evaluation_results.json

{
  "test_accuracy": 0.937962962962963,
  "classification_report": "               precision    recall  f1-score   support\n\n  CASE_REPORT     0.9657    0.9663    0.9660      6000\n      COMMENT     0.8575    0.8357    0.8465      6000\n    EDITORIAL     0.8386    0.8660    0.8521      6000\n   GUIDELINES     0.9962    1.0000    0.9981      6000\nMETA_ANALYSIS     0.9071    0.9877    0.9457      6000\n  PROSPECTIVE     0.9601    0.9898    0.9747      6000\n          RCT     0.9884    0.9768    0.9826      6000\nRETROSPECTIVE     0.9857    0.9653    0.9754      6000\n       REVIEW     0.9480    0.8540    0.8986      6000\n\n     accuracy                         0.9380     54000\n    macro avg     0.9386    0.9380    0.9377     54000\n weighted avg     0.9386    0.9380    0.9377     54000\n",
  "confusion_matrix": [
    [
      5798,
      12,
      2,
      0,
      1,
      0,
      7,
      2,
      178
    ],
    [
      0,
      5014,
      974,
      12,
      0,
      0,
      0,
      0,
      0
    ],
    [
      0,
      804,
      5196,
      0,
      0,
      0,
      0,
      0,
      0
    ],
    [
      0,
      0,
      0,
      6000,
      0,
      0,
      0,
      0,
      0
    ],
    [
      0,
      5,
      0,
      0,
      5926,
      1,
      25,
      0,
      43
    ],
    [
      0,
      0,
      0,
      0,
      0,
      5939,
      0,
      61,
      0
    ],
    [
      1,
      8,
      6,
      0,
      14,
      33,
      5861,
      17,
      60
    ],
    [
      0,
      0,
      0,
      0,
      0,
      208,
      0,
      5792,
      0
    ],
    [
      205,
      4,
      18,
      11,
      592,
      5,
      37,
      4,
      5124
    ]
  ]
}