Update app.py

app.py

@@ -1,22 +1,35 @@
 # imports
 import re
-import json
-import concurrent.futures
+import typing
 import plotly.graph_objects as go
 import streamlit as st
 from textblob import TextBlob
+import json
+import os
+import concurrent.futures
+from huggingface_hub import InferenceClient
 import textstat
 import trafilatura
 import requests
 from bs4 import BeautifulSoup
-from huggingface_hub import InferenceClient
 import nltk
-import os
 
-# INITIALIZATION
+# constants
+MAX_TEXT_LENGTH = 2000
+
+ARTICLE_A = """In a long-overdue victory for working-class families, lawmakers unveiled a bold new wealth tax targeting the nation's ultra-rich. For decades, billionaires have exploited gaping loopholes to hoard unprecedented wealth while paying a fraction of what ordinary citizens pay in taxes. This progressive legislation finally forces the top 0.1% to pay their fair share. Advocates argue the trillions generated will revitalize crumbling public schools, expand healthcare access, and begin to heal the gaping wounds of systemic economic inequality that have ravaged our communities."""
+ARTICLE_B = """A radical new wealth tax proposed today has sent shockwaves through the financial sector, with economists warning the punitive measure will severely cripple investment and drive capital overseas. The heavy-handed legislation directly penalizes success and job creators, fundamentally undermining the free-market principles that drive innovation. Analysts caution that this bureaucratic overreach will inevitably backfire, stifling economic growth, destroying millions of private-sector jobs, and ultimately passing the financial burden down to the everyday consumer."""
+
+URL_A = "https://www.foxnews.com/live-news/trump-iran-israel-war-updates-march-30"
+URL_B = "https://edition.cnn.com/2026/03/30/world/live-news/iran-war-us-israel-trump"
+
+# Initialize the Hugging Face Client
+HF_TOKEN = os.environ.get("HF_TOKEN")
+client = InferenceClient(model="mistralai/Mistral-7B-Instruct-v0.3", token=HF_TOKEN)
+
 @st.cache_resource
 def _initialize_app():
-    """Downloads NLTK data needed for highlighting."""
+    """Downloads lightweight NLTK data needed for highlighting."""
     try:
         nltk.data.find('tokenizers/punkt')
     except LookupError:
@@ -25,21 +38,6 @@ def _initialize_app():
 
 _initialize_app()
 
-# Initialize Hugging Face Client
-HF_TOKEN = os.environ.get("HF_TOKEN")
-client = InferenceClient(model="mistralai/Mistral-7B-Instruct-v0.3", token=HF_TOKEN)
-
-# constants
-MAX_TEXT_LENGTH = 2000 # 400 words
-
-ARTICLE_A = """In a long-overdue victory for working-class families, lawmakers unveiled a bold new wealth tax targeting the nation's ultra-rich. For decades, billionaires have exploited gaping loopholes to hoard unprecedented wealth while paying a fraction of what ordinary citizens pay in taxes. This progressive legislation finally forces the top 0.1% to pay their fair share. Advocates argue the trillions generated will revitalize crumbling public schools, expand healthcare access, and begin to heal the gaping wounds of systemic economic inequality that have ravaged our communities."""
-ARTICLE_B = """A radical new wealth tax proposed today has sent shockwaves through the financial sector, with economists warning the punitive measure will severely cripple investment and drive capital overseas. The heavy-handed legislation directly penalizes success and job creators, fundamentally undermining the free-market principles that drive innovation. Analysts caution that this bureaucratic overreach will inevitably backfire, stifling economic growth, destroying millions of private-sector jobs, and ultimately passing the financial burden down to the everyday consumer."""
-
-URL_A = "https://www.foxnews.com/live-news/trump-iran-israel-war-updates-march-30"
-URL_B = "https://edition.cnn.com/2026/03/30/world/live-news/iran-war-us-israel-trump"
-
-# CORE LOGIC
-
 def _extract_json_from_llm(response_text: str) -> dict:
     """Extracts JSON from an LLM response, ignoring markdown formatting."""
     try:
@@ -75,7 +73,6 @@ def analyze_article(text: str) -> dict:
         response = client.text_generation(prompt, max_new_tokens=250, temperature=0.1)
         llm_data = _extract_json_from_llm(response)
     except Exception as e:
-        st.error(f"API Error: {e}")
         llm_data = _extract_json_from_llm("") # fallback
 
