Classification Report

EBM — Breast Cancer Wisconsin — 114 samples · 2 classes

0.992
0.9917
AUC
Area Under the ROC Curve
96.49%
Accuracy
Fraction of all predictions that are correct: (TP+TN) / Total
95.24%
Balanced Acc
Average per-class recall, correcting for class imbalance
0.9474
Precision
Of predicted positives, how many are correct: TP / (TP+FP)
1.0000
Recall
Of actual positives, how many are found: TP / (TP+FN). Also called sensitivity
0.9730
F1 Score
Harmonic mean of precision and recall: 2·P·R / (P+R)
0.9258
MCC
Matthews Correlation Coefficient: balanced measure even with imbalanced classes. Range [-1, 1]
0.9231
Cohen κ
Agreement beyond chance between predictions and true labels. Range [-1, 1]
0.9917
AUC
Area Under the ROC Curve: probability that a random positive ranks above a random negative
0.1195
Log Loss
Negative log-likelihood of predicted probabilities. Lower is better
0.0265
Brier Score
Mean squared error of predicted probabilities. Lower is better. Range [0, 1]
0.9048
Specificity
Of actual negatives, how many are correctly identified: TN / (TN+FP)
1.0000
NPV
Negative Predictive Value: of predicted negatives, how many are correct: TN / (TN+FN)
0.9048
Informedness
Recall + Specificity − 1. How much the model informs beyond chance. Also called Youden's J
0.9474
Markedness
Precision + NPV − 1. How marked the predictions are beyond chance

Confusion Matrix

ROC Curve

Precision-Recall Curve

Calibration Plot

Threshold Analysis

Per-Class Metrics

Cumulative Gains

Feature Importances (Top 20)

Class Distribution (Test Set)

Prediction Score Distribution

Per-Class Metrics

Class                 Precision     Recall         F1    Support
----------------------------------------------------------------
malignant                1.0000     0.9048     0.9500         42
benign                   0.9474     1.0000     0.9730         72