Download [Powerpoint] - 20151121_MSDEVMTL_Analytics2

Analyse Prédictive
Partie 2
Charles Verdon
Spécialiste technique – BD & IA
Email: [email protected]
Twitter: @chverdon
Advanced Analytics Solution
HD Insight
SQL Server 2016
R Integration
SQL Server 2016
R Services
Azure Machine
Learning
Machine
Learning
Revolution
Analytics in Azure
Marketplace
Project Oxford
Azure ML Gallery
Model Your Way: Open source/our source
Python client library
Advanced Analytics Architecture
API
M
• Data factory
• Stream analytics
• Machine learning
• HDInsight
• Marketplace
• Azure portal
• Power BI
• Apps
3. Descriptive statistics and
visualization for datasets
2. Uploaded data tables or
4. Pre-built
commands to
transform or
manipulate data
connect to your data in the
cloud or on-premises
1. Pick & drop
models. No
obligation to write
scripts.
5. Specific settings to fine
tune the models
6. Evaluate models,
Visualize result or
export data
7. Publish the model as a standard web-service. You can then call it from ETL processes or any application
Comprehensive Toolbox
Regression
analysis
Clustering
Nearestneighbor
Associative
rule mining
Support for
vector machines
Decision tree
learning
Time series
processing
Text
analytics
Mathematical
programming
Online
analytical
processing
Graph
analytics
Monte Carlo
methods
Neural
networks
Support for
extensibility by
enabling users
to add their
own
algorithms as
modules
Data Science Process is All About Experimentation
Business
Understanding
Deployment
and
Monitoring
Data
Understanding
Data
Data
Preparation
Evaluation
Modeling
Dataset - Definition
•
•
•
•
•
•
•
•
•
•
•
survival Survival (0 = No; 1 = Yes)
pclass Passenger Class (1 = 1st; 2 = 2nd; 3 = 3rd)
name Name
sex Sex
age Age
sibsp Number of Siblings/Spouses Aboard
parch Number of Parents/Children Aboard
ticket Ticket Number
fare Passenger Fare
cabin Cabin
embarked Port of Embarkation (C = Cherbourg; Q = Queenstown; S = Southampton)
Dataset – Special Notes
• Pclass is a proxy for socio-economic status (SES) 1st ~ Upper; 2nd ~
Middle; 3rd ~
• Lower Age is in Years; Fractional if Age less than One (1) If the Age is
Estimated, it is in the form xx.5
• With respect to the family relation variables (i.e. sibsp and parch)
some relations were ignored. The following are the definitions used
for sibsp and parch.
• Sibling: Brother, Sister, Stepbrother, or Stepsister of Passenger Aboard Titanic
Spouse: Husband or Wife of Passenger Aboard Titanic (Mistresses and Fiances
Ignored)
• Parent: Mother or Father of Passenger Aboard Titanic Child: Son, Daughter,
Stepson, or Stepdaughter of Passenger Aboard Titanic
Setup
Environment
Explore Data
Load Data
Engineer Features
Build Model
Deploy Model
Sample Data
Refresh Model
Consume Model
Advanced Analytics Solution
HD Insight
SQL Server 2016
R Integration
SQL Server 2016
R Services
Azure Machine
Learning
Machine
Learning
Revolution
Analytics in Azure
Marketplace
Project Oxford
Azure ML Gallery
Merci!
Thank you!
谢谢!
Vielen Dank!
¡Gracias!
Спасибо!
ありがとう！
Charles Verdon
[email protected]
@chverdon
!‫شكرا‬