{ "_id": "6a101d50acfb0bcc41c8a167", "Package": "llmclean", "Type": "Package", "Title": "'LLM'-Assisted Data Cleaning with Multi-Provider Support", "Version": "0.1.0", "Date": "2026-04-15", "Authors@R": "person(\ngiven = \"Sadikul\",\nfamily = \"Islam\",\nemail = \"sadikul.islamiasri@gmail.com\",\nrole = c(\"aut\", \"cre\"),\ncomment = c(ORCID = \"0000-0003-2924-7122\")\n)", "Author": "Sadikul Islam [aut, cre] (ORCID:\n)", "Maintainer": "Sadikul Islam ", "Description": "Detects and suggests fixes for semantic inconsistencies in\ndata frames by calling large language models (LLMs) through a\nunified, provider-agnostic interface. Supported providers\ninclude 'OpenAI' ('GPT-4o', 'GPT-4o-mini'), 'Anthropic'\n('Claude'), 'Google' ('Gemini'), 'Groq' (free-tier 'LLaMA' and\n'Mixtral'), and local 'Ollama' models. The package identifies\nissues that rule-based tools cannot detect: abbreviation\nvariants, typographic errors, case inconsistencies, and\nmalformed values. Results are returned as tidy data frames with\ncolumn, row index, detected value, issue type, suggested fix,\nand confidence score. An offline fallback using statistical and\nfuzzy-matching methods is provided for use without any API key.\nInteractive fix application with human review is supported via\n'apply_fixes()'. Methods follow de Jonge and van der Loo (2013)\n\nand Chaudhuri et al. (2003) .", "License": "GPL-3", "VignetteBuilder": "knitr", "Encoding": "UTF-8", "LazyData": "true", "RoxygenNote": "7.3.3", "Config/testthat/edition": "3", "NeedsCompilation": "no", "Packaged": { "Date": "2026-05-22 09:06:42 UTC", "User": "root" }, "Repository": "https://cran.r-universe.dev", "Date/Publication": "2026-04-22 14:14:02 UTC", "RemoteUrl": "https://github.com/cran/llmclean", "RemoteRef": "HEAD", "RemoteSha": "ca2c6035cff3ba095da28bf493ff53e4ee4d4c6f", "MD5sum": "1a69d01d49af680c054f1979486de020", "_user": "cran", "_type": "src", "_file": "llmclean_0.1.0.tar.gz", "_fileid": "3ca2b897a09ccae91dbc51918fe808161a16631bb0f4953d18915827e191e211", "_filesize": 202236, "_sha256": "3ca2b897a09ccae91dbc51918fe808161a16631bb0f4953d18915827e191e211", "_created": "2026-05-22T09:06:42.000Z", "_published": "2026-05-22T09:09:36.310Z", "_distro": "noble", "_jobs": [ { "job": 77349821080, "time": 137, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "7156908127" }, { "job": 77349821010, "time": 128, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7156905373" }, { "job": 77349341729, "time": 183, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7156861569" }, { "job": 77349820978, "time": 106, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7156898594" } ], "_buildurl": "https://github.com/r-universe/cran/actions/runs/26278716101", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/cran/llmclean", "_commit": { "id": "ca2c6035cff3ba095da28bf493ff53e4ee4d4c6f", "author": "Sadikul Islam ", "committer": "cran-robot ", "message": "version 0.1.0\n", "time": 1776867242 }, "_maintainer": { "name": "Sadikul Islam", "email": "sadikul.islamiasri@gmail.com", "orcid": "0000-0003-2924-7122" }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 4.1.0", "role": "Depends" }, { "package": "stats", "role": "Imports" }, { "package": "utils", "role": "Imports" }, { "package": "dplyr", "version": ">= 1.0.0", "role": "Imports" }, { "package": "rlang", "version": ">= 1.0.0", "role": "Imports" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" }, { "package": "httr2", "version": ">= 1.0.0", "role": "Suggests" }, { "package": "jsonlite", "version": ">= 1.8.0", "role": "Suggests" } ], "_owner": "cran", "_selfowned": false, "_usedby": 0, "_updates": [ { "week": "2026-17", "n": 1 } ], "_tags": [ { "name": "0.1.0", "date": "2026-04-22" } ], "_stars": 0, "_userbio": { "uuid": 6899542, "type": "organization", "name": "cran", "description": "Unofficial read-only mirror of all CRAN R packages" }, "_downloads": { "count": 485, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/llmclean" }, "_searchresults": 0, "_rbuild": "4.6.0", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/llmclean.html", "manual.pdf" ], "_realowner": "cran", "_cranurl": false, "_releases": [ { "version": "0.1.0", "date": "2026-04-22" } ], "_exports": [ "apply_fixes", "detect_issues", "get_llm_provider", "llmclean_report", "offline_detect", "set_llm_provider", "suggest_fixes" ], "_datasets": [ { "name": "messy_employees", "title": "Hypothetical Messy Employee Records Dataset", "object": "messy_employees", "class": [ "data.frame" ], "fields": [ "emp_id", "name", "department", "email", "age", "salary", "status", "hire_date" ], "rows": 20, "table": true, "tojson": true }, { "name": "messy_survey", "title": "Hypothetical Messy Survey Response Dataset", "object": "messy_survey", "class": [ "data.frame" ], "fields": [ "respondent_id", "country", "satisfaction", "age_group", "income_usd" ], "rows": 15, "table": true, "tojson": true } ], "_help": [ { "page": "llmclean-package", "title": "llmclean: LLM-Assisted Data Cleaning with Multi-Provider Support", "topics": [ "llmclean-package", "llmclean" ] }, { "page": "apply_fixes", "title": "Apply Suggested Fixes to a Data Frame", "topics": [ "apply_fixes" ] }, { "page": "detect_issues", "title": "Detect Semantic Inconsistencies in a Data Frame Using an LLM", "topics": [ "detect_issues" ] }, { "page": "get_llm_provider", "title": "Get Current LLM Provider Configuration", "topics": [ "get_llm_provider" ] }, { "page": "llmclean_report", "title": "Generate a Summary Report of LLM-Assisted Data Cleaning", "topics": [ "llmclean_report" ] }, { "page": "messy_employees", "title": "Hypothetical Messy Employee Records Dataset", "topics": [ "messy_employees" ] }, { "page": "messy_survey", "title": "Hypothetical Messy Survey Response Dataset", "topics": [ "messy_survey" ] }, { "page": "offline_detect", "title": "Offline Detection of Data Inconsistencies Without an LLM", "topics": [ "offline_detect" ] }, { "page": "set_llm_provider", "title": "Configure the LLM Provider for Data Cleaning", "topics": [ "set_llm_provider" ] }, { "page": "suggest_fixes", "title": "Request Enriched Fix Suggestions for Detected Issues", "topics": [ "suggest_fixes" ] } ], "_rundeps": [ "cli", "dplyr", "generics", "glue", "lifecycle", "magrittr", "pillar", "pkgconfig", "R6", "rlang", "tibble", "tidyselect", "utf8", "vctrs", "withr" ], "_vignettes": [ { "source": "llmclean-intro.Rmd", "filename": "llmclean-intro.html", "title": "LLM-Assisted Data Cleaning with llmclean", "author": "Sadikul Islam", "engine": "knitr::rmarkdown", "headings": [ "Introduction", "Supported Providers", "Quick Start", "Step 1 — Configure the provider", "Step 2 — Inspect the built-in messy datasets", "Stage 1 — Detect Issues", "Issue type breakdown", "Case inconsistencies", "Typos and near-duplicates (Levenshtein)", "Malformed email addresses", "Numeric outliers (Tukey outer fence)", "Stage 2 — Suggest Fixes", "Stage 3 — Apply Fixes", "Dry run mode", "Stage 4 — Offline Detection (No API Key)", "Stage 5 — Summary Report", "Complete Workflow (One Pipeline)", "API Key Storage Best Practice", "Session Information", "References" ], "created": "2026-04-22 14:14:02", "modified": "2026-04-22 14:14:02", "commits": 1 } ], "_score": 2, "_indexed": true, "_nocasepkg": "llmclean", "_universes": [ "cran" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.1.0", "date": "2026-05-22T09:08:56.000Z", "distro": "noble", "commit": "ca2c6035cff3ba095da28bf493ff53e4ee4d4c6f", "fileid": "949471d3ee23ff5308ca294187cfa139ad7aa7fba3ca577ab78579755cddd817", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cran/actions/runs/26278716101" }, { "r": "4.6.0", "os": "linux", "version": "0.1.0", "date": "2026-05-22T09:08:51.000Z", "distro": "noble", "commit": "ca2c6035cff3ba095da28bf493ff53e4ee4d4c6f", "fileid": "87a6e3122ea346ad3b993c2043a15ff886100feb6a6cdc20167d08302ae301a7", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cran/actions/runs/26278716101" }, { "r": "4.6.0", "os": "wasm", "version": "0.1.0", "date": "2026-05-22T09:08:51.000Z", "commit": "ca2c6035cff3ba095da28bf493ff53e4ee4d4c6f", "fileid": "35c8152a1e7385fbc48aee6d02378cc39dffd662de25a1d99d6870bec7d2c57c", "status": "success", "buildurl": "https://github.com/r-universe/cran/actions/runs/26278716101" } ] }