Create app.py

app.py

@@ -0,0 +1,65 @@
+import streamlit as st
+import joblib
+import nltk
+import torch
+import torch.nn.functional as F
+import numpy as np
+
+from nltk.corpus import stopwords
+from nltk.tokenize import RegexpTokenizer
+from sklearn.neighbors import NearestNeighbors
+from sklearn.feature_extraction.text import TfidfVectorizer
+
+# ——— 1) Download NLTK data & set up tokenizer/stopwords ———
+nltk.download('stopwords')
+STOP_WORDS = set(stopwords.words('english'))
+TOKENIZER = RegexpTokenizer(r'\w+')
+
+def preprocess_text(text: str) -> str:
+    tokens = TOKENIZER.tokenize(text.lower())
+    return " ".join([t for t in tokens if t not in STOP_WORDS])
+
+# ——— 2) Load saved artifacts once ———
+@st.cache(allow_output_mutation=True)
+def load_artifacts():
+    tfidf: TfidfVectorizer = joblib.load("tfidf_vectorizer.pkl")
+    knn: NearestNeighbors = joblib.load("knn_model.pkl")
+    sage_model: torch.nn.Module = joblib.load("sage_model.pkl")
+    sage_model.eval()
+    return tfidf, knn, sage_model
+
+tfidf, knn, sage_model = load_artifacts()
+
+# ——— 3) Streamlit UI ———
+st.title("Disinformation Detection")
+st.write(
+    """Enter a snippet of text below and click **Predict** to see
+    whether it is more likely **True Information** or **Disinformation**."""
+)
+
+user_input = st.text_area("Article text", height=200)
+
+if st.button("Predict"):
+    if not user_input.strip():
+        st.warning("Please enter some text first.")
+    else:
+        # Preprocess & vectorize
+        clean = preprocess_text(user_input)
+        vec = tfidf.transform([clean]).toarray()
+        x = torch.from_numpy(vec).float()       # shape [1, D]
+
+        # Build an “empty” graph so SAGEConv still runs (no neighbor messages)
+        edge_index = torch.empty((2, 0), dtype=torch.long)
+
+        # Inference
+        with torch.no_grad():
+            out = sage_model(x, edge_index)    # [1, 2]
+            probs = torch.exp(out).numpy()[0]  # turn log‑softmax → probs
+
+        lst = [f"🔵 True information:  {probs[1]:.2%}", 
+               f"🔴 Disinformation: {probs[0]:.2%}"]
+        st.markdown("### Prediction probabilities")
+        st.write("\n\n".join(lst))
+
+        pred = "✅ Likely TRUE" if probs[1] > probs[0] else "❌ Likely DISINFORMATION"
+        st.markdown(f"## **{pred}**")