KNN on scaled data

The accuracy score on the unscaled wine dataset was decent, but let's see what you can achieve by using standardization. Once again, the knn model as well as the X and y data and labels set have already been created for you.

Deze oefening maakt deel uit van de cursus

Preprocessing for Machine Learning in Python

Cursus bekijken

Oefeninstructies

Create the StandardScaler() method, stored in a variable named scaler.
Scale the training and test features, being careful not to introduce data leakage.
Fit the knn model to the scaled training data.
Evaluate the model's performance by computing the test set accuracy.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=42)

# Instantiate a StandardScaler
scaler = ____

# Scale the training and test features
X_train_scaled = ____.____(____)
X_test_scaled = ____.____(____)

# Fit the k-nearest neighbors model to the training data
____.____(____, ____)

# Score the model on the test data
print(____.____(____, ____))

Code bewerken en uitvoeren