Adding associated services
After you create a project, you can add associated services to it at any time. You must have the Admin role to add associated services. Depending on the type of project you choose, you might be required to add a service during project creation.
To add any service to a project, go to the project Settings page and click Add service in the Associated Services section. If you don’t have an existing IBM service, you are prompted to provision it.
If you want to use different compute services than the built-in runtime environments, you can add these compute services to your project:
Some types of analytical assets require a service. If the service is not already in the project, you are prompted to add it the first time you create the type of asset that requires it:
- Cognos Dashboard Embedded for dashboard assets
- IBM Watson Machine Learning for Machine Learning model assets, modeler flow assets, and experiment assets
- IBM Streaming Analytics for streams flow assets
- Watson Natural Language Classifier for Watson Natural Language Classifier model assets
- Visual Recognition for Visual Recognition model assets
If you want to use other Watson services, you can use their APIs in notebooks by adding them to your project:
- Watson Discovery
- Watson Language Translator
- Natural Language Understanding
- Watson Personality Insights
- Watson Speech to Text
- Watson Text to Speech
- Watson Tone Analyzer
You can add the Spark service to your project. Spark is a fast, in-memory engine for very large data sets. In Watson Studio, you can use the Apache Spark service for your Python, Scala, or R notebooks.
To learn more about Apache Spark, see documentation and examples at spark.apache.org.
Amazon Elastic Map Reduce support in IBM Watson Studio is a beta release and is not available for all Watson Studio plans. See Offering plans.
Amazon EMR is a managed Spark cluster compute service that you can associate with a project in Watson Studio. If you stored your data in Amazon Simple Storage Service or in Amazon DynamoDB, you can continue using this data by running your notebook in an Amazon EMR service that you associate with your project. See Add an Amazon EMR Spark service.
To learn more about Amazon EMR, see documentation and examples at aws.amazon.com.
IBM Analytics Engine
With IBM Analytics Engine you can create Apache Spark and Apache Hadoop clusters in minutes and customize these clusters by using scripts. You can work with data in IBM Cloud Object Storage, as well as integrate other services like IBM Streaming Analytics, and Machine Learning. Before you can associate the IBM Analytics Engine service to your project, you must create the service in IBM Cloud.
See Analytics Engine for instructions on creating and customizing clusters.
Cognos Dashboard Embedded
With the Cognos Dashboard Embedded service, you can use the dashboard editor tool to create an analytics dashboard to find, explore, and share insights in your data. See Analytics dashboard.
With the IBM Watson Machine Learning service, you can build sophisticated analytical models using your own data, and deploy the models for use in applications. Machine Learning provides the model builder, Flow Editor, and Experiment Builder tools. If you don’t add the Machine Learning service before you start using the model builder, Flow Editor, or the Experiment Builder, you are prompted to specify your existing service or buy the IBM Watson Machine Learning. See Machine Learning.
With the IBM Streaming Analytics service, you can use streams flows in your projects to ingest, analyze, monitor, and correlate data as it arrives from real-time data sources. The Streaming Analytics service is powered by IBM Streams, which can analyze millions of events per second, enabling submillisecond response times and instant decision-making. See Get started with streams flows.
Watson Natural Language Classifier
With Watson Natural Language Classifier, you can use the Natural Language Classifier model builder tool to apply cognitive computing techniques to return the best matching classes for a sentence or phrase. You create a model by providing a set of representative strings and a set of one or more correct classes for training. After training, the new classifier can accept new questions or phrases and return the top matches with a probability value for each match. Getting started tutorial.
With IBM Watson Visual Recognition, you can use the Visual Recognition model builder tool to analyze images for scenes, objects, faces, and other content. Choose a default model off the shelf, or create your own custom classifier. Develop smart applications that analyze the visual content of images or video frames to understand what is happening in a scene. See Getting started tutorial.
With the Watson Discovery service, you can use APIs in notebooks to add a cognitive search and content analytics engine to applications to identify patterns, trends and actionable insights that drive better decision-making. Securely unify structured and unstructured data with pre-enriched content, and use a simplified query language to eliminate the need for manual filtering of results. See Getting started tutorial.
Watson Language Translator
With Watson Language Translator, you can use APIs in notebooks to dynamically translate news, patents, or conversational documents, instantly publish content in multiple languages, or allow your non-English-speaking staff to send emails in English. You can use Watson Language Translator with the following languages: English to or from Brazilian Portuguese, French, Modern Standard Arabic, or Spanish. See Getting started tutorial.
Natural Language Understanding
With IBM Watson Natural Language Understanding, you can use APIs in notebooks to analyze text to extract meta-data from content such as concepts, entities, keywords, categories, sentiment, emotion, relations, or semantic roles. With custom annotation models developed using Watson Knowledge Studio, identify industry or domain specific entities and relations in unstructured text. See Getting started tutorial.
Watson Personality Insights
With Watson Personality Insights, you can use APIs in notebooks to derive insights from transactional and social media data to identify psychological traits which can determine purchase decisions, intent and behavioral traits. Use Watson Personality Insights to improve conversion rates. See Getting started tutorial.
Watson Speech to Text
With Watson Speech to Text, you can use APIs in notebooks to convert the human voice into the written word. It can be used anywhere there is a need to bridge the gap between the spoken word and its written form, including voice control of embedded systems, transcription of meetings and conference calls, and dictation of email and notes. The service uses machine learning to combine information about grammar and language structure with knowledge of the composition of the audio signal to generate an accurate transcription. See Getting started tutorial.
Watson Text to Speech
With Watson Text to Speech, you can use APIs in notebooks to processe text and natural language to generate synthesized audio output complete with appropriate cadence and intonation. It is available in several voices: 2 female voices, 1 male voice (Watson’s voice from Jeopardy). See Getting started tutorial.
Watson Tone Analyzer
With Watson Tone Analyzer, you can use APIs in notebooks to use cognitive linguistic analysis to identify a variety of tones at both the sentence and document level. This insight can then be used to refine and improve communications. The service detects three types of tones, including emotion (anger, disgust, fear, joy and sadness), social propensities (openness, conscientiousness, extroversion, agreeableness, and emotional range), and language styles (analytical, confident and tentative) from text. See Getting started tutorial.