Sign in Subscribe

Catherine Ordun

Catherine Ordun

PhD Student at UMBC - Healthcare AI and Computer Vision

📍 Washington, D.C.

RegEx and News APIs

It's been a very long time since my last blog post, although I've been updating this one /2017/10/12/kibana-dashboard-for-amazon-food-reviews/, as recently as yesterday under the "Troubleshooting" section. Lately I've been working on a variety of models ranging from LSTMs for

Basic scp command to up/download

Fantastic! You finally followed all the tutorials and stood up your first Amazon AMI Deep Learning Notebook. https://aws.amazon.com/blogs/machine-learning/get-started-with-deep-learning-using-the-aws-deep-learning-ami/ https://livebook.manning.com/#!/book/deep-learning-with-python/appendix-b https://kenophobio.github.io/2017-01-10/deep-learning-jupyter-ec2/ ![](/content/images/2018/01/Screen-Shot-2018-01-22-at-5.43.16-PM.png)You've successfully launched

Deploying an R Shiny App to AWS

For a recent company project, I helped deploy an R Shiny app developed by a teammate to AWS. There are multiple blogs online that provide great, detailed instructions on how to do this. After doing it several times now, I wanted to share the website that I thought provided the

Kibana Dashboard for Amazon Food Reviews

I recently had the privilege of competing with my company's team at the State of Virginia Datathon [https://data.virginia.gov/datathon-2017], a hackathon merging policy innovations as well as data science work to find ways to fight the opioid crisis in Virginia. One of the things aside

Murder Accountability Project - Part 3 Predicting Murder by a Voting Classifier

Introduction Scikit learn has good documentation on how to write your own ensemble, through a voting classifier which can be written as 'hard vote' or 'soft vote'. Soft voting uses weights, and for this post I'll use weights based on the predictions generated from

Murder Accountability Project - Part 2 Looking at Weapons and Relationships

Part 2 - Weapon Trends At this point we can start looking at some of the weapon trends. crime_time = pd.pivot_table(data2,index=["Year", "Weapon"],values=["Record ID"],aggfunc=[len]) crime_time.reset_index(inplace=True) crime_time.columns.droplevel() crime_time.

Murder Accountability Project - Part 1 Data Prep and Map

The first job I ever had out of college was as an autopsy tech assistant at the Fulton County Medical Examiner's Office. I helped out first as an intern at DeKalb County on death scene investigations, and later after college in Fulton County helping the techs perform autopsies

Setting up Hortonworks Sandbox

It's time to learn how to process data at scale. I've always wanted to learn Hadoop and the nifty Apache tools, most notably Zeppelin. So in my quest to try out a Zeppelin notebook, I need to first start and download the Hortonworks Data Platform, or

Hello, 1983

My boss asked me the other day if I could automate a Python notebook I wrote about analyzing the content of customer comments made about experiences with staff. I said sure. Me: What do you mean automating ? Boss: Like, making it easy so I can just "run" it.

Predicting Animal Shelter Outcomes

I was preparing to give a talk for some important Veteran Advocacy Non-Profits here in DC the other day, and wanted to provide an easy to understand example of machine learning and classification. So, I found this interesting data set on Kaggle [https://www.kaggle.com/c/shelter-animal-outcomes/data] from