The code below is a small project which uses LSTM cells in Tensorflow to build an RNN. This network is trained to generate hurricane & tropical storm advisories. The dataset originates from the National Hurricane Center’s archives from…
BigQuery: https://bigquery.cloud.google.com/dataset/jbencina-144002:fb_news
GitHub (Data & Script): https://github.com/jbencina/facebook-news
The other day, I came across a dataset on Kaggle posted by Zach Thoutt which contained roughly 150,000 wine reviews scraped from Wine Enthusiast magazine. The dataset contains the price of the…
I was curious to see what kinds of blocked connection attempts were being made on my home router. I wrote this small notebook script which connects via SSH to the router and downloads all available logs into a local CSV…
In this series of posts, I collect and analyze NYPD motor vehicle collisions along with NOAA weather data. If you missed part one, head over there to find how the data was collected. You can also find the relevant Python…
On any given day, there are 200 to 400 motor vehicle collisions reported to the NYPD in New York City. This collision data has been made available through the NYC Open Data project and can also be found through Google’s…
I came across an interesting dataset on Google’s BigQuery containing the play-by-play data for 2016 MLB games. The data has been denormalized and can be a little tricky to work with at first. I suggest looking over the examples provided…
In this post, I summarize how you can use text within Amazon review data to identify topics and predict user rating. A more detailed discussion with examples can be found in the notebook at the end of this…
