Questions

1. What are some of the main ways of collecting datasets for a data science project?
2. Can Git LFS be used with Git? If so, what is the overall process?
3. Which type of attribute can have their missing values filled out with the mean? What about the mode?
4. What problem does one-hot encoding address? What problem can arise from using one-hot encoding?
5. Which type of attribute can benefit from bar charts? What about distribution plots?
6. Why is it important to consider the feature correlation matrix for a dataset?
7. Aside from predictive tasks, what can we use machine learning models for (like we did in this chapter)?