def drive(nsets):
print options.display()
hamdirs = [get_pathname_option("TestDriver", "ham_directories") % \
i for i in range(1, nsets+1)]
spamdirs = [get_pathname_option("TestDriver", "spam_directories") % \
i for i in range(1, nsets+1)]
d = TestDriver.Driver()
d.train(msgs.HamStream("%s-%d" % (hamdirs[1], nsets),
hamdirs[1:], train=1),
msgs.SpamStream("%s-%d" % (spamdirs[1], nsets),
spamdirs[1:], train=1))
for i in range(nsets):
h = hamdirs[i]
s = spamdirs[i]
hamstream = msgs.HamStream(h, [h], train=0)
spamstream = msgs.SpamStream(s, [s], train=0)
if i > 0:
if options["CV Driver", "build_each_classifier_from_scratch"]:
d.new_classifier()
hname = "%s-%d, except %d" % (hamdirs[0], nsets, i+1)
h2 = hamdirs[:]
del h2[i]
sname = "%s-%d, except %d" % (spamdirs[0], nsets, i+1)
s2 = spamdirs[:]
del s2[i]
d.train(msgs.HamStream(hname, h2, train=1),
msgs.SpamStream(sname, s2, train=1))
else:
d.untrain(hamstream, spamstream)
d.test(hamstream, spamstream)
d.finishtest()
if i < nsets - 1 and not options["CV Driver",
"build_each_classifier_from_scratch"]:
d.train(hamstream, spamstream)
d.alldone()
def drive(nsets):
print options.display()
spamdirs = [get_pathname_option("TestDriver", "spam_directories") % \
i for i in range(1, nsets+1)]
hamdirs = [get_pathname_option("TestDriver", "ham_directories") % \
i for i in range(1, nsets+1)]
spamhamdirs = zip(spamdirs, hamdirs)
d = TestDriver.Driver()
for spamdir, hamdir in spamhamdirs:
d.new_classifier()
d.train(msgs.HamStream(hamdir, [hamdir]),
msgs.SpamStream(spamdir, [spamdir]))
for sd2, hd2 in spamhamdirs:
if (sd2, hd2) == (spamdir, hamdir):
continue
d.test(msgs.HamStream(hd2, [hd2]),
msgs.SpamStream(sd2, [sd2]))
d.finishtest()
d.alldone()
def unlearn_compare(nsets, unsets):
print options.display()
spamdirs = [get_pathname_option("TestDriver", "spam_directories") % i for i in range(1, nsets+1)]
hamdirs = [get_pathname_option("TestDriver", "ham_directories") % i for i in range(1, nsets+1)]
spamhamdirs = zip(spamdirs, hamdirs)
unspamdirs = [get_pathname_option("TestDriver", "spam_directories") % i for i in range(1, unsets+1)]
unhamdirs = [get_pathname_option("TestDriver", "ham_directories") % i for i in range(1, unsets+1)]
unspamhamdirs = zip(unspamdirs, unhamdirs)
d = TestDriver.Driver()
d.new_classifier()
"""
for spamdir, hamdir in spamhamdirs:
d.train(msgs.HamStream(hamdir, [hamdir]),
msgs.SpamStream(spamdir, [spamdir]))
"""
d.train(msgs.HamStream(hamdirs[0], [hamdirs[0]]),
msgs.SpamStream(spamdirs[0], [spamdirs[0]]))
d.train(msgs.HamStream(hamdirs[1], [hamdirs[1]]),
msgs.SpamStream(spamdirs[1], [spamdirs[1]]))
d.test(msgs.HamStream(hamdirs[2], [hamdirs[2]]),
msgs.SpamStream(spamdirs[2], [spamdirs[2]]))
d.finishtest()
d.alldone()
unlearn_driver(d, spamhamdirs, unspamhamdirs)
def drive():
print options.display()
spam = [get_pathname_option("TestDriver", "spam_directories") % i for i in range(1, 5)]
ham = [get_pathname_option("TestDriver", "ham_directories") % i for i in range(1, 5)]
d = dictionarywriter.DictionaryWriter(150, 4)
d.write()
keep_going = True
trial_number = 1
au = ActiveUnlearnDriver.ActiveUnlearner([msgs.HamStream(ham[1], [ham[1]]),
msgs.HamStream(ham[2], [ham[2]])],
[msgs.SpamStream(spam[1], [spam[1]]),
msgs.SpamStream(spam[3], [spam[3]])],
msgs.HamStream(ham[0], [ham[0]]),
msgs.SpamStream(spam[0], [spam[0]]),
)
with open("C:\Users\Alex\Desktop\dict_correlation_stats.txt", 'w') as outfile:
while keep_going:
chosen = set()
current = au.select_initial()
cluster = au.determine_cluster(current)
chosen.add(current)
au.driver.test(au.testing_ham, au.testing_spam)
while not cluster:
current = au.select_initial(chosen)
cluster = au.determine_cluster(current)
chosen.add(current)
au.driver.test(au.testing_ham, au.testing_spam)
cluster_list = list(cluster.cluster_set)
dicts = au.driver.tester.train_examples[2]
data = v_correlation(cluster_list, dicts)
outfile.write("Trial " + str(trial_number) + " Percentage Overlap (Correlation): " + str(data))
answer = raw_input("Keep going (y/n)? You have performed " + str(trial_number) + " trial(s) so far. ")
valid_input = False
while not valid_input:
if answer == "n":
keep_going = False
valid_input = True
elif answer == "y":
au.learn(cluster)
au.init_ground()
trial_number += 1
valid_input = True
else:
print "Please enter either y or n."
