Evaluating Model Performance

After making predictions, the final step is to check how well the model performed using proper evaluation metrics rather than guesswork.

from sklearn.metrics import accuracy_score, confusion_matrix, classification_report

accuracy = accuracy_score(y_test, predictions)
print("Accuracy:", accuracy)

print(confusion_matrix(y_test, predictions))
print(classification_report(y_test, predictions))

Code Explanation

• accuracy_score(y_test, predictions) calculates the percentage of correct predictions out of all test samples.
• confusion_matrix(y_test, predictions) shows exactly how many predictions were correct or incorrect, broken down by species.
• classification_report(y_test, predictions) displays precision, recall, and F1 score for each species individually.

Accuracy Formula

Accuracy = Correct Predictions / Total Predictions

Once these results are generated, you should see a high accuracy score, often above 95 percent, since the Iris dataset is clean and well separated.