Python tgrocery.Grocery类代码示例

def train():
    print 'train start '+'.'*30
    #grocery=Grocery('sample')
    grocery=Grocery('version1.0')
    grocery.train(trainlist)
    grocery.save()
    print 'train end '+'.'*30

	def __init__(self, keyword):
		print '进行新闻分类'
		(db, cursor) = connectdb()
		cursor.execute("update task set status=1 where keyword=%s", [keyword])
		cursor.execute("select id, title from news where keyword=%s",[keyword])
		news = cursor.fetchall()
		new_grocery = Grocery('static/paris')
		new_grocery.load()

		for item in news:
			tag = new_grocery.predict(item['title'])
			if tag == '新闻背景':
				tag = 1
			elif tag == '事实陈述':
				tag = 2
			elif tag == '事件演化':
				tag = 3 
			elif tag == '各方态度':
				tag = 4
			elif tag == '直接关联':
				tag = 6
			elif tag == '暂无关联':
				tag = 7
			cursor.execute("update news set tag=%s where id=%s", [tag, item['id']])
		closedb(db, cursor)
		return

	def GET(self,name):
		#i = web.input(name=None)	
		#url = "http://"+name
		#html = urllib2.urlopen(url).read()
		#soup = BeautifulSoup(html)
		#title =  soup.html.head.title.contents.pop().encode('utf-8')
		title = name.encode('utf-8')
		new_grocery = Grocery('sample')
		new_grocery.load()
		return new_grocery.predict(title)

 def __train__model__():
     dataframe = pd.read_excel(Classify.__FILE_PATH__)
     data = dataframe[[u'类型',	u'释义']]
     train_data = [(x[0],x[1]) for x in data.values]
     
     grocery = Grocery('Classify')
     
     grocery.train(train_data)
     grocery.save()
     Classify.__MODEL__ = grocery

def tGrocery():
    outFile = open('testResult.tmp', 'w')
    [trainingSet, benchmark] = pickle.load(open('SampleSeg.pk'))
    testingSet = []
    correctLabel = []
    for i in xrange(len(benchmark)):
        print '%d out of %d' % (i, len(benchmark))
        testingSet.append(benchmark[i][1])
        correctLabel.append(benchmark[i][0]) 
    grocery = Grocery('test')
    grocery.train(trainingSet)
    grocery.save()
    # load
    new_grocery = Grocery('test')
    new_grocery.load()
    Prediction = []
    for i in xrange(len(testingSet)):
        print '%d out of %d' % (i, len(testingSet))
        prediction = new_grocery.predict(testingSet[i])
        Prediction.append(prediction)
        temp = correctLabel[i] + '<-->' + prediction + '  /x01' + testingSet[i] + '\n'
        outFile.write(temp)
    correct = 0
    for i in xrange(len(Prediction)):
        print Prediction[i], correctLabel[i],
        if Prediction[i] == correctLabel[i]:
            correct += 1
            print 'Correct'
        else:
            print 'False'
    print 'Correct Count:', correct
    print 'Accuracy: %f' % (1.0 * correct / len(Prediction))

class GroceryModel(object):
    def __init__(self):
        self.grocery = Grocery('TextClassify')
    
    def train(self,train_file):
        f = open(train_file,'r')
        line = f.readline().decode('utf8')
        dataset = []
        while line:
            tmp = line.split('\t')
            dataset.append((tmp[0],''.join(tmp[1:])))
            line = f.readline().decode('utf8')
        f.close()
        self.grocery.train(dataset)
        self.grocery.save()
    
    def load_model(self):
        self.grocery.load()
    
    def test(self,test_src):
        self.load_model()
        f = open(test_src,'r')
        line = f.readline().decode('utf8')
        dataset = []
        while line:
            tmp = line.split('\t')
            dataset.append((tmp[0],''.join(tmp[1:])))
            line = f.readline().decode('utf8')
        f.close()
        result = self.grocery.test(dataset)
        print result
    
    def predict(self,text):
        print self.grocery.predict(text)