def main(args):
global FMT
print options.display()
FMT = "unix"
NSETS = 10
SEED = 101
MAXMSGS = None
opts, args = getopt.getopt(args, "f:n:s:m:")
for k, v in opts:
if k == '-f':
FMT = v
if k == '-n':
NSETS = int(v)
if k == '-s':
SEED = int(v)
if k == '-m':
MAXMSGS = int(v)
ham, spam = args
random.seed(SEED)
nham = len(list(mbox(ham)))
nspam = len(list(mbox(spam)))
if MAXMSGS:
nham = min(nham, MAXMSGS)
nspam = min(nspam, MAXMSGS)
print "ham", ham, nham
print "spam", spam, nspam
ihams = map(tuple, randindices(nham, NSETS))
ispams = map(tuple, randindices(nspam, NSETS))
driver = Driver()
for i in range(1, NSETS):
driver.train(mbox(ham, ihams[i]), mbox(spam, ispams[i]))
i = 0
for iham, ispam in zip(ihams, ispams):
hams = mbox(ham, iham)
spams = mbox(spam, ispam)
if i > 0:
driver.untrain(hams, spams)
driver.test(hams, spams)
driver.finishtest()
if i < NSETS - 1:
driver.train(hams, spams)
i += 1
driver.alldone()
def main(args):
global FMT
print options.display()
FMT = "unix"
NSETS = 10
SEED = 101
MAXMSGS = None
opts, args = getopt.getopt(args, "f:n:s:m:")
for k, v in opts:
if k == '-f':
FMT = v
if k == '-n':
NSETS = int(v)
if k == '-s':
SEED = int(v)
if k == '-m':
MAXMSGS = int(v)
ham, spam = args
random.seed(SEED)
nham = len(list(mbox(ham)))
nspam = len(list(mbox(spam)))
if MAXMSGS:
nham = min(nham, MAXMSGS)
nspam = min(nspam, MAXMSGS)
print "ham", ham, nham
print "spam", spam, nspam
ihams = map(tuple, randindices(nham, NSETS))
ispams = map(tuple, randindices(nspam, NSETS))
driver = Driver()
for i in range(1, NSETS):
driver.train(mbox(ham, ihams[i]), mbox(spam, ispams[i]))
i = 0
for iham, ispam in zip(ihams, ispams):
hams = mbox(ham, iham)
spams = mbox(spam, ispam)
if i > 0:
driver.untrain(hams, spams)
driver.test(hams, spams)
driver.finishtest()
if i < NSETS - 1:
driver.train(hams, spams)
i += 1
driver.alldone()
def drive(nsets,decision):
print options.display()
spamdirs = [get_pathname_option("TestDriver", "spam_directories") % \
i for i in range(1, nsets+1)]
hamdirs = [get_pathname_option("TestDriver", "ham_directories") % \
i for i in range(1, nsets+1)]
spamfns = [(x,y,1) for x in spamdirs for y in os.listdir(x)]
hamfns = [(x,y,0) for x in hamdirs for y in os.listdir(x)]
nham = len(hamfns)
nspam = len(spamfns)
cc = CostCounter.nodelay()
allfns = {}
for fn in spamfns+hamfns:
allfns[fn] = None
d = hammie.open('weaktest.db', False)
hamtrain = 0
spamtrain = 0
n = 0
for dir,name, is_spam in allfns.iterkeys():
