Accuracy after dimensionality reduction

You'll reduce the overfit with the help of dimensionality reduction. In this case, you'll apply a rather drastic form of dimensionality reduction by only selecting a single column that has some good information to distinguish between genders. You'll repeat the train-test split, model fit and prediction steps to compare the accuracy on test versus training data.

All relevant packages and y have been pre-loaded.

Cet exercice fait partie du cours

Dimensionality Reduction in Python

Afficher le cours

Instructions

Select just the neck circumference ('neckcircumferencebase') column from ansur_df.
Split the data, instantiate a classifier and fit the data. This has been done for you.
Once again calculate the accuracy scores on both training and test set.

Exercice interactif pratique

Essayez cet exercice en complétant cet exemple de code.

# Assign just the 'neckcircumferencebase' column from ansur_df to X
X = ansur_df[[____]]

# Split the data, instantiate a classifier and fit the data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)
svc = SVC()
svc.fit(X_train, y_train)

# Calculate accuracy scores on both train and test data
accuracy_train = accuracy_score(____, svc.predict(____))
accuracy_test = accuracy_score(____, svc.predict(____))

print(f"{accuracy_test:.1%} accuracy on test set vs. {accuracy_train:.1%} on training set")

Modifier et exécuter le code