SlideShare a Scribd company logo
1 of 24
Download to read offline
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved.
Select ML from Databases
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved.
Nithish Raghunandanan
@nithishr
04th December 2021
Agenda
Fill in agenda items and numbers
Background
ML in Databases
Demo: ML in Couchbase
01/
01/
02/
03/
04/ Conclusion
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 3
1 Background
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 4
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 4
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 4
Background
A Journey into Machine Learning Capabilities in Databases
• Background in Data/ML Engineering
• Built Machine Learning Models for
Businesses
• Developer Advocate @ Couchbase
• Explore the ML Capabilities of Databases
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 5
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 5
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 5
● Extract Meaningful Insights from
Data
● Solve Business Problems
● Personalized Offers
● Anomaly Detection
● Customer Satisfaction
● Lots More
Why ML?
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 6
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 6
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 6
Common Approach
Get Training Data
● Transactional
Databases
● ETL Jobs
● Data
Engineers
Feature
Engineering
● Data
Wrangling
● ETL Jobs
● Feature
Stores
● Data
Scientists +
Engineers
Train Model
● Algorithms
● Data
Scientists
Call Model
from Apps
● Applications
call ML
Service
● Backend +
Data Engineer
+ Data
Scientist
Deploy Model
● Package
Model
● Microservice
to Serve
Model
● Data Engineer
+ Scientist
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 7
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 7
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 7
Pros
● Works Well
● Scale Services Independently
Common Approach
Cons
● Data Duplication
○ Transactional Database
○ Feature Stores / Copies of Data
● Non Trivial ETL Jobs
● Updating Data / Models
● Combined efforts of Data Engineers,
Scientists & Backend Engineers
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 8
2 Machine Learning in
Databases
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 9
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 9
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 9
● Inference using SQL
● Built In Machine Learning Methods
○ BigQuery, Redshift
● Third Party Additions to Existing Databases
○ MindsDB
● Support for Custom Machine Learning Models
(Python/R)
○ SQL Server, Oracle, Couchbase, Firebase
Database Support for AI
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 10
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 10
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 10
● Set of Built In ML algorithms for Most Use Cases
● Optionally import custom models
● Workflow
○ CREATE Model
○ SELECT Model(Inputs) as Inference from
Database
Built In Machine Learning Methods
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 11
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 11
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 11
MindsDB
● Pluggable ML Support for Existing DBs
● Emulate underlying DB API
● Workflow
○ CREATE PREDICTOR from DB
○ SELECT Outputs FROM Model where data={}
as Inference from Database
Third Party Additions to Databases
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 12
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 12
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 12
● Support for Custom Models in Python, R.
● Workflow
○ Build Model on Dev Machines
○ Package the Model
○ Create a Custom Procedure in DB
○ SELECT Procedure(Inputs) as Inference from
Database
Custom Machine Learning Methods
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 13
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 13
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 13
Feature Built in ML Third Party
Integrations
Custom ML
Methods
Flexibility Limited Limited High
Explainability Low Low - Medium High
Target Audience Data Analysts /
Engineers
Data Analysts /
Engineers
Data Scientists
Summary
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 14
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 14
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 14
Pros
● Out of the box Models
● Reduce ETL: DB single source of truth
● Easy Upgrade Path for Models
● No external Microservice for Model
Serving
Summary
Cons
● Flexibility
● Ensure Performance
● Explainability
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 15
3 Demo: ML in Couchbase
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 16
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 16
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 16
● Part of Analytics Service
● Real time Shadow Copy of Transactional Data
● Massively Parallel Processing(MPP) Architecture
● Custom User Defined Functions(UDFs) in Python
● ML Inference in SQL Statements
Machine Learning in Couchbase
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 17
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 17
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 17
● Insurance Quotes
● Custom Quotes based on Lifestyle
● Features: Age, Gender, BMI, Smoking,
Region, Children
● Customer gets real time estimates
Machine Learning in Couchbase: Demo
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 18
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 18
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 18
Steps
1. Train Model in Python locally
2. Package the Model into Python Library
3. Deploy Library to Couchbase Analytics
4. Create User Defined Function to use Python
Library
5. Model Inference using SQL statements
Machine Learning in Couchbase: Demo
OUTPUT
Machine Learning Model
{
"quote": 6390.90
}
INPUT
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 19
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 19
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 19
Machine Learning in Couchbase: Demo
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 20
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 20
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 20
● Create Custom Models in Python
● Run Inference directly using SQL in Workbench, SDK or Couchbase
REST API
● Update Models by Redeploying
● Reduced Infrastructure: Eliminate ML Microservices & ETL Jobs
Machine Learning in Couchbase: Summary
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 21
4 Conclusion
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 22
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 22
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 22
● Machine Learning Integration into Databases
● Models are becoming more flexible
● Not Suitable for all use cases
When to Use?
● Out of the Box Solutions
● Simplified Model Deployment Workflows
● Reduced Infrastructure: ETL Jobs & ML Services
Machine Learning in Databases
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 23
Web
Twitter
Facebook
couchbase.com
twitter.com/couchbase
facebook.com/couchbase
Nithish Raghunandanan
@nithishr
https://github.com/nithishr/machine_learning_couchbase/
CONTACT
Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved.
THANK YOU

