We maintain the Liip Data Science Stack to help you orient yourself in a highly crowded area. Thats how we want to help you find the right tools in one place. Because we love open source, we have sorted these tools to the top. Enjoy browsing the website or if you are a geek just download the JSON file.
Often just knowing about a myriad of tools won't help you much if you can't connect them to the business question. Don't worry - you are not lost. Our team will help you to select the right approach and methodology for your question. Transform your data into insights and action starting from today.
Stay up to date on the current developments. Subscribe to get a quarterly Email containing all the updates we did to the stack. We won't send you any spam or advertising for our services. Pinky promise.
Search for a technology in the stack.
Where does your data usually come from? For us, it's mainly websites and apps with sophisticated event tracking. Yet for some projects the data has to be scraped, comes from social media outlets or comes from IoT devices.
Social Media
Website Analytics
Tag Management
IoT
Heatmaps
Mobile Analytics
Data Processing
How can we initially clean or transform the data? How and where can we store the logs that those events create? Also from where do we also take additional valuable data?
ETL
Datacleaning
Alerting/Logging
MessageQueue
Database
What options are out there to store the data? How can we search through it? How can we connect big data sources like Hadoop efficiently with existing applications?
Open Data
Database
In Memory/Search
Hadoop Ecosystem
Analysis / ML
Which stats packages are available to analyze the data? Which frameworks are out there to do machine learning, deep learning, computer vision, natural language processing?
Deep Learning
Stats Software
General (focus python)
Assistant
Computer Vision
NLP
ChatBots Framework
Speech
Visualization / Dashboard
What happens with the results? What options do we have to visually communicate them? How do we turn those visualizations into dashboards or whole applications? Which additional ways of communicating with the user beside reports/emails are out there?
General
Dashboards
Javascript
Business Intelligence
What solutions are out there that try to integrate the data sourcing, data storage, analysis and visualization in one package? What solutions BI solutions are out there for big data? Are there platforms/solutions that offer more of a flexible data-scientist approach?
Business Intelligence
BI on Hadoop
Data Science Platforms
Discover More
A recipe for "smart" applications
Building intelligent applications is not just about the technical challenge. How does AI become reality? We share here one of our tools for crafting intelligent, data-intensive software solutions.
The magic of t-SNE for visualizing your data features
In data science we often spend a lot of our time with feature engineering. The t-SNE algorithm gives you a surprising way to visualize the quality of your features!
Real time numbers recognition (MNIST) on an iPhone with CoreML from A to Z
Learn how to build and train a deep learning network to recognize numbers (MNIST),how to convert it in the CoreML format to then deploy it on your iPhoneX and make it recognize numbers in realtime!
Zoo Pokedex Part 2: Hands on with Keras and Resnet50
After learning about the dirty tricks of deep learning for computer vision in part 1 of the blog post series, now we finally write some code to train an existing resnet50 network to distinguis llamas from oryxes. Learn two tricks that allow us to do deep learning with only 100 images.
Poke-Zoo - How to use deep learning image recognition to tell oryxes apart from llamas in a zoo
In this series of blog posts I will show you how to build a "zoo-pokedex app". That's an app that will tell different animals apart in a zoo. This blog post sells the idea of the app and demystifies the two most important basic concepts behind deep learning for image recognition.
Recipe Assistant Prototype with ASR and TTS on Socket.IO - Part 3 Developing the prototype
Learn how to combine automatic speech recognition (ASR) with text to speech solutions (TTS) in a simple hands free recipe assistant prototype that we've build in an innoday at Liip. Part three of three provides the code and shows how we put everything together into a small flask socket.io prototype.
Send us a message
or an Email to thomas.ebermann@liip.ch