def predication(self):
# 遍历每一个课程，选择相似度最高的分类（前三个）
for course_name in self.course_name_list:
if not self.sentence_words_dict.__contains__(course_name):
continue
course_name_word_list = self.sentence_words_dict[course_name]
if len(course_name_word_list) == 0:
self.course_catalog_unknow_list.append(course_name)
continue
# 遍历分类
index = 0
res_list = []
for catalog_name in self.catalog_code_dict.keys():
catalog_tuple = self.catalog_code_dict.get(catalog_name)
catalog_code = catalog_tuple[0]
catalog_name_word_list = catalog_tuple[2]
score = self.pred_similarity(course_name_word_list,
catalog_name_word_list)
res = ResultInfo.ResultInfo(index, score, catalog_code,
catalog_name)
res_list.append(res)
index += 1
# 对列表按score降序排列
res_list.sort(cmp=None, key=lambda x: x.score, reverse=True)
# 选前3个最高的得分分类
best_candidate_list = res_list[:3]
if best_candidate_list[0].score > 0.45:
self.course_catalogs_good_dict[
course_name] = best_candidate_list
else:
self.course_catalogs_bad_dict[
course_name] = best_candidate_list
def getKnowledgeByName(self, name, k):
"""
通过知识名称，查找知识对象
:param name:
:return:
"""
flag = False
if name is None:
return flag
for k_key in self.knowledgeByName.keys():
k_tup = self.knowledgeByName.get(k_key)
k_words = k_tup[0]
if len(k_words) == 0:
continue
if name == k_key:
res = ResultInfo.ResultInfo(0, 1.0, k_tup[2], k_key)
k.append(res)
flag = True
break
return flag
def predication(self):
self.bad_examquestion_list = []
self.course_score = CourseInfomation.CourseScore()
self.course_score.initCourse(self.course_path_info_list[0].course)
# match(n)-[:NEXT]-(m) where n.name in ['典型','金本位制','指','金币','本位'] return n,m
if self.examquestion_info is None:
return
qindex = 0
question_knowledge_map = {}
for course_path_info in self.course_path_info_list:
if not self.examquestion_info.examquestion_dict.__contains__(
course_path_info.course):
return
exam_question_list = self.examquestion_info.examquestion_dict.get(
course_path_info.course)
for exam_question in exam_question_list:
#line = "物权的分类:从设立的角度对他物权再做分类，可把其分为（）。,用益物权和担保物权"
k = exam_question.knowledge_list
q = exam_question.getContentAndAnswer()
question_knowledge_map[q] = k
qindex = qindex + 1
q_words = self.sentence.splitSentenceCanRepeat(q)
# 从q中找重点词, 并放大重点词
q_words = self.preprocessor.enlargeVipWords(q_words, q)
if len(q_words) == 0:
continue
# 然后再遍历知识点
index = 0
res_list = []
for k_key in self.knowledge.keys():
k_tup = self.knowledge.get(k_key)
k_words = k_tup[0]
if len(k_words) == 0:
continue
score = self.doc_vec.pred_similarity(q_words, k_words)
res = ResultInfo.ResultInfo(index, score, k_tup[2], k_key)
res_list.append(res)
index += 1
# 对列表按score降序排列
res_list.sort(cmp=None, key=lambda x: x.score, reverse=True)
# 取分值最高的几个，超过1%，的舍去，或者再限定具体数量，比如3个
# 统计得分的情况
self.computeScore(res_list)
# 统计不超过50分的试题
if self.badExamquestionStatistics(res_list) == True:
self.bad_examquestion_list.append(
(exam_question, res_list[0:3]))
# 获取上级 知识点
#reslist = self.getParentKnowledge(reslist)
# 格式化输出
reslist, wordlist = self.formatOutput(res_list, k)
# 统计正确率
if len(reslist) > 0:
ns = '问题{0}:'.format(qindex) + q
self.outputcontentlist.append(ns + '\n')
ns = '电脑标识知识点:' + ';'.join(wordlist)
self.outputcontentlist.append(ns + '\n')
ns = '知识点评估指标:' + ';'.join(reslist)
self.outputcontentlist.append(ns + '\n')
#print '老师标识知识点:' + k
ns = '老师标识知识点:'
self.outputcontentlist.append(ns + '\n')
self.outputcontentlist.append('\n')
#ns = '电脑标识是否正确:'
#self.outputcontentlist.append(ns)
# 计算正确率
# 题目总数
self.course_score.compute()
ns = '试题总数：{}'.format(self.course_score.score_scope_total)
