Python Natural Language Processing

Using scikit-learn

We will try to generate the TF-IDF model using a small Shakespeare dataset. For a new given document with a TF-IDF score model, we will suggest the top three keywords for the document. You can see the code snippet in Figure 5.61:

Figure 5.61: Using scikit-learn to generate a TF-IDF model

You can see the output in Figure 5.62:

Figure 5.62: Output of the TF-IDF model

Now it's time to see where we can use this TF-IDF concept, so let's look at some applications.