Machine Learning Workflows for Supervised, Unsupervised, and Causal Analysis

Documentation for package ‘PsyML’ version 2.4.2

Help Pages

-- A --

advanced_residual_analysis	Advanced Residual Analysis
analyze_dca	Clinical Utility Analysis (Decision Curve Analysis)
analyze_fairness	Fairness Analysis of a Classification Model
analyze_interactions_splines	Analyze Interactions and Nonlinear Effects
apply_custom_features	Domain Feature Engineering
apply_threshold	Apply a Classification Threshold
auto_feature_engineering	Automatic Feature Engineering

-- B --

block_split

Block-Based Train/Test Split for Enhanced Generalization

-- C --

calculate_shap	SHAP Values of a Fitted Workflow
calibrate_probabilities	Calibrate Predicted Probabilities
causal_ml	Automated Causal Inference Pipeline
cluster_profile	Cluster Profiles
compare_models	Compare Cross-Validated Models
correct_fairness_threshold	Fairness Correction with Group-Specific Thresholds
cv_feature_selection	Feature Selection with Cross-Validation

-- D --

define_models	Define Model Specifications
detect_data_leakage	Detect Possible Data Leakage (Post-Model Checks)
diversity_split	Diversity-Based Train/Test Split for True Generalization

-- E --

eda_basic	Basic Exploratory Data Analysis
eda_categorical	Categorical Variable Analysis
eda_categorical_basic	Basic Categorical Variable Analysis
eda_correlation	Correlation Matrix
eda_correlation_basic	Basic Correlation Matrix
eda_leakage	Basic Data Leakage Check
eda_missing	Missing Value Analysis
eda_normality	Normality Test of the Target
eda_numeric	Numeric Variable Analysis
eda_numeric_basic	Basic Numeric Variable Analysis
eda_outliers	Outlier Detection
eda_structure	Data Structure
eda_summary	Exploratory Data Analysis
eda_target_classification	Target Distribution for Classification
eda_target_regression	Target Distribution for Regression
eda_vif	Variance Inflation Factor Analysis
estimate_n	Estimate N for a Target Metric Using the Curve Fit
estimate_n_plateau	Estimate N to Reach the Plateau (Near Maximum Performance)
evaluate_model	Evaluate the Final Model on the Test Set
eval_calibration	Calibration Analysis by Probability Bins
eval_confusion	Compute the Confusion Matrix
eval_metrics	Compute Performance Metrics
eval_predictions	Generate Predictions on a Data Set
eval_pred_vs_obs	Compare Predicted and Observed Values
eval_residuals	Residual Analysis
eval_roc	Compute the ROC Curve
explain_with_ai	Interpret Results of supervised_ml() with a Large Language Model
export_verbose_json	Export the Results of an Analysis as a JSON File
export_verbose_txt	Export the Console Output of an Analysis as a TXT File

-- F --

fit_models_cv

Fit Models with Cross-Validation

-- G --

generate_all_plots	Generate All Plots of a supervisedml Object
generate_report_from_json	Generate a Report from an Exported JSON File
generate_report_with_ai	Generate a Scientific Report with AI
get_figures_catalog	Get the Catalog of Figures
get_importance	Variable Importance of a Fitted Workflow

-- I --

interpret_model

Model Interpretability Analysis

-- L --

launch_report_generator	Launch the Shiny Report Generator
launch_supervisedml_app	Launch the Integrated PsyML Shiny App

-- M --

ml_sample_size

Sample Size Estimation for Machine Learning via Monte Carlo Simulation

-- O --

optimize_threshold

Optimize the Classification Threshold

-- P --

plot.causalml	Plot a causalml Object
plot.supervisedml	Plot a supervisedml Object
plot.unsupervisedml	Plot an unsupervisedml Object
plot_all	Plot a Summary Panel of All Results
plot_all.ml_sample_size	Plot All Graphs for Sample Size Results
plot_all.supervisedml	Plot a Summary Panel of All Results
plot_calibration_curve	Plot the Calibration Curve
plot_distribution	Plot the Metric Distribution by Sample Size
plot_importance	Plot Variable Importance
plot_learning_curve	Plot the Learning Curve of a Sample Size Analysis
plot_metrics_profile	Plot the Profile of Performance Metrics
plot_residual_diagnostics	Residual Diagnostic Plots
plot_shap_bar	Plot SHAP Feature Importance
plot_shap_dependence	Plot SHAP Dependence for One Variable
plot_shap_summary	Plot a SHAP Summary (Beeswarm)
plot_threshold_optimization	Plot the Threshold Optimization
plot_tuning	Plot the Hyperparameter Tuning Results
predict.causalml	Predict Conditional Average Treatment Effects from a causalml Object
predict.supervisedml	Predict with a supervisedml Model
predict.unsupervisedml	Assign New Observations to Clusters
preprocess_data	Preprocessing Pipeline
prep_feature_selection	Feature Selection with Boruta
prep_recipe	Create the Preprocessing Recipe
prep_split	Train/Test Split
prep_target	Prepare the Target Variable
print.block_split	Print a Block-Based Split
print.causalml	Print a causalml Object
print.diversity_split	Print a Diversity-Based Split
print.ml_sample_size	Print ML Sample Size Results
print.supervisedml	Print a supervisedml Object
print.unsupervisedml	Print an unsupervisedml Object
print_figures_catalog	Print the Catalog of Figures

-- R --

resample_fairness	Fairness-Oriented Stratified Resampling
run_nested_cv	Nested Cross-Validation

-- S --

save_all_plots	Save All Plots to PNG Files
save_unsupervised_plots	Save All Figures of an Unsupervised Analysis
setup_cv	Set Up Cross-Validation Folds
summary.causalml	Summarize a causalml Object
summary.supervisedml	Summarize a supervisedml Object
summary.unsupervisedml	Summarize an unsupervisedml Object
supervised_ml	Supervised Machine Learning for Classification and Regression
supervised_ml_capture	Run supervised_ml() and Capture Its Console Output
supervised_ml_export	Run and Export a Complete Analysis

-- T --

train_models	Train and Compare Models with Cross-Validation
tune_best_model	Tune the Hyperparameters of the Best Model

-- U --

unsupervised_ml

Automated Unsupervised Learning Pipeline