Untitled

import pandas as pd 
import seaborn as sns 
import re
import nltk
import pickle
from nltk.corpus import stopwords 
from nltk.stem.porter import PorterStemmer 
from sklearn.feature_extraction.text import TfidfVectorizer 
from sklearn.model_selection import train_test_split 
from sklearn.linear_model import LogisticRegression 
from sklearn import metrics
from sklearn.metrics import ConfusionMatrixDisplay

nltk.download("stopwords")
tfidf_v = TfidfVectorizer() 
classifier = LogisticRegression()
true = pd.read_csv('data/True.csv') 
fake = pd.read_csv('data/Fake.csv') 
true.isnull().sum()
fake.isnull().sum()

true['label'] = 1
fake['label'] = 0 
frames = [true,fake] 
df = pd.concat(frames, ignore_index=True) 
df['date'] = pd.to_datetime(df['date'], errors = 'coerce') 
df['Year'] = df['date'].dt.year 
df['Month'] = df['date'].dt.month 
df.subject.value_counts()

sns.countplot(data= df, x="Year", hue="subject")

frames = [true.head(200), fake.head(200)]
df = pd.concat(frames)
X = df.drop("label", axis = 1)
y = df["label"]

df = df.dropna()
df2 = df.copy()
df2.reset_index(inplace=True)

ps = PorterStemmer()
corpus = []
for i in range(0, len(df2)): 
    review = re.sub('[^a-zA-Z]', ' ', df2['text'][i]) 
    review = review.lower() 
    review = review.split() 
    review = [ps.stem(word) for word in review if not word in stopwords.words('english')] 
    review = ' '.join(review) 
    corpus.append(review)
    
X = tfidf_v.fit_transform(corpus).toarray()
y = df2['label'] 

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=0)

classifier.fit(X_train, y_train) 
pred = classifier.predict(X_test) 
score = metrics.accuracy_score(y_test, pred) 

disp = ConfusionMatrixDisplay.from_estimator(classifier, X_test, y_test) 
disp.ax_.set_title("Confusion Matrix")

pickle.dump(classifier, open("model2.pkl","wb"))
pickle.dump(tfidf_v, open("tfidfvect2.pkl","wb"))


model = pickle.load(open('model2.pkl', 'rb')) 
tfidfvect = pickle.load(open('tfidfvect2.pkl', 'rb'))


def predict(text): 
    review = re.sub('[^a-zA-Z]', ' ', text) 
    review = review.lower() 
    review = review.split() 
    review = [ps.stem(word) for word in review if not word in stopwords.words('english')] 
    review = ' '.join(review) 
    review_vect = tfidfvect.transform([review]).toarray() 
    prediction = 'FAKE' if model.predict(review_vect) == 0 else 'REAL' 
    return prediction


text = "Trump is the former president" 
prediction = predict(text) 
print(prediction)