#获取测试数据
##testtree = ElementTree.parse(r"D:\Program Files\Python\Sample.xml")
testtree = ElementTree.parse(r"D:\QAhomework\testset\testset.xml")
#buildroot用于以xml形式保存测试数据stage2格式的生成文档
buildroot = ElementTree.Element("buildroot")
i=0
print i
clf = QClassifierImpl(train_data_path = '../data/pair.xml')
clf.train()
print i
fo = open("testwrite.txt", "a+")
for question in testtree.iter('question'):
testtags = jieba.analyse.extract_tags(question.getchildren ()[0].text, topK=5)
testkeys=" ".join(testtags)
## print testkeys
## testtype= classifier.classify(gender_features(testkeys))
## print testtype
#在buildroot建立子节点testquestion
testquestion = ElementTree.SubElement(buildroot, "testquestion")
#设置testquestion的各个属性
# -*- coding: utf-8 -*-
import sys, re, nltk
from QClassifier import QClassifierImpl
import jieba.analyse
from xml.etree import ElementTree
import xml.dom.minidom
reload(sys)
sys.setdefaultencoding('utf8')
testtree = ElementTree.parse("../data/testset.xml")
root = testtree.getroot()
buildroot = ElementTree.Element("QuestionSet")
clf = QClassifierImpl(train_data_path='../data/pair.xml')
# clf = QClassifierImpl(train_data_path = 'train.xml')
clf.train()
for question in root.getchildren():
q_text = question.getchildren()[0].text
testtags = jieba.analyse.extract_tags(q_text, topK=5)
testkeys = ' '.join(testtags)
testquestion = ElementTree.SubElement(buildroot, 'question')
testquestion.set('id', question.get('id'))
# question text
q = ElementTree.SubElement(testquestion, 'q')
q.text = q_text
# question category
# -*- coding: utf-8 -*-
import sys, re, nltk
from QClassifier import QClassifierImpl
import jieba.analyse
from xml.etree import ElementTree
import xml.dom.minidom
reload(sys)
sys.setdefaultencoding('utf8')
testtree = ElementTree.parse("../data/testset.xml")
root = testtree.getroot()
buildroot = ElementTree.Element("QuestionSet")
clf = QClassifierImpl(train_data_path = '../data/pair.xml')
# clf = QClassifierImpl(train_data_path = 'train.xml')
clf.train()
for question in root.getchildren():
q_text = question.getchildren()[0].text
testtags = jieba.analyse.extract_tags(q_text, topK=5)
testkeys = ' '.join(testtags)
testquestion = ElementTree.SubElement(buildroot, 'question')
testquestion.set('id', question.get('id'))
# question text
q = ElementTree.SubElement(testquestion, 'q')
q.text = q_text
# question category
# -*- coding: utf-8 -*- from QClassifier import QClassifierImpl # clf = QClassifierImpl(train_data_path = 'train.xml') clf = QClassifierImpl(train_data_path='../data/pair.xml') clf.train() print clf.get_type(u'西班牙的首都是哪座城市？') print clf.get_type(u'飞轮海中的吴尊现在多大了？') print clf.get_type(u'小美指的是哪位明星？') print clf.get_type(u'冯小刚的现任妻子是谁？') print clf.get_type(u'哪场战役代表美国正式卷入第二次世界大战?') print clf.get_type(u'《三国演义》中“官渡之战”中交战双方的指挥官分别是?') print clf.get_type(u'唱感动天感动地的人是那个歌手?')
stdi, stdo, stde = sys.stdin, sys.stdout, sys.stderr
reload(sys)
sys.setdefaultencoding('utf8')
sys.stdin, sys.stdout, sys.stderr = stdi, stdo, stde
print sys.getdefaultencoding()
#获取测试数据
##testtree = ElementTree.parse(r"D:\Program Files\Python\Sample.xml")
testtree = ElementTree.parse(r"D:\QAhomework\testset\testset.xml")
#buildroot用于以xml形式保存测试数据stage2格式的生成文档
buildroot = ElementTree.Element("buildroot")
i = 0
print i
clf = QClassifierImpl(train_data_path='../data/pair.xml')
clf.train()
print i
fo = open("testwrite.txt", "a+")
for question in testtree.iter('question'):
testtags = jieba.analyse.extract_tags(question.getchildren()[0].text,
topK=5)
testkeys = " ".join(testtags)
## print testkeys
## testtype= classifier.classify(gender_features(testkeys))
## print testtype
#在buildroot建立子节点testquestion
testquestion = ElementTree.SubElement(buildroot, "testquestion")
#设置testquestion的各个属性
# -*- coding: utf-8 -*- from QClassifier import QClassifierImpl # clf = QClassifierImpl(train_data_path = 'train.xml') clf = QClassifierImpl(train_data_path = '../data/pair.xml') clf.train() print clf.get_type(u'西班牙的首都是哪座城市？') print clf.get_type(u'飞轮海中的吴尊现在多大了？') print clf.get_type(u'小美指的是哪位明星？') print clf.get_type(u'冯小刚的现任妻子是谁？') print clf.get_type(u'哪场战役代表美国正式卷入第二次世界大战?') print clf.get_type(u'《三国演义》中“官渡之战”中交战双方的指挥官分别是?') print clf.get_type(u'唱感动天感动地的人是那个歌手?')
