def train(labeled_featuresets, label_freqdist, estimator=ELEProbDist):
...
# Create the P(label) distribution
label_probdist = estimator(label_freqdist)
...
# Create the P(fval|label, fname) distribution
feature_probdist = {}
...
return NaiveBayesClassifier(label_probdist, feature_probdist)
def train(self, train):
model = NaiveBayesClassifier(train)
ts = time.time()
st = datetime.datetime.fromtimestamp(ts).strftime('%Y-%m-%d_%H:%M:%S')
model_save = open('classifiers/models/naive_bayes' + st + '.pickle',
'wb')
pickle.dump(model, model_save)
model_save.close()
return st
print(nb_classifier.classify(posfeat))
print(accuracy(nb_classifier, test_feats))
probs = nb_classifier.prob_classify(test_feats[0][0])
print(probs.samples())
print(probs.max())
print(probs.prob('pos'))
print(probs.prob('neg'))
print(nb_classifier.most_informative_features(n=5))
print("############################################################################")
print(nb_classifier.show_most_informative_features(n=5))
print("############################################################################")
nb_classifier = NaiveBayesClassifier.train(train_feats, estimator=LaplaceProbDist)
print("Accuracy: " + str(accuracy(nb_classifier, test_feats)))
# Accuracy: 0.76
label_probdist = DictionaryProbDist({'pos': 0.5, 'neg': 0.5})
true_probdist = DictionaryProbDist({True: 1})
feature_probdist = {('pos', 'yes'): true_probdist, ('neg', 'no'): true_probdist}
classifier = NaiveBayesClassifier(label_probdist, feature_probdist)
print(classifier.classify({'yes': True}))
print(classifier.classify({'no': True}))
@author: noviayou
"""
from nltk.classify import NaiveBayesClassifier
def word_feats(words):
return dict([(word, True) for word in words])
positive_vocab = [
"awesome", "innovation", "outstanding", "fantastic", "terrific", "good",
"great"
]
negative_vocab = ["bad", "terrible", "useless", "hate"]
netural_vocab = ["Blockchain", "is", "was", "know", "technology"]
positive_features = [(word_feats(pos), "pos") for pos in positive_vocab]
negative_features = [(word_feats(neg), "neg") for neg in negative_vocab]
netural_features = [(word_feats(neu), "neu") for neu in netural_vocab]
train = positive_features + negative_features + netural_features
cl = NaiveBayesClassifier(train)
twi = r"/Users/noviayou/Downloads/twitter"
import json
day1 = r"/Users/noviayou/Downloads/twitter/00.json"
text = json.loads(day1)
print(text)
def _load_bayes_clf(data: dict, version: int) -> NaiveBayesClassifier:
return NaiveBayesClassifier(data['label_pdist'], data['feature_pdist'])
def __init__(self):
self.model = {} # {Sentence():'label'}
self.words = []
self.sentim = SentimentAnalyzer()
self.classify = NaiveBayesClassifier()
