{ "_id": "6a1e9dc61d7bb097a0a6f523", "Package": "ml", "Title": "Supervised Learning with Mandatory Splits and Seeds", "Version": "1.0.0", "Authors@R": "person(\"Simon\", \"Roth\", email = \"simon@epagogy.ai\", role = c(\"aut\", \"cre\"))", "Author": "Simon Roth [aut, cre]", "Maintainer": "Simon Roth ", "Description": "Implements the split-fit-evaluate-assess workflow from\nHastie, Tibshirani, and Friedman (2009, ISBN:978-0-387-84857-0)\n\"The Elements of Statistical Learning\", Chapter 7. Provides\nthree-way data splitting with automatic stratification,\nmandatory seeds for reproducibility, automatic data type\nhandling, and 10 algorithms out of the box. Uses 'Rust' backend\nfor cross-language deterministic splitting. Designed for\ntabular supervised learning with minimal ceremony. Polyglot\nparity with the 'Python' 'mlw' package on 'PyPI'.", "License": "MIT + file LICENSE", "SystemRequirements": "Cargo ('Rust' package manager), rustc (>= 1.56.0,\noptional)", "Encoding": "UTF-8", "Roxygen": "list(markdown = TRUE)", "RoxygenNote": "7.3.3", "URL": "https://github.com/epagogy/ml, https://epagogy.ai", "BugReports": "https://github.com/epagogy/ml/issues", "Config/testthat/edition": "3", "VignetteBuilder": "knitr", "Config/pak/sysreqs": "libclang-dev", "Repository": "https://epagogy.r-universe.dev", "Date/Publication": "2026-04-03 17:52:15 UTC", "RemoteUrl": "https://github.com/epagogy/ml", "RemoteRef": "HEAD", "RemoteSha": "733303866ecba86ab83fdbd7ef3e7b8d2a24bf1f", "RemoteSubdir": "r", "NeedsCompilation": "yes", "Packaged": { "Date": "2026-06-02 09:01:16 UTC", "User": "root" }, "MD5sum": "9fd9be84d4bb8dd64af38a1b96015266", "_user": "epagogy", "_type": "src", "_file": "ml_1.0.0.tar.gz", "_fileid": "a19eaa02dda49966718945b5f8cb3b7ba587a8ebf8691a10fa0c05cd27d9c204", "_filesize": 341617, "_sha256": "a19eaa02dda49966718945b5f8cb3b7ba587a8ebf8691a10fa0c05cd27d9c204", "_created": "2026-06-02T09:01:16.000Z", "_published": "2026-06-02T09:09:26.683Z", "_distro": "noble", "_jobs": [ { "job": 79035948628, "time": 254, "config": "linux-devel-arm64", "r": "4.7.0", "check": "WARNING", "artifact": "7353481168" }, { "job": 79035948629, "time": 275, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "WARNING", "artifact": "7353487644" }, { "job": 79035948642, "time": 216, "config": "linux-release-arm64", "r": "4.6.0", "check": "WARNING", "artifact": "7353467205" }, { "job": 79035948675, "time": 228, "config": "linux-release-x86_64", "r": "4.6.0", "check": "WARNING", "artifact": "7353470801" }, { "job": 79035948694, "time": 201, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "WARNING", "artifact": "7353449002" }, { "job": 79035948775, "time": 451, "config": "macos-oldrel-x86_64", "r": "4.5.3", "check": "WARNING", "artifact": "7353541996" }, { "job": 79035948670, "time": 239, "config": "macos-release-arm64", "r": "4.6.0", "check": "WARNING", "artifact": "7353459185" }, { "job": 79035948682, "time": 287, "config": "macos-release-x86_64", "r": "4.6.0", "check": "WARNING", "artifact": "7353485673" }, { "job": 79035134075, "time": 275, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7353386627" }, { "job": 79035948582, "time": 192, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7353457328" }, { "job": 79035948631, "time": 239, "config": "windows-devel", "r": "4.7.0", "check": "WARNING", "artifact": "7353474473" }, { "job": 79035948704, "time": 181, "config": "windows-oldrel", "r": "4.5.3", "check": "WARNING", "artifact": "7353453780" }, { "job": 