Create model.pkl and vectorizer.pkl

model.pkl and vectorizer.pkl

@@ -0,0 +1,52 @@
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.linear_model import LogisticRegression
+from nltk.corpus import stopwords
+from nltk.stem import PorterStemmer
+import string
+import nltk
+import pickle
+
+nltk.download('stopwords')
+
+# Load data
+true_df = pd.read_csv("True.csv")
+fake_df = pd.read_csv("Fake.csv")
+
+true_df["label"] = 1
+fake_df["label"] = 0
+
+df = pd.concat([true_df, fake_df], axis=0).reset_index(drop=True)
+
+# Text Cleaning
+stemmer = PorterStemmer()
+stop_words = stopwords.words("english")
+
+def clean_text(text):
+    text = text.lower()
+    text = "".join([c for c in text if c not in string.punctuation])
+    tokens = text.split()
+    tokens = [stemmer.stem(word) for word in tokens if word not in stop_words]
+    return " ".join(tokens)
+
+df["cleaned_text"] = df["text"].apply(clean_text)
+
+# TF-IDF and Model Training
+X = df["cleaned_text"]
+y = df["label"]
+
+tfidf = TfidfVectorizer()
+X_tfidf = tfidf.fit_transform(X)
+
+X_train, X_test, y_train, y_test = train_test_split(X_tfidf, y, test_size=0.2, random_state=42)
+
+model = LogisticRegression()
+model.fit(X_train, y_train)
+
+# Save model and vectorizer
+with open("model.pkl", "wb") as f:
+    pickle.dump(model, f)
+
+with open("vectorizer.pkl", "wb") as f:
+    pickle.dump(tfidf, f)