def main(locname, relLoc="./"):
csv.field_size_limit(sys.maxsize)
locD = geo.readIdToLoc(locname)
flist = glob.glob(relLoc + "20*")
fname = flist.pop()
fin = csv.reader(open(fname + "/profiles.csv", "r"))
pDict = prof.builddict(fin)
uin = csv.reader(open(fname + "/users.csv", "r"))
uDict = user.builddict(uin)
fullR = bcr.buildRosterDict(pDict, uDict, locD)
for f in flist:
fin = csv.reader(open(f + "/profiles.csv", "r"))
addDict = prof.builddict(fin)
uin = csv.reader(open(f + "/users.csv", "r"))
uDict = user.builddict(uin)
addR = bcr.buildRosterDict(addDict, uDict, locD)
for i in iter(addR):
if i not in fullR:
fullR[i] = addR[i]
outname = relLoc + "FullRoster.csv"
bcr.writeRoster(fullR, outname)
def main(locname, relLoc="./"):
csv.field_size_limit(sys.maxsize)
locD = geo.readIdToLoc(locname)
flist = glob.glob(relLoc + '20*')
fname = flist.pop()
fin = csv.reader(open(fname + '/profiles.csv', 'r'))
pDict = prof.builddict(fin)
uin = csv.reader(open(fname + '/users.csv', 'r'))
uDict = user.builddict(uin)
fullR = bcr.buildRosterDict(pDict, uDict, locD)
for f in flist:
fin = csv.reader(open(f + '/profiles.csv', 'r'))
addDict = prof.builddict(fin)
uin = csv.reader(open(f + '/users.csv', 'r'))
uDict = user.builddict(uin)
addR = bcr.buildRosterDict(addDict, uDict, locD)
for i in iter(addR):
if i not in fullR:
fullR[i] = addR[i]
outname = relLoc + 'FullRoster.csv'
bcr.writeRoster(fullR, outname)
'''
import glob
import sys
import csv
import classData.user as user
course = sys.argv[1]
flist = glob.glob('harvardx*/' + course + '/users.csv')
if len(flist) < 2:
exit()
f = iter(flist).next()
flist.remove(f)
ufile = open(f, 'r')
oldDict = user.builddict(ufile)
ufile.close()
out = csv.writer(open(course+'diffs.csv', 'w'))
for f in flist:
ufile = open(f, 'r')
newDict = user.builddict(csv.reader(ufile))
ufile.close()
out.writerow(['In older course list, not new'])
i = 0
for u in iter(oldDict):
if u not in newDict:
out.writerow([u, oldDict[u].username])
i += 1
out.writerow(['Total deleted between files: ', str(i)])
i = 0
out.writerow(['In new course list, not old'])
#!/usr/bin/env python
'''
Looks for differences between the user listed in the users file and those in the certificates file.
In particular, looks for any users not found in the users file who have received a certificate. This
was used for basic sanity testing on the invariant that if a user received a certificate, he or she
should also be in the users file. There are odd cases where this may not be the case, caused by the
habit of the edX group to delete a user (which may have been changed, we have asked for this), but
if there are large numbers (order 10s) then something is probably wrong.
