# `needsdiagnosis` model evaluation
## Full dataset (reverted original titles)
### Report

```
              precision    recall  f1-score   support
       False       0.90      0.99      0.94     11174
        True       0.70      0.24      0.36      1537

    accuracy                           0.90     12711
   macro avg       0.80      0.61      0.65     12711
weighted avg       0.88      0.90      0.87     12711

```

### Confusion matrix

```
[[11010   164]
 [ 1162   375]]
```

## Balanced dataset (reverted original titles)

### Report
```              precision    recall  f1-score   support
       False       0.71      0.77      0.74      1562
        True       0.75      0.68      0.72      1583

    accuracy                           0.73      3145
   macro avg       0.73      0.73      0.73      3145
weighted avg       0.73      0.73      0.73      3145

```
### Confusion matrix
```
[[1210  352]
 [ 501 1082]]
```