Skip to main content

Ctrl+K

Coding for data

What is data science?
Why Data Science?
Tools and techniques
- Computational Tools
- Statistical Techniques
Text is data
Surviving the computer
Our tools
Using Jupyter notebooks
More on the Jupyter notebook

On code

Ode to code
A sampling problem
A simpler problem
Introduction to variables
Variables in code and mathematics
Names and variables
Expressions
Introduction to functions
Call expressions
Expressions, and decoding code
A first pass at the simple problem

Data types

Types of things
Numbers
Strings
Strings, variables and expressions
String methods
Comparisons
Lists

Arrays

Arrays
Ranges
More on Arrays
Selecting values from an array
Making and filling arrays.
Function arguments
Random choice
Boolean arrays
Leaping ahead

Iteration

Iteration
Indentation, indentation, indentation
Reply to the Supreme Court
Inference

Population and permutation

Population and permutation
The idea of permutation
Permutation and the t-test
Permutations and pairs

Data frames

Data frames
Indexing with Boolean arrays
Introduction to data frames
The DataFrame and the index
Selecting columns from DataFrames
Sorting, heads and tails
Series are like arrays
Selecting rows from DataFrames
Value counts

Advanced indexing in Pandas

Indexing in Pandas
The doctrine of Pandas indexing
Assignment with indexing
Pandas and indexing expressions

Crosstabulation and inference

Cross-tabulation
Numpy repeat
Lady tasting tea
Counts to observations
Chi-squared and the lady tasting tea
Noble politics and comparing counts

Useful Pandas

Missing values
Pandas plotting methods
The power of groupby
Merging

Pandas pitfalls

Handling Pandas safely
Storing and loading text
Numbers and strings

More building blocks

More building blocks
Introducing Functions
On None
Functions
Conditional Statements
Functions as values
Apply functions

The mean and straight lines

The mean
The meaning of the mean
Argmin (and argmax)
The mean and slopes
Sum of squares, root mean square
Optimization
Finding lines
Using minimize
Inference on slopes
Combining boolean arrays
Standard scores
Correlation

Classification

Classification
Nearest neighbors
Training and testing
Rows of tables
Implementing the classifier
Accuracy of the classifier
Multiple regression
Simple and multiple regression

More on regression

Logistic regression

Confidence

On confidence
The Bootstrap
A problem for the education minister
The Central Limit Theorem
The law of large numbers
Laws of probability
First Bayes
Bayes theorem
Bayes and bars
Confident treatment
Bayes, confidence

The end of the beginning

The end of the beginning

Extra pages

Notes
More on lists
Introduction to Python
Brisk introduction to Python
Using the pathlib module
The Monty Hall problem, with lists
Data 8 explanation of functions
Why the differences from the mean must add to zero.
The mean and squared differences
Mathematics for the least-squares slope

Repository
Open issue

Index

By Matthew Brett, Ani Adhikari, John Denero, David Wagner

© Copyright 2023.