{ "_id": "6a4a17a00b5cb829d370755e", "Package": "emend", "Title": "Cleaning Text Data with an AI Assistant", "Version": "0.1.0", "Authors@R": "c(person(given = \"Emi\", family = \"Tanaka\", email = \"dr.emi.tanaka@gmail.com\", role = c(\"aut\", \"cph\"), comment = c(ORCID = \"0000-0002-1455-259X\")),\nperson(given = \"Jiajia\", family = \"Li\", email = \"lijia970324@gmail.com\", role = c(\"aut\", \"cre\"), comment = c(ORCID = \"0009-0003-7143-9336\")))", "Description": "Provides functions to clean and standardize messy data,\nincluding textual categories and free-text addresses, using\nLarge Language Models. The package corrects typos, expands\nabbreviations, and maps inconsistent entries to standardized\nvalues. Ideal for Bioinformatics, business, and general data\ncleaning tasks.", "License": "MIT + file LICENSE", "Encoding": "UTF-8", "Roxygen": "list(markdown = TRUE)", "RoxygenNote": "7.3.2", "LazyData": "true", "Config/testthat/edition": "3", "URL": "https://github.com/anuopensci/emend,\nhttps://anuopensci.github.io/emend/", "BugReports": "https://github.com/anuopensci/emend/issues", "Config/pak/sysreqs": "libssl-dev", "Repository": "https://emitanaka.r-universe.dev", "Date/Publication": "2025-04-08 22:57:41 UTC", "RemoteUrl": "https://github.com/anuopensci/emend", "RemoteRef": "HEAD", "RemoteSha": "da5e0abac80d3da209088b98547605d539fb6742", "NeedsCompilation": "no", "Packaged": { "Date": "2026-07-05 08:33:48 UTC", "User": "root" }, "Author": "Emi Tanaka [aut, cph] (ORCID: ),\nJiajia Li [aut, cre] (ORCID: )", "Maintainer": "Jiajia Li ", "_user": "emitanaka", "_type": "src", "_file": "emend_0.1.0.tar.gz", "_fileid": "https://r2.ropensci.org/dd26a9686e3f699b9483fba65bdc77e70e4fb6eddd463c6189e6ba77e344de34", "_filesize": 2695302, "_sha256": "dd26a9686e3f699b9483fba65bdc77e70e4fb6eddd463c6189e6ba77e344de34", "_expires": "2026-10-13T08:36:46.000Z", "_created": "2026-07-05T08:33:48.000Z", "_published": "2026-07-05T08:36:48.016Z", "_jobs": [ { "job": 85207267588, "time": 130, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "8090032884" }, { "job": 85207267591, "time": 130, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "8090032982" }, { "job": 85207267579, "time": 104, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "8090029605" }, { "job": 85207267603, "time": 89, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "8090027712" }, { "job": 85207094058, "time": 160, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "8090016445" }, { "job": 85207267586, "time": 141, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "8090034322" }, { "job": 85207267596, "time": 79, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "8090026672" }, { "job": 85207267592, "time": 70, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "8090025238" }, { "job": 85207267598, "time": 80, "config": "windows-release", "r": "4.6.1", "check": "OK", "artifact": "8090026647" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/emitanaka/actions/runs/28734852322", "_status": "success", "_upstream": "https://github.com/anuopensci/emend", "_commit": { "id": "da5e0abac80d3da209088b98547605d539fb6742", "author": "Jiajia Li ", "committer": "Jiajia Li ", "message": "Update README\n", "time": 1744153061 }, "_maintainer": { "name": "Jiajia Li", "email": "lijia970324@gmail.com", "login": "adrbmdns", "description": "Bioinformatics IT Support Officer", "uuid": 112752904 }, "_distro": "resolute", "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 