{ "_id": "6a102112acfb0bcc41c8be78", "Package": "EcoCleanR", "Title": "Enhancing Data Quality of Biogeographic Ranges with Application\nfor Marine Invertebrates", "Version": "1.0.3", "Language": "en-US", "Authors@R": "c(\nperson(given = \"Priyanka\",\nfamily = \"Soni\",\nemail = \"sonip@usc.edu\",\nrole = c(\"aut\", \"cre\"),\ncomment = c(ORCID = \"0000-0001-8358-1645\")),\nperson(given = \"Austin\",\nfamily = \"Hendy\",\nrole = \"ctb\",\ncomment = \"Manuscript mentoring and advising\"),\nperson(given = \"David\",\nfamily = \"Bottjer\",\nrole = \"ctb\",\ncomment = \"Manuscript mentoring and advising\"),\nperson(given = \"Vijay\",\nfamily = \"Barve\",\nrole = \"ctb\",\ncomment = \"Code development feedback and advising\"))", "Description": "Provides step-by-step automation for integrating\nbiodiversity data from multiple online aggregators, merging and\ncleaning datasets while addressing challenges such as taxonomic\ninconsistencies, georeferencing issues, and spatial or\nenvironmental outliers. Includes functions to extract\nenvironmental data and to define the biogeographic ranges in\nwhich species are most likely to occur. For methodological\ndetails see the associated publication..", "License": "MIT + file LICENSE", "Encoding": "UTF-8", "Roxygen": "list(markdown = TRUE)", "RoxygenNote": "7.3.3", "Config/testthat/edition": "3", "LazyData": "true", "VignetteBuilder": "knitr", "Config/Needs/website": "rmarkdown", "URL": "https://github.com/sonipri/EcoCleanR,\nhttps://sonipri.github.io/EcoCleanR/,\nhttps://doi.org/10.1002/ecog.08203", "BugReports": "https://github.com/sonipri/EcoCleanR/issues", "Config/pak/sysreqs": "libabsl-dev cmake libgdal-dev gdal-bin libgeos-dev\nmake libicu-dev libuv1-dev libxml2-dev libssl-dev libproj-dev\nlibrdf0-dev libsqlite3-dev libudunits2-dev libx11-dev", "Repository": "https://sonipri.r-universe.dev", "Date/Publication": "2026-02-13 03:28:49 UTC", "RemoteUrl": "https://github.com/sonipri/ecocleanr", "RemoteRef": "HEAD", "RemoteSha": "2f74bbfaa4b445ce753ae8e8a6dae6567f190a12", "NeedsCompilation": "no", "Packaged": { "Date": "2026-05-14 05:54:38 UTC", "User": "root" }, "Author": "Priyanka Soni [aut, cre] (ORCID:\n),\nAustin Hendy [ctb] (Manuscript mentoring and advising),\nDavid Bottjer [ctb] (Manuscript mentoring and advising),\nVijay Barve [ctb] (Code development feedback and advising)", "Maintainer": "Priyanka Soni ", "MD5sum": "162ab556069972cd129be1e1b831e42e", "_user": "sonipri", "_type": "src", "_file": "EcoCleanR_1.0.3.tar.gz", "_fileid": "25f9a035cead14c2de6bc6f29656ddbcc980ae3bed181d0b6b074ccf2b37f285", "_filesize": 520133, "_sha256": "25f9a035cead14c2de6bc6f29656ddbcc980ae3bed181d0b6b074ccf2b37f285", "_created": "2026-05-14T05:54:38.000Z", "_published": "2026-05-22T09:25:38.672Z", "_distro": "noble", "_jobs": [ { "job": 77352184945, "time": 289, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "6988183444" }, { "job": 77352185165, "time": 306, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "6988186163" }, { "job": 77352185163, "time": 238, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "6988167234" }, { "job": 77352184936, "time": 257, "config": "macos-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "6988170717" }, { "job": 77352184637, "time": 249, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "6988123192" }, { "job": 77352184371, "time": 171, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7157215409" }, { "job": 77352185173, "time": 387, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "6988201664" }, { "job": 77352185462, "time": 228, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "6988170457" }, { "job": 77352185354, "time": 221, "config": "windows-release", "r": "4.6.0", "check": "OK", "artifact": "6988169063" } ], "_buildurl": "https://github.com/r-universe/sonipri/actions/runs/25844278366", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/sonipri/ecocleanr", "_commit": { "id": "2f74bbfaa4b445ce753ae8e8a6dae6567f190a12", "author": "Priyanka