You're reading from Hands-On Data Preprocessing in Python Learn how to effectively prepare data for successful data analytics

Product type Paperback

Published in Jan 2022

Publisher Packt

ISBN-13 9781801072137

Length 602 pages

Edition 1st Edition

Languages

Python

Tools

Azure Functions

Concepts

Big Data

Author (1):

Roy Jafari

Preface

1. Part 1:Technical Needs

2. Chapter 1: Review of the Core Modules of NumPy and Pandas FREE CHAPTER

3. Chapter 2: Review of Another Core Module – Matplotlib

4. Chapter 3: Data – What Is It Really?

5. Chapter 4: Databases

6. Part 2: Analytic Goals

7. Chapter 5: Data Visualization

8. Chapter 6: Prediction

9. Chapter 7: Classification

10. Chapter 8: Clustering Analysis

11. Part 3: The Preprocessing

12. Chapter 9: Data Cleaning Level I – Cleaning Up the Table

13. Chapter 10: Data Cleaning Level II – Unpacking, Restructuring, and Reformulating the Table

14. Chapter 11: Data Cleaning Level III – Missing Values, Outliers, and Errors

15. Chapter 12: Data Fusion and Data Integration

16. Chapter 13: Data Reduction

17. Chapter 14: Data Transformation and Massaging

18. Part 4: Case Studies

19. Chapter 15: Case Study 1 – Mental Health in Tech

20. Chapter 16: Case Study 2 – Predicting COVID-19 Hospitalizations

21. Chapter 17: Case Study 3: United States Counties Clustering Analysis

22. Chapter 18: Summary, Practice Case Studies, and Conclusions

23. Other Books You May Enjoy

Exercises

The chapter asserts that before using KNN, you will need to have your independent attributes normalized. This is certainly true, but how come we were able to get away with no normalization when we performed KNN using visualization? (See Figure 7.3.)
We did not normalize the data when applying Decision Trees to the loan application problem. For practice and a deeper understanding, apply Decision Trees to the normalized data, and answer the following questions:
a) Did the conclusion of Decision Trees change? Why do you think that is? Use the mechanism of the algorithm to explain.
b) Did the Decision Trees tree-like structure change? In what ways? Did the change make a meaningful difference in the way that the tree-like structure could be used?
For this exercise, we are going to use the Customer Churn.csv dataset. This dataset is randomly collected from an Iranian telecom company's database over a period of 12 months. A total of 3,150 rows of data, each representing...