From 8317305752b74955f32d8a025ff6ee3b287a7645 Mon Sep 17 00:00:00 2001
From: Schneider Leo <leo.schneider@etu.ec-lyon.fr>
Date: Thu, 13 Feb 2025 15:04:19 +0100
Subject: [PATCH] df oktoberfest
---
data/msp_file_extraction.py | 2 ++
1 file changed, 2 insertions(+)
diff --git a/data/msp_file_extraction.py b/data/msp_file_extraction.py
index c27be7a..3dca185 100644
--- a/data/msp_file_extraction.py
+++ b/data/msp_file_extraction.py
@@ -66,6 +66,7 @@ if __name__ == '__main__':
seq.append(s)
df = pd.DataFrame(seq,columns=['sequence'])
+ df = df.drop_duplicates()
df['irt_scaled']=0
df['state'] = 'holdout'
df.to_csv('spectral_lib/df_predicted_library_oktoberfest.csv',index=False)
@@ -77,6 +78,7 @@ if __name__ == '__main__':
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')
--
GitLab