added print_high_confidence_samples

code/machine_learning_models/utilities.py

@@ -129,6 +129,13 @@ def plot_confusion_matrix(confusion_matrix: List[List[int]], accuracy: float, mo
     if show_plots:
         plt.show()
 
+def print_high_confidence_samples(model, x: pd.DataFrame):
+    # Get predicted probabilities
+    predicted_probabilities = pd.DataFrame(model.predict_proba(x)[:, 1],
+                                           columns=['confidence level'])  # Probability of being class 1
+    # Filter samples where the model is at least 90% sure
+    high_confidence_samples = predicted_probabilities[predicted_probabilities['confidence level'] > 0.9]
+    print(high_confidence_samples.head())
 
 def save_plot(name):
     plt.savefig("resulting_figures/" + name, dpi=300, bbox_inches='tight')