{ "_id": "6a107221acfb0bcc41cabe88", "Package": "MLDataR", "Type": "Package", "Title": "Collection of Machine Learning Datasets for Supervised Machine\nLearning", "Version": "1.0.1", "Authors@R": "c(\nperson(\"Gary\", \"Hutson\", , \"hutsons-hacks@outlook.com\", c(\"aut\", \"cre\"),\ncomment = c(ORCID=\"0000-0003-3534-6143\")),\nperson(\"Asif\", \"Laldin\", , \"laldin.asif@gmail.com\", c(\"aut\")),\nperson(\"Isabella\", \"Velásquez\", , \"ivelasq@gmail.com\", c(\"aut\"))\n)", "Maintainer": "Gary Hutson ", "Description": "Contains a collection of datasets for working with machine\nlearning tasks. It will contain datasets for supervised machine\nlearning Jiang (2020) and will\ninclude datasets for classification and regression. The aim of\nthis package is to use data generated around health and other\ndomains.", "License": "MIT + file LICENSE", "Encoding": "UTF-8", "LazyData": "true", "BugReports": "https://github.com/StatsGary/MLDataR/issues", "RoxygenNote": "7.1.2", "VignetteBuilder": "knitr", "Config/pak/sysreqs": "cmake make libicu-dev libuv1-dev", "Repository": "https://statsgary.r-universe.dev", "Date/Publication": "2023-11-23 19:50:01 UTC", "RemoteUrl": "https://github.com/statsgary/mldatar", "RemoteRef": "HEAD", "RemoteSha": "8a5338bf44a5d646b2cb28720b7b46a3ca8a45ec", "NeedsCompilation": "no", "Packaged": { "Date": "2026-05-07 06:32:24 UTC", "User": "root" }, "Author": "Gary Hutson [aut, cre] (ORCID: ),\nAsif Laldin [aut],\nIsabella Velásquez [aut]", "MD5sum": "cb5b04053dd2600d537f96d8eef5a7c7", "_user": "statsgary", "_type": "src", "_file": "MLDataR_1.0.1.tar.gz", "_fileid": "9a1c76ff6ee8ae2acbe3f9b439389d980b4da4bf87f484720b1ef69bab4e057a", "_filesize": 489078, "_sha256": "9a1c76ff6ee8ae2acbe3f9b439389d980b4da4bf87f484720b1ef69bab4e057a", "_created": "2026-05-07T06:32:24.000Z", "_published": "2026-05-22T15:11:29.206Z", "_distro": "noble", "_jobs": [ { "job": 77407660591, "time": 129, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "NOTE", "artifact": "6848432491" }, { "job": 77407661105, "time": 144, "config": "linux-release-x86_64", "r": "4.6.0", "check": "NOTE", "artifact": "6848437891" }, { "job": 77407661210, "time": 188, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "NOTE", "artifact": "6848437224" }, { "job": 77407661005, "time": 167, "config": "macos-release-arm64", "r": "4.6.0", "check": "NOTE", "artifact": "6848431060" }, { "job": 77407659874, "time": 218, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "6848400288" }, { "job": 77407659961, "time": 143, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7163886003" }, { "job": 77407661267, "time": 86, "config": "windows-devel", "r": "4.7.0", "check": "NOTE", "artifact": "6848421542" }, { "job": 77407661450, "time": 87, "config": "windows-oldrel", "r": "4.5.3", "check": "NOTE", "artifact": "6848422061" }, { "job": 77407660700, "time": 94, "config": "windows-release", "r": "4.6.0", "check": "NOTE", "artifact": "6848423820" } ], "_buildurl": "https://github.com/r-universe/statsgary/actions/runs/25479786191", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/statsgary/mldatar", "_commit": { "id": "8a5338bf44a5d646b2cb28720b7b46a3ca8a45ec", "author": "Gary Hutson <44023992+StatsGary@users.noreply.github.com>", "committer": "GitHub ", "message": "Update R-CMD-check.yaml", "time": 1700769001 }, "_maintainer": { "name": "Gary Hutson", "email": "hutsons-hacks@outlook.com", "orcid": "0000-0003-3534-6143" }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 