ChenNannan-Data preparation
Jump to navigation
Jump to search
|
|
|
|
Data Quality Issues
No missing value.
At least 2.5% of 0 value in value variables which is meaningless.
Year 1998 and 1999 are imported wrong. The time series range is from 1998 to 2016.
Same location, sample date and measure have different value record.
Data Preparation
Recode the sample date.
Use the summary function to avoid duplication record by mean.
'Dcast' the data
Standardize the value by each kinds of measure because different units.