Watson Studio provides the data science features in a collaborative environment for data scientists, developers, and domain experts to explore, analyze, and model data.
Create a Watson Studio project from a zipped file and from a GitHub repository
Watch this video to see how to create a Watson Studio project in IBM Cloud Pak for Data from a zipped file and from a GitHub Repository.
Jupyter notebook basics in Watson Studio
Watch this video which covers the basics for working with Jupyter notebooks in Watson Studio.
Collaborate on projects
Watch this video to see how to add collaborators to a Watson Studio project in IBM Cloud Pak for Data so you can work with others on project assets.
Create a custom environment for Jupyter notebooks in Watson Studio
Watch this video to see how to create a custom runtime environment for use with a Jupyter notebook in Watson Studio.
Add platform connections
This video shows you how to create a connection to a data source at the platform level in IBM Cloud Pak for Data 3.5.
Add a connection and connected data to a project
Watch this video to see how to set up a connection to a data source and add connected data to a Watson Studio project in IBM Cloud Pak for Data.
Visualize and analyze precipitation data in a Jupyter notebook
Watch this video to see how to analyze annual precipitation data from the UNdata portal in a Jupyter notebook in a Watson Studio project.
Enable Git integration
If you enable Git integration in a Watson Studio project, then you can sync your project with a GitHub repository and allow collaborators to use the JupyterLab Integrated Development Environment (IDE). Watch this video to see how to enable Git integration in a Watson Studio project to use the JupyterLab IDE.
Build a Watson Machine Learning model using AutoAI
If you add Watson Machine Learning to Watson Studio, you can deploy and evaluate models. And Watson Machine Learning includes AutoAI, which gives data scientists superpowers by automating 80% of core data science processes like preparing data, selecting the best machine learning algorithm, and applying feature engineering. Watch this video to see how to use AutoAI to build a binary classification model, and then deploy and test that model.
Build, deploy, and test a model in a notebook
This video shows you how to build a machine learning model using a Jupyter notebook.
Use the Data Refinery to shape raw data
Watson Studio and Watson Knowledge Catalog include the Data Refinery to saves you data preparation time by quickly transforming large amounts of raw data into consumable, quality information. Watch this video to see how to use the Data Refinery to shape raw data.
Streaming analytics in a Python sample notebook
See how to create an application that computes the rolling average of streaming data from a Python notebook. The notebook uses the IBM Streams Python API to process streaming data. Learn more about the Python API from the development guide: https://ibmstreams.github.io/streamsx.documentation/docs/latest/python/