import pandas as pd
import difflib
from DB.DBUtil import DB
"""
对原来的成绩文件进行扩展
增加：(课程类别，班级人数，教师) 三列
"""
# 年级 、课程名称、院系 三者找，找不到就用年级和课程找
if __name__ == "__main__":
root = "C://zxl/Data/GPA-large/"
gpa_dir = root + "grade/records/"
save_dir = root + "grade/records_completed/"
profile_path = root + "stu/profile.csv"
db = DB()
processed_dic = {}
for file_name in os.listdir(save_dir):
processed_dic[file_name[:-4]] = True
profile_df = pd.read_csv(profile_path)
stu_enrolltime = {
x: y[:4]
for x, y in zip(profile_df.stu_id, profile_df.enroll_time)
}
stu_dep = {x: y[2:-8] for x, y in zip(profile_df.stu_id, profile_df.dep)}
for file_name in os.listdir(gpa_dir):
stu_id = file_name[:-4]
if stu_id in processed_dic.keys():
continue
res.append([
semester, break_count[0], lunch_count[0], dinner_count[0],
break_count[1], lunch_count[1], dinner_count[1], break_count[2],
lunch_count[2], dinner_count[2]
])
return res
if __name__ == "__main__":
root = "C://zxl/Data/GPA-large/"
stu_file = root + "stu/stu_list.csv"
save_dir = root + "consume/records/"
complete_consume_dir = root + "new_consume/records/"
statistic_path = root + "processed/consume2.csv"
db = DB()
stu_df = pd.read_csv(stu_file)
#统计学生每学期的消费特征
stu_lst = []
fea_m = []
for file_name in os.listdir(complete_consume_dir):
stu_id = file_name[:-4]
df = pd.read_csv(complete_consume_dir + file_name)
fea = ExtractConsumeFea(df)
i = 0
while i < len(fea):
stu_lst.append(stu_id)
i += 1
fea_m.extend(fea)
# -*- coding: utf-8 -*-
# @Time : 2019/11/19 15:29
# @Author : zxl
# @FileName: InsertCourse.py
import pandas as pd
from DB.DBUtil import DB
if __name__ == "__main__":
db = DB()
file_path = "C://zxl/Data/StudyRelated/course.csv"
df = pd.read_csv(file_path)
df.columns = [
'idx1', 'dep_id', 'dep_name', 'c_id', 'c_name', 'stu_num', 'grade',
'type', 'teacher', 'week', 'week_num', 'section', 'classroom', 'campus'
]
i = 1
for (dep_id, dep_name, c_id, c_name, stu_num, grade, type, teacher, week,
week_num, section, classroom,
campus) in zip(df.dep_id, df.dep_name, df.c_id, df.c_name, df.stu_num,
df.grade, df.type, df.teacher, df.week, df.week_num,
df.section, df.classroom, df.campus):
c_name = str(c_name)
teacher = str(teacher)
c_name = c_name.replace('\'', '')
teacher = teacher.replace('\'', '')
if str(week_num) == 'nan':
week_num = '0'
print(i)
i += 1