ODSC Workshop on Experimental Reproducibility in Data Science
On May 2nd, we presented at the Open Data Science Conference in Boston, MA. We demonstrated how to build a machine learning project from scratch with Sacred, an open source library for experiment tracking, and how to view the results using Sacredboard.
Negative Sampling (in Numpy)
Alright, time to have some fun exploring efficient negative sampling implementations in NumPy…
Airing Out A New Job System
In this article I’ll be sharing some of the knowledge the Data team at Gilt picked up in replacing our old job system with Apache Airflow. We undertook the decision to overhaul our job orchestration system a few months ago due to a number of reasons but have now successfully migrated all our data ingestion jobs to the new system.
Sundial or AWS Batch, Why not both?
About a year ago, we (the Gilt/HBC personalization team) open sourced Sundial , a batch job orchestration system leveraging Amazon EC2 Container Service.
Visually Similar Recommendations
Pau Carré Cardona To Speak at O'Reilly AI Conference
The O’Reilly Artificial Intelligence Conference is coming to New York City in June. From June 27-29, the top minds in AI will be meeting for “a deep dive into emerging AI techniques and technologies with a focus on how to use it in real-world implementations.”
Deep Learning at GILT
Cognitive Fashion Industry Challenges
How to convert fully connected layers into equivalent convolutional ones
Importing Google Trends data
Google Trends offers a trove of data for analysis. It’s not used nearly enough partially because good folks at Google did not provide an API to access the data. You can play with Trends in you browser, embed it into your webpages but it’s not that simple to get the raw data behind it to use it in your analysis.There is a number of packages in Python, Perl, or R...