Prepping the stage
You are going to explore the attrition_num
dataset from the point of view of PCA to understand if it is feasible to reduce dimensionality while preserving most information. Start by creating a recipe that filters our near-zero variance features, normalizes the data, and implements PCA.
The attrition_num
dataset is already loaded for you.
This exercise is part of the course
Feature Engineering in R
Exercise instructions
- Remove possible near-zero variance features.
- Normalize all numeric data.
- Apply PCA.
- Access the names of the output elements by preparing the recipe.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
pc_recipe <- recipe(~., data = attrition_num) %>%
# Remove possible near-zero variance features
___(all_numeric()) %>%
# Normalize all numeric data
___(___()) %>%
# Apply PCA
___(all_numeric())
# Access the names of the output elements by preparing the recipe
pca_output <- ___(___)
names(pca_output)