Update src/streamlit_app.py

src/streamlit_app.py

@@ -2,62 +2,33 @@ import streamlit as st
 from transformers import pipeline
 from pypdf import PdfReader
 
-# --- PAGE SETUP ---
-st.set_page_config(page_title="Twitter Sentiment AI", page_icon="🐦")
-
-# --- MODEL LOADING (Cached) ---
+# --- MODEL LOADING ---
 @st.cache_resource
-def load_twitter_model():
-    # Using the specialized Twitter RoBERTa model
-    model_path = "cardiffnlp/twitter-roberta-base-sentiment-latest"
-    return pipeline("sentiment-analysis", model=model_path, tokenizer=model_path)
-
-classifier = load_twitter_model()
+def load_model():
+    # This is the specialized Twitter model we discussed
+    return pipeline("sentiment-analysis", model="cardiffnlp/twitter-roberta-base-sentiment-latest")
 
-def get_pdf_text(pdf_file):
-    reader = PdfReader(pdf_file)
-    text = ""
-    for page in reader.pages:
-        text += page.extract_text()
-    return text
+classifier = load_model()
 
-# --- UI ELEMENTS ---
+# --- UI ---
 st.title("🐦 Twitter-RoBERTa Sentiment AI")
-st.markdown("Analyze sentiment using a model trained on **124M+ tweets**.")
-
-# Tabbed interface for Input
-tab1, tab2 = st.tabs(["💬 Text Input", "📄 PDF Upload"])
 
-with tab1:
-    user_input = st.text_area("Paste your text or tweet:", height=150)
+uploaded_file = st.file_uploader("Upload a PDF file", type="pdf")
 
-with tab2:
-    uploaded_file = st.file_uploader("Upload a PDF file", type="pdf")
-    if uploaded_file:
-        with st.spinner("Extracting text from PDF..."):
-            user_input = get_pdf_text(uploaded_file)
-            st.info(f"Extracted {len(user_input)} characters from PDF.")
-
-if st.button("Analyze Sentiment"):
-    if user_input.strip():
-        with st.spinner("Analyzing with RoBERTa..."):
-            # The Twitter model outputs labels like 'positive', 'neutral', 'negative'
-            results = classifier(user_input[:2000]) # Truncate to avoid errors on huge PDFs
-            label = results[0]['label']
-            score = results[0]['score']
+if uploaded_file is not None:
+    try:
+        # Extract text from PDF
+        reader = PdfReader(uploaded_file)
+        text = ""
+        for page in reader.pages:
+            text += page.extract_text()
             
-            st.divider()
+        if st.button("Analyze PDF Sentiment"):
+            # Truncating text to stay within model limits (approx 512 tokens)
+            prediction = classifier(text[:1500]) 
+            label = prediction[0]['label']
+            score = prediction[0]['score']
             
-            # Custom formatting based on labels
-            if label.lower() == "positive":
-                st.success(f"### Result: {label.upper()} 😊")
-            elif label.lower() == "negative":
-                st.error(f"### Result: {label.upper()} 😡")
-            else:
-                st.warning(f"### Result: {label.upper()} 😐")
-                
-            st.metric(label="Confidence Level", value=f"{score:.2%}")
-    else:
-        st.warning("Please provide some text or a PDF file.")
-
-st.caption("Note: Large PDFs are truncated to the first 2000 characters for processing speed.")
+            st.write(f"**Result:** {label.upper()} (Confidence: {score:.2%})")
+    except Exception as e:
+        st.error(f"Error reading PDF: {e}")