More Related Content

Similar to Select ML from Databases

MLOps implemented - how we combine the cloud & open-source to boost data scie...
MLOps implemented - how we combine the cloud & open-source to boost data scie...MLOps implemented - how we combine the cloud & open-source to boost data scie...
MLOps implemented - how we combine the cloud & open-source to boost data scie...GetInData
 
Couchbase and Apache Kafka - Bridging the gap between RDBMS and NoSQL
Couchbase and Apache Kafka - Bridging the gap between RDBMS and NoSQLCouchbase and Apache Kafka - Bridging the gap between RDBMS and NoSQL
Couchbase and Apache Kafka - Bridging the gap between RDBMS and NoSQLDATAVERSITY
 
Montreal MuleSoft_Meetup_02-June.pptx
Montreal MuleSoft_Meetup_02-June.pptxMontreal MuleSoft_Meetup_02-June.pptx
Montreal MuleSoft_Meetup_02-June.pptxSadik Ali
 
NuoDB + MayaData: How to Run Containerized Enterprise SQL Applications in the...
NuoDB + MayaData: How to Run Containerized Enterprise SQL Applications in the...NuoDB + MayaData: How to Run Containerized Enterprise SQL Applications in the...
NuoDB + MayaData: How to Run Containerized Enterprise SQL Applications in the...NuoDB
 
Delhi_Meetup_flyway_Integration.pptx
Delhi_Meetup_flyway_Integration.pptxDelhi_Meetup_flyway_Integration.pptx
Delhi_Meetup_flyway_Integration.pptxAnuragSharma900
 
Who needs containers in a serverless world
Who needs containers in a serverless worldWho needs containers in a serverless world
Who needs containers in a serverless worldMatthias Luebken
 
Mumbai MuleSoft Meetup #17 - GraphQL
Mumbai MuleSoft Meetup #17 - GraphQLMumbai MuleSoft Meetup #17 - GraphQL
Mumbai MuleSoft Meetup #17 - GraphQLAkshata Sawant
 
Graph Data Science at Scale
Graph Data Science at ScaleGraph Data Science at Scale
Graph Data Science at ScaleNeo4j
 
How to Run Containerized Enterprise SQL Applications in the Cloud with NuoDB ...
How to Run Containerized Enterprise SQL Applications in the Cloud with NuoDB ...How to Run Containerized Enterprise SQL Applications in the Cloud with NuoDB ...
How to Run Containerized Enterprise SQL Applications in the Cloud with NuoDB ...MayaData Inc
 
AirBNB's ML platform - BigHead
AirBNB's ML platform - BigHeadAirBNB's ML platform - BigHead
AirBNB's ML platform - BigHeadKarthik Murugesan
 
Bighead: Airbnb’s End-to-End Machine Learning Platform with Krishna Puttaswa...
 Bighead: Airbnb’s End-to-End Machine Learning Platform with Krishna Puttaswa... Bighead: Airbnb’s End-to-End Machine Learning Platform with Krishna Puttaswa...
Bighead: Airbnb’s End-to-End Machine Learning Platform with Krishna Puttaswa...Databricks
 
Moving OBIEE to Oracle Analytics Cloud
Moving OBIEE to Oracle Analytics CloudMoving OBIEE to Oracle Analytics Cloud
Moving OBIEE to Oracle Analytics CloudEdelweiss Kammermann
 
