Please enable JavaScript.
Coggle requires JavaScript to display documents.
Summarization (Summarize (Process (Functions applied to each bucket:…
Summarization
Summarize
When data is not focused directly on the customer
Get a new column summarizing after joining tables
Summarized data to get back to order level
Reduces the number of columns and number of rows
Process
1 or more columns is selected
Virtual 'bucket" is created fro each unique group
Every row belonging to each unique group will be put inside bucket
Functions applied to each bucket:
Count
Sum
Min
Max
First
Last
Average
Median
Mode
Std. Dev
Possible to summarize more than 1 column
Provides summary and aggregate info on existing columns
Crosstab
Uses content inside columns to create new columns
Deals with 'skinny' data
Makes data intuitive and readable
Allows for ML to better predict target
Happens when data from sales when 1+ customers make purchases over time
Happens with IoT devices that report status back to owner every sub-second
"Event" is stored as its own row
Transfroms listed data into column form
Process
Select row of Interest
Select column content
Apply aggregate function (count)
Exercises