79035948598, "time": 204, "config": "windows-release", "r": "4.6.0", "check": "WARNING", "artifact": "7353462945" } ], "_buildurl": "https://github.com/r-universe/epagogy/actions/runs/26809394317", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/epagogy/ml", "_commit": { "id": "733303866ecba86ab83fdbd7ef3e7b8d2a24bf1f", "author": "Simon Roth ", "committer": "Simon Roth ", "message": "papers: wire Zenodo DOIs, flatten data, fix Dockerfile\n\n- Grammar refs.bib: landscape DOI 10.5281/zenodo.19406148\n- Landscape refs.bib: grammar DOI 10.5281/zenodo.19406355\n- Recompiled both PDFs with DOI cross-references\n- Flattened data/v3/ → data/ (verify scripts updated)\n- Removed grammar Dockerfile (no experiments to run)\n- Landscape Dockerfile: experiment runner only\n", "time": 1775238735 }, "_maintainer": { "name": "Simon Roth", "email": "simon@epagogy.ai", "login": "systats", "linkedin": "in/simon-roth-612840137", "description": "ML that reproduces. Agents that spawn. Pizza that vanishes. Powered by multivitamin Durstlöscher.", "uuid": 22753281 }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 4.1.0", "role": "Depends" }, { "package": "cli", "role": "Imports" }, { "package": "rlang", "role": "Imports" }, { "package": "stats", "role": "Imports" }, { "package": "utils", "role": "Imports" }, { "package": "withr", "role": "Imports" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" }, { "package": "xgboost", "version": ">= 2.0.0", "role": "Suggests" }, { "package": "ranger", "role": "Suggests" }, { "package": "rpart", "role": "Suggests" }, { "package": "e1071", "role": "Suggests" }, { "package": "kknn", "role": "Suggests" }, { "package": "glmnet", "role": "Suggests" }, { "package": "naivebayes", "role": "Suggests" }, { "package": "lightgbm", "role": "Suggests" }, { "package": "tm", "role": "Suggests" }, { "package": "tibble", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "caret", "role": "Suggests" }, { "package": "rsample", "role": "Suggests" } ], "_owner": "epagogy", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2026-11", "n": 22 }, { "week": "2026-12", "n": 6 }, { "week": "2026-14", "n": 5 } ], "_tags": [], "_stars": 9, "_contributors": [ { "user": "systats", "count": 29, "uuid": 22753281 } ], "_userbio": { "uuid": 265440983, "type": "organization", "name": "EPAGOGY", "description": "Independent research designing honest methodology." }, "_downloads": { "count": 480, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/ml" }, "_devurl": "https://github.com/epagogy/ml", "_searchresults": 61, "_rbuild": "4.6.0", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/ml.html", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "manual.pdf" ], "_homeurl": "https://github.com/epagogy/ml", "_realowner": "epagogy", "_cranurl": true, "_releases": [ { "version": "0.1.2", "date": "2026-03-19" } ], "_exports": [ "ml", "ml_algorithms", "ml_assess", "ml_best", "ml_calibrate", "ml_check", "ml_check_data", "ml_compare", "ml_config", "ml_cv", "ml_cv_group", "ml_cv_temporal", "ml_dataset", "ml_drift", "ml_embed", "ml_enough", "ml_evaluate", "ml_explain", "ml_fit", "ml_leak", "ml_load", "ml_optimize", "ml_plot", "ml_predict", "ml_predict_proba", "ml_prepare", "ml_profile", "ml_quick", "ml_report", "ml_save", "ml_screen", "ml_shelf", "ml_split", "ml_split_group", "ml_split_temporal", "ml_stack", "ml_tune", "ml_validate", "ml_verify" ], "_help": [ { "page": "ml", "title": "The ml module — all verbs accessed via ml$verb()", "topics": [ "ml" ] }, { "page": "ml_algorithms", "title": "List available ML algorithms", "topics": [ "ml_algorithms" ] }, { "page": "ml_assess", "title": "Assess model on held-out test data (do once)", "topics": [ "ml_assess" ] }, { "page": "ml_best", "title": "Get the best model from a leaderboard", "topics": [ "ml_best" ] }, { "page": "ml_calibrate", "title": "Calibrate predicted probabilities", "topics": [ "ml_calibrate" ] }, { "page": "ml_check", "title": "Verify bitwise reproducibility for a given dataset", "topics": [ "ml_check" ] }, { "page": "ml_check_data", "title": "Pre-flight data quality checks", "topics": [ "ml_check_data" ] }, { "page": "ml_compare", "title": "Compare pre-fitted models on the same data", "topics": [ "ml_compare" ] }, { "page": "ml_config", "title": "Configure ml package settings", "topics": [ "ml_config" ] }, { "page": "ml_cv", "title": "Create k-fold cross-validation from a split", "topics": [ "ml_cv" ] }, { "page": "ml_cv_group", "title": "Create group-aware cross-validation from a split", "topics": [ "ml_cv_group" ] }, { "page": "ml_cv_temporal", "title": "Create temporal cross-validation from a split", "topics": [ "ml_cv_temporal" ] }, { "page": "ml_dataset", "title": "Load a built-in dataset", "topics": [ "ml_dataset" ] }, { "page": "ml_drift", "title": "Detect data drift between reference and new data", "topics": [ "ml_drift" ] }, { "page": "ml_embed", "title": "Embed texts into numeric features", "topics": [ "ml_embed" ] }, { "page": "ml_enough", "title": "Learning curve analysis — do you need more data?", "topics": [ "ml_enough" ] }, { "page": "ml_evaluate", "title": "Evaluate model on validation data (iterate freely)", "topics": [ "ml_evaluate" ] }, { "page": "ml_explain", "title": "Explain model via feature importance", "topics": [ "ml_explain" ] }, { "page": "ml_fit", "title": "Fit a machine learning model", "topics": [ "ml_fit" ] }, { "page": "ml_leak", "title": "Detect potential data leakage", "topics": [ "ml_leak" ] }, { "page": "ml_load", "title": "Load a model from disk", "topics": [ "ml_load" ] }, { "page": "ml_optimize", "title": "Optimize decision threshold for binary classification", "topics": [ "ml_optimize" ] }, { "page": "ml_plot", "title": "Visual diagnostics for a fitted model", "topics": [ "ml_plot" ] }, { "page": "ml_predict", "title": "Predict from a fitted model (ml_predict style)", "topics": [ "ml_predict" ] }, { "page": "ml_predict_proba", "title": "Predict class probabilities", "topics": [ "ml_predict_proba" ] }, { "page": "ml_prepare", "title": "Prepare data for ML: encode, impute, and scale", "topics": [ "ml_prepare" ] }, { "page": "ml_profile", "title": "Profile data before modeling", "topics": [ "ml_profile" ] }, { "page": "ml_quick", "title": "One-call workflow: split + screen + fit + evaluate", "topics": [ "ml_quick" ] }, { "page": "ml_report", "title": "Generate an HTML training report", "topics": [ "ml_report" ] }, { "page": "ml_save", "title": "Save a model to disk", "topics": [ "ml_save" ] }, { "page": "ml_screen", "title": "Screen all algorithms on your data", "topics": [ "ml_screen" ] }, { "page": "ml_shelf", "title": "Check if a model is past its shelf life", "topics": [ "ml_shelf" ] }, { "page": "ml_split", "title": "Split data into train/valid/test partitions or cross-validation folds", "topics": [ "ml_split" ] }, { "page": "ml_split_group", "title": "Split data with group non-overlap — no group leaks across partitions", "topics": [ "ml_split_group" ] }, { "page": "ml_split_temporal", "title": "Split data chronologically — no future leakage", "topics": [ "ml_split_temporal" ] }, { "page": "ml_stack", "title": "Ensemble stacking", "topics": [ "ml_stack" ] }, { "page": "ml_tune", "title": "Tune hyperparameters via random or grid search", "topics": [ "ml_tune" ] }, { "page": "ml_validate", "title": "Validate model against rules and/or baseline", "topics": [ "ml_validate" ] }, { "page": "ml_verify", "title": "Verify provenance integrity of a model", "topics": [ "ml_verify" ] }, { "page": "predict.ml_model", "title": "Predict from a fitted model", "topics": [ "predict.ml_model" ] }, { "page": "predict.ml_tuning_result", "title": "Predict from best model in a tuning result", "topics": [ "predict.ml_tuning_result" ] }, { "page": "print.ml_cv_result", "title": "Print ml_cv_result", "topics": [ "print.ml_cv_result" ] }, { "page": "print.ml_drift_result", "title": "Print ml_drift_result", "topics": [ "print.ml_drift_result" ] }, { "page": "print.ml_embedder", "title": "Print ml_embedder", "topics": [ "print.ml_embedder" ] }, { "page": "print.ml_evidence", "title": "Print ml_evidence", "topics": [ "print.ml_evidence" ] }, { "page": "print.ml_explanation", "title": "Print ml_explanation", "topics": [ "print.ml_explanation" ] }, { "page": "print.ml_leaderboard", "title": "Print ml_leaderboard", "topics": [ "print.ml_leaderboard" ] }, { "page": "print.ml_metrics", "title": "Print ml_metrics", "topics": [ "print.ml_metrics" ] }, { "page": "print.ml_model", "title": "Print an ml_model", "topics": [ "print.ml_model" ] }, { "page": "print.ml_profile_result", "title": "Print ml_profile_result", "topics": [ "print.ml_profile_result" ] }, { "page": "print.ml_shelf_result", "title": "Print ml_shelf_result", "topics": [ "print.ml_shelf_result" ] }, { "page": "print.ml_split_result", "title": "Print an ml_split_result", "topics": [ "print.ml_split_result" ] }, { "page": "print.ml_tuning_result", "title": "Print an ml_tuning_result", "topics": [ "print.ml_tuning_result" ] }, { "page": "print.ml_validate_result", "title": "Print ml_validate_result", "topics": [ "print.ml_validate_result" ] } ], "_readme": "https://github.com/epagogy/ml/raw/HEAD/r/README.md", "_rundeps": [ "cli", "rlang", "withr" ], "_vignettes": [ { "source": "quickstart.Rmd", "filename": "quickstart.html", "title": "Getting Started with ml", "engine": "knitr::rmarkdown", "headings": [ "Overview", "Step 1: Profile your data", "Step 2: Split into train/valid/test", "Step 3: Screen algorithms", "Step 4: Fit and evaluate", "Step 5: Explain feature importance", "Step 6: Validate against rules", "Step 7: Assess on test data (once)", "Step 8: Save and load", "Module-style interface", "Regression example", "Available algorithms" ], "created": "2026-03-14 00:38:48", "modified": "2026-03-14 00:38:48", "commits": 1 } ], "_score": 5.915663603505773, "_indexed": true, "_nocasepkg": "ml", "_universes": [ "epagogy", "systats" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "1.0.0", "date": "2026-06-02T09:04:54.000Z", "distro": "noble", "arch": "aarch64", "commit": "733303866ecba86ab83fdbd7ef3e7b8d2a24bf1f", "fileid": "0e63e6336e18dcf918781fd54ba2f5426cc4d37f2982d7a54f6e1a910f244aee", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/epagogy/actions/runs/26809394317" }, { "r": "4.7.0", "os": "linux", "version": "1.0.0", "date": "2026-06-02T09:05:00.000Z", "distro": "noble", "arch": "x86_64", "commit": "733303866ecba86ab83fdbd7ef3e7b8d2a24bf1f", "fileid": "fe07e