## Classes

- The bn class structure
- The bn.fit class structure
- The bn.kcv class structure
- The bn.strength class structure

## Classifiers

## Convenience functions

- Utilities to manipulate fitted Bayesian networks
- Try to infer the direction of an undirected arc
- Construct configurations of discrete variables
- Miscellaneous utilities
- Build a model string from a Bayesian network and vice versa
- Utilities dealing with partial node orderings
- Manipulating the test counter

## Data preprocessing

- Construct configurations of discrete variables
- Predict or impute missing data from a Bayesian network
- Pre-process data to better learn Bayesian networks

## Datasets

- ALARM monitoring system (synthetic) data set
- Asia (synthetic) data set by Lauritzen and Spiegelhalter
- Synthetic (mixed) data set to test learning algorithms
- Coronary heart disease data set
- Synthetic (continuous) data set to test learning algorithms
- The HailFinder weather forecast system (synthetic) data set
- Insurance evaluation network (synthetic) data set
- Synthetic (discrete) data set to test learning algorithms
- Lizards' perching behaviour data set
- Examination marks data set

## Graphs

- Drop, add or set the direction of an arc or an edge
- Compare two or more different Bayesian networks
- Count graphs with specific characteristics
- Equivalence classes, moral graphs and consistent extensions
- Equivalence classes in the presence of interventions
- Test d-separation
- Utilities to manipulate graphs
- Miscellaneous utilities
- Utilities dealing with partial node orderings

## Import/export to file

## Independence tests

- Measure arc strength
- Try to infer the direction of an undirected arc
- Independence and conditional independence tests

## Inference

- Perform conditional probability queries
- Predict or impute missing data from a Bayesian network
- Simulate random data from a given Bayesian network

## Interfaces to other packages

- Plot fitted Bayesian networks
- Compare two or more different Bayesian networks
- Import and export networks from the gRain package
- Import and export networks from the graph package
- Plotting networks with probability bars
- Advanced Bayesian network plots
- Import and export networks from the pcalg package
- Generating a prediction object for ROCR
- Produce lm objects from Bayesian networks
- Arc strength plot

## Local learning

- Discover the structure around a single node
- Local discovery structure learning algorithms
- Identify relevant nodes without learning the Bayesian network

## Missing data

## Network scores

- Estimate the optimal imaginary sample size for BDe(u)
- Measure arc strength
- Bayes factor between two network structures
- Utilities to manipulate fitted Bayesian networks
- Try to infer the direction of an undirected arc
- Score of the Bayesian network

## Parameter learning

## Plots

- Plot fitted Bayesian networks
- Compare two or more different Bayesian networks
- Plotting networks with probability bars
- Advanced Bayesian network plots
- Plot a Bayesian network
- Plot arc strengths derived from bootstrap
- Arc strength plot

## Resampling

- Parametric and nonparametric bootstrap of Bayesian networks
- Cross-validation for Bayesian networks
- Try to infer the direction of an undirected arc

## Simulation

- Perform conditional probability queries
- Generate empty or random graphs
- Simulate random data from a given Bayesian network

## Structure learning

- Estimate the optimal imaginary sample size for BDe(u)
- Measure arc strength
- Bayes factor between two network structures
- Constraint-based structure learning algorithms
- Equivalence classes, moral graphs and consistent extensions
- Score-based structure learning algorithms
- Hybrid structure learning algorithms
- Naive Bayes classifiers
- Utilities dealing with partial node orderings
- Structure learning from missing data