Data Engineering FoundationsChapter 152
Answers
Section 1 of 2-~ 12 min read-Synced from Cuantum content
- b) Variance Thresholding
- c) Reindexing the data to a regular frequency and using forward-fill or backward-fill
- c) The proportion of the dataset’s variance captured by each principal component
- c) Encoding features with cyclical patterns, like day of the week
- c) They rely on model training to determine feature importance
- b) Principal Component Analysis (PCA)
- c) Correlation Thresholding
- c) When interaction effects between features need to be captured
- c) It may over-penalize features, potentially leading to underfitting
- b) To ensure that selected features generalize well to new data