Questions to answer

1. What does a data science project usually involve? What is the common theme across data science projects?

2. Does industry projects and research projects differ? Why and to what extent?

3. What are the some dataset repositories? Where can you get them?

4. Are all public datasets perfect for doing a project?

5. Can you get one dataset with all required data?

6. if you have different datasets with part of the data that you need -- what do you do? do you just abandon the project?

7. True or false. you get a dataset and then directly apply your algorithm to get the answer or to predict?

8. Is there any benefit to check the data details such as see the distribution of the data? mean and median and mode of the data?

9. What are the usual steps in a data science research project?

10. what is univariate analysis?

11. what is bivariate analysis?

12. is multivariate analysis?

13. Why do you do univariate, bivariate or multivariate analysis?

14. What is exploratory data analysis?

15. What are the two types of exploratory data analysis.

16. What are the pros and cons of visualizing the raw data?

17. Is there any need to use clustering while doing data exploration? or this can be more of a methodology of the research process?

18. what is data synthesis?

19. What is study selection?

20. What do the materials and methods section in a data science research project contain?

21. Difference between Methodology and experiment?

22. Difference between Exploratory analysis step and methodology step?

23. What makes a good experiment?

24. what is a regression analysis? Can it be an exploratory analysis? can it be as part of experimental analysis.

25. what is PCA?

26. What is Principal Component Analysis?

27. What is factor analysis?

28. True or false => PCA and Factor analysis do the same thing i,e. they are the same? why, why not explain

29. What is the measure name that indicates whether factor analysis is required or not

30. With PCA, you can always ignore the similar behaving/contributing features?

31. can you find out the purpose of decision trees, SVM, deep learning. is there an opportunity to apply those for the project in concern? to what extent and how? is ther any more work to do for the dataset preparation?

32. Can you write Python code to visualize a feature with a box plot? If not, can you google/startpage to find out the code and implement? What does the Boxplot for this feature saying?

33. what are the prediction methodology used in the project? Which one performed the best? Does the result make sense? Does the perfect result make sense? Do you think there can be bias and the code will not be able to give similar output for other datasets?

34. What are the measures used for prediction performance?

35. What was used for the project: Linear/Polynomial Regression or Logistics Regression. What is a better measure between these two for this project or in general?

36. True or false, Logistic regression is for Regression

37. True or false, Linear regression is for Classification

38. What is the significance of R square? Low or high values of R square is desirable to say that the Regression outcome is important?

39. What is f-score?

40. What is the train-test-split method in Python?

41. Did I use SQL in the project? Was that a must? What else could you do?

42. Can you join multiple dataframe (i.e. table) in Python? Do you have left, right, inner or similar joins in Python.

By

Sayed Ahmed

Linkedin: https://ca.linkedin.com/in/sayedjustetc

Blog: http://Bangla.SaLearningSchool.com, http://SitesTree.com
Online and Offline Training: http://Training.SitesTree.com

If you want to contribute to the operation of this site including occasional free online training (using Skype, Zoom.us): http://Training.SitesTree.com (or charitable/non-profit work in the education sector), you can financially contribute to: safoundation at salearningschool.com using Paypal. Sometime, we also provide

Affiliate Links:
Hottest Deals on Amazon USA: http://tiny.cc/38lddz

Hottest Deals on Amazon CA: http://tiny.cc/bgnddz

Hottest Deals on Amazon Europe: http://tiny.cc/w4nddz