本文整理汇总了Python中nltk.sentiment方法的典型用法代码示例。如果您正苦于以下问题:Python nltk.sentiment方法的具体用法?Python nltk.sentiment怎么用?Python nltk.sentiment使用的例子?那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类nltk
的用法示例。
在下文中一共展示了nltk.sentiment方法的5个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: demo_sent_subjectivity
# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import sentiment [as 别名]
def demo_sent_subjectivity(text):
"""
Classify a single sentence as subjective or objective using a stored
SentimentAnalyzer.
:param text: a sentence whose subjectivity has to be classified.
"""
from nltk.classify import NaiveBayesClassifier
from nltk.tokenize import regexp
word_tokenizer = regexp.WhitespaceTokenizer()
try:
sentim_analyzer = load('sa_subjectivity.pickle')
except LookupError:
print('Cannot find the sentiment analyzer you want to load.')
print('Training a new one using NaiveBayesClassifier.')
sentim_analyzer = demo_subjectivity(NaiveBayesClassifier.train, True)
# Tokenize and convert to lower case
tokenized_text = [word.lower() for word in word_tokenizer.tokenize(text)]
print(sentim_analyzer.classify(tokenized_text))
示例2: demo_liu_hu_lexicon
# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import sentiment [as 别名]
def demo_liu_hu_lexicon(sentence, plot=False):
"""
Basic example of sentiment classification using Liu and Hu opinion lexicon.
This function simply counts the number of positive, negative and neutral words
in the sentence and classifies it depending on which polarity is more represented.
Words that do not appear in the lexicon are considered as neutral.
:param sentence: a sentence whose polarity has to be classified.
:param plot: if True, plot a visual representation of the sentence polarity.
"""
from nltk.corpus import opinion_lexicon
from nltk.tokenize import treebank
tokenizer = treebank.TreebankWordTokenizer()
pos_words = 0
neg_words = 0
tokenized_sent = [word.lower() for word in tokenizer.tokenize(sentence)]
x = list(range(len(tokenized_sent))) # x axis for the plot
y = []
for word in tokenized_sent:
if word in opinion_lexicon.positive():
pos_words += 1
y.append(1) # positive
elif word in opinion_lexicon.negative():
neg_words += 1
y.append(-1) # negative
else:
y.append(0) # neutral
if pos_words > neg_words:
print('Positive')
elif pos_words < neg_words:
print('Negative')
elif pos_words == neg_words:
print('Neutral')
if plot == True:
_show_plot(x, y, x_labels=tokenized_sent, y_labels=['Negative', 'Neutral', 'Positive'])
示例3: demo_vader_instance
# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import sentiment [as 别名]
def demo_vader_instance(text):
"""
Output polarity scores for a text using Vader approach.
:param text: a text whose polarity has to be evaluated.
"""
from nltk.sentiment import SentimentIntensityAnalyzer
vader_analyzer = SentimentIntensityAnalyzer()
print(vader_analyzer.polarity_scores(text))
示例4: demo_movie_reviews
# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import sentiment [as 别名]
def demo_movie_reviews(trainer, n_instances=None, output=None):
"""
Train classifier on all instances of the Movie Reviews dataset.
The corpus has been preprocessed using the default sentence tokenizer and
WordPunctTokenizer.
Features are composed of:
- most frequent unigrams
:param trainer: `train` method of a classifier.
:param n_instances: the number of total reviews that have to be used for
training and testing. Reviews will be equally split between positive and
negative.
:param output: the output file where results have to be reported.
