{
  "name": "Classification report controls and research-record checks",
  "description": "Original crosswalk compiled from the official scikit-learn classification_report, precision_recall_fscore_support and train_test_split references. It pairs documented controls with their effects on report interpretation and the corresponding documented behavior to check; it contains no estimated model performance.",
  "page": "https://casrai.org/guides/sklearn-classification-report",
  "publisher": "CASRAI",
  "license": "https://creativecommons.org/licenses/by/4.0/",
  "dateModified": "2026-11-18T16:25:00Z",
  "temporalCoverage": null,
  "spatialCoverage": null,
  "columns": [
    {
      "name": "Control",
      "unit": "",
      "description": ""
    },
    {
      "name": "Documented behavior",
      "unit": "",
      "description": ""
    },
    {
      "name": "Interpretation check",
      "unit": "",
      "description": ""
    },
    {
      "name": "Primary reference",
      "unit": "",
      "description": ""
    }
  ],
  "rows": [
    {
      "Control": "labels and target_names",
      "Documented behavior": "Labels select report categories; names match their order.",
      "Interpretation check": "Keep the category subset and display-name order explicit.",
      "Primary reference": "https://scikit-learn.org/stable/modules/generated/sklearn.metrics.classification_report.html"
    },
    {
      "Control": "digits and output_dict",
      "Documented behavior": "digits formats the text report; dictionary values are not rounded.",
      "Interpretation check": "Distinguish display precision from exported numerical values.",
      "Primary reference": "https://scikit-learn.org/stable/modules/generated/sklearn.metrics.classification_report.html"
    },
    {
      "Control": "Macro and weighted averages",
      "Documented behavior": "Macro is an unweighted per-label mean; weighted uses label support.",
      "Interpretation check": "Different label supports produce different aggregation weights.",
      "Primary reference": "https://scikit-learn.org/stable/modules/generated/sklearn.metrics.precision_recall_fscore_support.html"
    },
    {
      "Control": "zero_division=np.nan",
      "Documented behavior": "Undefined values are excluded from averaging.",
      "Interpretation check": "An average can use fewer defined label values than a zero-filled average.",
      "Primary reference": "https://scikit-learn.org/stable/modules/generated/sklearn.metrics.precision_recall_fscore_support.html"
    },
    {
      "Control": "stratify and random_state",
      "Documented behavior": "stratify supplies class labels for splitting; an integer random_state makes repeated split calls reproducible.",
      "Interpretation check": "Keep split settings alongside the test-report output.",
      "Primary reference": "https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html"
    },
    {
      "Control": "Absent labels",
      "Documented behavior": "Explicit labels can include categories absent from the data, with zero support.",
      "Interpretation check": "A zero-support row is not evidence from observed examples of that class.",
      "Primary reference": "https://scikit-learn.org/stable/modules/generated/sklearn.metrics.precision_recall_fscore_support.html"
    }
  ],
  "sources": [
    {
      "title": "scikit-learn classification_report API",
      "url": "https://scikit-learn.org/stable/modules/generated/sklearn.metrics.classification_report.html",
      "accessed": "2026-11-16"
    },
    {
      "title": "scikit-learn precision_recall_fscore_support API",
      "url": "https://scikit-learn.org/stable/modules/generated/sklearn.metrics.precision_recall_fscore_support.html",
      "accessed": "2026-11-16"
    },
    {
      "title": "scikit-learn train_test_split API",
      "url": "https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html",
      "accessed": "2026-11-16"
    }
  ]
}