def predict(self, guess):
p = Password(guess)
p.analyze_frequencies()
if self.clf.decision_function([p.letter_frequencies.values()]) + 400 > 0:
return True
else:
return False
def predict(self, guess):
p = Password(guess)
p.analyze_frequencies()
if self.clf.decision_function([p.letter_frequencies.values()
]) + 400 > 0:
return True
else:
return False
def classify_and_generate():
wordfile = "input_dictionaries/linkedin.txt"
outputFile = "output_dictionaries/mutations.txt"
if len(sys.argv) != 3:
print "Number of arguments dif than 2, default filenames will be used"
else:
wordfile = sys.argv[1]
outputFile = sys.argv[2]
# delete the content of the output file if there are any
with open(outputFile, 'w'):
pass
print "Creating classifier"
classifier = PasswordClassifier()
classifier.train(wordfile)
print "Classifier built"
count = 10000000 # """ <<==== minimum number of passwords to be generated"""
letter_frequencies = dict()
with open(outputFile, 'a') as output:
with open(wordfile, 'r') as words:
print "Calculating letter frequencies"
for simpleWord in words:
# below should be the logic for the creation of the new dictionary
password = Password(simpleWord)
password.analyze_frequencies()
for c in password.letter_frequencies:
if c in letter_frequencies:
letter_frequencies[c] += password.letter_frequencies[c]
else:
letter_frequencies[c] = password.letter_frequencies[c]
# password.print_frequencies()
# mutations = password.mutate()
# mutations = password.append_numbers()
# write results to output file
# output.write('\n'.join(mutations) + "\n")
# for c in letter_frequencies:
# output.write(c + "," + str(letter_frequencies[c]) + "\n")
print "Generating new passwords"
n_created = 0
while n_created <= count:
tentative_passwords = PasswordGen.generate_passwords(
letter_frequencies, 1000, random.randint(7, 14))
output_buffer = []
for p in tentative_passwords:
if classifier.predict(p):
output_buffer.append(p)
P = Password(p)
mutations = P.mutate(change_factor=3)
output_buffer.extend(mutations)
n_created += len(mutations) + 1
output.write('\n'.join(output_buffer) + "\n")
print "Created: " + str(n_created)
print "done"
def classify_and_generate():
wordfile = "input_dictionaries/linkedin.txt"
outputFile = "output_dictionaries/mutations.txt"
if len(sys.argv) != 3:
print "Number of arguments dif than 2, default filenames will be used"
else:
wordfile = sys.argv[1]
outputFile = sys.argv[2]
# delete the content of the output file if there are any
with open(outputFile, 'w'):
pass
print "Creating classifier"
classifier = PasswordClassifier()
classifier.train(wordfile)
print "Classifier built"
count = 10000000 # """ <<==== minimum number of passwords to be generated"""
letter_frequencies = dict()
with open(outputFile, 'a') as output:
with open(wordfile, 'r') as words:
print "Calculating letter frequencies"
for simpleWord in words:
# below should be the logic for the creation of the new dictionary
password = Password(simpleWord)
password.analyze_frequencies()
for c in password.letter_frequencies:
if c in letter_frequencies:
letter_frequencies[c] += password.letter_frequencies[c]
else:
letter_frequencies[c] = password.letter_frequencies[c]
# password.print_frequencies()
# mutations = password.mutate()
# mutations = password.append_numbers()
# write results to output file
# output.write('\n'.join(mutations) + "\n")
# for c in letter_frequencies:
# output.write(c + "," + str(letter_frequencies[c]) + "\n")
print "Generating new passwords"
n_created = 0
while n_created <= count:
tentative_passwords = PasswordGen.generate_passwords(letter_frequencies, 1000, random.randint(7, 14))
output_buffer = []
for p in tentative_passwords:
if classifier.predict(p):
output_buffer.append(p)
P = Password(p)
mutations = P.mutate(change_factor=3)
output_buffer.extend(mutations)
n_created += len(mutations) + 1
output.write('\n'.join(output_buffer) + "\n")
print "Created: " + str(n_created)
print "done"
def train(self, TrainingFile):
training_data = []
with open(TrainingFile) as inputFile:
for word in inputFile:
p = Password(word)
p.analyze_frequencies()
training_data.append(p.letter_frequencies.values())
# print training_data
self.clf.fit(training_data)
def train(self, TrainingFile):
training_data = []
with open(TrainingFile) as inputFile:
for word in inputFile:
p = Password(word)
p.analyze_frequencies()
training_data.append(p.letter_frequencies.values())
# print training_data
self.clf.fit(training_data)
