Upload 6 files

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+fake_logo.jpg filter=lfs diff=lfs merge=lfs -text
+Fake.csv filter=lfs diff=lfs merge=lfs -text
+True.csv filter=lfs diff=lfs merge=lfs -text

Fake.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bebf8bcfe95678bf2c732bf413a2ce5f621af0102c82bf08083b2e5d3c693d0c
+size 62789876

True.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba0844414a65dc6ae7402b8eee5306da24b6b56488d6767135af466c7dcb2775
+size 53582940

app.py

@@ -0,0 +1,116 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import nltk
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.model_selection import train_test_split
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.linear_model import LogisticRegression
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
+from nltk.corpus import stopwords
+
+st.image("innomatics-footer-logo.webp")
+st.image("fake_logo.jpg")
+
+# Download NLTK stopwords
+nltk.download("stopwords")
+stop_words = set(stopwords.words("english"))
+
+# Load Datasets
+@st.cache_data
+def load_data():
+    df_fake = pd.read_csv("Fake.csv")
+    df_real = pd.read_csv("True.csv")
+
+    # Assign labels
+    df_fake["label"] = 0  # Fake News
+    df_real["label"] = 1  # Real News
+
+    # Merge datasets
+    df = pd.concat([df_fake, df_real], ignore_index=True)
+    df = df.sample(n=10000, random_state=27).reset_index(drop=True)  # Shuffle
+
+    return df
+
+df = load_data()
+
+# Text Preprocessing Function
+def preprocess_text(text):
+    text = text.lower()
+    text = " ".join(word for word in text.split() if word not in stop_words)
+    return text
+
+df["clean_text"] = df["text"].astype(str).apply(preprocess_text)
+
+# TF-IDF Vectorization
+vectorizer = TfidfVectorizer(max_features=2000)
+X = vectorizer.fit_transform(df["clean_text"])
+
+# Target variable
+y = df["label"].values
+
+# Split Data
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# Train Models
+models = {
+    "Logistic Regression": LogisticRegression(),
+    "Naive Bayes": MultinomialNB(),
+    "Random Forest": RandomForestClassifier(n_estimators=100, random_state=42),
+    "Decision Tree": DecisionTreeClassifier(random_state=42),
+}
+
+# Streamlit App UI
+st.markdown("<h1 style='color: #FF5733;'>📰 Fake News Detection App</h1>", unsafe_allow_html=True)
+st.markdown("<p style='color: #555;'>Select a machine learning model and enter a news article to predict if it's <i>Real or Fake</i>.</p>", unsafe_allow_html=True)
+
+
+# Model Selection Dropdown
+st.markdown("<h3 style='color: #8A2BE2; font-size: 20px;'>🔍 Choose a Machine Learning Model:</h3>", unsafe_allow_html=True)
+selected_model = st.selectbox("", list(models.keys()))
+
+
+# Train Selected Model
+model = models[selected_model]
+model.fit(X_train, y_train)
+
+# Predictions
+y_pred = model.predict(X_test)
+
+# Classification Report
+accuracy = accuracy_score(y_test, y_pred)
+precision = precision_score(y_test, y_pred)
+recall = recall_score(y_test, y_pred)
+f1 = f1_score(y_test, y_pred)
+
+# Display Model Performance
+st.markdown("<h2 style='color: #3399FF;'>📊 Model Performance</h2>", unsafe_allow_html=True)
+st.write(f"<b style='color: #4CAF50;'>Accuracy:</b> {accuracy:.4f}", unsafe_allow_html=True)
+st.write(f"<b style='color: #FF9800;'>Precision:</b> {precision:.4f}", unsafe_allow_html=True)
+st.write(f"<b style='color: #F44336;'>Recall:</b> {recall:.4f}", unsafe_allow_html=True)
+st.write(f"<b style='color: #9C27B0;'>F1 Score:</b> {f1:.4f}", unsafe_allow_html=True)
+
+# User Input
+# Styled Text Area Label
+st.markdown("<h3 style='color: #E91E63; font-size: 18px;'>📝 Enter News Article:</h3>", unsafe_allow_html=True)
+
+# Text Area for User Input
+news_input = st.text_area("", height=200)
+
+
+# Function to Predict News Authenticity
+def predict_news(article, model):
+    clean_text = preprocess_text(article)
+    text_features = vectorizer.transform([clean_text]).toarray()
+    prediction = model.predict(text_features)[0]
+    return "🟢 Real News" if prediction == 1 else "🔴 Fake News"
+
+if st.button("Check News Authenticity"):
+    if news_input.strip() == "":
+        st.warning("⚠ Please enter a news article before clicking the button.")
+    else:
+        result = predict_news(news_input, model)
+        st.markdown("<h2 style='color: #FFD700;'>Prediction Result:</h2>", unsafe_allow_html=True)
+        st.markdown(f"<h3 style='color: {'#4CAF50' if 'Real' in result else '#F44336'};'>{result}</h3>", unsafe_allow_html=True)

requirements .txt

@@ -0,0 +1,5 @@
+streamlit 
+pandas
+numpy
+scikit-learn
+nltk