{
  "name": "Learning cases for probabilistic graphical models and the free software that documents them",
  "description": "Maps the three learning situations in Murphy's graphical-models tutorial (known structure with complete data, known structure with missing data, unknown structure) to the method he names, what the pgmpy quickstart demonstrates, and the bnlearn functions listed in its manual index. Compiled from the cited pages on 2026-11-14; a cell reading 'Not shown' means the cited page does not demonstrate it.",
  "page": "https://casrai.org/guides/probabilistic-graphical-models",
  "publisher": "CASRAI",
  "license": "https://creativecommons.org/licenses/by/4.0/",
  "dateModified": "2026-11-18T13:30:00Z",
  "temporalCoverage": null,
  "spatialCoverage": null,
  "columns": [
    {
      "name": "Learning case",
      "unit": "",
      "description": ""
    },
    {
      "name": "Method named by Murphy",
      "unit": "",
      "description": ""
    },
    {
      "name": "pgmpy (quickstart)",
      "unit": "",
      "description": ""
    },
    {
      "name": "bnlearn (manual index)",
      "unit": "",
      "description": ""
    },
    {
      "name": "Language of package",
      "unit": "",
      "description": ""
    }
  ],
  "rows": [
    {
      "Learning case": "Known structure, complete data",
      "Method named by Murphy": "Maximum likelihood (counting for discrete variables)",
      "pgmpy (quickstart)": "fit with MaximumLikelihoodEstimator on DiscreteBayesianNetwork",
      "bnlearn (manual index)": "bn.fit, bn.net, custom.fit (fit the parameters of a Bayesian network)",
      "Language of package": "pgmpy: Python; bnlearn: R"
    },
    {
      "Learning case": "Known structure, missing data",
      "Method named by Murphy": "Expectation-maximisation (EM)",
      "pgmpy (quickstart)": "Not shown in the quickstart",
      "bnlearn (manual index)": "structural.em (structure learning from missing data); impute and predict for missing values",
      "Language of package": "pgmpy: Python; bnlearn: R"
    },
    {
      "Learning case": "Unknown structure, complete data",
      "Method named by Murphy": "Search over structures with a penalised score such as BIC",
      "pgmpy (quickstart)": "PC algorithm with ci_test chi_square, return_type dag",
      "bnlearn (manual index)": "Score-based: hc, tabu; constraint-based: gs, iamb, mmpc, pc.stable; hybrid: h2pc, mmhc, rsmax2",
      "Language of package": "pgmpy: Python; bnlearn: R"
    },
    {
      "Learning case": "Query given evidence",
      "Method named by Murphy": "Exact (variable elimination, junction tree) or approximate (variational, sampling, loopy belief propagation)",
      "pgmpy (quickstart)": "VariableElimination(model).query(variables, evidence)",
      "bnlearn (manual index)": "cpquery, cpdist (conditional probability queries)",
      "Language of package": "pgmpy: Python; bnlearn: R"
    }
  ],
  "sources": [
    {
      "title": "Murphy, A Brief Introduction to Graphical Models and Bayesian Networks",
      "url": "https://www.cs.ubc.ca/~murphyk/Bayes/bayes.html",
      "accessed": "2026-11-14"
    },
    {
      "title": "pgmpy quickstart",
      "url": "https://pgmpy.org/started/quickstart.html",
      "accessed": "2026-11-14"
    },
    {
      "title": "bnlearn manual page index",
      "url": "https://www.bnlearn.com/documentation/man/index.html",
      "accessed": "2026-11-14"
    }
  ]
}