n += 1
m=msgs.Msg(dir, name).guts
if debug > 1:
print "trained:%dH+%dS"%(hamtrain,spamtrain)
scr=d.score(m)
if debug > 1:
print "score:%.3f"%scr
if not decision.tooearly():
if is_spam:
if debug > 0:
print "Spam with score %.2f"%scr
cc.spam(scr)
else:
if debug > 0:
print "Ham with score %.2f"%scr
cc.ham(scr)
de = decision(scr,is_spam)
if de == TRAIN_AS_SPAM:
d.train_spam(m)
spamtrain += 1
elif de == TRAIN_AS_HAM:
d.train_ham(m)
hamtrain += 1
if n % 100 == 0:
print "%5d trained:%dH+%dS wrds:%d"%(
n, hamtrain, spamtrain, len(d.bayes.wordinfo))
print cc
print "="*70
print "%5d trained:%dH+%dS wrds:%d"%(
n, hamtrain, spamtrain, len(d.bayes.wordinfo))
print cc
def drive(nsets):
print options.display()
spamdirs = [get_pathname_option("TestDriver", "spam_directories") % i for i in range(1, nsets+1)]
hamdirs = [get_pathname_option("TestDriver", "ham_directories") % i for i in range(1, nsets+1)]
d = TestDriver.Driver()
d.new_classifier()
d.train(msgs.HamStream(hamdirs[0], [hamdirs[0]]), msgs.SpamStream(spamdirs[0], [spamdirs[0]]))
d.test(msgs.HamStream(hamdirs[1], [hamdirs[1]]), msgs.SpamStream(spamdirs[1], [spamdirs[1]]))
d.finishtest()
d.alldone()
def drive(nsets):
print options.display()
hamdirs = [get_pathname_option("TestDriver", "ham_directories") % \
i for i in range(1, nsets+1)]
spamdirs = [get_pathname_option("TestDriver", "spam_directories") % \
i for i in range(1, nsets+1)]
d = TestDriver.Driver()
# Train it on all sets except the first.
d.train(msgs.HamStream("%s-%d" % (hamdirs[1], nsets),
hamdirs[1:], train=1),
msgs.SpamStream("%s-%d" % (spamdirs[1], nsets),
spamdirs[1:], train=1))
# Now run nsets times, predicting pair i against all except pair i.
for i in range(nsets):
h = hamdirs[i]
s = spamdirs[i]
hamstream = msgs.HamStream(h, [h], train=0)
spamstream = msgs.SpamStream(s, [s], train=0)
if i > 0:
if options["CV Driver", "build_each_classifier_from_scratch"]:
# Build a new classifier from the other sets.
d.new_classifier()
hname = "%s-%d, except %d" % (hamdirs[0], nsets, i+1)
h2 = hamdirs[:]
del h2[i]
sname = "%s-%d, except %d" % (spamdirs[0], nsets, i+1)
s2 = spamdirs[:]
del s2[i]
d.train(msgs.HamStream(hname, h2, train=1),
msgs.SpamStream(sname, s2, train=1))
else:
# Forget this set.
d.untrain(hamstream, spamstream)
# Predict this set.
d.test(hamstream, spamstream)
d.finishtest()
if i < nsets - 1 and not options["CV Driver",
"build_each_classifier_from_scratch"]:
