bnlearn - Research notes

Dynamic Bayesian network of dermatologic and mental conditions in Scutari, Kerob and Salah (in the works).
1. The Data: an Overview
2. Dependence Structure of the Data
3. Bayesian Networks: Static versus Dynamic Structures
4. Learning the Dynamic Bayesian Network
5. Validating Predictive Accuracy
Structure learning benchmarks in Scutari, Marquis and Azzimonti, Proceedings of Machine Learning Research (2022)
1. Generating the ground-truth models
2. Scoring local distributions that are linear mixed-effects models
3. Learning the different types of networks
4. Comparing the learned networks
A network analysis of the symptoms from the Zung depression scale components, Psychological Reports (2020)
1. Loading the required libraries
2. Loading and exploring the data
3. Learning an undirected network model
4. Learning a directed network model
5. A network comparison test
Structure learning benchmarks in Scutari, Graafland and Gutiérrez, International Journal of Approximate Reasoning (2019)
1. The makefile
2. Generating the data
3. Performing structure learning
4. Collecting summary statistics
5. Generating the figures
Benchmarking optimizations in Scutari, Vitolo and Tucker, Statistics and Computing (2019)
1. Benchmarks on the MEHRA network
2. Benchmarks on other large data sets
Analysis of pollution, climate and health data in Vitolo et al., Earth and Space Science (2018)
1. The data
2. Learning the Bayesian network
Analysis of class III malocclusion in Scutari et al., Scientific Reports (2017)
1. The data
2. Preprocessing and exploratory data analysis
3. Learning the Bayesian network
4. Model validation
5. Interesting questions
Parallel structure learning benchmarking in Scutari, Journal of Statistical Software (2017)
1. Parallel computing benchmarks
2. Symmetry correction benchmarks
Structure learning benchmarks in Scutari, Journal of Machine Learning Research (2016)
1. Learning the network structures
2. Computing the metrics of interest to compare different network scores
3. Computing the averaged metrics for each network and sample size
4. Plotting the metrics of interest, for visual inspection
5. Plotting the metrics of interest, for slides presentations
Analysis of the MAGIC population in Scutari et al., Genetics (2014)
1. Reading and preparing the preprocessed data
2. Performing cross-validation
3. Averaging the network structures
4. Plotting the averaged network
Reproducing the causal signalling network in Sachs et al., Science (2005)
1. The raw data
2. Model averaging
3. Choosing the Significance Threshold
4. Handling Interventional Data
5. Querying the Network