C3_W1 assignment

hi

I have corrected the problem. Now I’m getting:

Vocabulary of labels looks like this {'sport': 1, 'business': 2, 'politics': 3, 'tech': 4, 'entertainment': 5}

First ten sequences [[1714], [159], [561], [561], [756], [993], [993], [561], [561], [756]]

any suggestions why the first ten sequences would be different from ‘expected’?

thank you,

I solved it; silly error

I’ll submit it now. thank you for your help!

kind Regards,
Ed

Learning alone is not easy. Come on.

I’m having the same issue. Everything appears to work but I’m getting:

Vocabulary of labels looks like this {'sport': 1, 'business': 2, 'politics': 3, 'tech': 4, 'entertainment': 5}

First ten sequences [[1714], [159], [561], [561], [756], [993], [993], [561], [561], [756]]

Any help?

Nm, figured it out. For future learners with this problem, just make sure you aren’t calling an old instance of tokenizer.