我无法从我输入的句子中生成语义情绪。我用pos标记。我在yml文件中有一些单词,如happy,positive,sad等。我想在yml文件中添加每个单词的计数,并显示最大的计数作为心情。通过在函数def value_of(情绪)中分别返回+1和-1,我可以产生正极性,如果它是负的或正的,但我不想要那样。我想要的是我无法产生的情绪。 请帮忙。这是整个代码:
from pprint import pprint
import nltk
import yaml
import sys
import os
import re
import json
import ast
class Splitter(object):
def __init__(self):
self.nltk_splitter = nltk.data.load('tokenizers/punkt/english.pickle')
self.nltk_tokenizer = nltk.tokenize.TreebankWordTokenizer()
def split(self, text):
sentences = self.nltk_splitter.tokenize(text)
tokenized_sentences = [self.nltk_tokenizer.tokenize(sent) for sent in sentences]
return tokenized_sentences
class POSTagger(object):
def __init__(self):
pass
def pos_tag(self, sentences):
pos = [nltk.pos_tag(sentence) for sentence in sentences]
#adapt format
pos = [[(word, word, [postag]) for (word, postag) in sentence] for sentence in pos]
return pos
class DictionaryTagger(object):
def __init__(self, dictionary_paths):
files = [open(path, 'r') for path in dictionary_paths]
dictionaries = [yaml.load(dict_file) for dict_file in files]
map(lambda x: x.close(), files)
self.dictionary = {}
self.max_key_size = 0
for curr_dict in dictionaries:
for key in curr_dict:
if key in self.dictionary:
self.dictionary[key].extend(curr_dict[key])
else:
self.dictionary[key] = curr_dict[key]
self.max_key_size = max(self.max_key_size, len(key))
def tag(self, postagged_sentences):
return [self.tag_sentence(sentence) for sentence in postagged_sentences]
def tag_sentence(self, sentence, tag_with_lemmas=False):
tag_sentence = []
N = len(sentence)
if self.max_key_size == 0:
self.max_key_size = N
i = 0
while (i < N):
j = min(i + self.max_key_size, N) #avoid overflow
tagged = False
while (j > i):
expression_form = ' '.join([word[0] for word in sentence[i:j]]).lower()
expression_lemma = ' '.join([word[1] for word in sentence[i:j]]).lower()
if tag_with_lemmas:
literal = expression_lemma
else:
literal = expression_form
if literal in self.dictionary:
#self.logger.debug("found: %s" % literal)
is_single_token = j - i == 1
original_position = i
i = j
taggings = [tag for tag in self.dictionary[literal]]
tagged_expression = (expression_form, expression_lemma, taggings)
if is_single_token: #if the tagged literal is a single token, conserve its previous taggings:
original_token_tagging = sentence[original_position][2]
tagged_expression[2].extend(original_token_tagging)
tag_sentence.append(tagged_expression)
tagged = True
else:
j = j - 1
if not tagged:
tag_sentence.append(sentence[i])
i += 1
return tag_sentence
def value_of(sentiment):
global count_happy
global count_positive
global count_negative
count_positive = 0
count_negative = 0
count_happy = 0
if sentiment == 'happy' : return count_happy+1
if sentiment == 'positive' : return count_positive+1
if sentiment == 'negative' : return count_negative+1
return 0
def sentence_score(sentence_tokens, previous_token, acum_score):
if not sentence_tokens:
return acum_score
else:
current_token = sentence_tokens[0]
tags = current_token[2]
token_score = sum([value_of(tag) for tag in tags])
if previous_token is not None:
previous_tags = previous_token[2]
if 'inc' in previous_tags:
token_score *= 2.0
elif 'dec' in previous_tags:
token_score /= 2.0
elif 'inv' in previous_tags:
token_score *= -1.0
return sentence_score(sentence_tokens[1:], current_token, acum_score + token_score)
def sentiment_score(review):
return sum([sentence_score(sentence, None, 0.0) for sentence in review])
if __name__ == "__main__":
text = """This school is expensive. i am very excited. cool"""
splitter = Splitter()
postagger = POSTagger()
dicttagger = DictionaryTagger([ 'dicts/positive.yml', 'dicts/negative.yml',
'dicts/inc.yml', 'dicts/dec.yml', 'dicts/inv.yml', 'dicts/happy.yml'])
splitted_sentences = splitter.split(text)
pprint(splitted_sentences)
pos_tagged_sentences = postagger.pos_tag(splitted_sentences)
pprint(pos_tagged_sentences)
dict_tagged_sentences = dicttagger.tag(pos_tagged_sentences)
pprint(dict_tagged_sentences)
print("analyzing sentiment...")
score = sentiment_score(dict_tagged_sentences)
print(score)
print(count_negative)
print(count_positive)
print(count_happy)
if count_happy > count_positive and count_happy>count_negative: print('Happy')
if count_positive> count_negative and count_positive>count_happy: print("positive")
if count_negative > count_positive and count_negative > count_happy: print("negative")
else: print ("Neutral")