training_config.json

{
  "model_name": "CBC Healthcare Readmission Classifier",
  "hf_repo": "careerbytecode/mlops-ref-healthcare-readmission",
  "task": "binary classification (30-day hospital readmission)",
  "model_type": "sigmoid-calibrated rf (sklearn Pipeline, 3-branch ColumnTransformer)",
  "framework": "scikit-learn",
  "serialization": "joblib",
  "loader": "joblib.load -> CalibratedClassifierCV; call .predict_proba(DataFrame)[:, 1]",
  "random_state": 42,
  "split": {
    "train": 61059,
    "val": 20353,
    "test": 20354
  },
  "feature_columns": [
    "time_in_hospital",
    "num_lab_procedures",
    "num_procedures",
    "num_medications",
    "number_diagnoses",
    "number_inpatient",
    "number_outpatient",
    "number_emergency",
    "race",
    "gender",
    "age",
    "A1Cresult",
    "max_glu_serum",
    "insulin",
    "change",
    "diabetesMed",
    "diag_1",
    "diag_2",
    "diag_3"
  ],
  "numeric_features": [
    "time_in_hospital",
    "num_lab_procedures",
    "num_procedures",
    "num_medications",
    "number_diagnoses",
    "number_inpatient",
    "number_outpatient",
    "number_emergency"
  ],
  "low_cardinality_categorical": [
    "race",
    "gender",
    "age",
    "A1Cresult",
    "max_glu_serum",
    "insulin",
    "change",
    "diabetesMed"
  ],
  "high_cardinality_diagnoses": [
    "diag_1",
    "diag_2",
    "diag_3"
  ],
  "dataset": "UCI Diabetes 130-US Hospitals 1999-2008 (id 296), CC BY 4.0",
  "python_version": "3.14.4",
  "library_versions": {
    "scikit-learn": "1.8.0",
    "numpy": "2.4.6",
    "pandas": "2.3.3",
    "joblib": "1.5.3"
  },
  "training_date": "2026-06-04T20:31:40.072484+00:00"
}