corrections

tiger.py

@@ -168,6 +168,7 @@ def find_off_targets(top_guides: pd.DataFrame):
         # progress update
         print('\rPercent complete: {:.2f}%'.format(100 * min(i / len(reference_transcripts), 1)), end='')
     print('')
+    del reference_transcripts
 
     return off_targets
 
@@ -238,19 +239,15 @@ if __name__ == '__main__':
         df_transcripts = load_transcripts([os.path.join(args.fasta_path, f) for f in os.listdir(args.fasta_path)])
 
         # process in batches
-        df_on_target = pd.DataFrame()
-        df_off_target = pd.DataFrame()
         batch = 1
         num_batches = len(df_transcripts) // BATCH_SIZE_TRANSCRIPTS
         num_batches += (len(df_transcripts) % BATCH_SIZE_TRANSCRIPTS > 0)
         for t in range(0, len(df_transcripts), BATCH_SIZE_TRANSCRIPTS):
             print('Batch {:d} of {:d}'.format(batch, num_batches))
             t_stop = min(t + BATCH_SIZE_TRANSCRIPTS, len(df_transcripts))
-            df_on_target_new, df_off_target_new = tiger_exhibit(df_transcripts[t:t_stop])
-            df_on_target = pd.concat([df_on_target, df_on_target_new])
-            df_off_target = pd.concat([df_off_target, df_off_target_new])
+            df_on_target, df_off_target = tiger_exhibit(df_transcripts[t:t_stop])
+            df_on_target.to_csv('on_target_{:d}.csv'.format(batch), index=False)
+            df_off_target.to_csv('off_target_{:d}.csv'.format(batch), index=False)
+            del df_on_target, df_off_target
             batch += 1
 
-        # save results
-        df_on_target.to_csv('on_target.csv')
-        df_off_target.to_csv('off_target.csv')