Data Cleaning in Python Essential Training

1h 6mIntermediate2022-11-09

Authors

Miki Tebeka

CEO at 353Solutions

Course details

If you’re looking for more efficient ways to prepare your data for analysis, it’s time to level up your skill set and reassess your approach to data cleaning. In this course, instructor Miki Tebeka shows you some of the most important features of productive data cleaning and acquisition, with practical coding examples using Python to test your skills. Learn about the organizational value of clean high-quality data, developing your ability to recognize common errors and quickly fix them as you go. Along the way, Miki offers cleaning strategies that can help optimize your workflow, including tips for causal analysis and easy-to-use tools for error prevention.

Skills covered

Data EngineeringPythonData AnalysisProgramming LanguagesData ScienceBusiness Analysis and StrategyBusiness Software and ToolsOpen SourceSoftware DevelopmentDeep Dive (X:Y)

Concepts

0. Introduction

01 - Why is clean data important
02 - What you should know
03 - Using GitHub Codespaces with this course

1. Bad Data

04 - Types of errors
05 - Missing values
06 - Bad values
07 - Duplicates

2. Causes of Errors

08 - Human errors
09 - Machine errors
10 - Design errors
11 - Challenge - UI design
12 - Solution - UI design

3. Detecting Errors

13 - Schemas
14 - Validation
15 - Finding missing data
16 - Domain knowledge
17 - Subgroups
18 - Challenge - Find bad data
19 - Solution - Find bad data

4. Preventing Errors

20 - Serialization formats
21 - Digital signature
22 - Data pipelines and automation
23 - Transactions
24 - Data organization and tidy data
25 - Process and data quality metrics
26 - Challenge - ETL
27 - Solution - ETL

5. Fixing Errors

28 - Renaming fields
29 - Fixing types
30 - Joining and splitting data
31 - Deleting bad data
32 - Filling missing values
33 - Reshaping data
34 - Challenge - Workshop earnings
35 - Solution - Workshop earnings

Conclusion

36 - Next steps