{ "_id": "6af714bdb90b31e79afd8170", "Package": "PsyML", "Type": "Package", "Title": "Machine Learning Workflows for Supervised, Unsupervised, and\nCausal Analysis", "Version": "2.4.2.9000", "Date": "2026-10-25", "Authors@R": "c(\nperson(\"Jose\", \"Ventura-Leon\",\nemail = \"jventuraleon@gmail.com\",\nrole = c(\"aut\", \"cre\"),\ncomment = c(ORCID = \"0000-0003-2996-4244\"))\n)", "Description": "Provides single-function pipelines for applied machine\nlearning with tabular data, as commonly found in psychological,\nbehavioral, and health research. The supervised pipeline,\nsupervised_ml(), performs exploratory checks, preprocessing,\ntraining of several models with cross-validation,\nhyperparameter tuning, test-set evaluation, threshold\noptimization, calibration, fairness analysis, decision curve\nanalysis, and model interpretation with permutation importance\nand Shapley values. The unsupervised pipeline,\nunsupervised_ml(), covers k-means, hierarchical, DBSCAN,\nGaussian mixture, and latent class clustering with selection of\nthe number of clusters, dimensionality reduction (PCA, t-SNE,\nUMAP), and anomaly detection (isolation forest, local outlier\nfactor, Mahalanobis distance). The causal pipeline,\ncausal_ml(), estimates treatment effects with propensity\nscores, meta-learners, double machine learning, causal forests,\nand targeted maximum likelihood estimation. Also includes\nlearning-curve based sample size estimation, block and\ndiversity-based data splitting, and export of results to text\nand JSON.", "License": "MIT + file LICENSE", "URL": "https://github.com/jventural/PsyML", "BugReports": "https://github.com/jventural/PsyML/issues", "Encoding": "UTF-8", "Roxygen": "list(markdown = TRUE)", "RoxygenNote": "7.3.2", "VignetteBuilder": "knitr", "Config/testthat/edition": "3", "Config/pak/sysreqs": "cmake make libicu-dev libuv1-dev", "Repository": "https://jventural.r-universe.dev", "Date/Publication": "2026-10-29 07:45:50 UTC", "RemoteUrl": "https://github.com/jventural/psyml", "RemoteRef": "HEAD", "RemoteSha": "992d6b7852c38e65ae43abfb0364557778258bcc", "NeedsCompilation": "no", "Packaged": { "Date": "2026-11-13 13:34:45 UTC", "User": "root" }, "Author": "Jose Ventura-Leon [aut, cre] (ORCID:\n)", "Maintainer": "Jose Ventura-Leon ", "_user": "jventural", "_type": "src", "_file": "PsyML_2.4.2.9000.tar.gz", "_fileid": "https://r2.ropensci.org/06b13234f572a7c03ae734e689ab9358b3835519858d5b66a768c4f213df52c9", "_filesize": 971395, "_sha256": "06b13234f572a7c03ae734e689ab9358b3835519858d5b66a768c4f213df52c9", "_expires": "2027-02-21T13:46:35.000Z", "_created": "2026-11-13T13:34:45.000Z", "_published": "2026-11-13T13:46:37.420Z", "_upstream": "https://github.com/jventural/psyml", "_status": "success", "_maintainer": { "name": "Jose Ventura-Leon", "email": "jventuraleon@gmail.com", "login": "jventural", "description": "", "uuid": 60574394, "orcid": "0000-0003-2996-4244" }, "_jobs": [ { "job": 131917520708, "time": 221, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "14042098194" }, { "job": 131917520662, "time": 229, "config": "linux-release-x86_64", "r": "4.6.2", "check": "OK", "artifact": "14043162112" }, { "job": 131917520681, "time": 138, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "14042538900" }, { "job": 131917520567, "time": 151, "config": "macos-release-arm64", "r": "4.6.2", "check": "OK", "artifact": "14043712732" }, { "job": 131915044780, "time": 296, "config": "source", "r": "4.6.2", "check": "OK", "artifact": "14043900915" }, { "job": 131917520670, "time": 158, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "14043121827" }, { "job": 131917520704, "time": 314, "config": "windows-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "14042193480" }, { "job": 131917520879, "time": 311, "config": "windows-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "14042378174" }, { "job": 131917520719, "time": 293, "config": "windows-release-x86_64", "r": "4.6.2", "check": "OK", "artifact": "14042887255" } ], "_buildurl": "https://github.com/r-universe/jventural/actions/runs/43434166357", "_commit": { "id": "992d6b7852c38e65ae43abfb0364557778258bcc", "author": "jventural ", "committer": "jventural ", "message": "Fix stratification of rare classes and balance_method = \"down\"\n\n- Classification splits (prep_split, setup_cv, nested CV, RFE folds) now call\n rsample with pool = 0. With the default pool = 0.1, rsample merged a class\n holding less than 10% of the data into another stratum, so rare outcomes\n were not stratified and the number of positives varied across partitions.