How can I do the following in Python?
row = [unicode(x.strip()) for x in row if x is not None else \'\']
Essentially:
You can combine conditional logic in a comprehension:
ps = PorterStemmer()
stop_words_english = stopwords.words('english')
best = sorted(word_scores.items(), key=lambda x: x[1], reverse=True)[:10000]
bestwords = set([w for w, s in best])
def best_word_feats(words):
return dict([(word, True) for word in words if word in bestwords])
# with stemmer
def best_word_feats_stem(words):
return dict([(ps.stem(word), True) for word in words if word in bestwords])
# with stemmer and not stopwords
def best_word_feats_stem_stop(words):
return dict([(ps.stem(word), True) for word in words if word in bestwords and word not in stop_words_english])