def preprocessOrgs():
orgs = csv.DictReader(open('CSV Files/reference/raw_org_list.csv','rU'))
w = csv.writer(open('CSV Files/org_id_list_new.csv', 'wb'))
w.writerow(['org_name', 'org_id'])
count = 1;
for o in orgs:
old = o["org_name"]
new = normalizeOrgs(old)
w.writerow([new, count])
count += 1
def preprocessFACA():
for i in range(1): #14
date = 1997 + i
oldDir = '/Users/kevinshin92/Research/datafeeds/FACAMemberLists/old/'
newDir = '/Users/kevinshin92/Research/datafeeds/FACAMemberLists/new/'
baseName = 'FACAMemberList%(date)d' % {'date':date}
readFile = open(oldDir + baseName +'.csv', 'rU')
writeFile = open(newDir + baseName + '_new.csv', 'wb')
r = csv.DictReader(readFile)
w = csv.DictWriter(writeFile, r.fieldnames)
w.writerow(dict((fn,fn) for fn in r.fieldnames))
for row in r:
old = row["OccupationOrAffiliation"]
# Run regular expressions on occupations
row["OccupationOrAffiliation"] = normalizeOrgs(old)
# Test to see if prefix, first, middle, and suffix fields are empty
organizeDates(row, "StartDate")
organizeDates(row, "EndDate")
if (row["FirstName"] == '' and row["MiddleName"] == ''): #Prefix/Suffix can be filled
organizeNames(row)
w.writerow(row)
readFile.close()
writeFile.close()