     subjectivity_score = TextBlob(safe_text).sentiment.subjectivity
@@ -90,29 +87,97 @@ def analyze_article(text: str) -> dict:
         "reading_ease": max(0.0, min(100.0, raw_reading_ease)),
     }
 
-def check_contradiction(text_a: str, text_b: str) -> dict:
-    """Uses the LLM to evaluate the stance between arguments."""
-    prompt = f"""
-    You are a fact-checking analyst. Compare these two news excerpts.
-    Return ONLY a valid JSON object with the exact keys below. Do not include markdown formatting.
+
+def _create_sentiment_gauge(score: float, title: str) -> go.Figure:
+    """Generates a Plotly gauge chart for sentiment visualization."""
+    fig = go.Figure(
+        go.Indicator(
+            mode="gauge+number",
+            value=score,
+            domain={"x": [0, 1], "y": [0, 1]},
+            title={"text": title, "font": {"size": 16}},
+            gauge={
+                "axis": {"range": [-1, 1], "tickwidth": 1, "tickcolor": "darkgrey"},
+                "bar": {"color": "#475569", "thickness": 0.2}, 
+                "bgcolor": "white",
+                "borderwidth": 0,
+                "steps": [
+                    {"range": [-1, -0.1], "color": "#fee2e2"}, 
+                    {"range": [-0.1, 0.1], "color": "#f1f5f9"}, 
+                    {"range": [0.1, 1], "color": "#dcfce3"},   
+                ],
+            },
+        )
+    )
+    fig.update_layout(height=280, margin=dict(l=20, r=20, t=60, b=20))
+    return fig
+
+
+def _create_comparison_radar_chart(results_a: dict, results_b: dict) -> go.Figure:
+    """Generates an overlapping radar chart to compare emotions."""
+    categories = sorted(list(set(list(results_a["tone_scores"].keys()) + list(results_b["tone_scores"].keys()))))
     
-    Keys to return:
-    "relationship": Choose ONE from: ["CONTRADICTION", "ENTAILMENT", "NEUTRAL"]. (Contradiction = disputing facts, Entailment = agreeing on premise).
-    "confidence": A float between 0.0 and 1.0 representing how confident you are.
+    val_a = [results_a["tone_scores"].get(c, 0) for c in categories]
+    val_b = [results_b["tone_scores"].get(c, 0) for c in categories]
     
