Introduction | A First Run | How the Search Works | The evaluation column | The Time Budget | Controlling the Search | Using the Result | AutoML Against a Single Choice | Preprocessing First | When a Model Is Missing or Scores NA | AutoML or Tuning? | Guidance | Where to Go Next

Where a fit runs | What this machine can do | Only two methods have a GPU path | Estimating before you commit | Cloud compute | Consent is explicit | Destinations are checked, not trusted | Bounding the cost | The contract is written down | What is coming | See also

Overview | Checking Assumptions | The dashboard | Influence | Refit without the influential rows | Outliers in the Data | Comparing Models | Is the difference real? | Interactions | Reading an interaction | Exploring Before Modelling | A Checklist

Introduction | Installation | The Unified Interface | Supervised Learning | Classification | Regression | Unsupervised Learning | Dimensionality Reduction | Clustering | Data Preprocessing | Train-Test Splitting | Wrapped Packages | Supervised Methods | Unsupervised Methods | Accessing the Underlying Model | The Whole Workflow | Next Steps

Overview | Mining Rules | Choosing the thresholds | Reading the Rules | Working With One Item | Recommending From a Basket | Visualising | From a Data Frame | What the Numbers Do Not Tell You | Function Reference

Overview | Plots | Regression | Classification | PCA | Regularisation | Tables | Evaluation Metrics | Coefficients | Confusion Matrix | Feature Importance | PCA Variance Explained | PCA Loadings | Cluster Summary | Model Comparison | Interactive Reporting with plotly | Putting It Together

Introduction | Classification | Binary Classification | Logistic Regression | Decision Trees | Multi-class Classification | Random Forest | Support Vector Machines | Regression | Linear Regression | Polynomial Regression | Random Forest Regression | Regularized Regression | Ridge Regression | LASSO | Elastic Net | Model Comparison | Advanced Features | Using Preprocessed Data | Formula Variations | Handling Different Data Types | Categorical Predictors | Missing Values | Best Practices | Replaying Preprocessing on the Test Set

Overview | Grid Search | Choosing the metric | Starting from a default grid | Random Search | Looking at the Search | Pipelines | Running it | Predicting through the pipeline | Saving and reloading | Tuning into a Pipeline | Cost | Where to Go Next

Two Ways In | Scale First | Principal Component Analysis | Scores back on the data | How Many Clusters? | K-means | Was it a good clustering? | PAM and CLARA | Hierarchical Clustering | DBSCAN | Multidimensional Scaling | Comparing Clusterings | A Worked Sequence | Function Reference

Overview | The tl_read() Dispatcher | File Formats | CSV and TSV | Excel | Parquet | JSON | RDS and RData | Databases | SQLite | Using a Live Connection | PostgreSQL, MySQL, and BigQuery | Cloud and API Sources | Amazon S3 | GitHub | Kaggle | Multi-File Reading | Multiple Paths | Directory Scanning | Zip Archives | The tidylearn_data Class | Full Pipeline | Supported Formats Reference

Introduction | Dimensionality Reduction as Preprocessing | Basic Usage | Comparison: Original vs Reduced Features | Cluster-Based Feature Engineering | Adding Cluster Features | Performance Comparison | Semi-Supervised Learning | Training with Limited Labels | Comparison: Semi-Supervised vs Fully Supervised | Anomaly-Aware Modeling | Flagging Anomalies | Removing Anomalies | Stratified Models | Training Stratified Models | Complete Integration Workflow | Practical Example: Credit Risk Assessment | What Each Combination Buys You | Function Reference | Where to Go Next