predictions_format.py

# IDs for the comment_text
idxs = test_df.loc[inf_dl.get_idxs()].id.reset_index(drop = True)

# The order id in test data
indices = inf_dl.get_idxs()

# Create a Predictions dataframe for submission
predictions = pd.DataFrame(all_predictions[0].numpy(), columns = learn_clf.dls.vocab[1])
predictions["id"] = idxs
predictions["order"] = indices

# Curate the dataframe to match the submission format
predictions = predictions.sort_values(by = ["order"])
predictions = predictions[["id", "toxic", "severe_toxic", "obscene", "threat", "insult", "identity_hate"]].reset_index(drop = True)
display_html(predictions.head().to_html(raw = True))

# Save the dataframe
predictions.to_csv("submissions_toxic.csv", index = False)