Skip to content
Snippets Groups Projects
Commit d2bcec95 authored by Schneider Leo's avatar Schneider Leo
Browse files

dataset

parent 6d8bfb33
No related branches found
No related tags found
No related merge requests found
...@@ -156,16 +156,16 @@ def numerical_to_alphabetical_str(s): ...@@ -156,16 +156,16 @@ def numerical_to_alphabetical_str(s):
if __name__ == '__main__': if __name__ == '__main__':
# main() # main()
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 = pd.read_csv('/lustre/fswork/projects/rech/bun/ucg81ws/these/dia-augmentation/data/data_PXD006109/e_coli/data_aligned_train_coli.csv')
df_base = df_base[['sequence', 'irt_scaled','state']] 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] t = [0.05,0.1,0.2,0.3,0.4,0.5,0.7,1,10]
#reste 07 1 et all #reste 07 1 et all
name = ['005','01','02','03','04','05','07','1','all'] name = ['005','01','02','03','04','05','07','1','all']
df_0 = pd.read_csv('/lustre/fswork/projects/rech/bun/ucg81ws/these/dia-augmentation/output/out_plasma_aligned_train_0.csv') df_0 = pd.read_csv('/lustre/fswork/projects/rech/bun/ucg81ws/these/dia-augmentation/output/out_coli_aligned_train_0.csv')
df_1 = pd.read_csv('/lustre/fswork/projects/rech/bun/ucg81ws/these/dia-augmentation/output/out_plasma_aligned_train_1.csv') df_1 = pd.read_csv('/lustre/fswork/projects/rech/bun/ucg81ws/these/dia-augmentation/output/out_coli_aligned_train_1.csv')
df_2 = pd.read_csv('/lustre/fswork/projects/rech/bun/ucg81ws/these/dia-augmentation/output/out_plasma_aligned_train_2.csv') df_2 = pd.read_csv('/lustre/fswork/projects/rech/bun/ucg81ws/these/dia-augmentation/output/out_coli_aligned_train_2.csv')
df_3 = pd.read_csv('/lustre/fswork/projects/rech/bun/ucg81ws/these/dia-augmentation/output/out_plasma_aligned_train_3.csv') df_3 = pd.read_csv('/lustre/fswork/projects/rech/bun/ucg81ws/these/dia-augmentation/output/out_coli_aligned_train_3.csv')
df_4 = pd.read_csv('/lustre/fswork/projects/rech/bun/ucg81ws/these/dia-augmentation/output/out_plasma_aligned_train_4.csv') df_4 = pd.read_csv('/lustre/fswork/projects/rech/bun/ucg81ws/these/dia-augmentation/output/out_coli_aligned_train_4.csv')
list_df = [df_0, df_1, df_2, df_3, df_4] list_df = [df_0, df_1, df_2, df_3, df_4]
for i in range(len(name)): for i in range(len(name)):
...@@ -173,12 +173,12 @@ if __name__ == '__main__': ...@@ -173,12 +173,12 @@ if __name__ == '__main__':
print('thresold {} en cours'.format(name[i])) print('thresold {} en cours'.format(name[i]))
# #
df = select_best_data(list_df, t[i]) df = select_best_data(list_df, t[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.to_pickle('/lustre/fswork/projects/rech/bun/ucg81ws/these/dia-augmentation/data/data_PXD006109/e_coli/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 = pd.read_pickle('/lustre/fswork/projects/rech/bun/ucg81ws/these/dia-augmentation/data/data_PXD006109/e_coli/data_ISA_additionnal_{}.pkl'.format(name[i]))
df['state'] = 'train' df['state'] = 'train'
df['sequence'] = df['sequence'].map(numerical_to_alphabetical_str) 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 = pd.concat([df, df_base], axis=0).reset_index(drop=True)
df_augmented_1.columns = ['sequence', 'irt_scaled','state'] df_augmented_1.columns = ['sequence', 'irt_scaled','state']
df_augmented_1.to_csv('/lustre/fswork/projects/rech/bun/ucg81ws/these/dia-augmentation/data/data_PXD006109/plasma_train/plasma_data_augmented_{}.csv'.format(name[i]), index=False) df_augmented_1.to_csv('/lustre/fswork/projects/rech/bun/ucg81ws/these/dia-augmentation/data/data_PXD006109/e_coli/plasma_data_augmented_{}.csv'.format(name[i]), index=False)
print(df_augmented_1.shape) print(df_augmented_1.shape)
\ No newline at end of file
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment