data processing for jz

data/data_processing.py

@@ -156,12 +156,12 @@ def numerical_to_alphabetical_str(s):
 if __name__ == '__main__':
     # main()
 
-    df_base = pd.read_csv('./data_PXD006109/plasma_train/data_aligned_train_plasma.csv')
+    df_base = pd.read_csv('/lustre/fswork/projects/rech/bun/ucg81ws/these/dia-augmentation/data/data_PXD006109/plasma_train/data_aligned_train_plasma.csv')
     df_base = df_base[['sequence', 'irt_scaled','state']]
     t = [0.05,0.1,0.2,0.3,0.4,0.5,0.7,1,10]
     #reste 07 1 et all
     name = ['005','01','02','03','04','05','07','1','all']
-    df_0 = pd.read_csv('../output/out_early_stop_plasma_train_prosit_0.csv')
+    df_0 = pd.read_csv('../output/out_early_stop_plasma_prosit_0.csv')
     df_1 = pd.read_csv('../output/out_early_stop_plasma_train_prosit_1.csv')
     df_2 = pd.read_csv('../output/out_early_stop_plasma_train_prosit_2.csv')
     df_3 = pd.read_csv('../output/out_early_stop_plasma_train_prosit_3.csv')
@@ -173,8 +173,8 @@ if __name__ == '__main__':
         print('thresold {} en cours'.format(name[i]))
         #
         df = select_best_data(list_df, t[i])
-        df.to_pickle('./data_PXD006109/plasma_train/data_ISA_additionnal_{}.pkl'.format(name[i]))
-        df = pd.read_pickle('./data_PXD006109/plasma_train/data_ISA_additionnal_{}.pkl'.format(name[i]))
+        df.to_pickle('/lustre/fswork/projects/rech/bun/ucg81ws/these/dia-augmentation/data/data_PXD006109/plasma_train/data_ISA_additionnal_{}.pkl'.format(name[i]))
+        df = pd.read_pickle('/lustre/fswork/projects/rech/bun/ucg81ws/these/dia-augmentation/data/data_PXD006109/plasma_train/data_ISA_additionnal_{}.pkl'.format(name[i]))
         df['state'] = 'train'
         df['sequence'] = df['sequence'].map(numerical_to_alphabetical_str)
         df_augmented_1 = pd.concat([df, df_base], axis=0).reset_index(drop=True)