Top Banner
An Obligatory Introduction to Data Science
29

An Obligatory Introduction to Data Science

Apr 12, 2017

Download

Data & Analytics

Wesley Eldridge
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: An Obligatory Introduction to Data Science

An Obligatory Introduction to Data Science

Page 2: An Obligatory Introduction to Data Science

Wesley Eldridge

Rebellious Labs

Software Engineer

University of AlabamaBSBA - Applied Economics

Page 3: An Obligatory Introduction to Data Science

Agenda

● The dirty history of data science● Data scientist roles● Using data in your product and business● Tools and resources to get started

Page 4: An Obligatory Introduction to Data Science

Before there was data science

Page 5: An Obligatory Introduction to Data Science
Page 6: An Obligatory Introduction to Data Science

Big Data

Page 7: An Obligatory Introduction to Data Science

Data Scientist

Page 8: An Obligatory Introduction to Data Science

What is a data scientist?

Page 9: An Obligatory Introduction to Data Science

“...data scientists do three fundamentally different things: math, code (and engineer systems), and communicate.”

- Hilary Mason

Page 10: An Obligatory Introduction to Data Science

Math &

StatsEngineering

Communication

Data Scientist

nerd

nerd

nerd

Page 11: An Obligatory Introduction to Data Science

What do data scientists do?

Page 12: An Obligatory Introduction to Data Science
Page 13: An Obligatory Introduction to Data Science

How to use data in your products and organization

Page 14: An Obligatory Introduction to Data Science

Collect all the data!

Page 15: An Obligatory Introduction to Data Science

“Data by itself is useless. Data is only useful if you apply it.” - Todd Park

Page 16: An Obligatory Introduction to Data Science
Page 17: An Obligatory Introduction to Data Science

Finding or building data

Page 18: An Obligatory Introduction to Data Science

“Many social/digital scientists are reluctant to invest in making data because it’s much more costly and risky than

analyzing data you already have available.” - Sean Taylor

Page 19: An Obligatory Introduction to Data Science

Using data to understand the question

Page 20: An Obligatory Introduction to Data Science

Metrics to define the success of the model

Page 21: An Obligatory Introduction to Data Science

Presenting the data to stakeholders or users

Page 22: An Obligatory Introduction to Data Science

1. Ask a question

2. Finding or building data

3. Using that data to understand the question

4. Presenting the data to stakeholders or users

Page 23: An Obligatory Introduction to Data Science

Building products and processes for better data

Page 24: An Obligatory Introduction to Data Science
Page 25: An Obligatory Introduction to Data Science

Do do not worry about the tools. Hire smart people and they will bring the tools with them.

Page 26: An Obligatory Introduction to Data Science

How do I become a data scientist?

Page 27: An Obligatory Introduction to Data Science

Start smallLearn to code● Python● JavaScript

Learn to move data● SQL ● Mongo

Learn to question everything● No gut feelings● Data-based decision making

Find some data and play with it.● Government/municipality data● Social data● Open data

Online learning● Kaggle.com● Udacity.com● Lynda.com

Develop math skills● Regression● Error analysis● Data distributions● Linear Algebra

Page 28: An Obligatory Introduction to Data Science

Then What?Mathematical Modeling● Logistics regression● One hot encoding● Decision trees● Correlation● Model assumptions

Data visualization● D3.js● Tell a story

Help a non-profit/municipality● Open up their data● Tell their story● Solve a problem

bit.ly/2bxnQgb

Page 29: An Obligatory Introduction to Data Science

Questions?@weseldridge