Current implementation takes the input files and enters the information into a pandas DataFrame object. This has to be done every time the program is run, and is relatively time consuming. It will only take longer when more alleles are added to the testing sets.
To save time and decrease redundancy, the parser should be edited to be a standalone program that takes the input files and generates .csv files that can then simply be read into pandas DataFrames to run on the model.
Current implementation takes the input files and enters the information into a pandas DataFrame object. This has to be done every time the program is run, and is relatively time consuming. It will only take longer when more alleles are added to the testing sets.
To save time and decrease redundancy, the parser should be edited to be a standalone program that takes the input files and generates .csv files that can then simply be read into pandas DataFrames to run on the model.