From the course: Advanced NLP with Python for Machine Learning

Unlock the full course today

Join today to access over 22,600 courses taught by industry experts or purchase this course individually.

Compare all methods using key performance metrics

Compare all methods using key performance metrics - Python Tutorial

From the course: Advanced NLP with Python for Machine Learning

Start my 1-month free trial

Compare all methods using key performance metrics

“

- [Instructor] So now that we've built four models using four different ways to represent text messages, let's zoom out and take a look at the metrics we're using to evaluate these models. Now, a few caveats here. You should not necessarily take the methods I've shown as the only ways to solve a problem like this. Problems you encounter are all unique. This just adds a few techniques to your toolbox to solve those problems. You also should not take the results of these techniques on this problem as the ground truth for any problem. Just because TF-IDF works really well here, it doesn't necessarily mean it will work really well on every problem. Third, these models are not deterministic. If you're running the code along with me, you'll probably get slightly different results, though the relative ranking of these methods should remain the same. Lastly, we're using a fairly small data set here, and we didn't spend much…

Contents