Soni ", "committer": "Priyanka Soni ", "message": "update\n", "time": 1770953329 }, "_maintainer": { "name": "Priyanka Soni", "email": "sonip@usc.edu", "login": "sonipri", "uuid": 89354734, "orcid": "0000-0001-8358-1645" }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 3.5", "role": "Depends" }, { "package": "dplyr", "role": "Imports" }, { "package": "geodata", "role": "Imports" }, { "package": "geosphere", "role": "Imports" }, { "package": "ggplot2", "role": "Imports" }, { "package": "mregions2", "role": "Imports" }, { "package": "patchwork", "role": "Imports" }, { "package": "rlang", "role": "Imports" }, { "package": "sdmpredictors", "role": "Imports" }, { "package": "sf", "role": "Imports" }, { "package": "worrms", "role": "Imports" }, { "package": "terra", "role": "Imports" }, { "package": "tidyr", "role": "Imports" }, { "package": "knitr", "role": "Suggests" }, { "package": "rgbif", "role": "Suggests" }, { "package": "robis", "role": "Suggests" }, { "package": "ridigbio", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" } ], "_owner": "sonipri", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2025-20", "n": 2 }, { "week": "2025-21", "n": 3 }, { "week": "2025-33", "n": 1 }, { "week": "2025-34", "n": 1 }, { "week": "2025-35", "n": 46 }, { "week": "2025-44", "n": 2 }, { "week": "2025-45", "n": 8 }, { "week": "2025-46", "n": 8 }, { "week": "2026-04", "n": 9 }, { "week": "2026-06", "n": 8 }, { "week": "2026-07", "n": 5 } ], "_tags": [], "_stars": 0, "_contributors": [ { "user": "sonipri", "count": 104, "uuid": 89354734 } ], "_userbio": { "uuid": 89354734, "type": "user", "name": "Priyanka" }, "_downloads": { "count": 201, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/EcoCleanR" }, "_devurl": "https://github.com/sonipri/ecocleanr", "_pkgdown": "https://sonipri.github.io/EcoCleanR/", "_searchresults": 7, "_rbuild": "4.6.0", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/EcoCleanR.html", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "manual.pdf" ], "_homeurl": "https://github.com/sonipri/ecocleanr", "_realowner": "sonipri", "_cranurl": true, "_releases": [ { "version": "1.0.1", "date": "2025-11-19" }, { "version": "1.0.2", "date": "2026-02-16" }, { "version": "1.0.3", "date": "2026-02-16" } ], "_exports": [ "decimal_places", "distance_calc", "ec_db_merge", "ec_extract_env_layers", "ec_filter_by_uncertainty", "ec_flag_non_east_atlantic", "ec_flag_non_east_pacific", "ec_flag_non_region", "ec_flag_non_west_atlantic", "ec_flag_non_west_pacific", "ec_flag_outlier", "ec_flag_precision", "ec_flag_with_locality", "ec_geographic_map", "ec_geographic_map_w_flag", "ec_impute_env_values", "ec_merge_corrected_coordinates", "ec_plot_distance", "ec_plot_var_range", "ec_rm_duplicate", "ec_rm_duplicate_occurid", "ec_trail_zero", "ec_var_summary", "ec_worms_synonym", "haversine_kmeans" ], "_datasets": [ { "name": "ecodata", "title": "dataset1: Documentation of data file - ecodata.rda", "object": "ecodata", "class": [ "data.frame" ], "fields": [ "X", "basisOfRecord", "occurrenceStatus", "institutionCode", "verbatimEventDate", "scientificName", "individualCount", "organismQuantity", "abundance", "decimalLatitude", "decimalLongitude", "coordinateUncertaintyInMeters", "locality", "verbatimLocality", "municipality", "county", "stateProvince", "country", "cleaned_catalog" ], "rows": 1115, "table": true, "tojson": true }, { "name": "ecodata_cleaned", "title": "dataset4: Documentation of data file - ecodata_cleaned.rda", "object": "ecodata_cleaned", "class": [ "data.frame" ], "fields": [ "X", "basisOfRecord", "occurrenceStatus", "institutionCode", "verbatimEventDate", "scientificName", "individualCount", "organismQuantity", "abundance", "decimalLatitude", "decimalLongitude", "coordinateUncertaintyInMeters", "locality", "verbatimLocality", "municipality", "county", "stateProvince", "country", "cleaned_catalog", "lat_precision", "lon_precision", "flag_cordinate_precision", "flag_cc_val", "flag_cc_equal", "flag_cc_zero", "flag_cc_cent", "flag_cc_gbif", "flag_cc_inst", "flag_non_region", "outliers", "BO_sstmean", "BO_sstmax", "BO_sstmin", "BO_chloro", "BO_dissox" ], "rows": 