def modelOutput(trainFile, testFile, modelType):
"""
output is:
(naive bayes) variable name | 'class'
(tan) variable name | name of its parents
# empty
followed by:
predict class | actual class | posterior probability (12 digits after decimal point)
# empty
followed by:
The number of the test-set examples that were correctly classified.
"""
attributes, labels, instances = data_provider(trainFile)
if modelType == 'n':
model = Bayes(attributes, labels, instances)
elif modelType == 't':
model = TAN(attributes, labels, instances)
else:
import sys
print >> sys.stderr, 'model type should be [n] or [t] !!!'
sys.exit()
attributes, labels, instances = data_provider(testFile)
# format output part1: attribute name | 'class'
model.printTree()
print
correctClassCnt = 0
for test in instances:
result = model.classify(test)
if result[0] == result[1]:
correctClassCnt += 1
# format output part2: predict class | actual class | posterior probability
print formatOutput(result)
print
# format output part3: correctly classified number of test instances
print correctClassCnt
class Sentiment:
def __init__(self):
self.classifier = Bayes()
self.seg = Seg()
self.seg.load('seg.pickle')
def save(self, fname):
self.classifier.save(fname)
def load(self, fname):
self.classifier = self.classifier.load(fname)
def handle(self, doc):
words = self.seg.seg(doc)
words = self.filter_stop(words)
return words
def train(self, neg_docs, pos_docs):
datas = []
for doc in neg_docs:
datas.append([self.handle(doc), 'neg'])
for doc in pos_docs:
datas.append([self.handle(doc), 'pos'])
self.classifier.train(datas)
def classify(self, doc):
ret, prob = self.classifier.classify(self.handle(doc))
if ret == 'pos':
return prob
else:
return 1 - prob
@staticmethod
def filter_stop(words):
return list(filter(lambda x: x not in stop_words, words))
from bayes import Bayes
# First you need to create an instance of this
# algorithm and defined what field/column
# you want to classify
instance = Bayes("Sex")
# Secondly, you will need to learn about a set
# of data to train the algorithm
instance.learn("static/data_test.csv")
# Finally you can use your trained instance to
# classify a set of data (In this example we
# will find the most probable sex)
print(instance.classify([6, 130, 8]))