35MB, just a little more than the SampleSubmission.

I literally just changed the original zeroes from submission['Target'] to the predictions of the model.

It has the same number of rows as well.

This is not much. What kind of error are you getting after submission ?

Normally, scoring takes time (expect 15mins wait ,,,, according to the data page)

this is the error:

It's not even loading to score. The file is immediately denied

Hello, we are looking in to this.

Did you solve using this? I will try here.

Unfortunatly this did not work for me...

Is your ID column of type 'object'?

It works to me I faced the same problem and I fixed it by change the Target col with np.int8 but I don't know how doesn't works for you. Anyway try to submit original sample submission file then if it works then you can try predict one

Hi @Yisakberhanu,

I tried your suggestion, but it did not work. I still have the same issue as @yanteixeira.

Could you please look at my snippet below and tell me if there is a mistake?

# Defining the dataframe
submission_df = pd.DataFrame()

# Copying the IDs into the submission dataframe
submission_df['ID'] = df_test['id'].copy()

# Adding the Target column to the submission dataframe with pred_test being the prediction array
submission_df.insert(loc=1, column='Target', value=pred_test)

# Reset index
submission_df.reset_index(inplace=True, drop=True)

# Convert Target predictions to int8
submission_df['Target'] = submission_df.Target.astype(np.int8)

# Save to local disk
submission_df.to_csv('submission.csv', index=False)

Yeah, I still have the same issue... I think I've already tried every data type possible. Even the submission with all zeroes for the target is not accepted

Okay I will share my notebook

It's like I said, the platform denied the file, even with only zeroes on the target. Good to know that it's been taken care of! Thanks!

@amyflorida626, from my end problem still persists.