 def test_main(self):
     grocery = Grocery(self.grocery_name)
     grocery.train(self.train_src)
     grocery.save()
     new_grocery = Grocery('test')
     new_grocery.load()
     assert grocery.get_load_status()
     assert grocery.predict('考生必读：新托福写作考试评分标准') == 'education'
     # cleanup
     if self.grocery_name and os.path.exists(self.grocery_name):
         shutil.rmtree(self.grocery_name)

def test_grocery():
    grocery = Grocery('model_redian')
    grocery.train('trdata_4.txt')
    grocery.save()
    new_grocery = Grocery('model_redian')
    new_grocery.load()
    test_result = new_grocery.test('tedata_4.txt')
    print test_result.accuracy_labels
    print test_result.recall_labels
    test_result.show_result()

def predict_corpus(input_file,output_csv):
    import csv
    csvfile = file(output_csv, 'wb')
    writer = csv.writer(csvfile)
    corpus = []
    f = xlrd.open_workbook(input_file)
    table = f.sheet_by_name('Sheet1')
    nrows = table.nrows  # 读取行数
    for rownum in range(0, nrows):
        row = table.row_values(rownum)
        row[2].strip()
        corpus.append(row[2])
    corpus_grocery = Grocery(project_name)
    corpus_grocery.load()
    output = []
    for sentence in corpus:
        predict = corpus_grocery.predict(sentence)
        output.append((sentence,predict))
    writer.writerows(output)
    print('Done!')
    csvfile.close()

class jdParser(object):

    def __init__(self):
        self.clf = Grocery("./jdclf")
        self.clf.load()
        self.LINE_SPLIT = re.compile(u"[；。;\n]")



    def get_demand_and_duty(self,jdstr):
        linelist = [ line.strip() for line in self.LINE_SPLIT.split(jdstr) if len(line.strip()>4) ]

        result = {}
        demand = []
        duty = []
        for line in linelist:
            pred = str(self.clf.predict(line))
            if pred =="demand":
                demand.append(line)
            elif pred == "duty":
                duty.append(line)

        result['demand'] = '\n'.join(demand)
        result['duty'] = '\n'.join(duty)

def sentiment_train(gro_name, train_set):
    """

    :param gro_name:
    :param train_set:
    :return:
    """
    gro_ins = Grocery(gro_name)
    # gro_ins.load()
    gro_ins.train(train_set)
    print("Is trained? ", gro_ins.get_load_status())
    gro_ins.save()

class MyGrocery(object):
  def __init__(self, name):
    super(MyGrocery, self).__init__()
    self.grocery = Grocery(name)
    self.loaded = False
    self.correct = 1.0

  def train(self, src):
    lines = []
    for line in csv.reader(open(src)):
      label, s = line[0],line[1]
      text = s.decode('utf8')
      lines.append((label, text))
    self.grocery.train(lines)

  def save_model(self):
    self.grocery.save()

  def train_and_save(self, src):
    self.train(src)
    self.save_model()

  def load_model(self):
    if not self.loaded:
      self.grocery.load()
      self.loaded = True

  def predict(self, text):
    self.load_model()
    return self.grocery.predict(text)

  def test(self, src):
    self.load_model()
    total, wrong_num = 0.0, 0.0
    for line in csv.reader(open(src)):
      total += 1
      if line[0] != self.predict(line[1]):
        wrong_num += 1

    print "load test file from " + src
    correct = (total - wrong_num ) / total
    self.correct = correct
    print "total: %d , wrong_num: %d, success percentage: %f" %(total, wrong_num, correct)
    result = dict(type="test", total=total, wrong_num=wrong_num, correct=correct)
    return json.dumps(result)

    def __init__(self):
        self.CLEAN_TEXT = re.compile(u"[^\u4e00-\u9fa5\w\d；:：;,。、\.，。！[email protected]（）\r\n\(\)\-\+ －　]")
        
        self.clf = Grocery(base_dir+"/jdclf")
        self.clf.load()
        
