file_name = 'ThicketDefCodingTestProcessed'
* Step 2 : specify the expected columns of your target filein "main()"
# expected number of columns, in case we have "None" in the table
expected_columns = 5
* Step 3 : specify the indices of the text and the label in "prepare_imdb_structure(file_name, expected_columns)"
# the index of the label in the tokens
label_index = 1
# the index of the text in the tokens
content_index = 4