7. All Big Picture Concepts¶
7.1. From Chapter 1 - Introduction to Data Science¶
The importance of Learning on Your Own
The importance of communication
7.2. From Chapter 2 - Mathematical Foundations¶
Functions and relations
Every table represents a relation.
7.3. From Chapter 3 - Jupyter¶
The structure of Jupyter
How to shut down Jupyter
7.4. From Chapter 4 - Review of Python and pandas¶
Writing to a slice of a DataFrame
7.5. From Chapter 5 - Before and After¶
Explanations before and after code
7.6. From Chapter 6 - Single-Table Verbs¶
The relationship between tall and wide data
7.7. From Chapter 7 - Abstraction¶
The value of abstraction in programming
7.8. From Chapter 8 - Version Control¶
Why people use tools like git
7.9. From Chapter 9 - Mathematics and Statistics in Python¶
Vectorization and its benefits
Models vs. fit models
7.10. From Chapter 10 - Visualization¶
Visualizing relations vs. functions
7.11. From Chapter 11 - Processing the Rows of a DataFrame¶
Informally, map is the same as apply
Important phrases: map-reduce and split-apply-combine
7.12. From Chapter 12 - Concatenating and Merging DataFrames¶
Concat adds rows and merge adds columns (usually!)
7.13. From Chapter 13 - Miscellaneous Munging Methods (ETL)¶
Munging/ETL is a large portion of data work
Information = Data + Context
Summary of key points about missing values
7.14. From Chapter 14 - Dashboards¶
Uses for data dashboards
7.15. From Chapter 15 - Relations as Graphs - Network Analysis¶
A graph depicts a binary relation of a set with itself
How pivoting/melting impacts graph data
7.16. From Chapter 16 - Relations as Matrices¶
What is a recommender system?
The SVD and approximation
7.17. From Chapter 17 - Introduction to Machine Learning¶
Supervised vs. unsupervised machine learning
A central issue: overfitting vs. underfitting
Why we split data into train and test sets