Snowflake: The most cost-effective agile and scalable data warehouse ever!
Snowflake: The most cost-effective agile and scalable data warehouse ever!Snowflake: The most cost-effective agile and scalable data warehouse ever!
Snowflake: The most cost-effective agile and scalable data warehouse ever!Visual_BI
 
Solving Enterprise Data Challenges with Apache Arrow
Solving Enterprise Data Challenges with Apache ArrowSolving Enterprise Data Challenges with Apache Arrow
Solving Enterprise Data Challenges with Apache ArrowWes McKinney
 
Which PostgreSQL is right for your multi cloud strategy? P2
Which PostgreSQL is right for your multi cloud strategy? P2Which PostgreSQL is right for your multi cloud strategy? P2
Which PostgreSQL is right for your multi cloud strategy? P2Ashnikbiz
 
Upleveling Analytics with Kafka with Amy Chen
Upleveling Analytics with Kafka with Amy ChenUpleveling Analytics with Kafka with Amy Chen
Upleveling Analytics with Kafka with Amy ChenHostedbyConfluent
 
Mule soft meetup Houston 16
Mule soft meetup Houston 16Mule soft meetup Houston 16
Mule soft meetup Houston 16Jim Andrews
 
PostgreSQL to Accelerate Innovation
PostgreSQL to Accelerate InnovationPostgreSQL to Accelerate Innovation
PostgreSQL to Accelerate InnovationEDB
 
Developing Microservices Directly in AKS/Kubernetes
Developing Microservices Directly in AKS/KubernetesDeveloping Microservices Directly in AKS/Kubernetes
Developing Microservices Directly in AKS/KubernetesChakradhar Rao Jonagam
 

Similar to Select ML from Databases (20)

MLOps implemented - how we combine the cloud & open-source to boost data scie...
MLOps implemented - how we combine the cloud & open-source to boost data scie...MLOps implemented - how we combine the cloud & open-source to boost data scie...
MLOps implemented - how we combine the cloud & open-source to boost data scie...
 
Couchbase and Apache Kafka - Bridging the gap between RDBMS and NoSQL
Couchbase and Apache Kafka - Bridging the gap between RDBMS and NoSQLCouchbase and Apache Kafka - Bridging the gap between RDBMS and NoSQL
Couchbase and Apache Kafka - Bridging the gap between RDBMS and NoSQL
 
Montreal MuleSoft_Meetup_02-June.pptx
Montreal MuleSoft_Meetup_02-June.pptxMontreal MuleSoft_Meetup_02-June.pptx
Montreal MuleSoft_Meetup_02-June.pptx
 
NuoDB + MayaData: How to Run Containerized Enterprise SQL Applications in the...
NuoDB + MayaData: How to Run Containerized Enterprise SQL Applications in the...NuoDB + MayaData: How to Run Containerized Enterprise SQL Applications in the...
NuoDB + MayaData: How to Run Containerized Enterprise SQL Applications in the...
 
Delhi_Meetup_flyway_Integration.pptx
Delhi_Meetup_flyway_Integration.pptxDelhi_Meetup_flyway_Integration.pptx
Delhi_Meetup_flyway_Integration.pptx
 
Who needs containers in a serverless world
Who needs containers in a serverless worldWho needs containers in a serverless world
Who needs containers in a serverless world
 
Mumbai MuleSoft Meetup #17 - GraphQL
Mumbai MuleSoft Meetup #17 - GraphQLMumbai MuleSoft Meetup #17 - GraphQL
Mumbai MuleSoft Meetup #17 - GraphQL
 
Graph Data Science at Scale
Graph Data Science at ScaleGraph Data Science at Scale
Graph Data Science at Scale
 
How to Run Containerized Enterprise SQL Applications in the Cloud with NuoDB ...
How to Run Containerized Enterprise SQL Applications in the Cloud with NuoDB ...How to Run Containerized Enterprise SQL Applications in the Cloud with NuoDB ...
How to Run Containerized Enterprise SQL Applications in the Cloud with NuoDB ...
 