698, "table": true, "tojson": true }, { "name": "ecodata_corrected", "title": "dataset2: Documentation of data file - ecodata_corrected.rda", "object": "ecodata_corrected", "class": [ "data.frame" ], "fields": [ "cleaned_catalog", "corrected_latitude", "corrected_longitude", "corrected_uncertainty" ], "rows": 433, "table": true, "tojson": true }, { "name": "ecodata_with_outliers", "title": "dataset3: Documentation of data file - ecodata_with_outliers.rda", "object": "ecodata_with_outliers", "class": [ "data.frame" ], "fields": [ "X", "basisOfRecord", "occurrenceStatus", "institutionCode", "verbatimEventDate", "scientificName", "individualCount", "organismQuantity", "abundance", "decimalLatitude", "decimalLongitude", "coordinateUncertaintyInMeters", "locality", "verbatimLocality", "municipality", "county", "stateProvince", "country", "cleaned_catalog", "lat_precision", "lon_precision", "flag_cordinate_precision", "flag_cc_val", "flag_cc_equal", "flag_cc_zero", "flag_cc_cent", "flag_cc_gbif", "flag_cc_inst", "flag_non_region", "outliers", "BO_sstmean", "BO_sstmax", "BO_sstmin", "BO_chloro", "BO_dissox" ], "rows": 713, "table": true, "tojson": true }, { "name": "ecodata_x", "title": "dataset5: Documentation of data file - ecodata_x.rda", "object": "ecodata_x", "class": [ "data.frame" ], "fields": [ "species", "decimalLatitude", "decimalLongitude", "temperature_mean_BO", "temperature_max_BO", "temperature_min_BO" ], "rows": 705, "table": true, "tojson": true }, { "name": "example_sp_invertebase", "title": "dataset6: Documentation of data file - example_sp_invertebase.rda", "object": "example_sp_invertebase", "class": [ "data.frame" ], "fields": [ "source", "catalogNumber", "basisOfRecord", "occurrenceStatus", "institutionCode", "verbatimEventDate", "scientificName", "individualCount", "organismQuantity", "abundance", "decimalLatitude", "decimalLongitude", "coordinateUncertaintyInMeters", "locality", "verbatimLocality", "municipality", "country", "stateProvince", "county", "countryCode" ], "rows": 710, "table": true, "tojson": true } ], "_help": [ { "page": "decimal_places", "title": "Get Decimal Places of Coordinate Values", "topics": [ "decimal_places" ] }, { "page": "distance_calc", "title": "Calculate geographic distance and mahalanobis distance to estimate outlier probability of a data point", "topics": [ "distance_calc" ] }, { "page": "ec_db_merge", "title": "Merge the Data sets Extracted from Various datasources.", "topics": [ "ec_db_merge" ] }, { "page": "ec_extract_env_layers", "title": "Extract the Environmental data", "topics": [ "ec_extract_env_layers" ] }, { "page": "ec_filter_by_uncertainty", "title": "Flag the Occurrences those has Extreme Uncertainty Error Radius", "topics": [ "ec_filter_by_uncertainty" ] }, { "page": "ec_flag_non_east_atlantic", "title": "Flag the occurrences those are not in east Atlantic and are inland", "topics": [ "ec_flag_non_east_atlantic" ] }, { "page": "ec_flag_non_east_pacific", "title": "Flag occurrences those are not in east Pacific and are inland", "topics": [ "ec_flag_non_east_pacific" ] }, { "page": "ec_flag_non_region", "title": "Flag Occurrences those are in wrong ocean basins and are inland", "topics": [ "ec_flag_non_region" ] }, { "page": "ec_flag_non_west_atlantic", "title": "Flag Occurrences those are not in west Atlantic and are inland", "topics": [ "ec_flag_non_west_atlantic" ] }, { "page": "ec_flag_non_west_pacific", "title": "Flag occurrences those are not in east Pacific and are inland", "topics": [ "ec_flag_non_west_pacific" ] }, { "page": "ec_flag_outlier", "title": "Flag Outlier Occurrences - using Spatial and Non-spatial Attributes", "topics": [ "ec_flag_outlier" ] }, { "page": "ec_flag_precision", "title": "Flag occurrences those has bad precision", "topics": [ "ec_flag_precision" ] }, { "page": "ec_flag_with_locality", "title": "Filter records to georeference using GEOLocate", "topics": [ "ec_flag_with_locality" ] }, { "page": "ec_geographic_map", "title": "Map view of occurrence data points", "topics": [ "ec_geographic_map" ] }, { "page": "ec_geographic_map_w_flag", "title": "Map view to visualize data points with outlier probability 0 to 1 on a map view", "topics": [ "ec_geographic_map_w_flag" ] }, { "page": "ec_impute_env_values", "title": "Impute Environmental Variables using Mean Values of occurrences within a certain radius", "topics": [ "ec_impute_env_values" ] }, { "page": "ec_merge_corrected_coordinates", "title": "Merge the Update Georeferenced Occurrence Points back to the Main Data File.", "topics": [ "ec_merge_corrected_coordinates" ] }, { "page": "ec_plot_distance", "title": "Scatter Plot between geo_distance vs maha_distance with geo- and maha- Quantile Threshold to Demonstrate the Outliers outside those threshold.", "topics": [ "ec_plot_distance" ] }, { "page": "ec_plot_var_range", "title": "Plot cleaned data overlay overall occurrence data to demonstrate accepted ranges of spatial and non-spatial attributes", "topics": [ "ec_plot_var_range" ] }, { "page": "ec_rm_duplicate", "title": "Remove Duplicate Records from the Merged Data", "topics": [ "ec_rm_duplicate" ] }, { "page": "ec_rm_duplicate_occurid", "title": "Remove Duplicate Records from the Merged Data based on occurrenceID", "topics": [ "ec_rm_duplicate_occurid" ] }, { "page": "ec_trail_zero", "title": "Trail Zeros from the Coordinate Values", "topics": [ "ec_trail_zero" ] }, { "page": "ec_var_summary", "title": "A Summary Table of Final Cleaned Spatial and Environmental Variables", "topics": [ "ec_var_summary" ] }, { "page": "ec_worms_synonym", "title": "Check Accepted Synonyms from WoRMs Taxonomy", "topics": [ "ec_worms_synonym" ] }, { "page": "ecodata", "title": "dataset1: Documentation of data file - ecodata.rda", "topics": [ "ecodata" ] }, { "page": "ecodata_cleaned", "title": "dataset4: Documentation of data file - ecodata_cleaned.rda", "topics": [ "ecodata_cleaned" ] }, { "page": "ecodata_corrected", "title": "dataset2: Documentation of data file - ecodata_corrected.rda", "topics": [ "ecodata_corrected" ] }, { "page": "ecodata_with_outliers", "title": "dataset3: Documentation of data file - ecodata_with_outliers.rda", "topics": [ "ecodata_with_outliers" ] }, { "page": "ecodata_x", "title": "dataset5: Documentation of data file - ecodata_x.rda", "topics": [ "ecodata_x" ] }, { "page": "example_sp_invertebase", "title": "dataset6: Documentation of data file - example_sp_invertebase.rda", "topics": [ "example_sp_invertebase" ] }, { "page": "haversine_kmeans", "title": "Calculate Harversine distance", "topics": [ "haversine_kmeans" ] } ], "_pkglogo": "https://github.com/sonipri/ecocleanr/raw/HEAD/man/figures/logo.png", "_readme": "https://github.com/sonipri/ecocleanr/raw/HEAD/README.md", "_rundeps": [ "askpass", "backports", "bit", "bit64", "brew", "cachem", "callr", "checkmate", "class", "classInt", "cli", "clipr", "commonmark", "cpp11", "crayon", "crul", "curl", "data.table", "DBI", "desc", "digest", "dplyr", "e1071", "evaluate", "farver", "fastmap", "fs", "generics", "geodata", "geosphere", "ggplot2", "glue", "gtable", "highr", "hms", "httpcode", "httr2", "isoband", "ISOcodes", "jsonlite", "KernSmooth", "knitr", "labeling", "lattice", "lifecycle", "magrittr", "MASS", "memoise", "mime", "mregions2", "openssl", "patchwork", "pillar", "pkgbuild", "pkgconfig", "pkgload", "prettyunits", "processx", "progress", "proxy", "ps", "purrr", "R.methodsS3", "R.oo", "R.utils", "R6", "rappdirs", "raster", "RColorBrewer", "Rcpp", "rdflib", "readr", "redland", "rlang", "roxygen2", "rprojroot", "s2", "S7", "scales", "sdmpredictors", "sf", "sp", "stringi", "stringr", "sys", "terra", "tibble", "tidyr", "tidyselect", "triebeard", "tzdb", "units", "urltools", "utf8", "vctrs", "viridisLite", "vroom", "withr", "wk", "worrms", "wrapr", "xfun", "xml2", "yaml" ], "_vignettes": [ { "source": "data_cleaning.Rmd", "filename": "data_cleaning.html", "title": "EcoCleanR: Overview on Steps for Data cleaning and defining Biogeographic ranges", "engine": "knitr::rmarkdown", "headings": [ "Introduction:", "Step1: Remove duplicates", "Step2: Remove bad taxa", "Step3: Georeferencing using external tool", "Step4: Extreme high uncertainty", "Step5: Coordinate precision and rounding", "Step6: Records tagged to wrong ocean/sea", "Step7: Extract the environmental data", "Step8: Identify outliers", "Step9: Display final accepted biogeographic range" ], "created": "2025-04-12 02:47:39", "modified": "2026-02-13 03:05:16", "commits": 12 }, { "source": "data_merging.Rmd", "filename": "data_merging.html", "title": "EcoCleanR: Overview on Steps for Data merging from online bioiversity resources", "engine": "knitr::rmarkdown", "headings": [ "Introduction", "Load packages", "Input species name", "Create a attribute list with TDWG standardize names", "GBIF - data extraction and standardization", "OBIS- data extraction and standardization", "IDIGBIO - data extraction and standardization", "Local file (InvertEbase) - data read and standardization", "Merging the databases" ], "created": "2025-04-12 02:47:39", "modified": "2026-02-13 03:05:16", "commits": 12 } ], "_score": 5.041392685158225, "_indexed": true, "_nocasepkg": "ecocleanr", "_universes": [ "sonipri" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "1.0.3", "date": "2026-05-14T05:58:00.000Z", "distro": "noble", "commit": "2f74bbfaa4b445ce753ae8e8a6dae6567f190a12", "fileid": "5d9fe19237bee082a44090110613c25815806f625a821280214dcd66f5376106", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/sonipri/actions/runs/25844278366" }, { "r": "4.6.0", "os": "linux", "version": "1.0.3", "date": "2026-05-14T05:58:16.000Z", "distro": "noble", "commit": "2f74bbfaa4b445ce753ae8e8a6dae6567f190a12", "fileid": "c00c47d6d6b81dd4c80c1377896f8bd4c559b76eabca97d3ea7e5715729b0b20", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/sonipri/actions/runs/25844278366" }, { "r": "4.5.3", "os": "mac", "version": "1.0.3", "date": "2026-05-14T05:57:10.000Z", "commit": "2f74bbfaa4b445ce753ae8e8a6dae6567f190a12", "fileid": "a6d7fd216093cffe4a8348ead77f828c2ad3d20ea8b337aed427215e3c240915", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/sonipri/actions/runs/25844278366" }, { "r": "4.6.0", "os": "mac", "version": "1.0.3", "date": "2026-05-14T05:57:32.000Z", "commit": "2f74bbfaa4b445ce753ae8e8a6dae6567f190a12", "fileid": "b1218900d842322ce499c3581b4596293d2b6d8edc09ce68b079691fe3cd1f54", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/sonipri/actions/runs/25844278366" }, { "r": "4.7.0", "os": "win", "version": "1.0.3", "date": "2026-05-14T05:59:05.000Z", "commit": "2f74bbfaa4b445ce753ae8e8a6dae6567f190a12", "fileid": "bd9486d778cdc44143c1d77c7aaf69e3698707342f66ac92c1330fd74f593b94", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/sonipri/actions/runs/25844278366" }, { "r": "4.5.3", "os": "win", "version": "1.0.3", "date": "2026-05-14T05:56:28.000Z", "commit": "2f74bbfaa4b445ce753ae8e8a6dae6567f190a12", "fileid": "5a38ef8672bafb89887c7d76d489747e5f1114b288d41e316b6e944ef2dec38d", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/sonipri/actions/runs/25844278366" }, { "r": "4.6.0", "os": "win", "version": "1.0.3", "date": "2026-05-14T05:56:21.000Z", "commit": "2f74bbfaa4b445ce753ae8e8a6dae6567f190a12", "fileid": "71c71e9bc730ceec5afa703753eafbe20d197bf8e30ee33d111011b183a2fd39", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/sonipri/actions/runs/25844278366" }, { "r": "4.6.0", "os": "wasm", "version": "1.0.3", "date": "2026-05-22T09:25:19.000Z", "commit": "2f74bbfaa4b445ce753ae8e8a6dae6567f190a12", "fileid": "01fa2619ecb9398c7ad76aaa56af6d2109031c70d948579840b44061ba081198", "status": "success", "buildurl": "https://github.com/r-universe/sonipri/actions/runs/25844278366" } ] }