2.10", "role": "Depends" }, { "package": "ConfusionTableR", "role": "Imports" }, { "package": "dplyr", "role": "Imports" }, { "package": "parsnip", "role": "Imports" }, { "package": "rsample", "role": "Imports" }, { "package": "recipes", "role": "Imports" }, { "package": "workflows", "role": "Imports" }, { "package": "ranger", "role": "Imports" }, { "package": "caret", "role": "Imports" }, { "package": "varhandle", "role": "Imports" }, { "package": "OddsPlotty", "role": "Imports" }, { "package": "ggplot2", "role": "Imports" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" } ], "_owner": "statsgary", "_selfowned": true, "_usedby": 0, "_updates": [], "_tags": [], "_stars": 55, "_contributors": [ { "user": "statsgary", "count": 2, "uuid": 44023992 } ], "_userbio": { "uuid": 44023992, "type": "user", "name": "Gary Hutson", "description": "Senior Data Scientist | Former Head of ML, Data Science / Senior DS. Loves: Python, R, ML/DL, modelling , Stats, Kaggle, anything data..." }, "_downloads": { "count": 287, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/MLDataR" }, "_devurl": "https://github.com/statsgary/mldatar", "_searchresults": 34, "_rbuild": "4.6.0", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/MLDataR.html", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "manual.pdf" ], "_homeurl": "https://github.com/statsgary/mldatar", "_realowner": "statsgary", "_cranurl": true, "_releases": [ { "version": "0.1.1", "date": "2022-01-05" }, { "version": "0.1.2", "date": "2022-02-02" }, { "version": "0.1.3", "date": "2022-03-08" }, { "version": "1.0.1", "date": "2022-10-03" } ], "_exports": [], "_datasets": [ { "name": "care_home_incidents", "title": "Care Home Incidents", "object": "care_home_incidents", "class": [ "spec_tbl_df", "tbl_df", "tbl", "data.frame" ], "fields": [ "CareHomeFail", "WeightLoss", "Medication", "Falls", "Choking", "UnexpectedDeaths", "Bruising", "Absconsion", "ResidentAbuseByResident", "ResidentAbuseByStaff", "ResidentAbuseOnStaff", "Wounds" ], "rows": 1216, "table": true, "tojson": true }, { "name": "csgo", "title": "csgo", "object": "csgo", "class": [ "spec_tbl_df", "tbl_df", "tbl", "data.frame" ], "fields": [ "map", "day", "month", "year", "date", "wait_time_s", "match_time_s", "team_a_rounds", "team_b_rounds", "ping", "kills", "assists", "deaths", "mvps", "hs_percent", "points", "result" ], "rows": 1133, "table": true, "tojson": true }, { "name": "diabetes_data", "title": "Diabetes datasets", "object": "diabetes_data", "class": [ "spec_tbl_df", "tbl_df", "tbl", "data.frame" ], "fields": [ "Age", "Gender", "ExcessUrination", "Polydipsia", "WeightLossSudden", "Fatigue", "Polyphagia", "GenitalThrush", "BlurredVision", "Itching", "Irritability", "DelayHealing", "PartialPsoriasis", "MuscleStiffness", "Alopecia", "Obesity", "DiabeticClass" ], "rows": 520, "table": true, "tojson": true }, { "name": "heartdisease", "title": "Heart disease dataset", "object": "heartdisease", "class": [ "tbl_df", "tbl", "data.frame" ], "fields": [ "Age", "Sex", "RestingBP", "Cholesterol", "FastingBS", "RestingECG", "MaxHR", "Angina", "HeartPeakReading", "HeartDisease" ], "rows": 918, "table": true, "tojson": true }, { "name": "long_stayers", "title": "Long stayers dataset", "object": "long_stayers", "class": [ "tbl_df", "tbl", "data.frame" ], "fields": [ "stranded.label", "age", "care.home.referral", "medicallysafe", "hcop", "mental_health_care", "periods_of_previous_care", "admit_date", "frailty_index" ], "rows": 