How To Predict ICU Mortality with Digital Health Data, DL4J, Apache Spark and Cloudera

Categories: CDH Data Science Spark

Modeling EHR Data in Healthcare

In this case study, we take a look at modeling electronic health record (EHR) data with deep learning and Deeplearning4j (DL4J). We draw inspiration from recent research showing that carefully designed neural network architectures can learn effectively from the complex, messy data collected in EHRs. Specifically, we describe how to train an  long short-term memory recurrent neural network (LSTM RNN) to predict in-hospital mortality among patients hospitalized in the intensive care unit (ICU).

Read more

Customizing Docker Images in Cloudera Data Science Workbench

Categories: Altus CDH Cloud Data Science How-to Tools

This article shows how to build and publish a customized Docker image for usage as an engine in Cloudera Data Science Workbench. Such an image or engine customization gives you the benefit of being able to work with your favorite tool chain inside the web based application.


Cloudera Data Science Workbench (CDSW) enables data scientists to use their favorite tools such as R, Python, or Scala based libraries out of the box in an isolated secure sandbox environment.

Read more

Deep Learning with Intel’s BigDL and Apache Spark

Categories: CDH Data Science Hadoop Spark

Cloudera recently published a blog post on how to use Deeplearning4J (DL4J) along with Apache Hadoop and Apache Spark to get state-of-the-art results on an image recognition task. Continuing on a similar stream of work, in this post we discuss a viable alternative that is specifically designed to be used with Spark, and data available in Spark and Hadoop clusters via a Scala or Python API.

The Deep Learning landscape is still evolving.

Read more

Accessing Secure Cluster from Web Applications

Categories: CDH Hadoop How-to

As customers use Apache Hadoop clusters in ways other than through HUE and Hadoop Command Line Interface (CLI) and integrate it closely with the applications they develop, we often get asked how to access their secure Hadoop cluster from within the custom applications. Many customers use a service account in their application and access the cluster with a fixed service account. However, other customers would like to access as the end users who have authenticated to the application.

Read more

Implementing Temporal Graphs with Apache TinkerPop and HGraphDB

Categories: Graph Processing Hadoop HBase How-to

When most people think of Big Data, often they imagine loads of unstructured data. However, there is always some sort of structure or relationships within this data. Based on these relationships there are one or more representation schemes best suited to handle this type of data. A common pattern seen in the field is hierarchy/relationship representation. This form of representation is adept in handling scenarios like complex business models, chain of event or plans, chain of stock orders in banks,

Read more