align train and reorganise

data/data_processing.py

@@ -129,7 +129,7 @@ def numerical_to_alphabetical_str(s):
 if __name__ == '__main__':
     # main()
 
-    df_base = pd.read_csv('data_PXD006109/plasma/data_aligned_train_plasma.csv')
+    df_base = pd.read_csv('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
@@ -146,12 +146,12 @@ if __name__ == '__main__':
         print('thresold {} en cours'.format(name[i]))
         #
         df = select_best_data(list_df, t[i])
-        df.to_pickle('data_PXD006109/plasma/data_ISA_additionnal_{}.pkl'.format(name[i]))
-        df = pd.read_pickle('data_PXD006109/plasma/data_ISA_additionnal_{}.pkl'.format(name[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['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)
         df_augmented_1.columns = ['sequence', 'irt_scaled','state']
 
-        df_augmented_1.to_csv('data_PXD006109/isa_data_augmented_{}.csv'.format(name[i]), index=False)
+        df_augmented_1.to_csv('data_PXD006109/plasma_train/plasma_data_augmented_{}.csv'.format(name[i]), index=False)
         print(df_augmented_1.shape)
\ No newline at end of file