Add data imputation capability

DOI-BOR / PyForecast

PyForecast is a statistical modeling tool used by Reclamation water managers and reservoir operators to train and build predictive models for seasonal inflows and streamflows. PyForecast allows users to make current water-year forecasts using models developed with the program.

Other

28 stars 12 forks source link

Add data imputation capability #30

Open tjrocha opened 5 years ago

tjrocha commented 5 years ago

Allow users to fill in missing data in the input data arrays. Propose

using the data imputation methods in the statsmodels package
and putting this feature in the DataAnalysis GUI for plotting and diagnostics

jslanini commented 5 years ago

I'm cautiously supportive. My concern is introducing bias into the dataset through imputation. Should we examine alternative imputation methods? See https://www.omicsonline.org/open-access/a-comparison-of-six-methods-for-missing-data-imputation-2155-6180-1000224.php?aid=54590

tjrocha commented 5 years ago

Propose having the GUI update to aid in the QA/QC/Acceptance of the imputed dataset. Something like:

show how many data-points were filled-in
plot time-series data for datasets with the imputed data -- color imputed data separately
allow user to overwrite main raw-data dataframe with the imputed dataframe

stretch goal(s)

integrate other imputation methods and allow user to customize which imputation method is used