-
Notifications
You must be signed in to change notification settings - Fork 0
/
machinelearning.py
40 lines (37 loc) · 1.16 KB
/
machinelearning.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
import passwordmeter
import os, glob, shutil
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
def getTokens(inputString):
tokens = []
for i in inputString:
tokens.append(i)
return tokens
def main():
CodedPasswords = []
PWs = []
STRENGTHs = []
file = open("Shortpws.txt", "r")
for line in file:
line=line.rstrip("\n")
TSS = []
cnt = 0
strength, improvements = passwordmeter.test(line)
cnt += 1
TSS.append(line)
PWs.append(line)
TSS.append(strength*100)
STRENGTHs.append(int(round(strength*100)))
# TSS.append(strength)
CodedPasswords.append(TSS)
print(CodedPasswords)
vectorizer = TfidfVectorizer(tokenizer=getTokens)
X = vectorizer.fit_transform(PWs)
X_train, X_test, y_train, y_test = train_test_split(X, STRENGTHs,
test_size=0.20, random_state=42)
lgs = LogisticRegression(penalty='l2',multi_class='ovr')
lgs.fit(X_train, y_train)
print(lgs.score(X_test, y_test))
if __name__ == "__main__":
main()