Package: ml 1.0.0

Simon Roth

ml: Supervised Learning with Mandatory Splits and Seeds

Implements the split-fit-evaluate-assess workflow from Hastie, Tibshirani, and Friedman (2009, ISBN:978-0-387-84857-0) "The Elements of Statistical Learning", Chapter 7. Provides three-way data splitting with automatic stratification, mandatory seeds for reproducibility, automatic data type handling, and 10 algorithms out of the box. Uses 'Rust' backend for cross-language deterministic splitting. Designed for tabular supervised learning with minimal ceremony. Polyglot parity with the 'Python' 'mlw' package on 'PyPI'.

Authors:Simon Roth [aut, cre]

ml_1.0.0.tar.gz
ml_1.0.0.zip(r-4.7-x86_64)ml_1.0.0.zip(r-4.7-arm64)ml_1.0.0.zip(r-4.6-x86_64)ml_1.0.0.zip(r-4.6-arm64)ml_1.0.0.zip(r-4.5-x86_64)
ml_1.0.0.tgz(r-4.6-x86_64)ml_1.0.0.tgz(r-4.6-arm64)ml_1.0.0.tgz(r-4.5-x86_64)ml_1.0.0.tgz(r-4.5-arm64)
ml_1.0.0.tar.gz(r-4.7-arm64)ml_1.0.0.tar.gz(r-4.7-x86_64)ml_1.0.0.tar.gz(r-4.6-arm64)ml_1.0.0.tar.gz(r-4.6-x86_64)
ml_1.0.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
ml/json (API)

# Install 'ml' in R:

install.packages('ml', repos = c('https://epagogy.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/epagogy/ml/issues

On CRAN:

5.13 score 9 stars 1 scripts 326 downloads 39 exports 3 dependencies

Last updated from:733303866e. Checks:11 WARNING, 2 OK, 2 ERROR. Indexed: yes.

Target	Result	Time
linux-devel-arm64	WARNING	198
linux-devel-x86_64	WARNING	231
source / vignettes	OK	240
linux-release-arm64	WARNING	179
linux-release-x86_64	WARNING	237
macos-release-arm64	WARNING	170
macos-release-x86_64	WARNING	441
macos-oldrel-arm64	WARNING	225
macos-oldrel-x86_64	WARNING	356
windows-devel-arm64	ERROR	398
windows-devel-x86_64	ERROR	224
windows-release-arm64	WARNING	418
windows-release-x86_64	WARNING	181
windows-oldrel-x86_64	WARNING	166
wasm-release	OK	168

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

Dependencies:cli rlang withr

Getting Started with ml

Rendered fromquickstart.Rmdusingknitr::rmarkdown

Last update: 2026-03-14
Started: 2026-03-14

Help page	Topics
The ml module — all verbs accessed via ml$verb()	ml
List available ML algorithms	ml_algorithms
Assess model on held-out test data (do once)	ml_assess
Get the best model from a leaderboard	ml_best
Calibrate predicted probabilities	ml_calibrate
Verify bitwise reproducibility for a given dataset	ml_check
Pre-flight data quality checks	ml_check_data
Compare pre-fitted models on the same data	ml_compare
Configure ml package settings	ml_config
Create k-fold cross-validation from a split	ml_cv
Create group-aware cross-validation from a split	ml_cv_group
Create temporal cross-validation from a split	ml_cv_temporal
Load a built-in dataset	ml_dataset
Detect data drift between reference and new data	ml_drift
Embed texts into numeric features	ml_embed
Learning curve analysis — do you need more data?	ml_enough
Evaluate model on validation data (iterate freely)	ml_evaluate
Explain model via feature importance	ml_explain
Fit a machine learning model	ml_fit
Detect potential data leakage	ml_leak
Load a model from disk	ml_load
Optimize decision threshold for binary classification	ml_optimize
Visual diagnostics for a fitted model	ml_plot
Predict from a fitted model (ml_predict style)	ml_predict
Predict class probabilities	ml_predict_proba
Prepare data for ML: encode, impute, and scale	ml_prepare
Profile data before modeling	ml_profile
One-call workflow: split + screen + fit + evaluate	ml_quick
Generate an HTML training report	ml_report
Save a model to disk	ml_save
Screen all algorithms on your data	ml_screen
Check if a model is past its shelf life	ml_shelf
Split data into train/valid/test partitions or cross-validation folds	ml_split
Split data with group non-overlap — no group leaks across partitions	ml_split_group
Split data chronologically — no future leakage	ml_split_temporal
Ensemble stacking	ml_stack
Tune hyperparameters via random or grid search	ml_tune
Validate model against rules and/or baseline	ml_validate
Verify provenance integrity of a model	ml_verify
Predict from a fitted model	predict.ml_model
Predict from best model in a tuning result	predict.ml_tuning_result
Print ml_cv_result	print.ml_cv_result
Print ml_drift_result	print.ml_drift_result
Print ml_embedder	print.ml_embedder
Print ml_evidence	print.ml_evidence
Print ml_explanation	print.ml_explanation
Print ml_leaderboard	print.ml_leaderboard
Print ml_metrics	print.ml_metrics
Print an ml_model	print.ml_model
Print ml_profile_result	print.ml_profile_result
Print ml_shelf_result	print.ml_shelf_result
Print an ml_split_result	print.ml_split_result
Print an ml_tuning_result	print.ml_tuning_result
Print ml_validate_result	print.ml_validate_result

Package: ml 1.0.0

ml: Supervised Learning with Mandatory Splits and Seeds

Citation

Development and contributors

Readme and manuals

Help Manual

Usage by other packages (reverse dependencies)