AirBNB's ML platform - BigHead
AirBNB's ML platform - BigHeadAirBNB's ML platform - BigHead
AirBNB's ML platform - BigHead
 
Bighead: Airbnb’s End-to-End Machine Learning Platform with Krishna Puttaswa...
 Bighead: Airbnb’s End-to-End Machine Learning Platform with Krishna Puttaswa... Bighead: Airbnb’s End-to-End Machine Learning Platform with Krishna Puttaswa...
Bighead: Airbnb’s End-to-End Machine Learning Platform with Krishna Puttaswa...
 
Moving OBIEE to Oracle Analytics Cloud
Moving OBIEE to Oracle Analytics CloudMoving OBIEE to Oracle Analytics Cloud
Moving OBIEE to Oracle Analytics Cloud
 
Snowflake: The most cost-effective agile and scalable data warehouse ever!
Snowflake: The most cost-effective agile and scalable data warehouse ever!Snowflake: The most cost-effective agile and scalable data warehouse ever!
Snowflake: The most cost-effective agile and scalable data warehouse ever!
 
Solving Enterprise Data Challenges with Apache Arrow
Solving Enterprise Data Challenges with Apache ArrowSolving Enterprise Data Challenges with Apache Arrow
Solving Enterprise Data Challenges with Apache Arrow
 
Which PostgreSQL is right for your multi cloud strategy? P2
Which PostgreSQL is right for your multi cloud strategy? P2Which PostgreSQL is right for your multi cloud strategy? P2
Which PostgreSQL is right for your multi cloud strategy? P2
 
Upleveling Analytics with Kafka with Amy Chen
Upleveling Analytics with Kafka with Amy ChenUpleveling Analytics with Kafka with Amy Chen
Upleveling Analytics with Kafka with Amy Chen
 
Mule soft meetup Houston 16
Mule soft meetup Houston 16Mule soft meetup Houston 16
Mule soft meetup Houston 16
 
PostgreSQL to Accelerate Innovation
PostgreSQL to Accelerate InnovationPostgreSQL to Accelerate Innovation
PostgreSQL to Accelerate Innovation
 
Mule ESB Intro
Mule ESB IntroMule ESB Intro
Mule ESB Intro
 
Developing Microservices Directly in AKS/Kubernetes
Developing Microservices Directly in AKS/KubernetesDeveloping Microservices Directly in AKS/Kubernetes
Developing Microservices Directly in AKS/Kubernetes
 

More from Nithish Raghunandanan

Creating data apps using Streamlit in Python
Creating data apps using Streamlit in PythonCreating data apps using Streamlit in Python
Creating data apps using Streamlit in PythonNithish Raghunandanan
 
Learnings from Organizing Internal Hackathons
Learnings from Organizing Internal HackathonsLearnings from Organizing Internal Hackathons
Learnings from Organizing Internal HackathonsNithish Raghunandanan
 
Learnings from Organizing an Internal Hackathon
Learnings from Organizing an Internal HackathonLearnings from Organizing an Internal Hackathon
Learnings from Organizing an Internal HackathonNithish Raghunandanan
 
Hodor: Solving Everyday Problems with Tech
Hodor: Solving Everyday Problems with TechHodor: Solving Everyday Problems with Tech
Hodor: Solving Everyday Problems with TechNithish Raghunandanan
 

More from Nithish Raghunandanan (8)

Virtual tourism in covid times
Virtual tourism in covid timesVirtual tourism in covid times
Virtual tourism in covid times
 
Life of a data engineer
Life of a data engineerLife of a data engineer
Life of a data engineer
 
Creating data apps using Streamlit in Python
Creating data apps using Streamlit in PythonCreating data apps using Streamlit in Python
Creating data apps using Streamlit in Python
 
Learnings from Organizing Internal Hackathons
Learnings from Organizing Internal HackathonsLearnings from Organizing Internal Hackathons
Learnings from Organizing Internal Hackathons
 
Learnings from Organizing an Internal Hackathon
Learnings from Organizing an Internal HackathonLearnings from Organizing an Internal Hackathon
Learnings from Organizing an Internal Hackathon
 
Pecha kucha Talk on web scraping
Pecha kucha Talk on web scrapingPecha kucha Talk on web scraping
Pecha kucha Talk on web scraping
 
Hodor: Solving Everyday Problems with Tech
Hodor: Solving Everyday Problems with TechHodor: Solving Everyday Problems with Tech
Hodor: Solving Everyday Problems with Tech
 
