def statistics(self):
"""
对course_score_list中的结果，进行统计
:return:
"""
# 课程的数量分布统计变量
n_coure_count_more50 = 0
n_coure_score_less50 = 0
# 统计所有课程，百分比的分布情况
n_coure_score = CourseInfomation.CourseScore()
for course_score in self.course_score_list:
n_coure_score.score_scope_more60_count += course_score.score_scope_more60_count
n_coure_score.score_scope_between5060_count += course_score.score_scope_between5060_count
n_coure_score.score_scope_between4050_count += course_score.score_scope_between4050_count
n_coure_score.score_scope_less40_count += course_score.score_scope_less40_count
# 如果50分以上的超过50%，则more50+1
if (n_coure_score.score_scope_between5060_count +
n_coure_score.score_scope_more60_count):
n_coure_count_more50 += 1
else:
n_coure_score_less50 += 1
n_coure_score.compute()
ns = '试题总数：{}'.format(n_coure_score.score_scope_total)
print ns
ns = '比较靠谱数(60分以上)：{} ，比较靠谱占比：{}%'.format(
n_coure_score.score_scope_more60_count,
round(n_coure_score.score_scope_more60_rate * 100, 2))
print ns
ns = '基本靠谱数(50-60分)：{} ，基本靠谱占比：{}%'.format(
n_coure_score.score_scope_between5060_count,
round(n_coure_score.score_scope_between5060_rate * 100, 2))
print ns
ns = '不太靠谱数(40-50分)：{} ，不太靠谱占比：{}%'.format(
n_coure_score.score_scope_between4050_count,
round(n_coure_score.score_scope_between4050_rate * 100, 2))
print ns
ns = '不靠谱数(40分以下)：{} ，不靠谱占比：{}%'.format(
n_coure_score.score_scope_less40_count,
round(n_coure_score.score_scope_less40_rate * 100, 2))
print ns
# 统计课程所在区域的分布情况
n_coure_count_total = n_coure_score_less50 + n_coure_count_more50
n_coure_score_less_rate = float(
n_coure_score_less50) / n_coure_count_total
n_coure_count_more_rate = float(
n_coure_count_more50) / n_coure_count_total
ns = '50%以上的试题得分大于50分的课程数量：{} 占比：{}'.format(n_coure_count_more50,
n_coure_count_more_rate)
print ns
ns = '50%以上的试题得分小于50分的课程数量：{} 占比：{}'.format(n_coure_score_less50,
n_coure_score_less_rate)
print ns
pass
def loadProcessedCourse(self, rootpath):
output_mid_filepath = '{}/statistics-mid.txt'.format(rootpath)
if not FilePath.fileExist(output_mid_filepath):
return
fout = open(output_mid_filepath, 'r')
lines = fout.readlines()
for one_course_str in lines:
course_score = CourseInfomation.CourseScore()
course_score.initByString(one_course_str)
key = '{}-{}'.format(course_score.school_code,
course_score.course_code)
self.course_processed_dict[key] = course_score
self.course_score_list.append(course_score)
fout.close()
def statistics(self, statistics_filepath):
"""
对course_score_list中的结果，进行统计
:return:
"""
# bad course list
bad_course_list = []
# 课程的数量分布统计变量
n_coure_count_more50 = 0
n_coure_score_less50 = 0
f_stat = open(statistics_filepath, 'w')
# 统计所有课程，百分比的分布情况
n_coure_score = CourseInfomation.CourseScore()
for course_score in self.course_score_list:
n_coure_score.score_scope_more60_count += course_score.score_scope_more60_count
n_coure_score.score_scope_between5060_count += course_score.score_scope_between5060_count
n_coure_score.score_scope_between4050_count += course_score.score_scope_between4050_count
n_coure_score.score_scope_less40_count += course_score.score_scope_less40_count
course_descrip = course_score.getDescription()
f_stat.write('\n'.join(course_descrip))
f_stat.write('\n\n')
# 如果50分以上的超过50%，则more50+1
if (course_score.score_scope_between5060_rate +
course_score.score_scope_more60_rate) > 0.5:
n_coure_count_more50 += 1
else:
n_coure_score_less50 += 1
bad_course_list.append(course_score)
f_stat.write('所有课程的汇总统计：')
course_descrip = n_coure_score.getDescription()
f_stat.write('\n'.join(course_descrip))
f_stat.write('\n\n')
# 统计课程所在区域的分布情况
n_coure_count_total = n_coure_score_less50 + n_coure_count_more50
if n_coure_count_total > 0:
n_coure_score_less_rate = float(
n_coure_score_less50) / n_coure_count_total
n_coure_count_more_rate = float(
n_coure_count_more50) / n_coure_count_total
ns = '50%以上的试题得分大于50分的课程数量：{} 占比：{}'.format(
n_coure_count_more50, n_coure_count_more_rate)
print ns
ns = '50%以上的试题得分小于50分的课程数量：{} 占比：{}'.format(
n_coure_score_less50, n_coure_score_less_rate)
print ns
# 保存bad course信息
print 'bad course information.'
for bad_course in bad_course_list:
course_descrip = bad_course.getDescription()
f_stat.write('\n'.join(course_descrip))
f_stat.write('\n')
# 保存未识别的课程
f_stat.write('\n\n')
f_stat.write('未识别的课程：')
f_stat.write('\n'.join(self.course_unrecongnized))
f_stat.write('\n\n')
f_stat.write('超出范围的课程：')
f_stat.write('\n'.join(self.course_over_scope))
f_stat.close()
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