estoy usandonltk para generar n-gramos a partir de oraciones eliminando primero las palabras de detención dadas. Sin embargo,nltk.pos_tag() es extremadamente lento y tarda hasta 0.6 segundos en mi CPU (Intel i7).

La salida:

['The first time I went, and was completely taken by the live jazz band and atmosphere, I ordered the Lobster Cobb Salad.']
0.620481014252
["It's simply the best meal in NYC."]
0.640982151031
['You cannot go wrong at the Red Eye Grill.']
0.644664049149

El código:

for sentence in source:

    nltk_ngrams = None

    if stop_words is not None:   
        start = time.time()
        sentence_pos = nltk.pos_tag(word_tokenize(sentence))
        print time.time() - start

        filtered_words = [word for (word, pos) in sentence_pos if pos not in stop_words]
    else:
        filtered_words = ngrams(sentence.split(), n)

¿Esto es realmente tan lento o estoy haciendo algo mal aquí?