Tutorial on Web Scraping in Python
Tutorial on Web Scraping in PythonTutorial on Web Scraping in Python
Tutorial on Web Scraping in Python
 

Recently uploaded

Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% SecureCall me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% SecurePooja Nehwal
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...amitlee9823
 
Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz1
 
Week-01-2.ppt BBB human Computer interaction
Week-01-2.ppt BBB human Computer interactionWeek-01-2.ppt BBB human Computer interaction
Week-01-2.ppt BBB human Computer interactionfulawalesam
 
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...amitlee9823
 
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightCheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightDelhi Call girls
 
Ravak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptxRavak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptxolyaivanovalion
 
Carero dropshipping via API with DroFx.pptx
Carero dropshipping via API with DroFx.pptxCarero dropshipping via API with DroFx.pptx
Carero dropshipping via API with DroFx.pptxolyaivanovalion
 
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al BarshaAl Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al BarshaAroojKhan71
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfMarinCaroMartnezBerg
 
Generative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusGenerative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusTimothy Spann
 
Smarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptxSmarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptxolyaivanovalion
 
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Callshivangimorya083
 
Midocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxMidocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxolyaivanovalion
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...amitlee9823
 
Zuja dropshipping via API with DroFx.pptx
Zuja dropshipping via API with DroFx.pptxZuja dropshipping via API with DroFx.pptx
Zuja dropshipping via API with DroFx.pptxolyaivanovalion
 
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779Delhi Call girls
 
Data-Analysis for Chicago Crime Data 2023
Data-Analysis for Chicago Crime Data  2023Data-Analysis for Chicago Crime Data  2023
Data-Analysis for Chicago Crime Data 2023ymrp368
 
Edukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxEdukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxolyaivanovalion
 

Recently uploaded (20)

Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% SecureCall me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
 
Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signals
 
Week-01-2.ppt BBB human Computer interaction
Week-01-2.ppt BBB human Computer interactionWeek-01-2.ppt BBB human Computer interaction
Week-01-2.ppt BBB human Computer interaction
 
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
 
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightCheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
 
Ravak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptxRavak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptx
 
Carero dropshipping via API with DroFx.pptx
Carero dropshipping via API with DroFx.pptxCarero dropshipping via API with DroFx.pptx
Carero dropshipping via API with DroFx.pptx
 
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al BarshaAl Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
Al Barsha Escorts $#$ O565212860 $#$ Escort Service In Al Barsha
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdf
 
Sampling (random) method and Non random.ppt
Sampling (random) method and Non random.pptSampling (random) method and Non random.ppt
Sampling (random) method and Non random.ppt
 
Generative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusGenerative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and Milvus
 
Smarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptxSmarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptx
 
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
 
Midocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxMidocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFx
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
 
Zuja dropshipping via API with DroFx.pptx
Zuja dropshipping via API with DroFx.pptxZuja dropshipping via API with DroFx.pptx
Zuja dropshipping via API with DroFx.pptx
 
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
 
Data-Analysis for Chicago Crime Data 2023
Data-Analysis for Chicago Crime Data  2023Data-Analysis for Chicago Crime Data  2023
Data-Analysis for Chicago Crime Data 2023
 
Edukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxEdukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFx
 

