| import pandas as pd | |
| import numpy as np | |
| import getpass | |
| import joblib | |
| from sklearn.feature_extraction.text import CountVectorizer | |
| from sklearn.feature_extraction.text import TfidfVectorizer | |
| from sklearn.model_selection import train_test_split | |
| from sklearn.ensemble import RandomForestClassifier | |
| def word(password): | |
| character=[] | |
| for i in password: | |
| character.append(i) | |
| return character | |
| def new(): | |
| x = np.array(data["password"]) | |
| y = np.array(data["strength"]) | |
| tdif = TfidfVectorizer(tokenizer=word) | |
| x = tdif.fit_transform(x) | |
| xtrain, xtest, ytrain, ytest = train_test_split(x, y, test_size=0.05, random_state=42) | |
| x = np.array(data["password"]) | |
| y = np.array(data["strength"]) | |
| tdif = TfidfVectorizer(tokenizer=word) | |
| x = tdif.fit_transform(x) | |
| joblib.dump(tdif,"tdif.joblib") | |
| model = RandomForestClassifier() | |
| model.fit(xtrain, ytrain) | |
| joblib.dump(model, "passmodel.joblib") | |
| def load(): | |
| m=joblib.load("passmodel.joblib") | |
| td=joblib.load("tdif.joblib") | |
| return m,td | |
| def test(i,m,td): | |
| data = td.transform([str(i)]) | |
| output = m.predict(data) | |
| return output | |