- Regular expresssions tutorial
Here’s an introduction to Python’s regex module. Alex Yang also provides common use cases and shows how to combine regex with Pandas to create flexible workflows.- On-device deep learning for facial recognition
The Apple Computer Vision Machine Learning Team explains the challenges they faced—and how they overcame them—in creating a low-latency, private deep learning inference for face detection in their Vision framework.- Using Python for data analysis
In this episode of the O’Reilly Programming Podcast, Katharine Jarmul and Jeff Bleiel discuss wrangling data with Python’s libraries and packages.
Last chance for Best Price: Save up to $400 on Strata 2018 passes
Where top data scientists, analysts, engineers, and executives converge—and the only place that cuts across vendors, technologies, and frameworks.
Strata Data Conference- Comparative audio analysis with Wavenet, MFCCs, UMAP, t-SNE, and PCA
This post takes a look at an audio dataset in two dimensions, using algorithms such as NSynth, UMAP, t-SNE, MFCCs, and PCA, and shows how to implement them in Python using Librosa and TensorFlow.- Data-driven in the media industry
In this episode of the O’Reilly Media Podcast, David Hsieh, senior vice president of marketing at Qubole, sat down with John Slocum, vice president of MediaMath’s data management platform, to discuss DataOps in the media industry.Check out the first Media, Entertainment, and Advertising track at the Strata Data Conference in San Jose, March 5–8, 2018.
In collaboration with MarkLogic
Free excerpt: Learning SPARQL
SPARQL is the RDF query language that’s bringing new possibilities to semantic web, linked data, and big data projects. Learning SPARQL shows you how to use SPARQL 1.1 with a variety of tools to retrieve, manipulate, and federate data from the public web as well as from private sources.And you can get chapters 2 and 7 free, courtesy of MarkLogic.
Get the free excerpt →
6. Can an algorithm predict when you will die?
Stanford University researchers developed a neural network that can determine a patient’s chance of dying in the next three to 12 months, according to MIT Technology Review. The purpose is to more effectively deliver palliative care.
7. Docker for data science
Here’s a quick intro to Docker for data scientists.Related resources:
Getting Started with Docker Learning Path (on the Safari learning platform)
Docker: Beyond the Basics (live online course on Safari, Jan 24-25)
Accelerating development velocity of production ML systems with Docker (session at Strata in San Jose)
8. Do you drive a Honda Accord?
“You are what you drive, as the saying goes, and researchers at Stanford have just taken that maxim to a new level.” Here’s how the car you drive can determine how you will vote.
4 este interesant. am avut o tentativa de a ma jca cu librosa pe micutul pi