Please enable JavaScript.
Coggle requires JavaScript to display documents.
CH 9: Data Integration (Two Methods (unions (imputation (the replacing of…
CH 9: Data Integration
Two Methods
joins
to access more features
combines two datasets w/ a shared identity value
Inner join
common with carefully curated databases
Outer Join
left
useful for projects where you want as much data as possible
good when paired with inner join
right
full
unions
to access more observations
assumption that there are mult columns in common
combine two datasets
approriate when there are similar info but not overlapping
imputation
the replacing of missing data in a column with resonable values
i.e. avg age