1. What is the primary goal of data reduction in data preprocessing?
a) To reduce the size of the dataset without losing significant information
b) To increase the dataset’s complexity
c) To remove missing values from the dataset
d) To convert data into a more suitable format for analysis
Answer: a) To reduce the size of the dataset without losing significant information
2. Which of the following is a common data reduction technique?
a) Feature selection
b) Data imputation
c) One-hot encoding
d) Normalization
Answer: a) Feature selection
3. Principal Component Analysis (PCA) is an example of which type of data reduction technique?
a) Feature extraction
b) Feature selection
c) Data transformation
d) Data integration
Answer: a) Feature extraction
4. What does feature selection aim to achieve in the context of data reduction?
a) Reducing the number of features by selecting only the most relevant ones
b) Removing duplicates from the dataset
c) Reducing the size of the dataset by removing entire rows
d) Scaling features to a common range
Answer: a) Reducing the number of features by selecting only the most relevant ones
5. Which of the following is an example of instance reduction in data reduction?
a) Applying dimensionality reduction methods like PCA
b) Removing irrelevant features from the dataset
c) Reducing the number of instances by selecting a subset of data
d) Scaling features to a standard range
Answer: c) Reducing the number of instances by selecting a subset of data
6. Which technique is used to remove unimportant or irrelevant features from the dataset?
a) Normalization
b) Feature selection
c) One-hot encoding
d) Data cleaning
Answer: b) Feature selection
7. What does dimensionality reduction refer to in the context of data reduction?
a) Removing duplicate rows from the dataset
b) Reducing the number of input variables or features
c) Scaling data to a uniform range
d) Combining features into a single feature
Answer: b) Reducing the number of input variables or features
8. Principal Component Analysis (PCA) works by:
a) Removing missing values
b) Selecting features based on importance
c) Projecting data into a lower-dimensional space while retaining variance
d) Normalizing data into a fixed range
Answer: c) Projecting data into a lower-dimensional space while retaining variance
9. Which of the following is a potential disadvantage of data reduction techniques?
a) The dataset becomes larger and more complex
b) The original relationships between the data points may be lost
c) The data becomes more redundant
d) It increases the computation time for model training
Answer: b) The original relationships between the data points may be lost
10. In which scenario would you typically use data reduction techniques?
a) When dealing with high-dimensional data
b) When the dataset has too many instances
c) When the data contains outliers
d) When you want to visualize the data in 3D
Answer: a) When dealing with high-dimensional data
11. What is the main purpose of data compression as a data reduction technique?
a) To reduce the dimensionality of data
b) To represent the data in a more compact form without losing information
c) To eliminate missing values
d) To encode categorical variables as numerical values
Answer: b) To represent the data in a more compact form without losing information
12. Discretization in data reduction refers to:
a) Converting continuous features into categorical ones by grouping values into bins
b) Removing outliers from the dataset
c) Scaling all features to a uniform range
d) Reducing the number of data instances
Answer: a) Converting continuous features into categorical ones by grouping values into bins
13. Which of the following is a method used for reducing the number of features?
a) K-means clustering
b) Principal Component Analysis (PCA)
c) Linear regression
d) Outlier detection
Answer: b) Principal Component Analysis (PCA)
14. What is feature extraction in the context of data reduction?
a) Selecting a subset of important features from the original set
b) Creating new features by combining or transforming existing ones
c) Normalizing the data
d) Removing redundant features
Answer: b) Creating new features by combining or transforming existing ones
15. k-means clustering can be used as a data reduction technique in the following way:
a) By selecting the most important clusters to retain
b) By grouping similar instances together and reducing the number of data points
c) By reducing the number of features to a lower dimension
d) By transforming data into a uniform scale
Answer: b) By grouping similar instances together and reducing the number of data points