Hey guys,
Trying to submit but keep encountering this error
""""""
Missing entries for IDs id_j7b6sokflo4k_X_0,
id_j7b6sokflo4k_X_1,
id_j7b6sokflo4k_X_2,
id_j7b6sokflo4k_X_3, and
id_j7b6sokflo4k_X_4
""""""
If you check closely these are the first 5 row IDs.
On openning the file in Excel, the rows label are well filled out.
""""""
event_id label
0 id_j7b6sokflo4k_X_0 7.56E-05
1 id_j7b6sokflo4k_X_1 8.97E-05
2 id_j7b6sokflo4k_X_2 5.77E-05
3 id_j7b6sokflo4k_X_3 0.000142
4 id_j7b6sokflo4k_X_4 0.000212
5 id_j7b6sokflo4k_X_5 0.000144
6 id_j7b6sokflo4k_X_6 0.000146
""""""
Someone who might know why this is happenng please!
@Freestar do this
put index =False. It should work if you have all you ids in the csv
test_df.to_csv('baseline.csv', index=False)
@AyomideOraegbu the error still persist
If you did this - test_df.to_csv('baseline.csv', index=False), and your error still persists. I will encourage you to check that your submission file contains all ids, with each id having a value from 0 - 729.
The reason your submission is missing entries could be because the event IDs in Test.csv contain multiple time steps (e.g., _X_0, _X_1, _X_2, etc.), but the image features do not contain multiple time steps so you might have removed the time steps when when merging with the image features. your final submission only has duplicated ID's without the time steps. To ensure that you solve that you can create test_df1 that contains the original ID's then use the example below to create your submission file.
create submission_df = pd.DataFrame({"ID": test_df1["event_id"], "Target": test_preds})