Oreilly – Starting Data Analytics with Generative AI and Python, Video Edition 2024-11

Oreilly – Starting Data Analytics with Generative AI and Python, Video Edition 2024-11 Downloadly IRSpace

Aug 16, 2025 - 07:14 Updated: Aug 17, 2025 - 19:51

0 0

Oreilly – Starting Data Analytics with Generative AI and Python, Video Edition 2024-11

Starting Data Analytics with Generative AI and Python, Video Edition. This course teaches you how to improve the speed and accuracy of your data analysis by combining the capabilities of ChatGPT and Python. Designed for all levels, from beginners to experts, this course focuses on practical applications of data analysis and is prepared by experienced professionals. You will learn how to write effective queries for ChatGPT, perform descriptive analysis, create an environment suitable for data analysis, assess data quality, and generate reliable reports. You will also optimize coding and tune data processing pipelines using artificial intelligence. This course shows you how to use artificial intelligence tools to implement analytical techniques with simple commands, while also gaining awareness of the limitations and risks of this technology. With a basic knowledge of data analysis, you can significantly reduce the time to complete projects. By the end of the course, you will be able to achieve faster and better results with less effort. From data collection and cleaning to selecting statistical methods and presenting results, this course will guide you through all stages of data analysis and enhance your skills.

What you will learn:

Writing Great Prompts for ChatGPT
Performing end-to-end descriptive analysis
Setting up an AI-friendly data analysis environment
Assess the quality of your data
Developing a strategic analysis plan
Generating code for analyzing non-textual data
Directly inspect text data with ChatGPT
Providing reliable reports

Who is this course suitable for?

Enthusiastic data analysts looking to learn data discovery methods.
Beginner Data Engineers looking to improve their data manipulation skills.
Data Engineers looking to use generative AI in their Data Pipelines.
Experienced professionals looking to increase speed and efficiency in data analysis.

Course details

Publisher: Oreilly
Instructor: Marian Siwiak , Marlena Siwiak , Artur Guja
Training level: Beginner to advanced
Training duration: 13 hours

Course headings

Chapter 1. Introduction to the use of generative AI in data analytics
Chapter 1. The role of generative AIs in data analytics
Chapter 1. Getting started with generative AIs for data analytics
Chapter 1. Summary
Chapter 2. Using generative AI to ensure sufficient data quality
Chapter 2. A note on best practices
Chapter 2. Getting started
Chapter 2. Quality assessment structure
Chapter 2. Data cleaning
Chapter 2. Exploratory data analysis
Chapter 2. Summary
Chapter 3. Descriptive analysis and statistical inference supported by generative AI
Chapter 3. Analysis design
Chapter 3. Descriptive data analysis
Chapter 3. Inferential analysis
Chapter 3. Summary
Chapter 4. Using generative AI for result interpretations
Chapter 4. Popularity of product categories
Chapter 4. Performance of products in their categories and regions
Chapter 4. Review scores distribution analysis
Chapter 4. Order status
Chapter 4. Relationship between product attributes and the shipping costs
Chapter 4. Relationship between product, transaction, shipping attributes, and the review score
Chapter 4. Differences in sales performance and customer satisfaction between sellers
Chapter 4. Summary
Chapter 5. Basic text mining using generative AI
Chapter 5. Preparing for analysis
Chapter 5. Frequency analysis
Chapter 5. Co-occurrence analysis
Chapter 5. Keyword search
Chapter 5. Dictionary-based methods
Chapter 5. Summary
Chapter 6. Advanced text mining with generative AI
Chapter 6. Sentiment analysis
Chapter 6. Text summarization
Chapter 6. Summary
Chapter 7. Scaling and performance optimization
Chapter 7. Improving code performance
Chapter 7. Cloud-based deployment
Chapter 7. Code conversion
Chapter 7. Summary
Chapter 8. Risk, mitigation, and tradeoffs
Chapter 8. General best practices
Chapter 8. AI delusion and hallucination risks
Chapter 8. Mitigating misinterpretation and miscommunication risks
Chapter 8. Model bias and fairness risks
Chapter 8. Privacy and security risks
Chapter 8. Legal and compliance risks
Chapter 8. Emergent risks
Chapter 8. Summary
Appendix B. On debugging ChatGPT’s code
Appendix C. On laziness and human errors