Chapter 25 of 30
Keep learning and build your Data Science skills.
Model Evaluation
Learn how to measure the performance of machine learning models.
Theory
Model evaluation measures how well a model performs on appropriate data.
For regression, common metrics include:
• MAE
• MSE
• RMSE
• R²
For classification:
• Accuracy
• Precision
• Recall
• F1 Score
• ROC-AUC
The chosen metric should match the problem and business objective.
Example
from sklearn.metrics import accuracy_score
actual = [0, 1, 1, 0]
predicted = [0, 1, 0, 0]
score = accuracy_score(
actual,
predicted
)
print(score)Output
The classification accuracy is calculated.
Practice
Evaluate a classification model using accuracy, precision, recall, and F1 score.
Interview Questions
1
Why is model evaluation important?
2
What is accuracy?
3
What is precision?
4
What is recall?
Quick Quiz
Which option best describes this chapter?
A.Measuring model performance
B.Creating databases
C.Writing HTML
D.Designing websites