The recent upgrade of the Streaming Analytics service on Bluemix also includes integration with the IBM Data Science Experience (DSX) platform. This allows you to create Streaming analytics applications in Python right in your browser!
What is the Data Science Experience?
The Data Science Experience (DSX) is an interactive, collaborative environment that allows you to quickly extract insights from your data. You can create your applications using popular languages like Python, R, and Scala, Jupyter Notebooks, Spark, RStudio and more. DSX has built in tutorials and notebooks, and even sample datasets! You can also import data from files, on-prem or cloud databases including dashDB, Cloudant, Object Storage, and the list is growing. It also makes it easy to build appealing visualizations using PixieDust and share content with others via GitHub.
Data Science Experience and Streaming Analytics
With the integration of DSx and Streaming Analytics, you can now create Python notebooks to analyze real-time data without having to store the data first or install any software. Using the Data Science Experience platform allows you to gain insights from data at rest, and now, you can gain insights from real time data by integrating with the Streaming Analytics service. You can now build and your applications in Python right from the DSX environment, without having to install Streams!
- Use your models and algorithms on real time data:
For example, you could create a Python application to predict the likelihood that a given engine will fail based on its temperature. After creating a model and training the model on historic failure data, you can submit the application to the service to run the model on real time data readings. You could even configure the application to alert you if a failure is imminent.
- Retrieve the analysis results from the service and visualize them within the notebook:
Create useful visualizations for your streaming data using Bokeh, Matplot, PixieDust, and more. More on this below.
With the launch of this feature, we have included 3 Python notebooks to help you get started. More notebooks will be added in the future, so be sure to check the DSX Community page or the IBM Streams samples catalog for the latest.
Included in the samples is a basic “Hello, World” notebook, which is a great way to verify that your connection to Streams from DSX is working properly.
We also released the Healthcare Analytics demo notebook, which uses the Streams Healthcare Analytics platform. In this notebook, you create a Streams application that monitors and analyzes patient vital signs. The notebook also shows how to retrieve the analysis results from a Streams view and visualize them in the notebook, as you can see here. The visualization is done using Bokeh.
The last notebook we included is based on the example we referred to earlier. It creates a neural network to determine the probability that an engine will fail based on its temperature. It also demonstrates how to create a sample data set to train the model. It uses PyBrain, NumPy, and Matplot.
Try it out
- Monitor vital signs in a streaming application
- Hello, World!
- Neural net notebook: Predict engine failure by creating and using a data model