I submitted a Tensorflow model for training to Express Lane (not sub-challenges) and received the following error from "DREAM_DM_starter_tf.py"   STDERR: Traceback (most recent call last): STDERR: File "DREAM_DM_starter_tf.py", line 701, in STDERR: main(sys.argv) STDERR: File "DREAM_DM_starter_tf.py", line 690, in main STDERR: X_tr, X_te, Y_tr, Y_te = create_data_splits(path_csv_crosswalk, path_csv_metadata) STDERR: File "DREAM_DM_starter_tf.py", line 90, in create_data_splits STDERR: dict_tuple_to_cancer[(row[0].strip(), 'L')] = int(row[3]) STDERR: ValueError: invalid literal for int() with base 10: '.'   I put a print row statement at line 89 of this Python code and looks like the metadata line for subject id 99jj4mwu has a dot symbol as the 3rd argument. Here is the line that produces the error message.   STDOUT: ['99jj4mwu', '1', '0', '.', '0', '.', '0', '63', '.', '.', '1', '10.5', '2', '0', '.', '0', '0', '0', '0', '22.7099', '1']  ` I will appreciate any help.

Created by Zafer Aydin zaferaydin
Dear Zafer, Apologies for the delay in response. Where in the wiki do you see this example? The metadata file has "." for samples that don't have information. The code will have to be modified to not do an `int()` operation when it is in fact a string. Best, Thomas

Invalid literal error when parsing metadata file for Express Lane data page is loading…