Cheatsheet¶
This page has helpful reminders
Jupyter Notebooks¶
Jupyter Notebooks are a computational tool for writing code and combining it with text.
Action |
How to |
|---|---|
execute a cell (block in the notebook) |
shift + enter (windows/linux) or shift + return (mac) |
get help for a Function |
shift + tab inside |
Vocabulary¶
term |
definition |
|---|---|
recidivism |
() measured approximately through |
COMPAS |
Correctional Offender Management Profiling for Alternative Sanctions a recidivisism risk assessment tool that is used by many police departments across the United States |
Propublica |
journalists |
Northpointe |
company that makes and sells COMPAS |
Broward County, FL |
Florida county where the Propublica collected the data for their investigation |
algorithm |
a set of specific instructions to solve a problem |
Jupyter Notebook |
an interface for coding that combines a text editor, interactive terminal, and visualization tool |
Python |
a programming language that is popular for data science |
protected attribute |
a variable in the dataset that we want to protect against discrimination with respect to (eg race, gender, or age); derives from the legal concept of protected class and the database terminology of referring to attributes |
Pandas¶
[pandas] is a data analysis library in python, it is fully open source and has detailed documentation online.
Below are some useful references just for this activity
function |
description |
example |
|---|---|---|
|
load data from a comma separated values (csv) files |
|
|
get basic statistics that summarize a dataset |
|