ML-POT

IBM Proof of Technology - Data Science Experience

Description:

Use IBM’s Data Science Experience (DSX) and BlueMix cloud services to create a working cloud-based application from start to finish. Participants will be led through a series of three labs that build upon one another so it is important that they are completed in order.

1. Lab-1 - The first lab will begin with loading data about the Titanic disaster and using machine learning to predict survivors with a Jupyter notebook in DSX with python.

2. Lab-2 - The second lab will leverage Watson Machine Learning (WML) on the Titanic data to create categorical predictions using muliple models using the DSX Model GUI.

3. Lab-3 - The final lab will guide participants in created a Principal Component Analysis model (PCA). Principal component analysis (PCA) is a statistical procedure that uses an orthogonal transformation to convert a set of observations of possibly correlated variables into a set of values of linearly uncorrelated variables called principal components. PCA is mostly used as a tool in exploratory data analysis and for making predictive models. It's often used to visualize genetic distance and relatedness between populations.

Instructions:

Step 1. Sign up for the IBM Data Science Experience (DSX). We recommend using the Firefox browser.

NOTE: If you already have a DSX account, please skip to Step 2.

Create an account.

1. Go to http://datascience.ibm.com/

2. Click the Sign Up button on the top right

3. Enter your email, click to accept the terms, and click Next. Note: If you already have an IBM id you can click Sign in with your IBM id -- if you don't have a DSX account one will be created for you.

4. On the next page, fill in the corresponsing fields and click Create Account

5. You will see the following screen. You need to go to your e-mail account to complete the sign up process.

6. In your e-mail inbox, there should be a message from The Bluemix Team.

7. Open the e-mail and click on Confirm Account.

8. Go back to the DSX session, and enter your DSX user id (e-mail account) and click Continue.

9. Enter your password and click Sign in.

10. Select the IBM Cloud Account (IBM), select the organization (your e-mail), and then select the space (dev) and click Continue.

11. It will take several minutes to set up the account. You will see several screens pop-up (e.g. Preparing Object-Storage, Initializing Environment). Wait until you see the following screen and then click on Get Started.

You are now in the Data Science Experience landing page. Your environment is automatically set up with one Apache Spark instance and 5 GB of object storage. From here you can explore any of the tutorials, videos, sample notebooks, totorials or articles in the community.

Step 2. Create a project

1. Click on Projects > View All Projects to see a list of your projects. You should only see a default project.

2. Click on the New project icon on the top right of the project list.

3. Type a name for your project. For instance, "DSX Lab". A Spark service and an object storage will be automatically selected as well as a container with a default name. A container is a directory on the object storage. Click on Create.

You are now in your new project where you can create notebooks and data assets as well as add collaborators.

You are now ready to begin Lab-1.