本文整理汇总了Python中classifier.Classifier.save_classifier方法的典型用法代码示例。如果您正苦于以下问题：Python Classifier.save_classifier方法的具体用法？Python Classifier.save_classifier怎么用？Python Classifier.save_classifier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classifier.Classifier的用法示例。
在下文中一共展示了Classifier.save_classifier方法的1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: __init__
# 需要导入模块: from classifier import Classifier [as 别名]
# 或者: from classifier.Classifier import save_classifier [as 别名]
class SentimentAnalyzer:
def __init__(self):
self.parser_options = tweetparser.options
self.classifier = Classifier()
if os.path.exists(CLASSIFIER_FILE):
self.classifier.load_classifier(CLASSIFIER_FILE)
else:
self.retrain_classifier()
def rebuild_features(self):
print 'Parsing tweets...'
tweetparser.parse_all_files(self.parser_options)
print 'Building features...'
# build features for training data
training_labels = read_labels(TRAINING)
training_tweets = pickle.load(open(TRAINING_TWEETS, 'rb'))
unigram_features = buildfeatures.build_unigram_feature_dict(training_tweets, training_labels)
training_data = buildfeatures.get_feature_vectors(training_tweets, unigram_features)
# save training data
np.savetxt(TRAINING_DATA_FILE, training_data, delimiter=',')
# build features for testing data
testing_tweets = pickle.load(open(TESTING_TWEETS, 'rb'))
testing_data = buildfeatures.get_feature_vectors(testing_tweets, unigram_features)
np.savetxt(TESTING_DATA_FILE, testing_data, delimiter=',')
# build features for development data
development_tweets = pickle.load(open(DEVELOPMENT_TWEETS, 'rb'))
development_data = buildfeatures.get_feature_vectors(development_tweets, unigram_features)
np.savetxt(DEVELOPMENT_DATA_FILE, development_data, delimiter=',')
# save unigram features processed
pickle.dump(unigram_features, open(UNIGRAM_FEATURES_FILE, 'wb'), -1)
def retrain_classifier(self):
if not os.path.exists(TRAINING_DATA_FILE):
self.rebuild_features()
training_data = np.loadtxt(TRAINING_DATA_FILE, delimiter=',')
training_labels = read_labels(TRAINING)
print 'Training classifier...'
self.classifier = Classifier()
self.classifier.train(training_data, training_labels)
self.classifier.save_classifier(CLASSIFIER_FILE)
def classify_test_tweets(self):
testing_tweets = pickle.load(open(TESTING_TWEETS, 'rb'))
testing_data = np.loadtxt(TESTING_DATA_FILE, delimiter=',')
testing_labels = read_labels(TESTING)
testing_topics = read_topics(TESTING)
print 'Predicting labels...'
print 'Testing Results: ' + str(self.classifier.predict_testing_data(testing_tweets, testing_data, testing_topics, testing_labels, RESULTS_FILE))
def classify_development_tweets(self):
development_tweets = pickle.load(open(DEVELOPMENT_TWEETS, 'rb'))
development_data = np.loadtxt(DEVELOPMENT_DATA_FILE, delimiter=',')
development_labels = read_labels(DEVELOPMENT)
development_topics = read_topics(DEVELOPMENT)
print 'Predicting labels...'
print 'Development Results: ' + str(self.classifier.predict_testing_data(development_tweets, development_data, development_topics, development_labels, RESULTS_FILE))
def classify_custom_tweets(self, custom_filename):
if not os.path.exists(custom_filename):
print 'The file ' + custom_filename + ' does not exist.'
return
try:
print 'Parsing tweets...'
custom_tweets = []
def collect(tweet):
custom_tweets.append(tweet)
tweetparser._parse_tweets(custom_filename, collect)
labels = read_labels(custom_filename)
topics = read_topics(custom_filename)
print 'Building features...'
unigram_features = pickle.load(open(UNIGRAM_FEATURES_FILE, 'rb'))
data = buildfeatures.get_feature_vectors(custom_tweets, unigram_features)
print 'Predicting labels...'
labels = read_labels(custom_filename)
topics = read_topics(custom_filename)
print 'Results: ' + str(self.classifier.predict_testing_data(custom_tweets, data, topics, labels, RESULTS_FILE))
print 'See labels at: ' + RESULTS_FILE
except:
print 'Something went wrong. File may be in wrong format.'
def cross_validation(self):
training_data = np.loadtxt(TRAINING_DATA_FILE, delimiter=',')
training_labels = read_labels(TRAINING)
raw_classifier = self.classifier.get_classifier()
kf_total = cross_validation.KFold(len(training_labels), n_folds=10, shuffle=True, random_state=4)
#.........这里部分代码省略.........