Skip to content

Instantly share code, notes, and snippets.

@behitek
Created October 29, 2021 09:48
Show Gist options
  • Save behitek/9186caec92ebf41a43f5daa0438036e1 to your computer and use it in GitHub Desktop.
Save behitek/9186caec92ebf41a43f5daa0438036e1 to your computer and use it in GitHub Desktop.

classification report threshold 0.1 precision recall f1-score support

accepted       0.97      0.75      0.85      8872
rejected       0.37      0.88      0.52      1505

accuracy                           0.77     10377

macro avg 0.67 0.81 0.68 10377 weighted avg 0.89 0.77 0.80 10377

classification report threshold 0.2 precision recall f1-score support

accepted       0.96      0.84      0.90      8872
rejected       0.46      0.79      0.58      1505

accuracy                           0.83     10377

macro avg 0.71 0.81 0.74 10377 weighted avg 0.89 0.83 0.85 10377

classification report threshold 0.3 precision recall f1-score support

accepted       0.95      0.90      0.92      8872
rejected       0.53      0.70      0.61      1505

accuracy                           0.87     10377

macro avg 0.74 0.80 0.76 10377 weighted avg 0.89 0.87 0.88 10377

classification report threshold 0.4 precision recall f1-score support

accepted       0.93      0.93      0.93      8872
rejected       0.60      0.60      0.60      1505

accuracy                           0.88     10377

macro avg 0.76 0.77 0.77 10377 weighted avg 0.88 0.88 0.88 10377

classification report threshold 0.5 precision recall f1-score support

accepted       0.92      0.96      0.94      8872
rejected       0.66      0.51      0.58      1505

accuracy                           0.89     10377

macro avg 0.79 0.73 0.76 10377 weighted avg 0.88 0.89 0.89 10377

classification report threshold 0.6 precision recall f1-score support

accepted       0.91      0.97      0.94      8872
rejected       0.73      0.42      0.53      1505

accuracy                           0.89     10377

macro avg 0.82 0.70 0.74 10377 weighted avg 0.88 0.89 0.88 10377

classification report threshold 0.7 precision recall f1-score support

accepted       0.90      0.99      0.94      8872
rejected       0.79      0.32      0.46      1505

accuracy                           0.89     10377

macro avg 0.84 0.65 0.70 10377 weighted avg 0.88 0.89 0.87 10377

classification report threshold 0.8 precision recall f1-score support

accepted       0.88      0.99      0.93      8872
rejected       0.84      0.22      0.35      1505

accuracy                           0.88     10377

macro avg 0.86 0.61 0.64 10377 weighted avg 0.88 0.88 0.85 10377

classification report threshold 0.9 precision recall f1-score support

accepted       0.87      1.00      0.93      8872
rejected       0.87      0.10      0.18      1505

accuracy                           0.87     10377

macro avg 0.87 0.55 0.56 10377 weighted avg 0.87 0.87 0.82 10377

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment