What methods would you use to fill null values in the salary column?

To handle null values in a salary column, I would first analyze the distribution and missingness pattern. If the missingness is random, a simple imputation such as the mean or median is often sufficient. For skewed salary data, median is preferable. If domain knowledge suggests a specific value, a constant (e.g., 0 or a typical entry‑level salary) can be used. For more sophisticated approaches, I might use predictive modeling: train a regression model (linear regression, random forest, XGBoost) on the other columns to predict the missing salary. In Pandas, this can be done with df['salary'].fillna(df['salary'].median(), inplace=True) or using sklearn's SimpleImputer. The choice depends on the business context, the proportion of missing data, and the impact on downstream analytics. Complexity is O(n) for simple fill, and higher for model‑based imputation.