How can I use Scikit-learn for feature selection?

How can I use Scikit-learn for feature selection?

You can use Scikit-learn's feature selection module, which includes methods like Recursive Feature Elimination (RFE) and SelectKBest.

What is Recursive Feature Elimination?

Recursive Feature Elimination (RFE) is a method that recursively removes the least important features based on a model's performance.

Can you show me an example of RFE in code?

Sure! Here's a simple example:

from sklearn.datasets import load_iris
from sklearn.feature_selection import RFE
from sklearn.linear_model import LogisticRegression

# Load dataset
iris = load_iris()
X, y = iris.data, iris.target

# Create a model
model = LogisticRegression()

# Create RFE model and select top 2 features
rfe = RFE(model, 2)
fit = rfe.fit(X, y)

print('Selected features:', fit.support_)
print('Feature ranking:', fit.ranking_)

What other feature selection methods does Scikit-learn offer?

Scikit-learn offers several methods, including SelectFromModel, SelectKBest, and VarianceThreshold, among others.