4.1.0", "role": "Depends" }, { "package": "cli", "role": "Imports" }, { "package": "jsonlite", "role": "Imports" }, { "package": "rlang", "role": "Imports" }, { "package": "ellmer", "role": "Imports" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" } ], "_owner": "anuopensci", "_selfowned": false, "_usedby": 0, "_updates": [], "_tags": [], "_stars": 17, "_contributors": [ { "user": "adrbmdns", "count": 48, "uuid": 112752904 }, { "user": "emitanaka", "count": 26, "uuid": 7620319 } ], "_userbio": { "uuid": 7620319, "type": "user", "name": "Emi Tanaka", "followers": 544, "description": "Senior Lecturer in Statistics. My research is on combination of statistics, genetics and computing. My application focus is in plant breeding." }, "_downloads": { "count": 38, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/emend" }, "_devurl": "https://github.com/anuopensci/emend", "_pkgdown": "https://anuopensci.github.io/emend/", "_searchresults": 3, "_rbuild": "4.6.1", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/emend.html", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "LICENSE", "manual.pdf" ], "_cranurl": false, "_releases": [ { "version": "0.1.0", "date": "2025-04-01" } ], "_exports": [ "emend_clean_address", "emend_clean_date", "emend_fct_match", "emend_fct_reorder", "emend_lvl_match", "emend_lvl_unique", "emend_translate", "emend_what_language", "get_default_chat" ], "_datasets": [ { "name": "airbnb_listings", "title": "Airbnb listings and reviews", "object": "airbnb_listings", "class": [ "tbl_df", "tbl", "data.frame" ], "fields": [ "id", "name", "description", "neighborhood_overview", "picture_url", "host_id", "host_name", "host_since", "host_location", "host_about", "host_response_time", "host_response_rate", "host_acceptance_rate", "host_is_superhost", "host_thumbnail_url", "host_picture_url", "host_neighbourhood", "host_listings_count", "host_total_listings_count", "host_verifications", "host_has_profile_pic", "host_identity_verified", "neighbourhood_cleansed", "latitude", "longitude", "property_type", "room_type", "accommodates", "bathrooms", "bathrooms_text", "bedrooms", "beds", "amenities", "price", "minimum_nights", "maximum_nights", "minimum_minimum_nights", "maximum_minimum_nights", "minimum_maximum_nights", "maximum_maximum_nights", "minimum_nights_avg_ntm", "maximum_nights_avg_ntm", "has_availability", "availability_30", "availability_60", "availability_90", "availability_365", "number_of_reviews", "number_of_reviews_ltm", "number_of_reviews_l30d", "first_review", "last_review", "review_scores_rating", "review_scores_accuracy", "review_scores_cleanliness", "review_scores_checkin", "review_scores_communication", "review_scores_location", "review_scores_value", "license", "instant_bookable", "calculated_host_listings_count", "calculated_host_listings_count_entire_homes", "calculated_host_listings_count_private_rooms", "calculated_host_listings_count_shared_rooms", "reviews_per_month" ], "rows": 1623, "table": true, "tojson": true }, { "name": "airbnb_reviews", "title": "Airbnb listings and reviews", "object": "airbnb_reviews", "class": [ "tbl_df", "tbl", "data.frame" ], "fields": [ "listing_id", "id", "date", "reviewer_id", "reviewer_name", "review_text" ], "rows": 5679, "table": true, "tojson": true }, { "name": "alcohol", "title": "Alcohol warehouse and retail sales", "object": "alcohol", "class": [ "spec_tbl_df", "tbl_df", "tbl", "data.frame" ], "fields": [ "year", "month", "supplier", "item_code", "item_description", "item_type", "retail_sales", "retail_transfers", "warehouse_sales" ], "rows": 1000, "table": true, "tojson": true }, { "name": "consumer", "title": "Amazon consumer reviews", "object": "consumer", "class": [ "tbl_df", "tbl", "data.frame" ], "fields": [ "overall", "verified", "review_date", "review_id", "reviewer_name", "review_text", "summary", "vote_helpful", "image" ], "rows": 4549, "table": true, "tojson": true }, { "name": "hotel", "title": "Hotel reviews", "object": "hotel", "class": [ "tbl_df", "tbl", "data.frame" ], "fields": [ "reviewer_name", "reviewer_nationality", "reviewer_rating", "review_date", "review_title", "review_text", "hotel_name", "avg_rating" ], "rows": 13193, "table": true, "tojson": true }, { "name": "likerts", "title": "A collection of different likert scales", "object": "likerts", "class": [ "tbl_df", "tbl", "data.frame" ], "fields": [ "likert1", "likert2", "likert3", "likert4", "likert5", "likert6", "likert7", "likert8", "likert9" ], "rows": 40, "table": true, "tojson": true }, { "name": "messy", "title": "A collection of messy inputs", "object": "messy", "class": [ "list" ], "fields": [], "table": false, "tojson": true }, { "name": "recipes", "title": "Recipes", "object": "recipes", "class": [ "tbl_df", "tbl", "data.frame" ], "fields": [ "name", "ingredients", "url", "image", "cook_time", "prep_time", "servings" ], "rows": 200, "table": true, "tojson": true }, { "name": "registration", "title": "Registration data for workshops", "object": "registration", "class": [ "tbl_df", "tbl", "data.frame" ], "fields": [ "Workshop", "Affiliation", "GroundTruth" ], "rows": 221, "table": true, "tojson": true }, { "name": "restaurant", "title": "Review of Iori restaurant", "object": "restaurant", "class": [ "tbl_df", "tbl", "data.frame" ], "fields": [ "review", "rating" ], "rows": 20, "table": true, "tojson": true }, { "name": "salary", "title": "Ask A Manager Salary Survey 2021", "object": "salary", "class": [ "tbl_df", "tbl", "data.frame" ], "fields": [ "timestamp", "age", "industry", "job_title", "job_title_context", "salary_annual", "salarly_additional", "currency", "currency_other", "salary_context", "country", "state", "city", "experience_overall", "experience_in_field", "education", "gender", "race" ], "rows": 28083, "table": true, "tojson": true } ], "_help": [ { "page": "airbnb_listings", "title": "Airbnb listings and reviews", "topics": [ "airbnb_listings", "airbnb_reviews" ] }, { "page": "alcohol", "title": "Alcohol warehouse and retail sales", "topics": [ "alcohol" ] }, { "page": "consumer", "title": "Amazon consumer reviews", "topics": [ "consumer" ] }, { "page": "emend_clean_address", "title": "Standardise address format", "topics": [ "emend_clean_address" ] }, { "page": "emend_clean_date", "title": "Standardise date format", "topics": [ "emend_clean_date" ] }, { "page": "emend_fct_match", "title": "Match input factor to specified levels.", "topics": [ "emend_fct_match" ] }, { "page": "emend_fct_reorder", "title": "Reorder the levels of the input factor in a meaningful way.", "topics": [ "emend_fct_reorder" ] }, { "page": "emend_lvl_match", "title": "Match the input factor to supplied levels.", "topics": [ "emend_lvl_match" ] }, { "page": "emend_lvl_unique", "title": "Get the unique levels of messy categorical data", "topics": [ "emend_lvl_unique" ] }, { "page": "emend_translate", "title": "Translate text from one language to another.", "topics": [ "emend_translate" ] }, { "page": "emend_what_language", "title": "Identify the language in the text.", "topics": [ "emend_what_language" ] }, { "page": "get_default_chat", "title": "Get or create the default chat object", "topics": [ "get_default_chat" ] }, { "page": "hotel", "title": "Hotel reviews", "topics": [ "hotel" ] }, { "page": "likerts", "title": "A collection of different likert scales", "topics": [ "likerts" ] }, { "page": "messy", "title": "A collection of messy inputs", "topics": [ "messy" ] }, { "page": "recipes", "title": "Recipes", "topics": [ "recipes" ] }, { "page": "registration", "title": "Registration data for workshops", "topics": [ "registration" ] }, { "page": "restaurant", "title": "Review of Iori restaurant", "topics": [ "restaurant" ] }, { "page": "salary", "title": "Ask A Manager Salary Survey 2021", "topics": [ "salary" ] } ], "_readme": "https://github.com/anuopensci/emend/raw/HEAD/README.md", "_rundeps": [ "askpass", "cli", "coro", "curl", "ellmer", "fastmap", "glue", "httr2", "jsonlite", "later", "lifecycle", "magrittr", "openssl", "otel", "pillar", "pkgconfig", "promises", "R6", "rappdirs", "Rcpp", "rlang", "S7", "sys", "tibble", "utf8", "vctrs", "withr" ], "_score": 2.929418925714293, "_indexed": false, "_nocasepkg": "emend", "_universes": [ "emitanaka" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.1.0", "date": "2026-07-05T08:35:59.000Z", "distro": "resolute", "commit": "da5e0abac80d3da209088b98547605d539fb6742", "fileid": "https://r2.ropensci.org/01fc5bbbad61508eb1f5cf7613322162474797ac56ecfe25d665ab7c620612cf", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/emitanaka/actions/runs/28734852322" }, { "r": "4.6.1", "os": "linux", "version": "0.1.0", "date": "2026-07-05T08:36:02.000Z", "distro": "resolute", "commit": "da5e0abac80d3da209088b98547605d539fb6742", "fileid": "https://r2.ropensci.org/ce37380e24c46a86164c4171cbe04593e23923e6702069b272de8e1432401fb1", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/emitanaka/actions/runs/28734852322" }, { "r": "4.5.3", "os": "mac", "version": "0.1.0", "date": "2026-07-05T08:35:37.000Z", "commit": "da5e0abac80d3da209088b98547605d539fb6742", "fileid": "https://r2.ropensci.org/6306cfe622e480c9d7a635932054d84cf166b985c3349f69c66bff171e61d44c", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/emitanaka/actions/runs/28734852322" }, { "r": "4.6.1", "os": "mac", "version": "0.1.0", "date": "2026-07-05T08:35:24.000Z", "commit": "da5e0abac80d3da209088b98547605d539fb6742", "fileid": "https://r2.ropensci.org/e9ccd1ae5424f6f2c88f1e1a53269552bdfc88fef18db244e1162e0ad1793fa4", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/emitanaka/actions/runs/28734852322" }, { "r": "4.6.0", "os": "wasm", "version": "0.1.0", "date": "2026-07-05T08:36:25.000Z", "commit": "da5e0abac80d3da209088b98547605d539fb6742", "fileid": "https://r2.ropensci.org/5f71436439aead6601791049761ddc6df0aa7ea7c5a2831ff00aa633a6a1523a", "status": "success", "buildurl": "https://github.com/r-universe/emitanaka/actions/runs/28734852322" }, { "r": "4.7.0", "os": "win", "version": "0.1.0", "date": "2026-07-05T08:35:02.000Z", "commit": "da5e0abac80d3da209088b98547605d539fb6742", "fileid": "https://r2.ropensci.org/dd92474f24d790c19c5dbb88ba284307b4c3dfebfde226adc1f4d50839f9e077", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/emitanaka/actions/runs/28734852322" }, { "r": "4.5.3", "os": "win", "version": "0.1.0", "date": "2026-07-05T08:34:57.000Z", "commit": "da5e0abac80d3da209088b98547605d539fb6742", "fileid": "https://r2.ropensci.org/2d38fe4eda71a4d4a4409716ce496bf2a6998950efd8c12ecd2813b3347edf02", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/emitanaka/actions/runs/28734852322" }, { "r": "4.6.1", "os": "win", "version": "0.1.0", "date": "2026-07-05T08:35:06.000Z", "commit": "da5e0abac80d3da209088b98547605d539fb6742", "fileid": "https://r2.ropensci.org/f6c1e39bb708ae9563b8a8303b3216a0d27750ce9d46142630c9b58fe4cb9ea2", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/emitanaka/actions/runs/28734852322" } ] }