# Add this set back in.
d.train(hamstream, spamstream)
d.alldone()
def drive(nsets, decision):
print options.display()
spamdirs = [get_pathname_option("TestDriver", "spam_directories") % i for i in range(1, nsets + 1)]
hamdirs = [get_pathname_option("TestDriver", "ham_directories") % i for i in range(1, nsets + 1)]
spamfns = [(x, y, 1) for x in spamdirs for y in os.listdir(x)]
hamfns = [(x, y, 0) for x in hamdirs for y in os.listdir(x)]
nham = len(hamfns)
nspam = len(spamfns)
cc = CostCounter.nodelay()
allfns = {}
for fn in spamfns + hamfns:
allfns[fn] = None
d = hammie.open("weaktest.db", False)
hamtrain = 0
spamtrain = 0
n = 0
for dir, name, is_spam in allfns.iterkeys():
n += 1
m = msgs.Msg(dir, name).guts
if debug > 1:
print "trained:%dH+%dS" % (hamtrain, spamtrain)
scr = d.score(m)
if debug > 1:
print "score:%.3f" % scr
if not decision.tooearly():
if is_spam:
if debug > 0:
print "Spam with score %.2f" % scr
cc.spam(scr)
else:
if debug > 0:
print "Ham with score %.2f" % scr
cc.ham(scr)
de = decision(scr, is_spam)
if de == TRAIN_AS_SPAM:
d.train_spam(m)
spamtrain += 1
elif de == TRAIN_AS_HAM:
d.train_ham(m)
hamtrain += 1
if n % 100 == 0:
print "%5d trained:%dH+%dS wrds:%d" % (n, hamtrain, spamtrain, len(d.bayes.wordinfo))
print cc
print "=" * 70
print "%5d trained:%dH+%dS wrds:%d" % (n, hamtrain, spamtrain, len(d.bayes.wordinfo))
print cc
def drive(nsets):
print options.display()
hamdirs = [get_pathname_option("TestDriver", "ham_directories") % \
i for i in range(1, nsets+1)]
spamdirs = [get_pathname_option("TestDriver", "spam_directories") % \
i for i in range(1, nsets+1)]
d = TestDriver.Driver()
# Train it on all sets except the first.
d.train(
msgs.HamStream("%s-%d" % (hamdirs[1], nsets), hamdirs[1:], train=1),
msgs.SpamStream("%s-%d" % (spamdirs[1], nsets), spamdirs[1:], train=1))
# Now run nsets times, predicting pair i against all except pair i.
for i in range(nsets):
h = hamdirs[i]
s = spamdirs[i]
hamstream = msgs.HamStream(h, [h], train=0)
spamstream = msgs.SpamStream(s, [s], train=0)
if i > 0:
if options["CV Driver", "build_each_classifier_from_scratch"]:
# Build a new classifier from the other sets.
d.new_classifier()
hname = "%s-%d, except %d" % (hamdirs[0], nsets, i + 1)
h2 = hamdirs[:]
del h2[i]
sname = "%s-%d, except %d" % (spamdirs[0], nsets, i + 1)
s2 = spamdirs[:]
del s2[i]
d.train(msgs.HamStream(hname, h2, train=1),
msgs.SpamStream(sname, s2, train=1))
else:
# Forget this set.
d.untrain(hamstream, spamstream)
# Predict this set.
d.test(hamstream, spamstream)
d.finishtest()
if i < nsets - 1 and not options["CV Driver",
"build_each_classifier_from_scratch"]:
# Add this set back in.
d.train(hamstream, spamstream)
d.alldone()
def drive(num):
print options.display()
spamdirs = [
get_pathname_option("TestDriver", "spam_directories") % i
for i in range(1, 4)
]
hamdirs = [
get_pathname_option("TestDriver", "ham_directories") % i
for i in range(1, 4)
]
r = mislabeledfilemover.MislabeledFileMover(num)
r.random_move_file()
d = TestDriver.Driver()
d.new_classifier()
d.train(msgs.HamStream(hamdirs[0], [hamdirs[0]]),
msgs.SpamStream(spamdirs[0], [spamdirs[0]]))
d.train(msgs.HamStream(hamdirs[2], [hamdirs[2]]),
msgs.SpamStream(spamdirs[2], [spamdirs[2]]))
d.test(msgs.HamStream(hamdirs[1], [hamdirs[1]]),
msgs.SpamStream(spamdirs[1], [spamdirs[1]]))
guess = d.classifier.spamprob
polluted = []
for msg in msgs.HamStream(hamdirs[2], [hamdirs[2]]):
msg.prob = guess(msg)
polluted.append(msg)
for msg in msgs.SpamStream(spamdirs[2], [spamdirs[2]]):
msg.prob = guess(msg)
polluted.append(msg)
mislabeled = []
