Building Models from Structured data with AutoML Tables

This is an introduction talk for AutoML Tables given at GDG Johannesburg Virtual Meetup

Transcript

1. Peter-John Welcome GDE Firebase @pjapplez Building models from structured data with AutoML Tables An Introduction to AutoML Tables
2. Half screen photo slide if text is necessary Who I am Mobile Engineering Lead at DVT Google Developer Expert for Firebase
3. Structured vs Unstructured Data
4. • Quantitative Data • Consistent field types • Easily searchable • Similar to relational databases or spreadsheets • Eg. Dates, Address, Coordinates, Money Structured Data
5. • Qualitative Data • Inconsistent • More difficult to analysis and process • NoSQL Databases • Eg. Text, Audio, Images, Video Unstructured Data
6. Structured and Unstructured data https://learn.g2.com/structured-vs-unstructured-data
7. AutoML Tables
8. ML Decision Pyramid https://www.youtube.com/watch?v=pm_-pVPvZ-4
9. AutoML Tables Define your problem Retails Customer History: I am a retail company with customers and would like to predict how much money a customer will spend and what kind of products they are interested in. Conference Abstracts: I have a bunch of conference abstracts and I would like to predict if my abstract is likely to be accepted or reject.
10. AutoML Tables Define your problem
11. AutoML Tables https://cloud.google.com/automl
12. • Allows us to build and deploy ML models at speed and scale • Supports 3 types of Models: Binary classification, Multi-class classification, Regression Models • Has the ability to generate a REST API to access the model • Gives you the ability to Extract the model to test locally AutoML Tables
13. • Training Data is split into 3 Categories: Training, Validation, Testing • By default its a 80(Training), 10(Validation),10 spilt(Testing) - This can be modified • Must have a minimum of 1000 rows • There is the ability to choose your optimization objectives AutoML Tables (Train)
14. • Precision and Recall graphs • Confusion Matrix • Interactive Threshold score for precision and recall accuracy • Feature Importance AutoML Tables (Eval.)
15. • Online Prediction • Batch predictions through BigQuery • REST endpoint deployment for client side interaction • Extraction of model to docker container to deploy in any environment AutoML Tables (Predict)
16. Demo Time
17. • Easy to setup and get a model trained • Easy to deploy and lets Google Cloud scale the model for you • Model Size was really large • No way to extract the Model to TF model or TFLite model • Can get very expensive to Train large sets of data. • Can get expensive to deploy model. AutoML Tables (Observations)
18. AutoML Tables (Ref.) • https://cloud.google.com/automl-tables/docs • https://www.youtube.com/watch?v=pm_-pVPvZ-4 • https://www.youtube.com/watch?v=tWbiOuHae0c • https://www.youtube.com/watch?v=MqO_L9nIOWM • https://www.youtube.com/watch?v=XrMtF_inTZ0
19. Peter-John Welcome GDE Firebase @pjapplez Thank You!