "impute_matrix" ] }, { "page": "matrix_rank", "title": "Estimate rank of a given matrix", "topics": [ "matrix_rank" ] }, { "page": "proj_rank_r", "title": "Project matrix to rank r", "topics": [ "proj_rank_r" ] }, { "page": "queens", "title": "Daily chemical concentrations of 26 PM2.5 species from Queens, NYC (2001-2021)", "topics": [ "queens" ] }, { "page": "root_pcp", "title": "Square root principal component pursuit (convex PCP)", "topics": [ "root_pcp" ] }, { "page": "rrmc", "title": "Rank-based robust matrix completion (non-convex PCP)", "topics": [ "rrmc" ] }, { "page": "sim_data", "title": "Simulate simple mixtures data", "topics": [ "sim_data" ] }, { "page": "sim_lod", "title": "Simulate limit of detection data", "topics": [ "sim_lod" ] }, { "page": "sim_na", "title": "Simulate random missingness in a given matrix", "topics": [ "sim_na" ] }, { "page": "sing", "title": "Compute singular values of given matrix", "topics": [ "sing" ] }, { "page": "sparsity", "title": "Estimate sparsity of given matrix", "topics": [ "sparsity" ] } ], "_pkglogo": "https://github.com/columbia-prime/pcpr/raw/HEAD/man/figures/logo.png", "_readme": "https://github.com/columbia-prime/pcpr/raw/HEAD/README.md", "_rundeps": [ "backports", "checkmate", "cli", "codetools", "digest", "dplyr", "foreach", "furrr", "future", "generics", "globals", "glue", "iterators", "lifecycle", "listenv", "magrittr", "parallelly", "pillar", "pkgconfig", "progressr", "purrr", "R6", "rlang", "tibble", "tidyselect", "utf8", "vctrs", "withr" ], "_vignettes": [ { "source": "pcp-applied.Rmd", "filename": "pcp-applied.html", "title": "Air pollution source apportionment with PCP", "engine": "knitr::rmarkdown", "headings": [ "Preprocessing", "Exploring the raw data", "Data standardization", "Principal component pursuit", "Model selection", "Grid search for parameter tuning", "Running PCP", "The recovered L matrix", "The recovered S matrix", "PCP and NMF for source apportionment", "PCP-NMF Loadings", "Variance Explained", "Loadings replotted", "PCP-NMF Scores", "Conclusion", "References" ], "created": "2025-03-20 06:02:26", "modified": "2025-04-02 19:17:47", "commits": 8 }, { "source": "pcp-quickstart.Rmd", "filename": "pcp-quickstart.html", "title": "Quickstart: applying PCP to a simulated environmental mixture", "engine": "knitr::rmarkdown", "headings": [ "Simulating data", "Model selection", "Grid search for parameter tuning", "Running PCP", "Benchmarking with PCA", "Evaluating PCP against the ground truth", "After PCP" ], "created": "2025-03-20 06:02:26", "modified": "2025-04-02 19:17:47", "commits": 8 }, { "source": "theory-crash-course.Rmd", "filename": "theory-crash-course.html", "title": "Theory crash course", "engine": "knitr::rmarkdown", "headings": [ "PCP modeling overview", "The low-rank matrix", "The sparse matrix", "Extensions for environmental health data", "Missing value functionality", "Leveraging potential limit of detection (LOD) information", "Non-negativity constraint on the estimated L matrix", "Convex vs. non-convex PCP", "Convex PCP", "Non-convex PCP", "PCP parameters", "Intuition behind lambda, mu, and eta", "Theoretically optimal parameters", "Empirically optimal parameters", "Tuning parameters with grid_search_cv()", "Cross-validation procedure", "Best practices for $\\xi$ and $K$", "Interpretation of results", "Coded example analyses", "References" ], "created": "2025-03-23 00:20:16", "modified": "2025-03-25 18:37:39", "commits": 5 } ], "_score": 5.276461804173244, "_indexed": true, "_nocasepkg": "pcpr", "_universes": [ "columbia-prime", "lawrence-chillrud" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "1.0.0.9000", "date": "2026-10-15T09:15:23.000Z", "distro": "resolute", "commit": "d4543329c8b4bacb9baffb43c40d3a54de6246a2", "fileid": "https://r2.ropensci.org/4c3a8cb25a0094f2b41befc158f3878d7a28c2becebdf9280a465fa7fb5dc66b", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/columbia-prime/actions/runs/38710879183" }, { "r": "4.6.1", "os": "linux", "version": "1.0.0.9000", "date": "2026-10-15T09:15:22.000Z", "distro": "resolute", "commit": "d4543329c8b4bacb9baffb43c40d3a54de6246a2", "fileid": "https://r2.ropensci.org/8f45803b7fe94813024b54f205e1a1ce0242f7f451ea73192e9fef61627827db", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/columbia-prime/actions/runs/38710879183" }, { "r": "4.5.3", "os": "mac", "version": "1.0.0.9000", "date": "2026-10-15T09:27:10.000Z", "commit": "d4543329c8b4bacb9baffb43c40d3a54de6246a2", "fileid": "https://r2.ropensci.org/6ed51f0504e2a490efc07edc71e58ee95029a780893b3ea7208d45c459915a34", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/columbia-prime/actions/runs/38710879183" }, { "r": "4.6.1", "os": "mac", "version": "1.0.0.9000", "date": "2026-10-15T09:27:00.000Z", "commit": "d4543329c8b4bacb9baffb43c40d3a54de6246a2", "fileid": "https://r2.ropensci.org/b43d29e2dba1929f99ff922adf9b62735abb90d25bbf7b38f1ae53b60691046a", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/columbia-prime/actions/runs/38710879183" }, { "r": "4.6.0", "os": "wasm", "version": "1.0.0.9000", "date": "2026-10-15T09:15:16.000Z", "commit": "d4543329c8b4bacb9baffb43c40d3a54de6246a2", "fileid": "https://r2.ropensci.org/a1c0dc1eb04713ee648e07ac05d0b205fb029f6decec124d6d3975beedeeb18d", "status": "success", "buildurl": "https://github.com/r-universe/columbia-prime/actions/runs/38710879183" }, { "r": "4.7.0", "os": "win", "version": "1.0.0.9000", "date": "2026-10-15T09:14:30.000Z", "commit": "d4543329c8b4bacb9baffb43c40d3a54de6246a2", "fileid": "https://r2.ropensci.org/fec4f334efe95a435b3ab56aaed4e8f6803f61502576d886557c6439e04a19f8", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/columbia-prime/actions/runs/38710879183" }, { "r": "4.5.3", "os": "win", "version": "1.0.0.9000", "date": "2026-10-15T09:14:34.000Z", "commit": "d4543329c8b4bacb9baffb43c40d3a54de6246a2", "fileid": "https://r2.ropensci.org/2d0773a6563f34562449335dbe2a489c881028b16bec592f809201e95a97b96d", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/columbia-prime/actions/runs/38710879183" }, { "r": "4.6.1", "os": "win", "version": "1.0.0.9000", "date": "2026-10-15T09:14:52.000Z", "commit": "d4543329c8b4bacb9baffb43c40d3a54de6246a2", "fileid": "https://r2.ropensci.org/c8807d4d8b514f402f12cb9f6b809a439b3ab02bbe5e70b36b24a2d7fda4c1d3", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/columbia-prime/actions/runs/38710879183" } ] }