"""
from nltk.corpus import movie_reviews
from nltk.sentiment import SentimentAnalyzer
if n_instances is not None:
n_instances = int(n_instances/2)
pos_docs = [(list(movie_reviews.words(pos_id)), 'pos') for pos_id in movie_reviews.fileids('pos')[:n_instances]]
neg_docs = [(list(movie_reviews.words(neg_id)), 'neg') for neg_id in movie_reviews.fileids('neg')[:n_instances]]
# We separately split positive and negative instances to keep a balanced
# uniform class distribution in both train and test sets.
train_pos_docs, test_pos_docs = split_train_test(pos_docs)
train_neg_docs, test_neg_docs = split_train_test(neg_docs)
training_docs = train_pos_docs+train_neg_docs
testing_docs = test_pos_docs+test_neg_docs
sentim_analyzer = SentimentAnalyzer()
all_words = sentim_analyzer.all_words(training_docs)
# Add simple unigram word features
unigram_feats = sentim_analyzer.unigram_word_feats(all_words, min_freq=4)
sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats)
# Apply features to obtain a feature-value representation of our datasets
training_set = sentim_analyzer.apply_features(training_docs)
test_set = sentim_analyzer.apply_features(testing_docs)
classifier = sentim_analyzer.train(trainer, training_set)
try:
classifier.show_most_informative_features()
except AttributeError:
print('Your classifier does not provide a show_most_informative_features() method.')
results = sentim_analyzer.evaluate(test_set)
if output:
extr = [f.__name__ for f in sentim_analyzer.feat_extractors]
output_markdown(output, Dataset='Movie_reviews', Classifier=type(classifier).__name__,
Tokenizer='WordPunctTokenizer', Feats=extr, Results=results,
Instances=n_instances)
示例5: demo_subjectivity
# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import sentiment [as 别名]
def demo_subjectivity(trainer, save_analyzer=False, n_instances=None, output=None):
"""
Train and test a classifier on instances of the Subjective Dataset by Pang and
Lee. The dataset is made of 5000 subjective and 5000 objective sentences.
All tokens (words and punctuation marks) are separated by a whitespace, so
we use the basic WhitespaceTokenizer to parse the data.
:param trainer: `train` method of a classifier.
:param save_analyzer: if `True`, store the SentimentAnalyzer in a pickle file.
:param n_instances: the number of total sentences that have to be used for
training and testing. Sentences will be equally split between positive
and negative.
:param output: the output file where results have to be reported.
"""
from nltk.sentiment import SentimentAnalyzer
from nltk.corpus import subjectivity
if n_instances is not None:
n_instances = int(n_instances/2)
subj_docs = [(sent, 'subj') for sent in subjectivity.sents(categories='subj')[:n_instances]]
obj_docs = [(sent, 'obj') for sent in subjectivity.sents(categories='obj')[:n_instances]]
# We separately split subjective and objective instances to keep a balanced
# uniform class distribution in both train and test sets.
train_subj_docs, test_subj_docs = split_train_test(subj_docs)
train_obj_docs, test_obj_docs = split_train_test(obj_docs)
training_docs = train_subj_docs+train_obj_docs
testing_docs = test_subj_docs+test_obj_docs
sentim_analyzer = SentimentAnalyzer()
all_words_neg = sentim_analyzer.all_words([mark_negation(doc) for doc in training_docs])
# Add simple unigram word features handling negation
unigram_feats = sentim_analyzer.unigram_word_feats(all_words_neg, min_freq=4)
sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats)
# Apply features to obtain a feature-value representation of our datasets
training_set = sentim_analyzer.apply_features(training_docs)
test_set = sentim_analyzer.apply_features(testing_docs)
classifier = sentim_analyzer.train(trainer, training_set)
try:
classifier.show_most_informative_features()
except AttributeError:
print('Your classifier does not provide a show_most_informative_features() method.')
results = sentim_analyzer.evaluate(test_set)
if save_analyzer == True:
save_file(sentim_analyzer, 'sa_subjectivity.pickle')
if output:
extr = [f.__name__ for f in sentim_analyzer.feat_extractors]
output_markdown(output, Dataset='subjectivity', Classifier=type(classifier).__name__,
Tokenizer='WhitespaceTokenizer', Feats=extr,
Instances=n_instances, Results=results)
return sentim_analyzer