data science learning – Becoming A Data Scientist

Summer of Data Science 2018 #SoDS18 Launch Day!

Renee — Mon, 28 May 2018 17:53:49 +0000

Memorial Day is the unofficial start of summer in the U.S., so in the past, we’ve also used it as the start date for the Summer of Data Science! The main goal of the Summer of Data Science is to learn something new during a fixed period of time, and share your progress and references to help and inspire others (and to get help from and get inspired by others, too!). If you want to learn more about the origin and history of the hashtag, I gave more background in last year’s post.

But I’m sure the main thing you’re here to find out is how to get involved yourself! So, here are the basics:

How to participate in the Summer of Data Science:

Pick a thing or a short list of things related to data science that you want to learn more about this summer (or this winter if you’re in the southern hemisphere!)

Make a plan to learn it (like an online course, a practice project, etc.).

Share that plan on social media, then post updates as you make progress, with the hashtag #SoDS18.

Here’s a twitter moment with a bunch of entries from #SoDS17 for reference!

We’ll run this one from today – May 28, 2018 – through Labor Day in the U.S. – September 3, 2018. What you can realistically get done in that time depends on where you are in your data science learning journey, what your work schedule and family obligations are like, and many other factors – so think about what’s realistic for you to accomplish during this time.

Week 1 will be about brainstorming and researching possibilities and resources for summer projects, courses, etc. And in Week 2 we’ll set specific goals for the rest of the summer. So, start thinking of ideas now!

If you would like some ideas for beginners, here’s a list of beginner content on my site DataSciGuide:
Recommended Resources for Beginners
You might want to pick a book or course and go through it, trying out the exercises this summer.

I also have a Flipboard where I have collected a bunch of Data Science Tutorials you might want to check out (note: these aren’t all aimed at beginners).

There are also a whole bunch of online communities where you can join others in a project, or ask questions if you get stuck on yours. I’ll be writing another post highlighting those this week!

Follow me on twitter @becomingdatasci, and tweet with the hashtag #SoDS18 when you post updates about your progress! (It’s a good idea to “thread” your tweets throughout the summer, or add them to a Twitter Moment, so others can easily follow along!)

I’ll be retweeting a bunch of people’s ideas and resources, so keep an eye out there for more ideas if you aren’t sure where to start!

Becoming a Data Scientist Podcast Episode 12: Data Science Learning Club Members

Renee — Wed, 15 Jun 2016 05:08:12 +0000

Verena, David, Kerry, and Anthony are members of the Becoming a Data Scientist Podcast Data Science Learning Club! They appear in the order in which they joined the club, and each discuss their starting points before joining, their participation in the activities, and advice they have for new data science learners.

Podcast Audio Links:
Link to podcast Episode 12 audio
Podcast’s RSS feed for podcast subscription apps
Podcast on Stitcher
Podcast on iTunes

Podcast Video Playlist:
Youtube playlist of interview videos

More about the Data Science Learning Club:
Data Science Learning Club Welcome Message
Data Science Learning Club Meet & Greet

1) Verena Haunschmid

bioinformatics

R Markdown
ggplot2
jupyter

Data Science Learning Club Activity 07: Linear Regression
Verena’s Results for Linear Regression on Salary Dataset

Verena’s website
@ExpectAPatronum on Twitter

GPS Cat Tracking Project

2) David Asboth

business intelligence

SQL

City University London Msc Data Science

Coursera
Udacity
Khan Academy

Data Science Learning Club Activity 02: Creating Visuals for Exploratory Data Analysis
David’s results exploring London Underground data

Data Science Learning Club Activity 07: K-Means Clustering
David’s results using k-means to draw puppies in 3 colors

FlyLady (the house cleaning system I mentioned)

David’s website
@davidasboth on Twitter

3) Kerry Benjamin

Data Science Learning Club Activity 01: Find, Import, and Explore a Dataset
Kerry’s results for Activity 1 IGN Game Review Data exploration

Data Science Learning Club Activity 02: Creating Visuals for Exploratory Data Analysis
Kerry’s Blog Post about Activity 02 – “My First Data Set Part 2: The Fun Stuff”

ggplot2
dplyr
XLConnect

Blog post about Data Camp – “The Data Science Journey Begins”

Sharp Sight Labs

Kerry’s blog post “Getting Started in Data Science: A Beginner’s Perspective”

#Rstats (twitter hashtag)

Kerry’s Blog “The Data Logs”
@kerry_benjamin1 on Twitter

4) Anthony Peña

molecular biology
biotechnology

Data Science Learning Club Activity 07: K-Means Clustering
Anthony’s results for Activity 07

ggplot2
tidyR
dplyr

R bloggers

Anthony’s website
@agpena_ on Twitter

Data Science Learning Club Update

Renee — Sun, 21 Feb 2016 04:57:51 +0000

For anyone that hasn’t yet joined the Becoming a Data Scientist Podcast Data Science Learning Club, I thought I’d write up a summary of what we’ve been doing!

The first activity involved setting up a development environment. Some people are using R, some using python, and there are several different development tools represented. In this thread, several people posted what setup they were using. I posted a “hello world” program and the code to output the package versions.

Activities 1-3 built upon one another to explore a dataset and generate descriptive statistics and visuals, culminating with a business Q&A:

Activity 1 – Find & Explore a Dataset
Activity 2 – Visuals for Exploratory Data Analysis
Activity 3 – Business Questions & Data Answers

I analyzed a subset of data from the eBird bird observation dataset from Cornell Ornithology for these activities. Some highlights included:

– Learning how to use the pandas python package to explore a dataset (code)

– Learning how to create cool exploratory visuals in Seaborn and Tableau. Here is an example scatterplot matrix made in Seaborn:

– I was most excited to learn how to build interactive Jupyter Notebook inputs, which I used to control Bokeh data visualizations to display Ruby-Throated Hummingbird migration into North America (notebook). Unfortunately, until I host them on a server where you can run the “live” version, you won’t be able to see the interactive widgets (a slider and dynamic dropdowns), but you can see a video of the slider working here:

Here’s my final output for Activity 3, a Jupyter Notebook (with code hidden, and unfortunately interactive widgets disabled) with the Q&A about the hummingbird migration:
Ruby-Throated Hummingbird Migration into North America

Activity 4 was built as a catch-up week for those of us who were behind, but had some ideas of math concepts to learn for those who had time.

We’re currently working on Activity 5, our first machine learning activity where we’re implementing Naive Bayes Classification.

All of my work is available in this github repository: https://github.com/paix120/DataScienceLearningClubActivities

I strongly encourage you to click through the forums and look at some of the other data explorations the members have been doing, including analysis of NFL data, personal music listening habits, transportation in London, German Soccer League data, top-grossing movies, and more!

It’s never too late to join the Data Science Learning Club! If you aren’t sure where to start, check out the welcome message for some clarification.

I’ll post again when I complete some of the machine learning activities!