如何使用scikit-learn对文本进行分类

Question

I want to classify two text by using scikit-learn. But I want to extract features by myself. Just like using stop_words='english' to stop word list for English is used on CountVectorizer . How to set my own word list to let CountVectorizer to count?

Answer 1

You can provide your own list of stop words to the stop_words argument in the CountVectorizer and it will not count the words that you don't want it to be counted in your input text in scikit-learn. For example, if I don't want words such as "cat", "dog" and "elephant" to use as tokens, I would instantiate CountVectorizer as the following:

CountVectorizer(stop_words=['cat','dog', elephant'])

Hope that helps.