diff --git a/alignement.py b/alignement.py index 2b88a0c905c861d30b6a4ca0dc8fa898481c48cb..39892fc10f955ff126ff8bca2dbd7aa97ce82e7b 100644 --- a/alignement.py +++ b/alignement.py @@ -146,7 +146,7 @@ def filter_cysteine(df, col): # dataset_train.to_pickle('database/data_DIA_ISA_55_train.pkl') # dataset_train.to_pickle('database/data_DIA_ISA_55_test.pkl') -data_train_1 = pd.read_pickle('database/data_DIA_ISA_55_train.pkl').reset_index(drop=True) +data_train_1 = pd.read_csv('database/data_holdout.csv').reset_index(drop=True) # data_train_2 = pd.read_pickle('database/data_DIA_ISA_55_test.pkl').reset_index(drop=True) # data_ori = pd.read_csv('database/data_train.csv').reset_index(drop=True) # data_ori['Sequence']=data_ori['sequence'] @@ -154,4 +154,4 @@ data_train_1 = pd.read_pickle('database/data_DIA_ISA_55_train.pkl').reset_index( # data_train = pd.concat([data_train_2,data_train_1]).reset_index(drop=True) # data_align = align(data_train, data_ori) -df = filter_cysteine(data_train_1,'Sequence') +df = filter_cysteine(data_train_1,'sequence')