'''
import csv
from classData import certificates, user
if __name__ == '__main__':
ufile = csv.reader(open('users.csv', 'r'))
udict = user.builddict(ufile)
cfile = csv.reader(open('certificates.csv', 'r'))
cDict = certificates.builddict(cfile)
certsMissing = []
for c in iter(cDict):
if (cDict[c].status == 'downloadable') and (c not in udict):
certsMissing.append(c)
if len(certsMissing) > 0:
print 'found ' + str(
len(certsMissing)) + ' certificates with no associated user'
outfile = csv.writer(open('certsAndusers.csv', 'w'))
outfile.writerow(['Missing user ids that have certificates'])
for u in certsMissing:
outfile.writerow([u])
if __name__ == '__main__':
ck_course = sys.argv[1]
wk1 = sys.argv[2]
wk2 = sys.argv[3]
week1 = wk1 + '/' + ck_course
week2 = wk2 + '/' + ck_course
userFile = '/users.csv'
certFile = '/certificates.csv'
enroll = '/enrollment.csv'
uf1 = csv.reader(open(week2 + userFile, 'r'))
uf2 = csv.reader(open(week1 + userFile, 'r'))
cf1 = csv.reader(open(week2 + certFile, 'r'))
cf2 = csv.reader(open(week1 + certFile, 'r'))
ef1 = csv.reader(open(week2 + enroll, 'r'))
ef2 = csv.reader(open(week1 + enroll, 'r'))
u1dict = user.builddict(uf1)
u2dict = user.builddict(uf2)
c1dict = certificates.builddict(cf1)
c2dict = certificates.builddict(cf2)
e1dict = course_enrollment.builddict(ef1)
e2dict = course_enrollment.builddict(ef2)
OneNotTwo = compareUsers(u1dict, u2dict)
TwoNotOne = compareUsers(u2dict, u1dict)
for u in iter(OneNotTwo):
if u in c1dict and c1dict[u].status == 'downloadable':
OneNotTwo[u] = 'y'
for u in iter(TwoNotOne):
if u in c2dict and c2dict[u].status == 'downloadable':
TwoNotOne[u] = 'y'
from classData import user, userprofile as userp
import sys
import csv
def split(name):
"""
Splits a string of form firstname lastname into two strings, returning a list
containing those names.
"""
spIn = name.rfind(' ')
first = name[ :spIn]
last = name[spIn + 1: ]
return [first, last]
if __name__ == '__main__':
csv.field_size_limit(sys.maxsize)
ufile = csv.reader(open('users.csv','r'))
udict = user.builddict(ufile)
pfile = csv.reader(open('profiles.csv', 'r'))
pdict = userp.builddict(pfile)
outfile = csv.writer(open('mailAddresses.csv','w'))
for uid in iter(udict):
if uid in pdict:
name = pdict[uid].name
else :
name = 'Missing Profile'
[first, last] = split(name)
outfile.writerow([first, last, udict[uid].email])
script is run, and takes as arguments the file names of the two user
files to be compared.
'''
import csv
import sys
from classData import certificates, user
if __name__ == '__main__':
f1 = csv.reader(open(sys.argv[1], 'r'))
f2 = csv.reader(open(sys.argv[2], 'r'))
f3 = csv.writer(open('additions.csv', 'w'))
f4 = csv.reader(open('certificates.csv', 'r'))
f3.writerow(['id', 'in certificate file'])
f3.writerow(['User ids in first file, not in second'])
u1 = user.builddict(f1)
u2 = user.builddict(f2)
cdict = certificates.builddict(f4)
for key in u1.iterkeys():
if u1[key].id not in u2:
if key in cdict:
f3.writerow([key, 'Yes'])
else:
f3.writerow([key, 'No'])
f3.writerow(['User ids in second file, not in first'])
for key in u2.iterkeys():
if u2[key].id not in u1:
if key in cdict:
f3.writerow([key, 'Yes'])
else:
entries in the profiles and enrollment file have entries in the user file.
The program takes no arguments, but assumes that the files are name users.csv,
profiles.csv, enrollment.csv, and produces a userDiffs.csv file.
'''
import csv
from classData import user
from classData import userprofile as uprofile
from classData import course_enrollment as ce
if __name__ == '__main__':
csv.field_size_limit(1000000)
uIn = csv.reader(open('users.csv', 'r'))
uDict = user.builddict(uIn)
upIn = csv.reader(open('profiles.csv', 'r'))
upDict = uprofile.builddict(upIn)
ceIn = csv.reader(open('enrollment.csv', 'r'))
ceDict = ce.builddict(ceIn)
of = csv.writer(open('userDiffs.csv', 'w'))
of.writerow(['ids in user file, not in profiles file'])
for u in iter(uDict):
if u not in upDict:
of.writerow([u])
of.writerow(['ids in profiles file, not in user file'])
for p in iter(upDict):
if p not in uDict:
of.writerow([p])
rl = rosterLine(sid, name, uname, maddr, cnt, age, edu, gender)
retDict[sid] = rl
ofile.close()
return retDict
def writeRoster(rDict, filein):
"""
Write a roster dictionary to a .csv file
Write a class roster dictionary to a .csv file named by the input parameter.
"""
ofile = open(filein, 'w')
rf = csv.writer(ofile)
rf.writerow(['Student ID', 'Name', 'User Name', 'Email', 'Country', 'Age', 'Education Level', 'Gender'])
for s in iter(rDict):
wl = rDict[s]
rf.writerow([wl.sid, wl.name, wl.uname, wl.maddr, wl.cnt, wl.age, wl.ed, wl.gender])
ofile.close()
if __name__ == '__main__':
csv.field_size_limit(sys.maxsize)
cl_name = sys.argv[1]
proDict = profile.builddict(csv.reader(open(cl_name + '/profiles.csv', 'r')))
uDict = user.builddict(csv.reader(open(cl_name + '/users.csv', 'r')))
loc_name = sys.argv[2]
locDict = geo.readIdToLoc(loc_name)
rDict = buildRosterDict(proDict, uDict, locDict)
writeRoster(rDict, cl_name + '/class_roster.csv')
if __name__ == '__main__':
ck_course = sys.argv[1]
wk1 = sys.argv[2]
wk2 = sys.argv[3]
week1 = wk1 + '/' + ck_course
week2 = wk2 + '/' + ck_course
userFile = '/users.csv'
certFile = '/certificates.csv'
enroll = '/enrollment.csv'
uf1 = csv.reader(open(week2 + userFile, 'r'))
uf2 = csv.reader(open(week1 + userFile, 'r'))
cf1 = csv.reader(open(week2 + certFile, 'r'))
cf2 = csv.reader(open(week1 + certFile, 'r'))
ef1 = csv.reader(open(week2 + enroll, 'r'))
ef2 = csv.reader(open(week1 + enroll, 'r'))
u1dict = user.builddict(uf1)
u2dict = user.builddict(uf2)
c1dict = certificates.builddict(cf1)
c2dict = certificates.builddict(cf2)
e1dict = course_enrollment.builddict(ef1)
e2dict = course_enrollment.builddict(ef2)
OneNotTwo = compareUsers(u1dict, u2dict)
TwoNotOne = compareUsers(u2dict, u1dict)
for u in iter(OneNotTwo):
if u in c1dict and c1dict[u].status == 'downloadable':
OneNotTwo[u] = 'y'
for u in iter(TwoNotOne):
if u in c2dict and c2dict[u].status == 'downloadable':
TwoNotOne[u] = 'y'
self.uname = uname
self.country = ''
self.classList = [className]
if __name__ == '__main__':
geoFile = csv.reader(open(sys.argv[1], 'r'))
geoDict = loc.builddict(geoFile)
fList = glob.glob('*/users.csv')
classDict = {}
for d in fList:
filein = open(d, 'r')
fin = csv.reader(filein)
cName = d[ :10]
fin.next()
udict = user.builddict(fin)
for u in iter(udict):
if u in classDict:
classDict[u].numClasses += 1
classDict[u].classList.append(cName)
if udict[u].username != classDict[u].uname:
classDict[u].uname = 'Duplicate user name'
else:
classDict[u] = userClasses(udict[u].username, cName)
if udict[u].username in geoDict:
classDict[u].country = geoDict[udict[u].username]
filein.close()
outf = csv.writer(open('studentClassList.csv', 'w'))
outf.writerow(['user Id', 'User name', 'country', 'number of classes', 'classes'])
script is run, and takes as arguments the file names of the two user
files to be compared.
'''
import csv
import sys
from classData import certificates, user
if __name__ == '__main__':
f1 = csv.reader(open(sys.argv[1], 'r'))
f2 = csv.reader(open(sys.argv[2], 'r'))
f3 = csv.writer(open('additions.csv', 'w'))
f4 = csv.reader(open('certificates.csv', 'r'))
f3.writerow(['id', 'in certificate file'])
f3.writerow(['User ids in first file, not in second'])
u1 = user.builddict(f1)
u2 = user.builddict(f2)
cdict = certificates.builddict(f4)
for key in u1.iterkeys():
if u1[key].id not in u2:
if key in cdict:
f3.writerow([key, 'Yes'])
else:
f3.writerow([key, 'No'])
f3.writerow(['User ids in second file, not in first'])
for key in u2.iterkeys():
if u2[key].id not in u1:
if key in cdict:
f3.writerow([key, 'Yes'])
else:
