Building and Deploying models with Jupyter Notebooks

Pooja Mistry
Developer Advocate - IBM
@Poojamakes

IBM Developer

Join IBM Cloud: https://ibm.biz/BdqqLb

Workshop:ibm.biz/jupyterworkshop

Slides: https://slides.com/poojamistry/jupyternotebooks

Welcome!

Name + Title/Company/Program
Where You’re From/Joining From
Something You Love
Quirk: Something that’s uniquely weird or different about you

IBM Developer

@poojamakes

Watson Studio

IBM Watson Studio is an interactive, collaborative, cloud-based environment where data scientists can use multiple tools to activate their insights.
Data scientists can work with a growing set of data science tools such as

```
R Studio
```
```
Jupyter
```
```
Python
```
```
Scala
```
```
Spark
```
```
IBM Watson Machine Learning
```
```
Watson Visual Recognition
```
```
Natural Language Classifier
```
```
Auto AI
```
```
and more....
```

IBM Developer

@poojamakes

IBM Developer

@poojamakes

Today we will learn how to use Watson Studio to build projects with Jupyter Notebooks :

Goals :

Create Watson Studio Project
Create a Jupyter Notebook to analyze data using Pandas
Create a Jupyter Notebook to analyze data using Pixie Dust
Create Jupyter Notebooks to create predictive models with Watson Machine Learning

Prerequisites

1. Create IBM Cloud Account using THIS URL

https://ibm.biz/BdqqLb

2. Check your email and activate your account. Once activated, log back into your IBM Cloud account using the link above.

3. If you already have an account, use the above URL to sign into your IBM Cloud account.

@poojamakes

IBM Developer

Acquire Data

Cleanse Data

Explore Data

Model Development Phase

IBM Developer

@poojamakes

Source: https://gist.github.com/Tahsin-Mayeesha/092b5d02f7f2eef6983746680de31581

IBM Developer

@poojamakes

Source: https://www.edureka.co/blog/wp-content/uploads/2018/10/Jupyter_Notebook_CheatSheet_Edureka.pdf

@poojamakes

IBM Developer

Python Data Analysis Library
Built on top of Numpy
Used to :
- Clean Data
- Manage Data
- Analyze Data
- Model Data
- Organize Data in a form suitable for plotting

@poojamakes

Source : https://www.learndatasci.com/tutorials/python-pandas-tutorial-complete-introduction-for-beginners/

IBM Developer

@poojamakes

Getting Started With Pandas :

Install Pandas

Import Pandas

Install Pandas

Get Data

Set as Data Frame

View output

IBM Developer

@poojamakes

Open source Python helper library. that helps analyze Apache Spark Data frames .
Works as an add-on to Jupyter notebooks to improve the user experience of working with data
Works with Pandas
One single API called display() lets you visualize your Spark object in different ways: table, charts, maps, etc.

Source :https://pixiedust.github.io/pixiedust/

IBM Developer

@poojamakes

IBM Developer

@poojamakes

Watson Machine Learning

IBM Developer

@poojamakes

API Documentation : http://wml-api-pyclient.mybluemix.net/index.html#api

IBM Developer

@poojamakes

Lets Get Started

Jupyter Notebook Workshop:

ibm.biz/jupyterworkshop

@poojamakes

IBM Developer

@poojamakes

IBM Developer

CODAIT Projects

@poojamakes

Curated List of Data : https://developer.ibm.com/exchanges/data/

IBM Developer

@poojamakes

Resources

Data analysis in Python using pandas : https://developer.ibm.com/tutorials/data-analysis-in-python-using-pandas/
Working with geospatial vector data in Python : https://developer.ibm.com/tutorials/working-with-geospatial-vector-data-in-python/
Visualize data with Python : https://developer.ibm.com/patterns/visualize-data-with-python/
Machine learning using synthesized patient health records : https://developer.ibm.com/patterns/machine-learning-using-synthesized-patient-health-records/
Data analysis, model building, and deploying with Watson Machine Learning with notebook : https://developer.ibm.com/patterns/data-analysis-model-building-and-deploying-with-wml/
Build models using Jupyter Notebooks in IBM Watson Studio : https://developer.ibm.com/tutorials/watson-studio-using-jupyter-notebook/