\n- balance_method = \"down\" passed over_ratio to themis::step_downsample(),\n which expects under_ratio, so every model failed.\n- Version 2.4.2.9000 (development; 2.4.2 is under CRAN review).\n", "time": 1793259950 }, "_distro": "resolute", "_host": "GitHub-Actions", "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 4.1.0", "role": "Depends" }, { "package": "dials", "role": "Imports" }, { "package": "dplyr", "role": "Imports" }, { "package": "ggplot2", "role": "Imports" }, { "package": "grDevices", "role": "Imports" }, { "package": "graphics", "role": "Imports" }, { "package": "hardhat", "role": "Imports" }, { "package": "jsonlite", "role": "Imports" }, { "package": "nnet", "role": "Imports" }, { "package": "parallel", "role": "Imports" }, { "package": "parsnip", "role": "Imports" }, { "package": "pROC", "role": "Imports" }, { "package": "ranger", "role": "Imports" }, { "package": "recipes", "role": "Imports" }, { "package": "rlang", "role": "Imports" }, { "package": "rsample", "role": "Imports" }, { "package": "stats", "role": "Imports" }, { "package": "tibble", "role": "Imports" }, { "package": "tidyr", "role": "Imports" }, { "package": "tidyselect", "role": "Imports" }, { "package": "tune", "role": "Imports" }, { "package": "utils", "role": "Imports" }, { "package": "workflows", "role": "Imports" }, { "package": "xgboost", "role": "Imports" }, { "package": "yardstick", "role": "Imports" }, { "package": "Boruta", "role": "Suggests" }, { "package": "bslib", "role": "Suggests" }, { "package": "cluster", "role": "Suggests" }, { "package": "cobalt", "role": "Suggests" }, { "package": "commonmark", "role": "Suggests" }, { "package": "dbscan", "role": "Suggests" }, { "package": "doParallel", "role": "Suggests" }, { "package": "DoubleML", "role": "Suggests" }, { "package": "DT", "role": "Suggests" }, { "package": "e1071", "role": "Suggests" }, { "package": "finetune", "role": "Suggests" }, { "package": "flextable", "role": "Suggests" }, { "package": "foreach", "role": "Suggests" }, { "package": "ggdendro", "role": "Suggests" }, { "package": "glmnet", "role": "Suggests" }, { "package": "grf", "role": "Suggests" }, { "package": "htmltools", "role": "Suggests" }, { "package": "httr", "role": "Suggests" }, { "package": "httr2", "role": "Suggests" }, { "package": "isotree", "role": "Suggests" }, { "package": "kernelshap", "role": "Suggests" }, { "package": "kernlab", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "MatchIt", "role": "Suggests" }, { "package": "mclust", "role": "Suggests" }, { "package": "mlr3", "role": "Suggests" }, { "package": "mlr3learners", "role": "Suggests" }, { "package": "officer", "role": "Suggests" }, { "package": "patchwork", "role": "Suggests" }, { "package": "poLCA", "role": "Suggests" }, { "package": "readxl", "role": "Suggests" }, { "package": "reticulate", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "rpart", "role": "Suggests" }, { "package": "Rtsne", "role": "Suggests" }, { "package": "shapviz", "role": "Suggests" }, { "package": "shiny", "role": "Suggests" }, { "package": "shinydashboard", "role": "Suggests" }, { "package": "SuperLearner", "role": "Suggests" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" }, { "package": "themis", "role": "Suggests" }, { "package": "tmle", "role": "Suggests" }, { "package": "umap", "role": "Suggests" }, { "package": "VIM", "role": "Suggests" } ], "_owner": "jventural", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2026-44", "n": 