MeMDLM / benchmarks /Supervised /Localization /process_cell_local_data.py
sgoel30's picture
Upload 34 files
d8ed92a verified
raw
history blame
506 Bytes
import pandas as pd
path = "/home/sg666/MDpLM/benchmarks/Supervised/Localization"
train_val = pd.read_csv(path + "/deeploc2.0_train_val.csv")
test = pd.read_csv(path + "/deeploc2.0_test.csv")
train_val = train_val[train_val['Sequence'].apply(len) < 1024].reset_index(drop=True)
test = test[test['Sequence'].apply(len) < 1024].reset_index(drop=True)
train_val.to_csv(path + "/true_deeploc2.0_cell-local_train-val.csv", index=False)
test.to_csv(path + "/true_deeploc2.0_cell-local_test.csv", index=False)