Algemene informatie over de cursus
In deze unieke 4-daagse training doet u de kennis en ervaring op om een aantal van de analytische functies die oorspronkelijk voorbehouden waren aan de Data Scientist uit te voeren. Na deze training bent u in staat om als niet-Data Scientist de belangrijkste data gerelateerde taken uit te voeren met gebruikmaking van de point-and-click mogelijkheden van SAS Visual Analytics: data toegang en data manipulatie, data onderzoek met gebruikmaking van analytics en het opzetten van voorspellende modellen.U leert hoe u:
- data uit verschillende formats kunt laden
- data kunt voorbereiden voor analyse
- data kunt analyseren met gebruikmaking van effectieve data visualisering
- data mining tools kunt opzetten en vergelijken
Inhoud van de cursus
I. BIG DATA AND ANALYTICSData Science - introduction
- The era of abundance
- Big Data explained
- Data analysis overview
Statistics - introduction
- Examining data distributions
- Obtaining and interpreting sample statistics
- Examining data distributions graphically
- Using exploratory data analysis
- Producing correlations
- Fitting a simple linear regression model
II. PREPARING FOR ANALYSIS
Getting started with Visual Analytics
- Exploring SAS Visual Analytics concepts
- Using the SAS Visual Analytics home page
- Discussing the course environment and scenario
Using Visual Analytics Explorer
- Examining SAS Visual Analytics Explorer
- Selecting data and defining data item properties
- Creating visualizations
- Enhancing visualizations with analytics
- Interacting with visualizations and explorations
Examining Visual Data Builder
- Exploring SAS Visual Data Builder
- Creating simple queries
Creating complex queries in Visual Data Builder
- Importing data using SAS Visual Data Builder
- Creating calculated columns and filtering data
- Creating advanced queries
Advanced topics for Visual Data Builder
- Accessing user-defined formats
Using the Explorer and Designer to load data
- Using the Explorer and Designer to import data
- Using the Explorer and Designer to create calculated columns
III. ANALYTICAL DATA VISUALIZATION AND MODELING DATA
Cluster segmentation
- Understanding segmentation
- Using cluster analysis
Models with continuous targets
- Managing projects and models
- Using linear regression models
- Using generalized linear models
Models with categorical targets
- Using logistic regression
- Using decision trees
Model comparison and assessment
- Comparing models
- Scoring models
CASE STUDY
You will be able to put your knowledge into practice with real-world, scenario-based examples.