Here are the slides and Python code from the hands-on workshop at Open Data Day DC 2016 where we did k-means clustering after scraping text from NIST's newsfeed:
Slides and code for the Data Analysis with R class I taught at the Data Academy at the US Department of Commerce.
It focuses on using analysis to clean, wrangle, summarize/aggregate/visualize, and select features/models:
Here is the code for this project.
Women In Bio wanted a central repository of mentorship ideas, topics and articles. So I created a bunch of Google Forms to collect that sort of information, the responses for which are saved to a Google spreadsheet that is published to the web (so it is read-only for users with the link).
I created an html file that links to all the forms and spreadsheets and saved that to a folder in Google Drive. This is how I got Drive to host those resources and display them as a website. Note: you may need to change your Drive upload settings so it doesn't automatically convert your html and css files into Google docs format.
In addition to a little force layout visualization (because who doesn't like playing with those? They're so sproingy) I included a bar chart that displays the number of submissions in each form.
One day I will pick up my d3.js, python, twitter and feminism project again.