rnn
I tend to focus a lot on how the data is wired, snipped, and prepared for models. I think the preprocessing steps of data lay the foundations by which all models are built and provides me a highly valuable exercise to understand the nooks and crannies of my dataset, especially
tx2
I'm starting to do a lot more with GPUs. At my company, I'm one over several data scientists that routinely access our cluster of 4 Titan cards. It's an older cluster, but we're upgrading across the country including bringing online a DGX-1
regex
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
linux
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/ You've successfully launched
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
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
ensemble
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
seaborn
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.
EDA
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
hdp
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
colorama
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.
random forest classifier
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