def fill_dict(fp):
d = {}
with open(fp) as entity_file:
csv_reader = CSVUnicodeReader(entity_file)
headers = csv_reader.next()
for line in csv_reader:
d[line[0]] = line[1]
return d
# levels_fp = os.path.join(basedir, 'levels.csv')
schools_fp = os.path.join(basedir, 'schools.csv')
# subjects_fp = os.path.join(basedir, 'subjects.csv')
def fill_dict(fp):
d = {}
with open(fp) as entity_file:
csv_reader = CSVUnicodeReader(entity_file)
headers = csv_reader.next()
for line in csv_reader:
d[line[0]] = line[1]
return d
# levels = fill_dict(levels_fp)
schools = fill_dict(schools_fp)
# subjects = fill_dict(subjects_fp)
with open(item_filepath, mode='r') as item_f, open(item_cover, mode='w') as item_fw:
item_r = CSVUnicodeReader(item_f)
item_r.next()
item_w = CSVUnicodeWriter(item_fw)
for idx, course in enumerate(item_r):
if idx > 4805:
break
course_id = course[0]
course_school = course[7][1:]
school_cover_image = schools[course_school]
course[3] = school_cover_image
item_w.writerow(course)
headers = csv_reader.next()
for line in csv_reader:
d[line[0]] = line[1:]
return d
levels = fill_dict(levels_fp)
schools = fill_dict(schools_fp)
subjects = fill_dict(subjects_fp)
with open(item_filepath, mode='r') as item_f, open(item_uog_level, mode='w') as level_f, \
open(item_in_school, mode='w') as school_f, open(item_is_subject_of, mode='w') as subject_f:
item_r = CSVUnicodeReader(item_f)
level_w = CSVUnicodeWriter(level_f)
school_w = CSVUnicodeWriter(school_f)
subject_w = CSVUnicodeWriter(subject_f)
item_r.next() # headers
level_w.writerow(('uog_id', 'uog_id'))
school_w.writerow(('uog_id', 'uog_id'))
subject_w.writerow(('uog_id', 'wikidata_id'))
for idx, course in enumerate(item_r):
if idx > 4805:
break
course_id = course[0]
course_level = course[6][1:]
level_id = levels[course_level]
level_w.writerow((course_id, level_id[0]))
course_school = course[7][1:]
school_id = schools[course_school]
school_w.writerow((course_id, school_id[0]))