![Example: LinkedIn 2006Example: LinkedIn 2006
â[LinkedIn] was like arriving at a conference reception
and realizing you donât know anyone. So you just stand
in the corner sipping your drinkâand you probably
leave early.â
-LinkedIn Manager, June 2006](https://image.slidesharecdn.com/what-is-a-ds-266-340-458-180509154222/85/Intro-to-Python-for-Data-Science-8-320.jpg)
Intro to Python for Data Science
- 1. Intro to Python for DSIntro to Python for DS 2 birds. One stone. Â WIFI: MakeO ces 5Ghz Password: Internet!23 Â http://bit.ly/thinkful-dc-python
- 2. TJ Stalcup Lead DC Mentor @Thinkful API Evangelist @540 Pokemon Master About UsAbout Us
- 4. What's your name? What do you do? Why are you interested in data science or python? About youAbout you
- 5. Online Bootcamp since 2012. We have worked with over 6000 students around the world paired up with over 400 mentors.  We get you ready for a career and guarantee your rst job  92% success rate About ThinkfulAbout Thinkful Local DC Crew
- 6.  Learn why DS is a thing  What is Python  How do we use it with a real world project?  How do I learn more? TONIGHT: Learn Python by DoingTONIGHT: Learn Python by Doing
- 7. What is a Data Scientist?What is a Data Scientist?
- 8. Example: LinkedIn 2006Example: LinkedIn 2006 â[LinkedIn] was like arriving at a conference reception and realizing you donât know anyone. So you just stand in the corner sipping your drinkâand you probably leave early.â -LinkedIn Manager, June 2006
- 9. Enter: Jonathan GoldmanEnter: Jonathan Goldman Data Scientist Joined LinkedIn in 2006, only 8M users (450M in 2016) Started experiments to predict peopleâs networks Engineers were dismissive: âyou can already import your address bookâ
- 10. DS ProcessDS Process Frame the question Collect the raw data Process the data Explore the data Communicate results
- 11. Frame the QuestionFrame the Question What questions do we want to answer? What connections (type and number) lead to higher user engagement? Which connections do people want to make but are currently limited from making? How might we predict these types of connections with limited data from the user?
- 12. Collect the DataCollect the Data What data do we need to answer these questions? Connection data (who is who connected to?) Demographic data (what is the pro le of the connection) Engagement data (how do they use the site)
- 13. Process the DataProcess the Data How is the data âdirtyâ and how can we clean it? âą User input âą Redundancies âą Feature changes âą Data model changes
- 14. Explore the DataExplore the Data What are the meaningful patterns in the data? âą Triangle closing âą Time overlaps âą Geographic overlaps
- 15. Communicate FindingsCommunicate Findings How do we communicate this? To whom? Marketing - this will enable us to sell X more ad space. Results in X more impressions per day Product - this will allow us to build X more features Development - this will allow us to grow our team by X Sales - this will attract X more premium accounts C-Level - this will result in $$$ more revenue 8M - 450M in 10 years
- 16. The ResultThe Result   Career Whack-A-Mole
- 17. Why DS now?Why DS now? Big Data: datasets whose size is beyond the ability of typical database software tools to capture, store, manage, and analyze
- 18. Big DataBig Data Trend "started" in 2005 Web 2.0 - Majority of content is created by users Mobile accelerates this â data/person skyrockets
- 19. The Data ProblemThe Data Problem We are generating more data every year than existed before.........
- 20. The SolutionThe Solution There goes my hero.... Â watch 'em as they code....
- 21. Just need to do everything....Just need to do everything....
- 22. Just need to do everything....Just need to do everything.... Knowledge of statistics, algorithms, & software Comfort with languages & tools (Python, SQL, Tableau) Inquisitiveness and intellectual curiosity Strong communication skills Itâs all Teachable!
- 23. Coming Soon....Coming Soon.... Intro to SQL Intro to Tableau Intro to Statistics  http://meetup.com/Thinkful-DC
- 24. Let's Learn Python TonightLet's Learn Python Tonight Python for Programming Great for Data Science Robotics Web Development (Python/Django) Automation
- 25. Let's Learn Python TonightLet's Learn Python Tonight firstName = 'TJ' lastName = "Stalcup" age = 34 // wow, much old print firstName // TJ print firstName + lastName // TJStalcup print firstName + ' ' + lastName // TJ Stalcup print lastName + ', ' + firstName // Stalcup, TJ print age * 2 // 68, hopefully retired def greet(name): print 'Hello', name greet('Jack') // Hello, Jack greet('Jill') // Hello, Jill greet('Bob') // Hello, Bob greet(firstName) // Hello, TJ greet(firstName + ' ' + lastName) // Hello, TJ Stalcup
- 26. The ModelThe Model Our model is going to be a Decision Tree. Â Decision trees predict the most likely outcome based on input. Â You can think of it like a computer building a version of 20 questions.
- 27. Decision Trees - Golf?Decision Trees - Golf?
- 28. The NotebookThe Notebook We're going to use a Google hosted Python to build this model. This app is called Colaboratory (Collaboration + Laboratory)  http://colab.research.google.com  New Notebook > New Python3 Notebook notebook
- 29. ShortcomingsShortcomings Our model has a few weaknesses: Â -Limited inputs -Assumptions
- 30. Data Science @ ThinkfulData Science @ Thinkful Flexible, project-based curriculum to help you become the data scientist you want to be You donât just learn skills, you get to make things Mentor support from experts in the industry Also, there's a job guarantee
- 31. Link for the third party audit jobs report: https://www.thinkful.com/bootcamp-jobs-stats Thinkful Graduates 92% Job Placement Rate
- 32. Learning Mentor Career MentorProgram Manager Local Community You Unprecedented SupportUnprecedented Support
- 33. http://bit.ly/dc-ds-trial Initial 2-week trial course Start with Python and Statistics Unlimited Q&A Sessions Option to continue with full bootcamp Financing & scholarships available O er valid for tonight only Aaron Lamphere Trial Program Manager  Thinkful Two Week TrialThinkful Two Week Trial