0cf98542be15ad68c8e5e1eabdc82fb45107e90215df5e1511c40bebb68", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/epagogy/actions/runs/26809394317" }, { "r": "4.6.0", "os": "linux", "version": "1.0.0", "date": "2026-06-02T09:04:15.000Z", "distro": "noble", "arch": "aarch64", "commit": "733303866ecba86ab83fdbd7ef3e7b8d2a24bf1f", "fileid": "84ab782a80e09fd1485186d030e7eae8e00f88dc9f092b105cf18033a2c5dc44", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/epagogy/actions/runs/26809394317" }, { "r": "4.6.0", "os": "linux", "version": "1.0.0", "date": "2026-06-02T09:04:20.000Z", "distro": "noble", "arch": "x86_64", "commit": "733303866ecba86ab83fdbd7ef3e7b8d2a24bf1f", "fileid": "7f448bbdc70d4e467472dc8e41e402842c3126b98ba6898178c24688a37d84fb", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/epagogy/actions/runs/26809394317" }, { "r": "4.5.3", "os": "mac", "version": "1.0.0", "date": "2026-06-02T09:03:39.000Z", "arch": "aarch64", "commit": "733303866ecba86ab83fdbd7ef3e7b8d2a24bf1f", "fileid": "a3980238f348cf69f2df078b6a268dbee900473a38a93d42fb42633b35bf8955", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/epagogy/actions/runs/26809394317" }, { "r": "4.5.3", "os": "mac", "version": "1.0.0", "date": "2026-06-02T09:07:01.000Z", "arch": "x86_64", "commit": "733303866ecba86ab83fdbd7ef3e7b8d2a24bf1f", "fileid": "4aa3150abd628d34afe53941b38bbe4359e2b3dc691f356ddef2f80d376f78e6", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/epagogy/actions/runs/26809394317" }, { "r": "4.6.0", "os": "mac", "version": "1.0.0", "date": "2026-06-02T09:03:41.000Z", "arch": "aarch64", "commit": "733303866ecba86ab83fdbd7ef3e7b8d2a24bf1f", "fileid": "ab876e414ab355d243e61cde33d11142a92036110d283c41bc0810fc2bcf3d1b", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/epagogy/actions/runs/26809394317" }, { "r": "4.6.0", "os": "mac", "version": "1.0.0", "date": "2026-06-02T09:04:44.000Z", "arch": "x86_64", "commit": "733303866ecba86ab83fdbd7ef3e7b8d2a24bf1f", "fileid": "2391d2e161d3629c71b58068583dd17764b2e3c56cc31436b70c91c834f2a17b", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/epagogy/actions/runs/26809394317" }, { "r": "4.6.0", "os": "wasm", "version": "1.0.0", "date": "2026-06-02T09:04:45.000Z", "arch": "emscripten", "commit": "733303866ecba86ab83fdbd7ef3e7b8d2a24bf1f", "fileid": "a0de9123f80b23d70a8d805e226493551da836ce8cffe2399e14e032cf3e96ec", "status": "success", "buildurl": "https://github.com/r-universe/epagogy/actions/runs/26809394317" }, { "r": "4.7.0", "os": "win", "version": "1.0.0", "date": "2026-06-02T09:03:40.000Z", "arch": "x86_64", "commit": "733303866ecba86ab83fdbd7ef3e7b8d2a24bf1f", "fileid": "98e94ecd5cf03c86be929b8ab6669ac41bb436991499a7c2e29011a57326eaae", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/epagogy/actions/runs/26809394317" }, { "r": "4.5.3", "os": "win", "version": "1.0.0", "date": "2026-06-02T09:03:02.000Z", "arch": "x86_64", "commit": "733303866ecba86ab83fdbd7ef3e7b8d2a24bf1f", "fileid": "82c8206dfed32f126c122734f00b2bf4dfdf753720dcadeeae2db08e9fdd9e57", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/epagogy/actions/runs/26809394317" }, { "r": "4.6.0", "os": "win", "version": "1.0.0", "date": "2026-06-02T09:03:20.000Z", "arch": "x86_64", "commit": "733303866ecba86ab83fdbd7ef3e7b8d2a24bf1f", "fileid": "240ede8e5d8c97d90f63a6354bfb51b0c15f6e3116ce3df2773eb8f23e603f42", "status": "success", "check": "WARNING", "buildurl": "https://github.com/r-universe/epagogy/actions/runs/26809394317" } ] }