Azure Machine Learning
Jasjit Chopra & Apoorva Kumar
Twitter: @jasjitchopra
Twitter: @apoorva___
https://www.youtube.com/watch?v=R2mC-NUAmMk
Agenda
• How to Get Started?
• Azure Machine Learning Basics
• What is Machine Learning Studio?
• Overview
• Capabilities
• Interface
• Components of an Experiment
• Scenario
• DEMO
How to get started?
Azure Machine Learning
• Fully managed cloud service for building
and operationalizing ML models
Fully
managed
Integrated Best in Class
Algorithms + R
Deploy in
minutes
No software to install,
no hardware to manage,
and one portal to view
and update.
Simple drag, drop and
connect interface for
Data Science. No need
for programming for
common tasks.
Built-in collection of
best of breed
algorithms. Support for
R and popular CRAN
packages.
Operationalize models
with a single click.
Monetize in Machine
Learning Marketplace.
Machine Learning Studio Interface
Components of an Experiment
• The experiment has at least one dataset and one module
• Datasets may be connected only to modules
• Modules may be connected to either datasets or other modules
• All input ports for modules must have some connection to the data
flow
• All required parameters for each module must be set
Scenario
Predict the price of an automobile based on different
variables such as make and technical specifications
Demo
• Create a model
• Get Data
• Prepare the data
• Define features
• Train the model
• Choose and apply a learning algorithm
• Score and test the model
• Predict new automobile prices
Free e-Book
http://bit.ly/a4r-mlbook
Supporting Slides
How to pick the right algorithm
How to pick the right algorithm
How to pick the right algorithm
How to pick the right algorithm
How to pick the right algorithm
Machine Learning in Action
http://aka.ms/MLCheatSheet

Introduction to Azure machine learning

  • 1.
    Azure Machine Learning JasjitChopra & Apoorva Kumar Twitter: @jasjitchopra Twitter: @apoorva___
  • 2.
  • 3.
    Agenda • How toGet Started? • Azure Machine Learning Basics • What is Machine Learning Studio? • Overview • Capabilities • Interface • Components of an Experiment • Scenario • DEMO
  • 4.
    How to getstarted?
  • 5.
    Azure Machine Learning •Fully managed cloud service for building and operationalizing ML models Fully managed Integrated Best in Class Algorithms + R Deploy in minutes No software to install, no hardware to manage, and one portal to view and update. Simple drag, drop and connect interface for Data Science. No need for programming for common tasks. Built-in collection of best of breed algorithms. Support for R and popular CRAN packages. Operationalize models with a single click. Monetize in Machine Learning Marketplace.
  • 7.
  • 8.
    Components of anExperiment • The experiment has at least one dataset and one module • Datasets may be connected only to modules • Modules may be connected to either datasets or other modules • All input ports for modules must have some connection to the data flow • All required parameters for each module must be set
  • 9.
    Scenario Predict the priceof an automobile based on different variables such as make and technical specifications
  • 10.
    Demo • Create amodel • Get Data • Prepare the data • Define features • Train the model • Choose and apply a learning algorithm • Score and test the model • Predict new automobile prices
  • 11.
  • 13.
  • 14.
    How to pickthe right algorithm
  • 15.
    How to pickthe right algorithm
  • 16.
    How to pickthe right algorithm
  • 17.
    How to pickthe right algorithm
  • 18.
    How to pickthe right algorithm
  • 19.
  • 20.

Editor's Notes

  • #4 If you've never used Azure Machine Learning Studio before, this session is for you. This session is not for Advanced users. We will not be covering algorithms here.
  • #5 Quick Evaluation: https://studio.azureml.net/Home/Anonymous Free Workspace: https://studio.azureml.net/Home Standard Workspace: https://azure.microsoft.com/en-us/documentation/articles/machine-learning-create-workspace
  • #6 Azure Machine Learning is a cloud-based predictive-analytics service that offers a streamlined experience for data scientists of all skill levels. It's accompanied by the Azure Machine Learning Studio (ML Studio), which is a browser-based tool that provides an easy to use, drag-and-drop interface for building machine-learning models. It comes with a library of time-saving experiments and features best-in-class algorithms developed and tested in the real world by Microsoft businesses such as Bing. And its built-in support for R and Python means you can build custom scripts  to customize your model. Once you've built and trained your model in the ML Studio, you can easily expose it as a Web service that is consumable from a variety of programming languages, or share it with the community by placing it in the Cortana Intelligence Gallery.
  • #7 http://download.microsoft.com/download/C/4/6/C4606116-522F-428A-BE04-B6D3213E9E52/ml_studio_overview_v1.1.pdf
  • #8 PROJECTS - Collections of experiments, datasets, notebooks, and other resources representing a single project EXPERIMENTS - Experiments that you have created and run or saved as drafts WEB SERVICES - Web services that you have deployed from your experiments NOTEBOOKS - Jupyter notebooks that you have created DATASETS - Datasets that you have uploaded into Studio TRAINED MODELS - Models that you have trained in experiments and saved in Studio SETTINGS - A collection of settings that you can use to configure your account and resources.
  • #12 Good book -- and free! Another recommended book on Azure Machine is Learning is "Predictive Analytics with Microsoft Azure Machine Learning " (https://www.amazon.com/Predictive-Analytics-Microsoft-Machine-Learning/dp/1484212010).
  • #20 https://how-old.net/# offers a great example of machine learning in action. Created by Microsoft, the site uses advanced image-recognition techniques to analyze photos you upload and then uses an ML model to "predict" the ages of the people in the photos.
  • #21 The Azure ML Cheat Sheet helps you pick the right algorithm for a model, even if you're not a trained data scientist. One example is if you want to use a set of input values to predict an output value from a continuous set of values (e.g., a person's age), use linear regression. But if you're more interested in the distribution of the output, you might use fast forest quantile regression instead. An example of when you would use the latter is using growth charts to assess child development. "Abby's height is in the 10% quantile of the heights of kids her age." Classification algorithms, by contrast, are used to predict a value from a discrete set of values -- for example, classifying an e-mail as spam or not spam.