        self.SPLIT_LINE = re.compile(u"[\r\n；:：。！？;]|[　\s \xa0\u724b]{4,}")
        self.CLEAN_LINE = re.compile(u"^[\u2022（【\[\s\t\r\n\(\- 　]?[\da-z１２３４５７８９]{1,2}[\.,。、，：:）】\]\)\s]|^[！＠＃￥％……＆×（）\(\)｛｝：“｜、－\-，。：:\.]|^[一二三四五六七八九１２３４５６７８９\d]{0,2}[\.、\s:：　]|[，；。、\s　\.]$|^[\s　\u2022 \uff0d \u25cf]")
        self.CLEAN_JOBNAME = re.compile(u"急聘|诚聘|高薪|包[食住宿餐]|.险一金|待遇|^急?招|职位编号\s?[\s\d:：]")

        self.PAY = re.compile("(\d{3,}\-)?\d{3,}元")
        self.SEX = re.compile(u"性别|男|女")
        self.AGE = re.compile(u"\d+周?岁|年龄")
        self.JOB_TAG = re.compile(u"全职|实习")
        self.DEGREE = re.compile(u"小学|初中|高中|职技|本科|研究生|硕士|博士|教授|专科|大专|中专|无要求|不限|无限")

        self.START_DEMAND = re.compile(u"(任职资格|岗位要求|工作要求|任职条件|任职要求|职位要求)[：:\s】\n　]?")
        self.START_DUTY = re.compile(u"(工作内容|岗位职责|工作职责|职位描述|工作描述|职位介绍|职位职责|岗位描述)[:：\s 】\n　]")
        self.START_BENEFIT = re.compile(u"(福利待遇|待遇|福利)[:：\s\n】]")
        
        self.INC_URL = re.compile(u"(主页|网站|网址|官网).{0,3}[\w\d_/\.:\-]+")
        self.DEMAND = re.compile(u"精通|熟悉|熟练|有.+经验")
        self.DUTY = re.compile(u"负责|促成|为客户|安排的其.工作")
        self.BENEFIT = re.compile(u".险一金|福利|晋身|休假|带薪|补助|补贴")
        self.CERT = re.compile(u"(\S{2,8}证书|CET-\d|普通话|英语|口语|.语|日文|雅思|托福|托业)(至少)?(通过)?[\d一二三四五六七八九]级[及或]?(以上)?|(英语)?CET-\d级?(以上)?|\
                                 医学.{0,3}证|会计.{0,3}证|律师.{0,3}证|有.{1,8}证书")


        self.degreedic = set([line.strip() for line in codecs.open(base_dir+'/data/degrees.txt','rb','utf-8')])
        self.majordic = set([line.strip() for line in codecs.open(base_dir+'/data/majordic.txt','rb','utf-8')])
        self.skilldic = set([line.strip() for line in codecs.open(base_dir+'/data/skills.txt','rb','utf-8')])
        self.jobdic = set([line.strip() for line in codecs.open(base_dir+'/data/jobnames.txt','rb','utf-8')])

        jieba.load_userdict(base_dir+'/data/majordic.txt')
        jieba.load_userdict(base_dir+'/data/skills.txt')
        jieba.load_userdict(base_dir+'/data/firm.txt')
        jieba.load_userdict(base_dir+'/data/degrees.txt')
        jieba.load_userdict(base_dir+'/data/benefits.txt')

    def __init__(self):
        self.data = []
        self.clf = Grocery("jdclf")
        self.clf.load()
        
        self.SEX = re.compile(u"性别不限|性别|男|女")
        self.AGE = re.compile(u"\d+周?岁|年龄")
        self.DEGREE = re.compile(u"(全日制)?(初中|高中|中专|大专|专科|大学专科|中职|本科|大学本科|硕士|研究生|博士|博士后)(.?以上)?")
        self.MAJOR = re.compile(u"\S+(相关专业|专业优先|及其.专业|[类等]专业[优先]?)")
        self.EXP = re.compile(u"工作经验：|工作经[历验]|工作年限|年.{0,4}经[历验]|经[历验].{1,6}年")
        self.PUB_TIME = re.compile(u"(\d+)(天前发布)")
        