-    Text 1: "{text_a[:1000]}"
-    Text 2: "{text_b[:1000]}"
-    """
-    try:
-        response = client.text_generation(prompt, max_new_tokens=100, temperature=0.1)
-        result = _extract_json_from_llm(response)
-        return {"relationship": result.get("relationship", "NEUTRAL"), "confidence": result.get("confidence", 0.0)}
-    except:
-        return {"relationship": "NEUTRAL", "confidence": 0.0}
+    categories.append(categories[0])
+    val_a.append(val_a[0])
+    val_b.append(val_b[0])
+
+    fig = go.Figure()
+    fig.add_trace(go.Scatterpolar(
+          r=val_a, theta=categories, fill='toself', name='Source A', 
+          line=dict(color='#4f46e5', shape='spline', width=2),
+          fillcolor='rgba(79, 70, 229, 0.2)' 
+    ))
+    fig.add_trace(go.Scatterpolar(
+          r=val_b, theta=categories, fill='toself', name='Source B', 
+          line=dict(color='#10b981', shape='spline', width=2),
+          fillcolor='rgba(16, 185, 129, 0.2)' 
+    ))
+    fig.update_layout(
+      polar=dict(
+          radialaxis=dict(visible=True, showticklabels=False, showline=False, gridcolor='rgba(0,0,0,0.1)'),
+          angularaxis=dict(gridcolor='rgba(0,0,0,0.1)', linecolor='rgba(0,0,0,0.1)')
+      ),
+      showlegend=True,
+      legend=dict(orientation="h", yanchor="bottom", y=-0.2, xanchor="center", x=0.5), 
+      title={"text": "Relative Emotion Profile", "font": {"size": 18, "family": "sans-serif"}},
+      height=400,
+      margin=dict(l=40, r=40, t=60, b=40),
+      paper_bgcolor='rgba(0,0,0,0)', # Transparent
+      plot_bgcolor='rgba(0,0,0,0)'
+    )
+    return fig
+
+
+def _highlight_framing_words(text: str) -> str:
+    """Highlights subjective or emotional words in the text snippet."""
+    raw_sentences = re.split(r'(?<=[.!?]) +', text)
+    snippet = " ".join(raw_sentences[:3])
+    if not snippet:
+        return ""
+
+    blob = TextBlob(snippet)
+    target_words = set()
+    
+    for word in blob.words:
+        w_sentiment = TextBlob(word).sentiment 
+        if w_sentiment.subjectivity > 0.5 or abs(w_sentiment.polarity) > 0.3:
+            if len(word) > 2: 
+                target_words.add(str(word))
+                
+    highlighted_snippet = snippet
+    for word in target_words:
+        pattern = r'\b(' + re.escape(word) + r')\b'
+        replacement = r"<span style='background-color: #fef08a; color: #854d0e; font-weight: 600; padding: 0.1rem 0.2rem; border-radius: 4px;'>\1</span>"
+        highlighted_snippet = re.sub(pattern, replacement, highlighted_snippet, flags=re.IGNORECASE)
+
+    return highlighted_snippet + ("..." if len(raw_sentences) > 3 else "")
 
 @st.cache_data(ttl=3600, show_spinner=False)
 def fetch_article_text(url: str) -> str:
-    """Scrapes article text with caching to prevent re-scraping."""
+    """Scrapes article text."""
     downloaded = trafilatura.fetch_url(url)
     if downloaded:
         text = trafilatura.extract(downloaded)
@@ -122,6 +187,7 @@ def fetch_article_text(url: str) -> str:
     try:
         headers = {
             'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36',
+            'Accept-Language': 'en-US,en;q=0.9',
         }
         response = requests.get(url, headers=headers, timeout=10)
         soup = BeautifulSoup(response.content, 'html.parser')
@@ -134,76 +200,75 @@ def fetch_article_text(url: str) -> str:
         
         if text and len(text) > 200:
             return text.strip()
-    except Exception:
-        return f"Error: Could not fetch URL."
-
-    return "Error: Could not extract text. The site may be protected by paywalls."
-
-# UI
-def _highlight_framing_words(text: str) -> str:
-    """Highlights subjective or emotional words in the text snippet."""
-    raw_sentences = re.split(r'(?<=[.!?]) +', text)
-    snippet = " ".join(raw_sentences[:3])
-    if not snippet: return ""
-
-    blob = TextBlob(snippet)
-    target_words = {str(w) for w in blob.words if len(w) > 2 and (TextBlob(w).sentiment.subjectivity > 0.5 or abs(TextBlob(w).sentiment.polarity) > 0.3)}
-                
-    highlighted_snippet = snippet
-    for word in target_words:
-        pattern = r'\b(' + re.escape(word) + r')\b'
-        replacement = r"<span style='background-color: #fef08a; color: #854d0e; font-weight: 600; padding: 0.1rem 0.2rem; border-radius: 4px;'>\1</span>"
-        highlighted_snippet = re.sub(pattern, replacement, highlighted_snippet, flags=re.IGNORECASE)
+            
+    except Exception as e:
+        return f"Error: Could not fetch URL. Connection failed."
 
