Tokenizer labels not give the proper week1

[Mauro_Vincio_Pazmino]

Word index for the labels looked wrong. When the assignment was graded, I got:

Failed test case: incorrect label_sequences when using labels: [‘tech’, ‘tech’, ‘entertainment’, ‘sport’, ‘business’].
Expected:
[[1], [1], [2], [3], [4]],
but got:
[[124], [124], [102], [55], [29]].

Failed test case: incorrect label_word_index when using labels: [‘tech’, ‘tech’, ‘entertainment’, ‘sport’, ‘business’].
Expected:
{‘tech’: 1, ‘entertainment’: 2, ‘sport’: 3, ‘business’: 4},
but got:
{‘’: 1, ‘s’: 2, ‘said’: 3, ‘will’: 4, ‘not’: 5, ‘mr’: 6, ‘year’: 7, ‘also’: 8, ‘people’: 9, ‘new’: 10, ‘us’: 11, ‘one’: 12, ‘can’: 13, ‘last’: 14, ‘first’: 15, ‘t’: 16, ‘time’: 17, ‘two’: 18, ‘world’: 19, ‘government’: 20, ‘now’: 21, ‘uk’: 22, ‘years’: 23, ‘no’: 24,

I do not know what I need to look for when dealing with labels. When I called the tokenizer, I just coded: Tokenizer() without arguments.

[ajaykumar3456]

Hello,
Welcome to the Community. There is a mistake on how you split the data or how you encoded the target labels.

In the text file that is given as input to the parse_data_to_the_file(), each line is a row where the values are separated by a semi-colon (;). You need to parse through each row and then extract the 1st value and add them to the labels list and then the subsequent values in that row to the sentences.
If that’s the mistake, please correct and re-run the cells from beginning.

If you still get the same error, I would like you to share the notebook by clicking on my name and send it as a personal message. I would be more than happy to help you figure this out.
Thanks,
Ajay