evaluation.json

{
  "n_test": 59,
  "tta": true,
  "leakage_free": true,
  "accuracy": 0.9830508474576272,
  "balanced_accuracy": 0.9642857142857143,
  "qwk": 0.9882727092029417,
  "mcc": 0.971513726759843,
  "macro_auc": NaN,
  "mae_grades": 0.01694915254237288,
  "within_one_grade": 1.0,
  "log_loss": 0.1904372375299754,
  "bootstrap_ci": {
    "accuracy": {
      "mean": 0.9830169491525423,
      "lo": 0.9491525423728814,
      "hi": 1.0
    },
    "balanced_accuracy": {
      "mean": 0.9636371017360907,
      "lo": 0.875,
      "hi": 1.0
    },
    "qwk": {
      "mean": 0.9874861564441398,
      "lo": 0.9562298281312692,
      "hi": 1.0
    }
  },
  "confusion_matrix": [
    [
      7,
      0,
      0,
      0
    ],
    [
      0,
      6,
      1,
      0
    ],
    [
      0,
      0,
      35,
      0
    ],
    [
      0,
      0,
      0,
      10
    ]
  ],
  "per_class": {
    "0": {
      "precision": 1.0,
      "recall": 1.0,
      "f1-score": 1.0,
      "support": 7.0
    },
    "1": {
      "precision": 1.0,
      "recall": 0.8571428571428571,
      "f1-score": 0.9230769230769231,
      "support": 7.0
    },
    "2": {
      "precision": 0.9722222222222222,
      "recall": 1.0,
      "f1-score": 0.9859154929577465,
      "support": 35.0
    },
    "3": {
      "precision": 1.0,
      "recall": 1.0,
      "f1-score": 1.0,
      "support": 10.0
    },
    "accuracy": 0.9830508474576272,
    "macro avg": {
      "precision": 0.9930555555555556,
      "recall": 0.9642857142857143,
      "f1-score": 0.9772481040086674,
      "support": 59.0
    },
    "weighted avg": {
      "precision": 0.9835216572504708,
      "recall": 0.9830508474576272,
      "f1-score": 0.9825183172043997,
      "support": 59.0
    }
  }
}