2 } ], "_tags": [], "_stars": 0, "_contributors": [ { "user": "jventural", "count": 2, "uuid": 60574394 } ], "_userbio": { "uuid": 60574394, "type": "user", "name": "José Ventura-León", "followers": 3 }, "_downloads": { "count": 0, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/PsyML" }, "_devurl": "https://github.com/jventural/psyml", "_searchresults": 0, "_rbuild": "4.6.2", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/manual.pdf", "extra/NEWS.html", "extra/NEWS.txt", "extra/PsyML.html", "extra/readme.html", "extra/readme.md", "LICENSE" ], "_homeurl": "https://github.com/jventural/psyml", "_realowner": "jventural", "_cranurl": true, "_releases": [ { "version": "2.4.2", "date": "2026-11-12" } ], "_exports": [ "advanced_residual_analysis", "analyze_dca", "analyze_fairness", "analyze_interactions_splines", "apply_custom_features", "apply_threshold", "auto_feature_engineering", "block_split", "calculate_shap", "calibrate_probabilities", "causal_ml", "cluster_profile", "compare_models", "correct_fairness_threshold", "cv_feature_selection", "define_models", "detect_data_leakage", "diversity_split", "eda_basic", "eda_categorical", "eda_categorical_basic", "eda_correlation", "eda_correlation_basic", "eda_leakage", "eda_missing", "eda_normality", "eda_numeric", "eda_numeric_basic", "eda_outliers", "eda_structure", "eda_summary", "eda_target_classification", "eda_target_regression", "eda_vif", "estimate_n", "estimate_n_plateau", "eval_calibration", "eval_confusion", "eval_metrics", "eval_pred_vs_obs", "eval_predictions", "eval_residuals", "eval_roc", "evaluate_model", "explain_with_ai", "export_verbose_json", "export_verbose_txt", "fit_models_cv", "generate_all_plots", "generate_report_from_json", "generate_report_with_ai", "get_figures_catalog", "get_importance", "interpret_model", "launch_report_generator", "launch_supervisedml_app", "ml_sample_size", "optimize_threshold", "plot_all", "plot_calibration_curve", "plot_distribution", "plot_importance", "plot_learning_curve", "plot_metrics_profile", "plot_residual_diagnostics", "plot_shap_bar", "plot_shap_dependence", "plot_shap_summary", "plot_threshold_optimization", "plot_tuning", "prep_feature_selection", "prep_recipe", "prep_split", "prep_target", "preprocess_data", "print_figures_catalog", "resample_fairness", "run_nested_cv", "save_all_plots", "save_unsupervised_plots", "setup_cv", "supervised_ml", "supervised_ml_capture", "supervised_ml_export", "train_models", "tune_best_model", "unsupervised_ml" ], "_help": [ { "page": "advanced_residual_analysis", "title": "Advanced Residual Analysis", "concept": [ "supervised learning" ], "topics": [ "advanced_residual_analysis" ] }, { "page": "analyze_dca", "title": "Clinical Utility Analysis (Decision Curve Analysis)", "concept": [ "supervised learning" ], "topics": [ "analyze_dca" ] }, { "page": "analyze_fairness", "title": "Fairness Analysis of a Classification Model", "concept": [ "supervised learning" ], "topics": [ "analyze_fairness" ] }, { "page": "analyze_interactions_splines", "title": "Analyze Interactions and Nonlinear Effects", "concept": [ "supervised learning" ], "topics": [ "analyze_interactions_splines" ] }, { "page": "apply_custom_features", "title": "Domain Feature Engineering", "concept": [ "supervised learning" ], "topics": [ "apply_custom_features" ] }, { "page": "apply_threshold", "title": "Apply a Classification Threshold", "concept": [ "supervised learning" ], "topics": [ "apply_threshold" ] }, { "page": "auto_feature_engineering", "title": "Automatic Feature Engineering", "concept": [ "supervised learning" ], "topics": [ "auto_feature_engineering" ] }, { "page": "block_split", "title": "Block-Based Train/Test Split for Enhanced Generalization", "concept": [ "study design" ], "topics": [ "block_split" ] }, { "page": "calculate_shap", "title": "SHAP Values of a Fitted Workflow", "concept": [ "supervised learning" ], "topics": [ "calculate_shap" ] }, { "page": "calibrate_probabilities", "title": "Calibrate