From 2b420b9e767f24c2d611e8bf5eac9341e01a2f8b Mon Sep 17 00:00:00 2001
From: Schneider Leo <leo.schneider@etu.ec-lyon.fr>
Date: Wed, 12 Feb 2025 17:42:46 +0100
Subject: [PATCH] df oktoberfest
---
data/msp_file_extraction.py | 24 ++++++++++++------------
1 file changed, 12 insertions(+), 12 deletions(-)
diff --git a/data/msp_file_extraction.py b/data/msp_file_extraction.py
index ebd4b9d..631c933 100644
--- a/data/msp_file_extraction.py
+++ b/data/msp_file_extraction.py
@@ -60,7 +60,7 @@ if __name__ == '__main__':
if 'Name:'in content[i]:
s=content[i].split(':')[1].split('/')[0]
- if 'C' in s :
+ if 'C' in s or len(s)>30:
remove=True
else :
seq.append(s)
@@ -69,17 +69,17 @@ if __name__ == '__main__':
df['irt_scaled']=0
df['state'] = 'holdout'
df.to_csv('spectral_lib/df_predicted_library_oktoberfest.csv',index=False)
-
- updated_content=[]
- ind=0
- predicted_lib=pd.read_csv('../output/out_lib_oktoberfest.csv')
-
- predicted_lib['seq'] = predicted_lib['seq'].map(numerical_to_alphabetical_str)
-
- predicted_lib['sequence']=predicted_lib['seq']
- pred_rt=predicted_lib['rt pred']
-
- df_joined = pd.merge(df,predicted_lib[['rt pred','sequence']],on='sequence',how='left')
+ #
+ # updated_content=[]
+ # ind=0
+ # predicted_lib=pd.read_csv('../output/out_lib_oktoberfest.csv')
+ #
+ # predicted_lib['seq'] = predicted_lib['seq'].map(numerical_to_alphabetical_str)
+ #
+ # predicted_lib['sequence']=predicted_lib['seq']
+ # pred_rt=predicted_lib['rt pred']
+ #
+ # df_joined = pd.merge(df,predicted_lib[['rt pred','sequence']],on='sequence',how='left')
#1787661 avec C , 15104040 sans
\ No newline at end of file
--
GitLab