Python Data Structures and Algorithms

Prediction

To test whether our model has learned enough to predict the category that an unknown post is likely to belong to, we have the following sample data:

    test_data = ["My God is good", "Arm chip set will rival intel"]     test_counts = count_vect.transform(test_data)     new_tfidf = matrix_transformer.transform(test_counts) 

The list test_data is passed to the count_vect.transform function to obtain the vectorized form of the test data. To obtain the term frequency--inverse document frequency representation of the test dataset, we call the transform method of the matrix_transformer object.

To predict which category the docs may belong to, we do the following:

    prediction = model.predict(new_tfidf)  

The loop is used to iterate over the prediction, ...