Predicted Probabilities", "concept": [ "supervised learning" ], "topics": [ "calibrate_probabilities" ] }, { "page": "causal_ml", "title": "Automated Causal Inference Pipeline", "concept": [ "causal inference" ], "topics": [ "causal_ml" ] }, { "page": "cluster_profile", "title": "Cluster Profiles", "concept": [ "unsupervised learning" ], "topics": [ "cluster_profile" ] }, { "page": "compare_models", "title": "Compare Cross-Validated Models", "concept": [ "supervised learning" ], "topics": [ "compare_models" ] }, { "page": "correct_fairness_threshold", "title": "Fairness Correction with Group-Specific Thresholds", "concept": [ "supervised learning" ], "topics": [ "correct_fairness_threshold" ] }, { "page": "cv_feature_selection", "title": "Feature Selection with Cross-Validation", "concept": [ "supervised learning" ], "topics": [ "cv_feature_selection" ] }, { "page": "define_models", "title": "Define Model Specifications", "concept": [ "supervised learning" ], "topics": [ "define_models" ] }, { "page": "detect_data_leakage", "title": "Detect Possible Data Leakage (Post-Model Checks)", "concept": [ "supervised learning" ], "topics": [ "detect_data_leakage" ] }, { "page": "diversity_split", "title": "Diversity-Based Train/Test Split for True Generalization", "concept": [ "study design" ], "topics": [ "diversity_split" ] }, { "page": "eda_basic", "title": "Basic Exploratory Data Analysis", "concept": [ "exploratory data analysis" ], "topics": [ "eda_basic" ] }, { "page": "eda_categorical", "title": "Categorical Variable Analysis", "concept": [ "exploratory data analysis" ], "topics": [ "eda_categorical" ] }, { "page": "eda_categorical_basic", "title": "Basic Categorical Variable Analysis", "concept": [ "exploratory data analysis" ], "topics": [ "eda_categorical_basic" ] }, { "page": "eda_correlation", "title": "Correlation Matrix", "concept": [ "exploratory data analysis" ], "topics": [ "eda_correlation" ] }, { "page": "eda_correlation_basic", "title": "Basic Correlation Matrix", "concept": [ "exploratory data analysis" ], "topics": [ "eda_correlation_basic" ] }, { "page": "eda_leakage", "title": "Basic Data Leakage Check", "concept": [ "exploratory data analysis" ], "topics": [ "eda_leakage" ] }, { "page": "eda_missing", "title": "Missing Value Analysis", "concept": [ "exploratory data analysis" ], "topics": [ "eda_missing" ] }, { "page": "eda_normality", "title": "Normality Test of the Target", "concept": [ "exploratory data analysis" ], "topics": [ "eda_normality" ] }, { "page": "eda_numeric", "title": "Numeric Variable Analysis", "concept": [ "exploratory data analysis" ], "topics": [ "eda_numeric" ] }, { "page": "eda_numeric_basic", "title": "Basic Numeric Variable Analysis", "concept": [ "exploratory data analysis" ], "topics": [ "eda_numeric_basic" ] }, { "page": "eda_outliers", "title": "Outlier Detection", "concept": [ "exploratory data analysis" ], "topics": [ "eda_outliers" ] }, { "page": "eda_structure", "title": "Data Structure", "concept": [ "exploratory data analysis" ], "topics": [ "eda_structure" ] }, { "page": "eda_summary", "title": "Exploratory Data Analysis", "concept": [ "exploratory data analysis" ], "topics": [ "eda_summary" ] }, { "page": "eda_target_classification", "title": "Target Distribution for Classification", "concept": [ "exploratory data analysis" ], "topics": [ "eda_target_classification" ] }, { "page": "eda_target_regression", "title": "Target Distribution for Regression", "concept": [ "exploratory data analysis" ], "topics": [ "eda_target_regression" ] }, { "page": "eda_vif", "title": "Variance Inflation Factor Analysis", "concept": [ "exploratory data analysis" ], "topics": [ "eda_vif" ] }, { "page": "estimate_n", "title": "Estimate N for a Target Metric Using the Curve Fit", "concept": [ "study design" ], "topics": [ "estimate_n" ] }, { "page": "estimate_n_plateau", "title": "Estimate N to Reach the Plateau (Near Maximum Performance)", "concept": [ "study design" ], "topics": [ "estimate_n_plateau" ] }, { "page": "eval_calibration", "title": "Calibration Analysis by Probability Bins", "concept": [ "supervised learning" ], "topics": [ "eval_calibration" ] }, { "page": "eval_confusion", "title": "Compute the Confusion Matrix", "concept": [ "supervised learning" ], "topics": [ "eval_confusion" ] }, { "page": "eval_metrics", "title": "Compute Performance Metrics", "concept": [ "supervised learning" ], "topics": [ "eval_metrics" ] }, { "page": "eval_pred_vs_obs", "title": "Compare Predicted and Observed Values", "concept": [ "supervised learning" ], "topics": [ "eval_pred_vs_obs" ] }, { "page": "eval_predictions", "title": "Generate Predictions on a Data Set", "concept": [ "supervised learning" ], "topics": [ "eval_predictions" ] }, { "page": "eval_residuals", "title": "Residual Analysis", "concept": [ "supervised learning" ], "topics": [ "eval_residuals" ] }, { "page": "eval_roc", "title": "Compute the ROC Curve", "concept": [ "supervised learning" ], "topics": [ "eval_roc" ] }, { "page": "evaluate_model", "title": "Evaluate the Final Model on the Test Set", "concept": [ "supervised learning" ], "topics": [ "evaluate_model" ] }, { "page": "explain_with_ai", "title": "Interpret Results of supervised_ml() with a Large Language Model", "concept": [ "reporting and export" ], "topics": [ "explain_with_ai" ] }, { "page": "export_verbose_json", "title": "Export the Results of an Analysis as a JSON File", "concept": [ "reporting and export" ], "topics": [ "export_verbose_json" ] }, { "page": "export_verbose_txt", "title": "Export the Console Output of an Analysis as a TXT File", "concept": [ "reporting and export" ], "topics": [ "export_verbose_txt" ] }, { "page": "fit_models_cv", "title": "Fit Models with Cross-Validation", "concept": [ "supervised learning" ], "topics": [ "fit_models_cv" ] }, { "page": "generate_all_plots", "title": "Generate All Plots of a supervisedml Object", "concept": [ "supervised learning" ], "topics": [ "generate_all_plots" ] }, { "page": "generate_report_from_json", "title": "Generate a Report from an Exported JSON File", "concept": [ "reporting and export" ], "topics": [ "generate_report_from_json" ] }, { "page": "generate_report_with_ai", "title": "Generate a Scientific Report with AI", "concept": [ "reporting and export" ], "topics": [ "generate_report_with_ai" ] }, { "page": "get_figures_catalog", "title": "Get the Catalog of Figures", "concept": [ "supervised learning" ], "topics": [ "get_figures_catalog" ] }, { "page": "get_importance", "title": "Variable Importance of a Fitted Workflow", "concept": [ "supervised learning" ], "topics": [ "get_importance" ] }, { "page": "interpret_model", "title": "Model Interpretability Analysis", "concept": [ "supervised learning" ], "topics": [ "interpret_model" ] }, { "page": "launch_report_generator", "title": "Launch the Shiny Report Generator", "concept": [ "reporting and export" ], "topics": [ "launch_report_generator" ] }, { "page": "launch_supervisedml_app", "title": "Launch the Integrated PsyML Shiny App", "concept": [ "reporting and export" ], "topics": [ "launch_supervisedml_app" ] }, { "page": "ml_sample_size", "title": "Sample Size Estimation for Machine Learning via Monte Carlo Simulation", "concept": [ "study design" ], "topics": [ "ml_sample_size" ] }, { "page": "optimize_threshold", "title": "Optimize the Classification Threshold", "concept": [ "supervised learning" ], "topics": [ "optimize_threshold" ] }, { "page": "plot_all", "title": "Plot a Summary Panel of All Results", "concept": [ "supervised learning" ], "topics": [ "plot_all", "plot_all.supervisedml" ] }, { "page": "plot_all.ml_sample_size", "title": "Plot All Graphs for Sample Size Results", "concept": [ "study design" ], "topics": [ "plot_all.ml_sample_size" ] }, { "page": "plot_calibration_curve", "title": "Plot the Calibration Curve", "concept": [ "supervised learning" ], "topics": [ "plot_calibration_curve" ] }, { "page": "plot_distribution", "title": "Plot the Metric Distribution by Sample Size", "concept": [ "study design" ], "topics": [ "plot_distribution" ] }, { "page": "plot_importance", "title": "Plot Variable Importance", "concept": [ "supervised learning" ], "topics": [ "plot_importance" ] }, { "page": "plot_learning_curve", "title": "Plot the Learning Curve of a Sample Size Analysis", "concept": [ "study design" ], "topics": [ "plot_learning_curve" ] }, { "page": "plot_metrics_profile", "title": "Plot the Profile of Performance Metrics", "concept": [ "supervised learning" ], "topics": [ "plot_metrics_profile" ] }, { "page": "plot_residual_diagnostics", "title": "Residual Diagnostic Plots", "concept": [ "supervised learning" ], "topics": [ "plot_residual_diagnostics" ] }, { "page": "plot_shap_bar", "title": "Plot SHAP Feature Importance", "concept": [ "supervised learning" ], "topics": [ "plot_shap_bar" ] }, { "page": "plot_shap_dependence", "title": "Plot SHAP Dependence for One Variable", "concept": [ "supervised learning" ], "topics": [ "plot_shap_dependence" ] }, { "page": "plot_shap_summary", "title": "Plot a SHAP Summary (Beeswarm)", "concept": [ "supervised learning" ], "topics": [ "plot_shap_summary" ] }, { "page": "plot_threshold_optimization", "title": "Plot the Threshold Optimization", "concept": [ "supervised learning" ], "topics": [ "plot_threshold_optimization" ] }, { "page": "plot_tuning", "title": "Plot the Hyperparameter Tuning Results", "concept": [ "supervised learning" ], "topics": [ "plot_tuning" ] }, { "page": "plot.causalml", "title": "Plot a causalml Object", "concept": [ "causal inference" ], "topics": [ "plot.causalml" ] }, { "page": "plot.supervisedml", "title": "Plot a supervisedml Object", "concept": [ "supervised learning" ], "topics": [ "plot.supervisedml" ] }, { "page": "plot.unsupervisedml", "title": "Plot an unsupervisedml Object", "concept": [ "unsupervised learning" ], "topics": [ "plot.unsupervisedml" ] }, { "page": "predict.causalml", "title": "Predict Conditional Average Treatment Effects from a causalml Object", "concept": [ "causal inference" ], "topics": [ "predict.causalml" ] }, { "page": "predict.supervisedml", "title": "Predict with a supervisedml Model", "concept": [ "supervised learning" ], "topics": [ "predict.supervisedml" ] }, { "page": "predict.unsupervisedml", "title": "Assign New Observations to Clusters", "concept": [ "unsupervised learning" ], "topics": [ "predict.unsupervisedml" ] }, { "page": "prep_feature_selection", "title": "Feature Selection with Boruta", "concept": [ "supervised learning" ], "topics": [ "prep_feature_selection" ] }, { "page": "prep_recipe", "title": "Create the Preprocessing Recipe", "concept": [ "supervised learning" ], "topics": [ "prep_recipe" ] }, { "page": "prep_split", "title": "Train/Test Split", "concept": [ "supervised learning" ], "topics": [ "prep_split" ] }, { "page": "prep_target", "title": "Prepare the Target Variable", "concept": [ "supervised learning" ], "topics": [ "prep_target" ] }, { "page": "preprocess_data", "title": "Preprocessing Pipeline", "concept": [ "supervised learning" ], "topics": [ "preprocess_data" ] }, { "page": "print_figures_catalog", "title": "Print the Catalog of Figures", "concept": [ "supervised learning" ], "topics": [ "print_figures_catalog" ] }, { "page": "print.block_split", "title": "Print a Block-Based Split", "topics": [ "print.block_split" ] }, { "page": "print.causalml", "title": "Print a causalml Object", "concept": [ "causal inference" ], "topics": [ "print.causalml" ] }, { "page": "print.diversity_split", "title": "Print a Diversity-Based Split", "topics": [ "print.diversity_split" ] }, { "page": "print.ml_sample_size", "title": "Print ML Sample Size Results", "topics": [ "print.ml_sample_size" ] }, { "page": "print.supervisedml", "title": "Print a supervisedml Object", "concept": [ "supervised learning" ], "topics": [ "print.supervisedml" ] }, { "page": "print.unsupervisedml", "title": "Print an unsupervisedml Object", "concept": [ "unsupervised learning" ], "topics": [ "print.unsupervisedml" ] }, { "page": "resample_fairness", "title": "Fairness-Oriented Stratified Resampling", "concept": [ "supervised learning" ], "topics": [ "resample_fairness" ] }, { "page": "run_nested_cv", "title": "Nested Cross-Validation", "concept": [ "supervised learning" ], "topics": [ "run_nested_cv" ] }, { "page": "save_all_plots", "title": "Save All Plots to PNG Files", "concept": [ "supervised learning" ], "topics": [ "save_all_plots" ] }, { "page": "save_unsupervised_plots", "title": "Save All Figures of an Unsupervised Analysis", "concept": [ "unsupervised learning" ], "topics": [ "save_unsupervised_plots" ] }, { "page": "setup_cv", "title": "Set Up Cross-Validation Folds", "concept": [ "supervised learning" ], "topics": [ "setup_cv" ] }, { "page": "summary.causalml", "title": "Summarize a causalml Object", "concept": [ "causal inference" ], "topics": [ "summary.causalml" ] }, { "page": "summary.supervisedml", "title": "Summarize a supervisedml Object", "concept": [ "supervised learning" ], "topics": [ "summary.supervisedml" ] }, { "page": "summary.unsupervisedml", "title": "Summarize an unsupervisedml Object", "concept": [ "unsupervised learning" ], "topics": [ "summary.unsupervisedml" ] }, { "page": "supervised_ml", "title": "Supervised Machine Learning for Classification and Regression", "concept": [ "supervised learning" ], "topics": [ "supervised_ml" ] }, { "page": "supervised_ml_capture", "title": "Run supervised_ml() and Capture Its Console Output", "concept": [ "reporting and export" ], "topics": [ "supervised_ml_capture" ] }, { "page": "supervised_ml_export", "title": "Run and Export a Complete Analysis", "concept": [ "reporting and export" ], "topics": [ "supervised_ml_export" ] }, { "page": "train_models", "title": "Train and Compare Models with Cross-Validation", "concept": [ "supervised learning" ], "topics": [ "train_models" ] }, { "page": "tune_best_model", "title": "Tune the Hyperparameters of the Best Model", "concept": [ "supervised learning" ], "topics": [ "tune_best_model" ] }, { "page": "unsupervised_ml", "title": "Automated Unsupervised Learning Pipeline", "concept": [ "unsupervised learning" ], "topics": [ "unsupervised_ml" ] } ], "_readme": "https://github.com/jventural/psyml/raw/HEAD/README.md", "_rundeps": [ "base64enc", "bslib", "cachem", "class", "cli", "clock", "codetools", "cpp11", "data.table", "diagram", "dials", "DiceDesign", "digest", "dplyr", "evaluate", "farver", "fastmap", "fontawesome", "fs", "furrr", "future", "future.apply", "GauPro", "generics", "ggplot2", "globals", "glue", "gower", "gtable", "hardhat", "highr", "htmltools", "ipred", "isoband", "jquerylib", "jsonlite", "KernSmooth", "knitr", "labeling", "lattice", "lava", "lbfgs", "lifecycle", "listenv", "lubridate", "magrittr", "MASS", "Matrix", "memoise", "mime", "mixopt", "modelenv", "nnet", "numDeriv", "parallelly", "parsnip", "pillar", "pkgconfig", "prettyunits", "pROC", "prodlim", "progressr", "purrr", "R6", "ranger", "rappdirs", "RColorBrewer", "Rcpp", "RcppArmadillo", "RcppEigen", "recipes", "rlang", "rmarkdown", "rpart", "rsample", "S7", "sass", "scales", "sfd", "shape", "slider", "sparsevctrs", "splitfngr", "SQUAREM", "stringi", "stringr", "survival", "tailor", "tibble", "tidyr", "tidyselect", "timechange", "timeDate", "tinytex", "tune", "tzdb", "utf8", "vctrs", "viridisLite", "warp", "withr", "workflows", "xfun", "xgboost", "yaml", "yardstick" ], "_vignettes": [ { "source": "sample-size-estimation.Rmd", "filename": "sample-size-estimation.html", "title": "Sample Size Estimation for Machine Learning", "author": "Jose Ventura-Leon", "engine": "knitr::rmarkdown", "headings": [ "Introduction", "Quick Start", "Core Concepts", "The Learning Curve", "Power-Law Model", "Decision Criteria", "Example 1: Basic Classification", "Interpreting the Output", "Key Output Components", "Visualizing the Learning Curve", "Example 2: Choosing the Number of Repetitions (R)", "Example 3: Small Datasets (N < 1000)", "Interpreting Multiple Partition Results", "Example 