for fp in d.tester.false_positives():
mislabeled.append(fp)
for fn in d.tester.false_negatives():
mislabeled.append(fn)
for unsure in d.unsure:
mislabeled.append(unsure)
d.finishtest()
d.alldone()
data = v_correlation(polluted, mislabeled)
print "Percentage Overlap (Correlation): " + str(data)
def drive(num):
print options.display()
spamdirs = [get_pathname_option("TestDriver", "spam_directories") %
i for i in range(1, 4)]
hamdirs = [get_pathname_option("TestDriver", "ham_directories") %
i for i in range(1, 4)]
r = mislabeledfilemover.MislabeledFileMover(num)
r.random_move_file()
d = TestDriver.Driver()
d.new_classifier()
d.train(msgs.HamStream(hamdirs[0], [hamdirs[0]]),
msgs.SpamStream(spamdirs[0], [spamdirs[0]]))
d.train(msgs.HamStream(hamdirs[2], [hamdirs[2]]),
msgs.SpamStream(spamdirs[2], [spamdirs[2]]))
d.test(msgs.HamStream(hamdirs[1], [hamdirs[1]]),
msgs.SpamStream(spamdirs[1], [spamdirs[1]]))
guess = d.classifier.spamprob
polluted = []
for msg in msgs.HamStream(hamdirs[2], [hamdirs[2]]):
msg.prob = guess(msg)
polluted.append(msg)
for msg in msgs.SpamStream(spamdirs[2], [spamdirs[2]]):
msg.prob = guess(msg)
polluted.append(msg)
mislabeled = []
for fp in d.tester.false_positives():
mislabeled.append(fp)
for fn in d.tester.false_negatives():
mislabeled.append(fn)
for unsure in d.unsure:
mislabeled.append(unsure)
d.finishtest()
d.alldone()
data = v_correlation(polluted, mislabeled)
print "Percentage Overlap (Correlation): " + str(data)
def drive(nsets):
print options.display()
spamdirs = [get_pathname_option("TestDriver", "spam_directories") % \
i for i in range(1, nsets+1)]
hamdirs = [get_pathname_option("TestDriver", "ham_directories") % \
i for i in range(1, nsets+1)]
spamhamdirs = zip(spamdirs, hamdirs)
d = TestDriver.Driver()
for spamdir, hamdir in spamhamdirs:
d.new_classifier()
d.train(msgs.HamStream(hamdir, [hamdir]),
msgs.SpamStream(spamdir, [spamdir]))
for sd2, hd2 in spamhamdirs:
if (sd2, hd2) == (spamdir, hamdir):
continue
d.test(msgs.HamStream(hd2, [hd2]),
msgs.SpamStream(sd2, [sd2]))
d.finishtest()
d.alldone()
def drive():
print options.display()
spam = [
get_pathname_option("TestDriver", "spam_directories") % i
for i in range(1, 5)
]
ham = [
get_pathname_option("TestDriver", "ham_directories") % i
for i in range(1, 5)
]
d = dictionarywriter.DictionaryWriter(150, 4)
d.write()
keep_going = True
trial_number = 1
au = ActiveUnlearnDriver.ActiveUnlearner(
[msgs.HamStream(ham[1], [ham[1]]),
msgs.HamStream(ham[2], [ham[2]])],
[
msgs.SpamStream(spam[1], [spam[1]]),
msgs.SpamStream(spam[3], [spam[3]])
],
msgs.HamStream(ham[0], [ham[0]]),
msgs.SpamStream(spam[0], [spam[0]]),
)
with open("C:\Users\Alex\Desktop\dict_correlation_stats.txt",
'w') as outfile:
while keep_going:
chosen = set()
current = au.select_initial()
cluster = au.determine_cluster(current)
chosen.add(current)
au.driver.test(au.testing_ham, au.testing_spam)
while not cluster:
current = au.select_initial(chosen)
cluster = au.determine_cluster(current)
chosen.add(current)
au.driver.test(au.testing_ham, au.testing_spam)
cluster_list = list(cluster.cluster_set)
dicts = au.driver.tester.train_examples[2]
data = v_correlation(cluster_list, dicts)
outfile.write("Trial " + str(trial_number) +
" Percentage Overlap (Correlation): " + str(data))
answer = raw_input("Keep going (y/n)? You have performed " +
str(trial_number) + " trial(s) so far. ")
valid_input = False
while not valid_input:
if answer == "n":
keep_going = False
valid_input = True
elif answer == "y":
au.learn(cluster)
au.init_ground()
trial_number += 1
valid_input = True
else:
print "Please enter either y or n."
