Accelerate large-scale machine learning with NP on MXNet

Addressing the Scarcity of Data Scientist

ADTK: An open-source Python toolkit for anomaly detection in time series

AI pipelines powered by Jupyter notebooks

An Introduction to Sentiment Analysis of Textual Data

Becoming a Data Head, a reflection on the trade offs and decision points in build a data team

Building a User Maintainable Visualization Dashboard for the Large Synoptic Survey Telescope (LSST)

Customizing JupyterLab using extensions

Develop Data Science for Business Value: a Phoenix Story

Enhancing Common Natural Language Processing with Cognitive Linguistics

Evaluation of Cloud Hosting Frameworks for Machine Learning Based Equipment Monitoring

Extending Python Into the Future

Frictionless Data Pipelines

Hyperrest: A new Apache Arrow API For High Performance Data Access in Pandas

Introducting Dask-Gateway: Dask clusters as a service

Lightning Talks

Machine Learning Crash Course

metadsl: separating API from execution

Multilingual embeddings to scale NLP models to multiple languages

Objectionable Content

Panel: Dashboards for PyData

Productionalizing a Data Science Team

Putting Tensorflow Models into Production

Q&A with Keynote Katrina Riehl

Q&A with Keynote Travis Oliphant

Recommendations at Rappi: from MVP to Data Product

Saving Animals with Data: 3 Case Studies in Applying Advanced Technology in Animal Shelters

Speeding up Machine Learning tasks using GPUs in Python

The Cortex in the Code: How Neuroscience Makes AI Intelligent

uarray: Separating interface from implementation

Values-based OSS Open Discussion

Visualizing Machine Learning of Units of Measure using PyViz

What the...? Data Science Questions Asked and Answered

Working interactively with large and remote datasets in JupyterLab