4: Bootstrap Confidence Intervals", "Example 5: Comparing Multiple Models", "Example 6: Checking Fit Quality Before Extrapolation", "Example 7: Extrapolation Functions", "Estimating N for a Specific Target", "Finding the Plateau", "Example 8: Regression Tasks", "Best Practices", "1. Start with Exploration", "2. Always Check Diagnostics", "3. Report Uncertainty", "4. Consider Hyperparameter Tuning", "Troubleshooting", "Curve Fit Fails", "High Variability in n*", "Target Seems Unachievable", "Summary Table", "References", "Session Info" ], "created": "2026-10-27 17:47:20", "modified": "2026-10-27 17:47:20", "commits": 1 }, { "source": "three-approaches.Rmd", "filename": "three-approaches.html", "title": "Three Approaches: Supervised, Unsupervised, and Causal", "author": "Jose Ventura-Leon", "engine": "knitr::rmarkdown", "headings": [ "1. Supervised learning: predicting a known outcome", "2. Unsupervised learning: finding groups without an outcome", "3. Causal inference: estimating the effect of a treatment", "Tools shared by the three approaches" ], "created": "2026-10-27 17:47:20", "modified": "2026-10-27 17:47:20", "commits": 1 } ], "_score": 4, "_indexed": true, "_nocasepkg": "psyml", "_universes": [ "jventural" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "2.4.2.9000", "date": "2026-11-13T13:37:58.000Z", "distro": "resolute", "commit": "992d6b7852c38e65ae43abfb0364557778258bcc", "fileid": "https://r2.ropensci.org/8c491e7f1cb6b4b20cfb6d675916a9689dbd6d32c42572740f986cfa9bd59de1", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/jventural/actions/runs/43434166357" }, { "r": "4.6.2", "os": "linux", "version": "2.4.2.9000", "date": "2026-11-13T13:38:10.000Z", "distro": "resolute", "commit": "992d6b7852c38e65ae43abfb0364557778258bcc", "fileid": "https://r2.ropensci.org/86ae59e3d5f213ae67ebd6e06815e929b659bbcaf02cb908e37b3e69c8d579b7", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/jventural/actions/runs/43434166357" }, { "r": "4.5.3", "os": "mac", "version": "2.4.2.9000", "date": "2026-11-13T13:45:02.000Z", "commit": "992d6b7852c38e65ae43abfb0364557778258bcc", "fileid": "https://r2.ropensci.org/65d9912db92b40b95004fbcda0e7c4ab58c39240cc7203fc7826827087f3f3f5", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/jventural/actions/runs/43434166357" }, { "r": "4.6.2", "os": "mac", "version": "2.4.2.9000", "date": "2026-11-13T13:44:32.000Z", "commit": "992d6b7852c38e65ae43abfb0364557778258bcc", "fileid": "https://r2.ropensci.org/6359eae69e4174d8b54ba401d811502f5583bb9c140d2d275b7b3b0e813ae9ee", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/jventural/actions/runs/43434166357" }, { "r": "4.6.0", "os": "wasm", "version": "2.4.2.9000", "date": "2026-11-13T13:37:51.000Z", "commit": "992d6b7852c38e65ae43abfb0364557778258bcc", "fileid": "https://r2.ropensci.org/6d95e46f34656ca6ffec32cde609000a1bd54a553133bae45c4e873d464d26a0", "status": "success", "buildurl": "https://github.com/r-universe/jventural/actions/runs/43434166357" }, { "r": "4.7.0", "os": "win", "version": "2.4.2.9000", "date": "2026-11-13T13:38:16.000Z", "commit": "992d6b7852c38e65ae43abfb0364557778258bcc", "fileid": "https://r2.ropensci.org/77443840ec0fbbef83e9619d9ef972bd2b86e308ebb6a0c2e3a8b528defaff81", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/jventural/actions/runs/43434166357" }, { "r": "4.5.3", "os": "win", "version": "2.4.2.9000", "date": "2026-11-13T13:38:11.000Z", "commit": "992d6b7852c38e65ae43abfb0364557778258bcc", "fileid": "https://r2.ropensci.org/5ea6f0338d26c8fb2638455bb77e6ded9868bc1714d2fc42edbdc0a51ca4bc54", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/jventural/actions/runs/43434166357" }, { "r": "4.6.2", "os": "win", "version": "2.4.2.9000", "date": "2026-11-13T13:37:53.000Z", "commit": "992d6b7852c38e65ae43abfb0364557778258bcc", "fileid": "https://r2.ropensci.org/01c54e601cf1bf22f7d6089c85bbcc6160667df191c2a6f2f50f19c1337a9eb2", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/jventural/actions/runs/43434166357" } ] }