Currently, experiments work by calling classify_cancer_type.py for each gene/cancer type combination. This script reloads all of the data into memory each time, which takes 5-10 minutes.
Creating classifiers for many genes/cancer types would be a lot faster if the code were refactored to load the data once, then run all combinations subsequently (i.e in a single script).
Currently, experiments work by calling
classify_cancer_type.py
for each gene/cancer type combination. This script reloads all of the data into memory each time, which takes 5-10 minutes.Creating classifiers for many genes/cancer types would be a lot faster if the code were refactored to load the data once, then run all combinations subsequently (i.e in a single script).