self.outputcontentlist.append(ns + '\n')
print ns
ns = '比较靠谱数(60分以上)：{} ，比较靠谱占比：{}%'.format(
self.course_score.score_scope_more60_count,
round(self.course_score.score_scope_more60_rate * 100, 2))
self.outputcontentlist.append(ns + '\n')
print ns
ns = '基本靠谱数(50-60分)：{} ，基本靠谱占比：{}%'.format(
self.course_score.score_scope_between5060_count,
round(self.course_score.score_scope_between5060_rate * 100, 2))
self.outputcontentlist.append(ns + '\n')
print ns
ns = '不太靠谱数(40-50分)：{} ，不太靠谱占比：{}%'.format(
self.course_score.score_scope_between4050_count,
round(self.course_score.score_scope_between4050_rate * 100, 2))
self.outputcontentlist.append(ns + '\n')
print ns
ns = '不靠谱数(40分以下)：{} ，不靠谱占比：{}%'.format(
self.course_score.score_scope_less40_count,
round(self.course_score.score_scope_less40_rate * 100, 2))
self.outputcontentlist.append(ns + '\n')
print ns
def predication(self):
# match(n)-[:NEXT]-(m) where n.name in ['典型','金本位制','指','金币','本位'] return n,m
if self.input_subject_file is None:
self.input_subject_file = self.doc_vec.train_input_subject_file
question = open(self.input_subject_file, 'r')
ids_lines = question.readlines()
qindex = 0
question_knowledge_map = {}
self.course_score = CourseInfomation.CourseScore()
for line in ids_lines:
#line = "物权的分类:从设立的角度对他物权再做分类，可把其分为（）。,用益物权和担保物权"
line = line.strip('\n')
index = line.index(':')
k = line[0:index]
q = line[index + 1:]
question_knowledge_map[q] = k
qindex = qindex + 1
q_words = self.sentence.splitSentenceCanRepeat(q)
# 从q中找重点词, 并放大重点词
q_words = self.preprocessor.enlargeVipWords(q_words, q)
if len(q_words) == 0:
continue
# 然后再遍历知识点
index = 0
res_list = []
for k_key in self.knowledge.keys():
k_tup = self.knowledge.get(k_key)
k_words = k_tup[0]
if len(k_words) == 0:
continue
score = self.doc_vec.pred_similarity(q_words, k_words)
res = ResultInfo.ResultInfo(index, score,
k_tup[2] + ' ' + k_key)
res_list.append(res)
index += 1
# 对列表按score降序排列
res_list.sort(cmp=None, key=lambda x: x.score, reverse=True)
# 取分值最高的几个，超过1%，的舍去，或者再限定具体数量，比如3个
# 统计得分的情况
self.computeScore(res_list)
# 获取上级 知识点
#reslist = self.getParentKnowledge(reslist)
# 格式化输出
reslist, wordlist = self.formatOutput(res_list)
# 统计正确率
if len(reslist) > 0:
ns = '问题{0}:'.format(qindex) + q
self.outputcontentlist.append(ns + '\n')
ns = '电脑标识知识点:' + ';'.join(wordlist)
self.outputcontentlist.append(ns + '\n')
ns = '知识点评估指标:' + ';'.join(reslist)
self.outputcontentlist.append(ns + '\n')
#print '老师标识知识点:' + k
ns = '老师标识知识点:' + k
self.outputcontentlist.append(ns + '\n')
self.outputcontentlist.append('\n')
#ns = '电脑标识是否正确:'
#self.outputcontentlist.append(ns)
# 计算正确率
# 题目总数
self.course_score.compute()
ns = '试题总数：{}'.format(self.course_score.score_scope_total)
self.outputcontentlist.append(ns + '\n')
print ns
ns = '比较靠谱数(60分以上)：{} ，比较靠谱占比：{}%'.format(
self.course_score.score_scope_more60_count,
round(self.course_score.score_scope_more60_rate * 100, 2))
self.outputcontentlist.append(ns + '\n')
print ns
ns = '基本靠谱数(50-60分)：{} ，基本靠谱占比：{}%'.format(
self.course_score.score_scope_between5060_count,
round(self.course_score.score_scope_between5060_rate * 100, 2))
self.outputcontentlist.append(ns + '\n')
print ns
ns = '不太靠谱数(40-50分)：{} ，不太靠谱占比：{}%'.format(
self.course_score.score_scope_between4050_count,
round(self.course_score.score_scope_between4050_rate * 100, 2))
self.outputcontentlist.append(ns + '\n')
print ns
ns = '不靠谱数(40分以下)：{} ，不靠谱占比：{}%'.format(
self.course_score.score_scope_less40_count,
round(self.course_score.score_scope_less40_rate * 100, 2))
self.outputcontentlist.append(ns + '\n')
print ns