Select ML from Databases

  • 1. Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. Select ML from Databases Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. Nithish Raghunandanan @nithishr 04th December 2021
  • 2. Agenda Fill in agenda items and numbers Background ML in Databases Demo: ML in Couchbase 01/ 01/ 02/ 03/ 04/ Conclusion
  • 3. Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 3 1 Background
  • 4. Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 4 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 4 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 4 Background A Journey into Machine Learning Capabilities in Databases • Background in Data/ML Engineering • Built Machine Learning Models for Businesses • Developer Advocate @ Couchbase • Explore the ML Capabilities of Databases
  • 5. Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 5 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 5 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 5 ● Extract Meaningful Insights from Data ● Solve Business Problems ● Personalized Offers ● Anomaly Detection ● Customer Satisfaction ● Lots More Why ML?
  • 6. Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 6 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 6 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 6 Common Approach Get Training Data ● Transactional Databases ● ETL Jobs ● Data Engineers Feature Engineering ● Data Wrangling ● ETL Jobs ● Feature Stores ● Data Scientists + Engineers Train Model ● Algorithms ● Data Scientists Call Model from Apps ● Applications call ML Service ● Backend + Data Engineer + Data Scientist Deploy Model ● Package Model ● Microservice to Serve Model ● Data Engineer + Scientist
  • 7. Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 7 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 7 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 7 Pros ● Works Well ● Scale Services Independently Common Approach Cons ● Data Duplication ○ Transactional Database ○ Feature Stores / Copies of Data ● Non Trivial ETL Jobs ● Updating Data / Models ● Combined efforts of Data Engineers, Scientists & Backend Engineers
  • 8. Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 8 2 Machine Learning in Databases
  • 9. Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 9 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 9 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 9 ● Inference using SQL ● Built In Machine Learning Methods ○ BigQuery, Redshift ● Third Party Additions to Existing Databases ○ MindsDB ● Support for Custom Machine Learning Models (Python/R) ○ SQL Server, Oracle, Couchbase, Firebase Database Support for AI
  • 10. Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 10 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 10 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 10 ● Set of Built In ML algorithms for Most Use Cases ● Optionally import custom models ● Workflow ○ CREATE Model ○ SELECT Model(Inputs) as Inference from Database Built In Machine Learning Methods
  • 11. Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 11 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 11 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 11 MindsDB ● Pluggable ML Support for Existing DBs ● Emulate underlying DB API ● Workflow ○ CREATE PREDICTOR from DB ○ SELECT Outputs FROM Model where data={} as Inference from Database Third Party Additions to Databases
  • 12. Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 12 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 12 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 12 ● Support for Custom Models in Python, R. ● Workflow ○ Build Model on Dev Machines ○ Package the Model ○ Create a Custom Procedure in DB ○ SELECT Procedure(Inputs) as Inference from Database Custom Machine Learning Methods
  • 13. Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 13 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 13 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 13 Feature Built in ML Third Party Integrations Custom ML Methods Flexibility Limited Limited High Explainability Low Low - Medium High Target Audience Data Analysts / Engineers Data Analysts / Engineers Data Scientists Summary
  • 14. Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 14 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 14 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 14 Pros ● Out of the box Models ● Reduce ETL: DB single source of truth ● Easy Upgrade Path for Models ● No external Microservice for Model Serving Summary Cons ● Flexibility ● Ensure Performance ● Explainability
  • 15. Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 15 3 Demo: ML in Couchbase
  • 16. Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 16 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 16 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 16 ● Part of Analytics Service ● Real time Shadow Copy of Transactional Data ● Massively Parallel Processing(MPP) Architecture ● Custom User Defined Functions(UDFs) in Python ● ML Inference in SQL Statements Machine Learning in Couchbase
  • 17. Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 17 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 17 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 17 ● Insurance Quotes ● Custom Quotes based on Lifestyle ● Features: Age, Gender, BMI, Smoking, Region, Children ● Customer gets real time estimates Machine Learning in Couchbase: Demo
  • 18. Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 18 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 18 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 18 Steps 1. Train Model in Python locally 2. Package the Model into Python Library 3. Deploy Library to Couchbase Analytics 4. Create User Defined Function to use Python Library 5. Model Inference using SQL statements Machine Learning in Couchbase: Demo OUTPUT Machine Learning Model { "quote": 6390.90 } INPUT
  • 19. Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 19 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 19 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 19 Machine Learning in Couchbase: Demo
  • 20. Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 20 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 20 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 20 ● Create Custom Models in Python ● Run Inference directly using SQL in Workbench, SDK or Couchbase REST API ● Update Models by Redeploying ● Reduced Infrastructure: Eliminate ML Microservices & ETL Jobs Machine Learning in Couchbase: Summary
  • 21. Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 21 4 Conclusion
  • 22. Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 22 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 22 Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 22 ● Machine Learning Integration into Databases ● Models are becoming more flexible ● Not Suitable for all use cases When to Use? ● Out of the Box Solutions ● Simplified Model Deployment Workflows ● Reduced Infrastructure: ETL Jobs & ML Services Machine Learning in Databases
  • 23. Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. 23 Web Twitter Facebook couchbase.com twitter.com/couchbase facebook.com/couchbase Nithish Raghunandanan @nithishr https://github.com/nithishr/machine_learning_couchbase/ CONTACT
  • 24. Confidential and Proprietary. Do not distribute without Couchbase consent. © Couchbase 2021. All rights reserved. THANK YOU