Package: bayesiansurpriser 0.1.0

Introduction | Prerequisites | Understanding cancensus Data Structure | Example 1: Low Income Rates by Census Division | Fetch Census Data | Compute Bayesian Surprise | Visualize Surprising Regions | Identify Most Surprising Regions | Example 2: Housing Analysis in Metro Vancouver | Example 3: Language at Home Analysis | Example 4: Provincial Comparison with Funnel Plot | Example 5: Comparing Census Years | Example 6: Custom Model Space for Census Data | Interpreting Surprise Values | Session Info

Introduction | When to Use Bayesian Surprise | Prerequisites | Example 1: State-Level Poverty Analysis | Visualize State-Level Results | Example 2: Funnel Plot Visualization | County-Level Funnel (Classic Shape) | Example 3: Tract-Level Analysis (Same-Scale Comparison) | Example 4: Large Counties Only | Understanding the Methodology | Why Small Regions Can Be Misleading | Recommendations | Session Info

bayesiansurpriser: Complete Reference | 1. Core Surprise Computation | 1.1 surprise() - Main Function | 1.2 auto_surprise() - Simple Vector API | 1.3 compute_surprise() - Low-Level Function | 2. Model Types | 2.1 bs_model_uniform() - Uniform Distribution | 2.2 bs_model_baserate() - Base Rate Model | 2.3 bs_model_gaussian() - Normal Distribution | 2.4 bs_model_sampled() - KDE Model | 2.5 bs_model_funnel() - de Moivre Funnel | 2.6 bs_model_bootstrap() - Bootstrap Model | 2.7 bs_model_gaussian_mixture() - Mixture Model | 3. Model Space Operations | 3.1 model_space() - Create Model Space | 3.2 default_model_space() - Quick Default | 3.3 Model Space Manipulation | 3.4 bayesian_update() - Update Posterior | 3.5 cumulative_bayesian_update() - Sequential Updates | 4. Accessor Functions | 4.1 get_surprise() and get_model_space() | 5. Temporal and Streaming Analysis | 5.1 surprise_temporal() - Panel Data | 5.2 update_surprise() - Streaming Updates | 5.3 surprise_rolling() - Rolling Window | 5.4 get_surprise_at_time() - Extract Time Slice | 5.5 surprise_animate() - Animation-Ready Data | 6. Funnel Analysis Functions | 6.1 compute_funnel_data() | 6.2 funnel_zscore() and funnel_pvalue() | 7. Normalization Utilities | 7.1 normalize_prob() - Probability Distribution | 7.2 normalize_rate() - Per-Capita Rates | 7.3 normalize_zscore() - Z-Score | 7.4 normalize_minmax() - Min-Max Scaling | 7.5 normalize_robust() - Robust Scaling | 8. Mathematical Utilities | 8.1 kl_divergence() - KL-Divergence | 8.2 log_sum_exp() - Numerically Stable | 9. ggplot2 Integration | 9.1 Color Scales | Sequential Scale | Diverging Scale | Binned Scale | Diverging Binned Scale | 9.2 stat_surprise() - Compute in ggplot2 | 9.3 Histogram and Density Geoms | 10. sf Spatial Functions | 10.1 st_surprise() - Convenience Wrapper | 10.2 st_density() - Spatial KDE | 10.3 st_aggregate_surprise() - Aggregate to Larger Regions | 11. Base R Plot Methods | 11.1 plot.bs_surprise_sf() | 11.2 plot.bs_surprise() | 11.3 plot.bs_model_space() | 11.4 plot.bs_surprise_temporal() | 12. Summary Statistics | 12.1 summary.bs_surprise() | 13. Included Datasets | 13.1 canada_mischief | 13.2 example_counties | Session Info

Overview | The Problem: Cognitive Biases in Data Visualization | The Solution: Bayesian Surprise | Quick Start | Basic Usage with sf Objects | Plotting Results | Understanding the Output | Customizing Models | Next Steps

Overview | Basic sf Workflow | Loading Spatial Data | Computing Surprise | Convenience Function: st_surprise | Accessing Results | Extracting Surprise Values | Accessing the Model Space | Working with the sf Object | Visualization | ggplot2 Integration | Comparing Time Periods | Advanced: Custom Model Spaces | Integration with dplyr | Tips for Large Datasets

Overview | Temporal Analysis with surprise_temporal() | Streaming Updates | Cumulative Bayesian Updates | Rolling Window Analysis | Anomaly Detection Over Time | Best Practices

Overview | The Five Model Types | 1. Uniform Model (bs_model_uniform) | 2. Base Rate Model (bs_model_baserate) | 3. Gaussian Model (bs_model_gaussian) | 4. Sampled/KDE Model (bs_model_sampled) | 5. de Moivre Funnel Model (bs_model_funnel) | Combining Models: Model Space | How Models Affect Surprise | Global Model Updates | Guidelines for Model Selection

Overview | Loading Example Data | Basic Workflow: Compute then Plot | Color Scales | Sequential Scale: scale_fill_surprise() | Diverging Scale: scale_fill_surprise_diverging() | Binned Scale: scale_fill_surprise_binned() | Combining with Other ggplot2 Elements | Adding Labels | Faceting | Theme Customization | Non-Spatial Data | Best Practices