def main():
orig_df = get_data()
check_missing_unis(orig_df)
#assumes unis have been added and assigned university_ids
courses = get_courses(orig_df)
gcat.put_file('tmp_brazil_courses', courses, update=True)
#assumes courses have been added and assigned course_ids
students = get_students(orig_df)
gcat.put_file('tmp_brazil_student', students, update=True)
def main():
""" get the original data and clean it """
# orig_df = load_rtfs()
# gcat.put_file('wep_us_canada',df)
orig_df = gcat.get_file("wep_us_canada", fmt="pandas", usecache=False)
""" get course meta data """
orig_courses = set(orig_df["course"])
courses = get_course_meta_data(orig_courses)
""" find universities """
courses_with_uni = get_universities(courses)
# this file contains the new rows to be added to the course sheet
# gcat.put_file('tmp_us_canada_courses', courses_final, update=True)
""" merge original data with the courses """
students_with_courses = get_courses(orig_df)
print students_with_courses
# this file contains new rows that need to be added to the student sheet
gcat.put_file("tmp_us_canada_students_NEW", students_with_courses, update=True)
import gcat
import pandas as pd
frank = gcat.get_file('tmp_frank_students',fmt='pandas', sheet='student')
jami = gcat.get_file('tmp_us_canada_students_NEW',fmt='pandas')
annie = gcat.get_file('tmp_ar_students', fmt='pandas')
tom = gcat.get_file('tmp_brazil_student', fmt='pandas')
jami = jami.rename(columns={'username' : 'student_idstudent_username', 'course_id' : 'student_course_id'})
annie = annie.rename(columns={'course_id' : 'student_course_id'})
tom = tom.rename(columns={'student' : 'student_idstudent_username', 'course_id' : 'student_course_id'})
print frank
print jami
print annie
print tom
all_students = pd.concat([frank, jami, annie, tom])
all_students = all_students[['student_idstudent_username','student_course_id','student_lastname','student_firstname','student_email']]
final = gcat.get_file('WEP Summary Data', fmt='pandas')
final['student'] = all_students
gcat.put_file('WEP Summary Data', final, update=True)
'university_city',
'university_country']
course_fields = ['course_id',
'course_coursename',
'course_instructor',
'course_university_id',
'course_language',
'course_year',
'course_term',
'course_startdate',
'course_enddate']
student_fields = ['student_id'
'student_username',
'student_course_id',
'student_lastname',
'student_firstname',
'student_email']
data = {
'university' : pd.read_table('frank_db/Education Program_2013-01-09_universities.csv', sep=';', names=univ_fields),
'course' : pd.read_table('frank_db/Education Program_2013-01-09_courses.csv', sep=';', names=course_fields),
'student' : pd.read_table('frank_db/Education Program_2013-01-09_students.csv', sep=';', names=student_fields),
}
print data
dest_name = 'tmp_frank_students'
gcat.put_file(dest_name, data, update=True)
