IBM Call for Code Hackathon

IBM Sign up - https://ibm.biz/BdzRaf

Text

Call For Code Slack - https://callforcode.org/slack/

@lidderupk

IBM Developer

• Get Started Quickly

• Gather and Store Data

• Refine Data

• Use Pre-built Models

• Guided ML with Data

• Model Asset Exchange

@lidderupk

IBM Developer

IBM Call for Code - Get started quickly

https://developer.ibm.com/callforcode/

• Background

• Research

• Data

• Videos

• Solutions

• Blogs/Articles

• Code patterns

@lidderupk

IBM Developer

IBM Code Patterns - Get started quickly

Create visualizations to understand food insecurity

1. Open Watson Studio and create a notebook.
2. Download the data in Watson Studio and explore it - US Bureau of Labor Statistics and The United States Department of Agriculture

3. Load PixieDust and use for visualizations - low access, diet-related diseases, race, poverty, geography.

4. Download the dataframe as a .csv file from Watson Studio.
5. Upload the .csv file to Watson Analytics and visualize.

https://developer.ibm.com/patterns/create-visualizations-to-understand-food-insecurity/

@lidderupk

IBM Developer

Gather and Store Data

@lidderupk

IBM Developer

Data Sources - some examples

@lidderupk

IBM Developer

• IBM Call for Code site
  • https://developer.ibm.com/callforcode/

​

• IBM Communities
  • https://dataplatform.cloud.ibm.com/community
• OpenData
  • https://www.data.gov/
• Others
  • https://www.imf.org/en/Data
  • https://www.kaggle.com/datasets
  • https://data.worldbank.org/

Data Storage - Cloud Object Storage

@lidderupk

IBM Developer

Java - ibm-cos-java-sdk
Javascript - npm install ibm-cos-sdk
Python - pip install -U ibm-cos-sdk

Data Storage - Cloudant

@lidderupk

IBM Developer

CURL - every operation has an endpoint https://ibm.biz/cloudant-api
Javascript - npm install --save @cloudant/cloudant
Java - java-cloudant
Python - pip install cloudant
Swift - pod 'SwiftCloudant'

Refine Data

@lidderupk

IBM Developer

@lidderupk

IBM Developer

Watson Studio Refinery - Explore/Refine

@lidderupk

IBM Developer

Watson Studio Refinery - Shape/Blend/Filter

Watson Cognitive Services

@lidderupk

IBM Developer

•General model: Default classification from thousands of classes.

•Face model: Facial analysis with age and gender.

•Explicit model (Beta): Whether an image is inappropriate for general use.

•Food model (Beta): Specifically for images of food items.

•Text model (Private beta): Text extraction from natural scene images.

Requires training:

•Custom model: Train a custom classifier by providing positive and negative images.

Watson Cognitive Services - Visual Recognition

https://cloud.ibm.com/apidocs/visual-recognition

@lidderupk

IBM Developer

Watson Cognitive Services - Visual Recognition

https://ibm.biz/ibm-burned-houses

@lidderupk

IBM Developer

Watson Cognitive Services - Visual Recognition

https://ibm.biz/ibm-burned-houses

@lidderupk

IBM Developer

Watson Cognitive Services - NLU

@lidderupk

IBM Developer

Emotion

Entities

Keywords

Relations

Multiple language support. Multiple SDK support.

https://cloud.ibm.com/apidocs/natural-language-understanding

@lidderupk

IBM Developer

Watson Cognitive Services - assistant

@lidderupk

IBM Developer

https://cloud.ibm.com/docs/services/assistant

@lidderupk

IBM Developer

Watson Cognitive Services - assistant

@lidderupk

IBM Developer

• Intent recommendations
  • leverage human-to-human logs
• Digressions
  • handle related questions
• Slots / Handlers
  • handle interruptions
• Complicated flow in the Dialog editor
  • jumps and conditions
• Disambiguation
  • multiple intents matched for an utterance

• Search Skill

  • Discovery Integration

• Service Desk Integration
  • Intercom, Zendesk

• Free preview link

  • good for hackathon demos

• Quick integration with Facebook and Slack

• Voice Agent

  • STT

  • Watson Assistant

  • TTS

• ​Call Cloud Functions from inside assistant

  • integrate with other services

Watson Studio ML - Guided Experience

@lidderupk

IBM Developer

https://ibm.biz/watson-ml-demo

Watson Studio ML - Guided Experience

@lidderupk

IBM Developer

@lidderupk

IBM Developer

Watson Studio ML - Guided Binary Classification

@lidderupk

IBM Developer

Watson Studio ML - Guided Multiclass Classification

@lidderupk

IBM Developer

Watson Studio ML - Guided Regression

Watson Studio - deploy own model

@lidderupk

IBM Developer

• Spark MLlib
• scikit-learn
• XGBoost
• TensorFlow
• Keras
• Caffe
• PyTorch
• IBM SPSS Modeler

https://dataplatform.cloud.ibm.com/docs

• IBM CLI with ML plugin
• REST API
• WML Python Client

Supported Frameworks

Deploy / Manage

Watson Studio - deploy own model

@lidderupk

IBM Developer

Model Asset Exchange

@lidderupk

IBM Developer

https://ibm.biz/model-exchange

IBM Model Asset Exchange - MAX

@lidderupk

IBM Developer

IBM MAX - Deploy model

@lidderupk

IBM Developer

Deploy from Docker Hub

docker build -t max-object-detector .
docker run -it -p 5000:5000 max-object-detector

Deploy locally

docker run -it -p 5000:5000 codait/max-object-detector

End points for Model

IBM MAX - Use model

@lidderupk

IBM Developer

Cloud Foundry Buildpacks

@lidderupk

IBM Developer

https://github.com/cloudfoundry-community/cf-docs-contrib/wiki/Buildpacks

Cloud Foundry Buildpacks - IBM CLI 👍🏽

@lidderupk

IBM Developer

https://cloud.ibm.com/docs/cli

IBM Cloud Functions

@lidderupk

IBM Developer

• Event Driven Programming
  • Changes in database
  • Stream Processing
  • Social events

• Secure and scalable APIs
  • API Gateway ➸ Function

• Backend services / micro services

IBM Cloud Functions

@lidderupk

IBM Developer

IBM Cloud Functions

@lidderupk

IBM Developer

Javascript

Python

IBM Cloud Functions - CLI to the rescue !

@lidderupk

IBM Developer

@lidderupk

IBM Developer

Thank you

Good Luck !

@lidderupk

IBM Developer

Upkar Lidder, IBM

@lidderupk

https://github.com/lidderupk/

ulidder@us.ibm.com