実践 機械学習システム

6.6

 単語の種類を考慮する

139

l = len(sent)

avg_pos_val = np.mean(pos_vals)

avg_neg_val = np.mean(neg_vals)

return [1-avg_pos_val-avg_neg_val,

avg_pos_val, avg_neg_val,

nouns/l, adjectives/l, verbs/l, adverbs/l]

def transform(self, documents):

obj_val, pos_val, neg_val, nouns, adjectives, \

verbs, adverbs = np.array([self._get_sentiments

(d) \

for d in documents]).T

allcaps = []

exclamation = []

question = []

hashtag = []

mentioning = []

for d in documents:

allcaps.append(np.sum([t.isupper() \

for t in d.split() if len(t)>2]))

exclamation.append(d.count("!"))

question.append(d.count("?"))

hashtag.append(d.count("#"))

mentioning.append(d.count("@"))

result ...