How do I evaluate a scikit-learn pipeline?

How do I evaluate a scikit-learn pipeline?

To evaluate a scikit-learn pipeline, you can use cross-validation methods like cross_val_score or GridSearchCV.

Can you show me an example of using cross_val_score?

Sure! Here's a simple example:

from sklearn.pipeline import Pipeline
from sklearn.model_selection import cross_val_score
from sklearn.datasets import load_iris
from sklearn.ensemble import RandomForestClassifier

# Load dataset
X, y = load_iris(return_X_y=True)

# Create a pipeline
pipeline = Pipeline([
    ('classifier', RandomForestClassifier())
])

# Evaluate the pipeline
scores = cross_val_score(pipeline, X, y, cv=5)
print('Cross-validation scores:', scores)

What does cv=5 mean in this context?

The cv=5 parameter means that the dataset will be split into 5 folds for cross-validation, allowing for a more robust evaluation.

Are there other metrics I can use to evaluate the model?

Yes, you can use metrics like accuracy, precision, recall, F1-score, and ROC-AUC, depending on your specific needs.