        self.INCNAME = re.compile(u"\S+(有限公司|酒店|银行|集团|研究中心|研究所|学校|旅行社|分?公司|研发中心|技术部|事.部|招聘)") 
        self.NOT_INC = re.compile(u"职位|描述|收藏|推荐|地址|邮箱|主页|介绍|欢迎|加入|要求|简介|险一金|奖金|包吃住|社区|厂房|人员|职责") 
        self.INCTAG = re.compile(u"大公司|五百强|全球500强|小公司|成长型公司|创业公司|私有经济|集体经济|集团|外企|已上市|稳定性高|平均年龄\d岁|妹纸多|学历高|福利待遇好|晋升机会大|民营公司|民营企业\
                                 |互联网|创业型|国企|央企")

        self.JOBNAME = re.compile(u'\S*(研发工程师|工程师|经理|助理|顾问|前台|秘书|主管|研究员|实习生|操作员|专员|教学人员|技术人员|管理员|业务员|公关|程序员|教师|老师|培训生|\
                                  文员|研究员|策划|主任|总监|设计师|分析师|架构师|摄影师|编辑|BD|游戏UI|Android(开发)?|PHP(开发)?|Python(开发)?|.?(急招|急聘|初级|中级|高级|方向).?[\s）】\)])|\
                                  |行政人事|网店设计|客服|会计|电话销售|外贸跟单|web前端|游戏UI|后.开发|产品运营|商业数据分析')

        self.START_DEMAND = re.compile(u"(岗位要求|应聘条件|任职要求|岗位资格|任职资格|岗位条件|工作要求|任职条件|人员条件|职位.求|职位条件|职位描述|岗位资格|职位资格|具备条件)[:：\s]\
                                       |如果你.{0,10}[:：\s]|我们希望你.{0,12}[:：\s]|(要求|条件)[:：\s]|你需要?具备什么.+[？\?:：\s]|任职资格[:：\s]")

        self.DEMAND = re.compile(u"熟悉|熟练|具有|善于|懂得|掌握|具备|能够|优先|不少于|不超过|至少|团队.作|良好的|工作经验|开发经验|实习经历|能力强|富有|以上学历|经验|喜欢|\
                                 较强的.{2,8}能力|相关专业|相关学历|者优先|精通|了解|及以上|技术全面|.强的责任心|[能有]独立|英文流利")

        self.DUTY = re.compile(u"跟进|协助|负责|配合|其他工作|领导交办的|对.+提供|审核|参与|提出|跟踪|报告|为.+提出|日常.+工作|指导|跟进|拓展|运营|用户|客户|协调|拟写|通过|协同\
                               |完成|沟通|需求|秘书.{2,5}翻译")

        self.START_DUTY = re.compile(u"(岗位职责|岗位描述|职位描述|职责描述|任职描述|职位职责|工作职责|工作职能|职位职能|工作内容|实习内容|职位内容)[:：\s]|做这样的事[:：\s]|职责.{0,5}[:：\s]")

        self.PAY = re.compile(u"薪酬|待遇|月薪|薪资|年薪|底薪|\d+k|\d+万|\d+元|工资|报酬|薪水|福利")

        self.BENEFIT = re.compile(u"周休|补助|补贴|假日|餐补|提成|交通补助|食宿|加班工资|期权|年假|领导|扁平化|管理|氛围|空间|休假|月假|带薪|全休|晋升|培训|舒适的|旅游|奖励|过节费|五险一金|奖金|\
                                  |弹性工作|氛围|成长空间|实训|培训|高薪|前景|旅游|活动|分红")

# -*- coding: utf-8 -*-
import sys
reload(sys)
sys.path.append('../../')
from config import *

from tgrocery import Grocery
STOP_WORDS_FILE = 'stopwords.txt'
USER_DICT_FILE = 'user_dict.txt'

model_fintext = Grocery('model_fintext')
model_fintext.load()
sys.path.append('../')
from get_es import *
es = Elasticsearch([{'host':ES_HOST,'port':ES_PORT}])

def search(index_name):
    es_search_options = set_search_optional()
    es_result = get_search_result(es_search_options,index=index_name)
    # final_result = get_result_list(es_result)
    # return final_result
    return es_result


def get_result_list(es_result):
    final_result = []
    for item in es_result:
        final_result.append(item['_source'])
    return final_result