Model Evaluation Metrics (Advanced)

Machine Learning Tutorial Part 12: Model Evaluation Metrics

📏 Why Evaluate a Model?

Evaluating a machine learning model ensures it performs well not only on training data but also generalizes to unseen data. Let’s explore key metrics used for classification tasks.

✅ Accuracy

Measures how often the model makes correct predictions:

from sklearn.metrics import accuracy_score

accuracy = accuracy_score(y_true, y_pred)
print("Accuracy:", accuracy)

Limitation: Not reliable with imbalanced datasets.

🎯 Precision & Recall

Precision: Of all predicted positives, how many are truly positive.
Recall: Of all actual positives, how many were correctly predicted.

from sklearn.metrics import precision_score, recall_score

precision = precision_score(y_true, y_pred)
recall = recall_score(y_true, y_pred)

📊 F1 Score

Harmonic mean of precision and recall. It’s useful when you need a balance between both.

from sklearn.metrics import f1_score

f1 = f1_score(y_true, y_pred)
print("F1 Score:", f1)

🔁 Confusion Matrix

A table to visualize the performance of the model by showing TP, FP, FN, TN.

from sklearn.metrics import confusion_matrix
import seaborn as sns
import matplotlib.pyplot as plt

cm = confusion_matrix(y_true, y_pred)
sns.heatmap(cm, annot=True, fmt='d')
plt.xlabel('Predicted')
plt.ylabel('Actual')
plt.show()

📌 Summary

• Accuracy: Good for balanced classes.
• Precision: Important when false positives are costly.
• Recall: Important when missing positives is costly.
• F1 Score: Best when you want a balance.
• Confusion Matrix: Visual breakdown of prediction results.