768, "table": true, "tojson": true }, { "name": "PreDiabetes", "title": "PreDiabetes dataset", "object": "PreDiabetes", "class": [ "spec_tbl_df", "tbl_df", "tbl", "data.frame" ], "fields": [ "Age", "Sex", "IMD_Decile", "BMI", "Age_PreDiabetes", "HbA1C", "Time_Pre_To_Diabetes", "Age_Diabetes", "PreDiabetes_Checks_Before_Diabetes" ], "rows": 3059, "table": true, "tojson": true }, { "name": "stroke_classification", "title": "Stroke Classification dataset", "object": "stroke_classification", "class": [ "data.frame" ], "fields": [ "pat_id", "stroke", "gender", "age", "hypertension", "heart_disease", "work_related_stress", "urban_residence", "avg_glucose_level", "bmi", "smokes" ], "rows": 5110, "table": true, "tojson": true }, { "name": "thyroid_disease", "title": "Thyroid disease dataset", "object": "thyroid_disease", "class": [ "data.frame" ], "fields": [ "ThryroidClass", "patient_age", "patient_gender", "presc_thyroxine", "queried_why_on_thyroxine", "presc_anthyroid_meds", "sick", "pregnant", "thyroid_surgery", "radioactive_iodine_therapyI131", "query_hypothyroid", "query_hyperthyroid", "lithium", "goitre", "tumor", "hypopituitarism", "psych_condition", "TSH_measured", "TSH_reading", "T3_measured", "T3_reading", "T4_measured", "T4_reading", "thyrox_util_rate_T4U_measured", "thyrox_util_rate_T4U_reading", "FTI_measured", "FTI_reading", "ref_src" ], "rows": 3772, "table": true, "tojson": true } ], "_help": [ { "page": "care_home_incidents", "title": "Care Home Incidents", "topics": [ "care_home_incidents" ] }, { "page": "csgo", "title": "csgo", "topics": [ "csgo" ] }, { "page": "diabetes_data", "title": "Diabetes datasets", "topics": [ "diabetes_data" ] }, { "page": "heartdisease", "title": "Heart disease dataset", "topics": [ "heartdisease" ] }, { "page": "long_stayers", "title": "Long stayers dataset", "topics": [ "long_stayers" ] }, { "page": "PreDiabetes", "title": "PreDiabetes dataset", "topics": [ "PreDiabetes" ] }, { "page": "stroke_classification", "title": "Stroke Classification dataset", "topics": [ "stroke_classification" ] }, { "page": "thyroid_disease", "title": "Thyroid disease dataset", "topics": [ "thyroid_disease" ] } ], "_readme": "https://github.com/statsgary/mldatar/raw/HEAD/README.md", "_rundeps": [ "backports", "base64enc", "broom", "bslib", "cachem", "caret", "class", "cli", "clock", "codetools", "conflicted", "ConfusionTableR", "cpp11", "data.table", "diagram", "dials", "DiceDesign", "digest", "dplyr", "e1071", "evaluate", "farver", "fastmap", "fontawesome", "foreach", "fs", "furrr", "future", "future.apply", "GauPro", "generics", "ggplot2", "ggthemes", "globals", "glue", "gower", "gtable", "hardhat", "highr", "htmltools", "infer", "ipred", "isoband", "iterators", "jquerylib", "jsonlite", "KernSmooth", "knitr", "labeling", "lattice", "lava", "lbfgs", "lifecycle", "listenv", "lubridate", "magrittr", "MASS", "Matrix", "memoise", "mime", "mixopt", "mlbench", "modeldata", "modelenv", "ModelMetrics", "nlme", "nnet", "numDeriv", "OddsPlotty", "parallelly", "parsnip", "patchwork", "pillar", "pkgconfig", "plyr", "prettyunits", "pROC", "prodlim", "progressr", "proxy", "purrr", "R6", "ranger", "rappdirs", "RColorBrewer", "Rcpp", "RcppArmadillo", "RcppEigen", "recipes", "reshape2", "rlang", "rmarkdown", "rpart", "rsample", "rstudioapi", "S7", "sass", "scales", "sfd", "shape", "slider", "sparsevctrs", "splitfngr", "SQUAREM", "stringi", "stringr", "survival", "tailor", "tibble", "tidymodels", "tidyr", "tidyselect", "timechange", "timeDate", "tinytex", "tune", "tzdb", "utf8", "varhandle", "vctrs", "viridisLite", "warp", "withr", "workflows", "workflowsets", "xfun", "yaml", "yardstick" ], "_vignettes": [ { "source": "MLDataR.Rmd", "filename": "MLDataR.html", "title": "MLDataR - A Package for ML datasets", "engine": "knitr::rmarkdown", "headings": [ "Installing the NHSDataR package", "What datasets are included", "Thyroid Disease dataset", "Create TidyModels recipe to model the thyroid dataset", "Data preparation", "Split the data", "Create a recipe with preprocessing steps", "Getting modelling with Parsnip", "Create the model workflow", "Make predictions and evaluate with ConfusionTableR", "Diabetes dataset", "Heart disease prediction", "Dummy encode the dataset", "Long stayers", "What's on the horizon?" ], "created": "2023-10-13 11:22:23", "modified": "2023-10-13 11:22:23", "commits": 1 } ], "_score": 5.970811610872518, "_indexed": true, "_nocasepkg": "mldatar", "_universes": [ "statsgary" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "1.0.1", "date": "2026-05-07T06:34:33.000Z", "distro": "noble", "commit": "8a5338bf44a5d646b2cb28720b7b46a3ca8a45ec", "fileid": "e77ea60eb5cd3c7315b36dbcd01221ef86fb44c8d71a007c6eb3e5854ebc40e5", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/statsgary/actions/runs/25479786191" }, { "r": "4.6.0", "os": "linux", "version": "1.0.1", "date": "2026-05-07T06:34:56.000Z", "distro": "noble", "commit": "8a5338bf44a5d646b2cb28720b7b46a3ca8a45ec", "fileid": "c7e9a0050f98dea7a8c5db080ef3633478f7a1fce90d0a61ddc7655024f740c9", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/statsgary/actions/runs/25479786191" }, { "r": "4.5.3", "os": "mac", "version": "1.0.1", "date": "2026-05-07T06:34:55.000Z", "commit": "8a5338bf44a5d646b2cb28720b7b46a3ca8a45ec", "fileid": "a682eef2112747b240f57cba3bb73e524bf976e4450ceff55565b5d3db70dcf9", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/statsgary/actions/runs/25479786191" }, { "r": "4.6.0", "os": "mac", "version": "1.0.1", "date": "2026-05-07T06:34:26.000Z", "commit": "8a5338bf44a5d646b2cb28720b7b46a3ca8a45ec", "fileid": "522f5f6bb0c92a93f0d4244d1621d9b850485b01b0c8b60238c000c0d108ae83", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/statsgary/actions/runs/25479786191" }, { "r": "4.7.0", "os": "win", "version": "1.0.1", "date": "2026-05-07T06:33:45.000Z", "commit": "8a5338bf44a5d646b2cb28720b7b46a3ca8a45ec", "fileid": "bfe8f182cc0a321a5a73dcaa7fc0fae8086dfac13dbeb38358984c625123021f", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/statsgary/actions/runs/25479786191" }, { "r": "4.5.3", "os": "win", "version": "1.0.1", "date": "2026-05-07T06:33:47.000Z", "commit": "8a5338bf44a5d646b2cb28720b7b46a3ca8a45ec", "fileid": "38e215fec924b774ce8c6435eb5380ec8743eadcce4d72435c216d2aca52fa2b", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/statsgary/actions/runs/25479786191" }, { "r": "4.6.0", "os": "win", "version": "1.0.1", "date": "2026-05-07T06:33:55.000Z", "commit": "8a5338bf44a5d646b2cb28720b7b46a3ca8a45ec", "fileid": "72e733a2c95247a8129880e30aeee0444c93223710dd7149e23440b3ff49938e", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/statsgary/actions/runs/25479786191" }, { "r": "4.6.0", "os": "wasm", "version": "1.0.1", "date": "2026-05-22T15:11:12.000Z", "commit": "8a5338bf44a5d646b2cb28720b7b46a3ca8a45ec", "fileid": "f26577d2f03f5bebb9bcca8791b9de5e12f7a1bb7cef076c12e5cbbb6853e651", "status": "success", "buildurl": "https://github.com/r-universe/statsgary/actions/runs/25479786191" } ] }