Q1: Which of the following methods could be used to handle missing numerical values in a dataset? A1: *a. Filling with mean values, b. Dropping rows with NaN values, c. Filling with median values, d. Filling with most frequent values.

Q2: How can outliers be detected with a histogram? A2: *a. By looking for data points that don’t fit in the overall pattern, b. By clustering the data, c. By using the three-sigma rule, d. By calculating variance.

Q3: What does an OneHotEncoder convert categorical features into? A3: *a. Numerical values, b. Images, c. Text, d. Dates.

Q4: What is the Z-score transformation? A4: *a. A normalization technique that brings all values into the same scale, b. A method to handle missing values, c. A visualization technique to detect outliers, d. A convolutional layer of a neural network.

Q5: How could a categorical feature be converted into numerical values? A5: *a. Using LabelEncoder, b. Using Feature Importance, c. Using Robust Scaler, d. Using MinMax Scaler.

Q6: What is the Robust scaler useful for? A6: *a. Normalizing data by scaling them to a given range, b. Handling missing values, c. Detecting outliers, d. Encoding categorical features.

Q7: What does one hot encoding do? A7: *a. It converts categorical values into numerical data by transforming them into boolean values, b. It detects outliers using the three-sigma rule, c. It calculates variance, d. It normalizes data with the Z-score transformation.

Q8: What scaler could be used to transform numerical features into the same range? A8: *a. MinMax scaler, b. OneHotEncoder, c. MaxMin scaler, d. Robust scaler.

Q9: What is the three-sigma rule? A9: *a. A technique to detect outliers, b. A technique to handle missing values, c. A normalization technique, d. A visualization technique.

Q10: What technique would help to convert a categorical feature into two binary values? A10: *a. OneHotEncoder, b. Feature Importance, c. MinMax scaler, d. LabelEncoder.