df oktoberfest

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