-    return highlighted_snippet + ("..." if len(raw_sentences) > 3 else "")
+    return "Error: Could not extract text. The site may be protected by hard paywalls."
 
-def _create_sentiment_gauge(score: float, title: str) -> go.Figure:
-    fig = go.Figure(go.Indicator(
-        mode="gauge+number", value=score, domain={"x": [0, 1], "y": [0, 1]},
-        title={"text": title, "font": {"size": 16}},
-        gauge={
-            "axis": {"range": [-1, 1], "tickwidth": 1, "tickcolor": "darkgrey"},
-            "bar": {"color": "#475569", "thickness": 0.2}, 
-            "bgcolor": "white", "borderwidth": 0,
-            "steps": [{"range": [-1, -0.1], "color": "#fee2e2"}, {"range": [-0.1, 0.1], "color": "#f1f5f9"}, {"range": [0.1, 1], "color": "#dcfce3"}],
-        }
-    ))
-    fig.update_layout(height=280, margin=dict(l=20, r=20, t=60, b=20))
-    return fig
 
-def _create_comparison_radar_chart(results_a: dict, results_b: dict) -> go.Figure:
-    categories = sorted(list(set(list(results_a["tone_scores"].keys()) + list(results_b["tone_scores"].keys()))))
-    val_a = [results_a["tone_scores"].get(c, 0) for c in categories]
-    val_b = [results_b["tone_scores"].get(c, 0) for c in categories]
+def check_contradiction(text_a: str, text_b: str) -> dict:
+    """Uses the LLM to evaluate the stance between arguments."""
+    prompt = f"""
+    You are a fact-checking analyst. Compare these two news excerpts.
+    Return ONLY a valid JSON object with the exact keys below. Do not include markdown formatting.
+    
+    Keys to return:
+    "relationship": Choose ONE from: ["CONTRADICTION", "ENTAILMENT", "NEUTRAL"]. (Contradiction = disputing facts, Entailment = agreeing on premise).
+    "confidence": A float between 0.0 and 1.0 representing how confident you are.
+    
+    Text 1: "{text_a[:1000]}"
+    Text 2: "{text_b[:1000]}"
+    """
+    try:
+        response = client.text_generation(prompt, max_new_tokens=100, temperature=0.1)
+        result = _extract_json_from_llm(response)
+        return {"relationship": result.get("relationship", "NEUTRAL"), "confidence": result.get("confidence", 0.0)}
+    except:
+        return {"relationship": "NEUTRAL", "confidence": 0.0}
     
-    if categories:
-        categories.append(categories[0])
-        val_a.append(val_a[0])
-        val_b.append(val_b[0])
-
-    fig = go.Figure()
-    fig.add_trace(go.Scatterpolar(r=val_a, theta=categories, fill='toself', name='Source A', line=dict(color='#4f46e5', width=2), fillcolor='rgba(79, 70, 229, 0.2)'))
-    fig.add_trace(go.Scatterpolar(r=val_b, theta=categories, fill='toself', name='Source B', line=dict(color='#10b981', width=2), fillcolor='rgba(16, 185, 129, 0.2)'))
-    fig.update_layout(
-      polar=dict(radialaxis=dict(visible=True, showticklabels=False, showline=False), angularaxis=dict(gridcolor='rgba(0,0,0,0.1)')),
-      showlegend=True, legend=dict(orientation="h", yanchor="bottom", y=-0.2, xanchor="center", x=0.5), 
-      title={"text": "Relative Emotion Profile", "font": {"size": 18}}, height=400, margin=dict(l=40, r=40, t=60, b=40), paper_bgcolor='rgba(0,0,0,0)', plot_bgcolor='rgba(0,0,0,0)'
-    )
-    return fig
 
-# STREAMLIT UI
+# USER INTERFACE
 st.set_page_config(page_title="FrameVis | Media Framing", layout="wide")
+
+if not HF_TOKEN:
+    st.warning("Hugging Face Token Missing.")
+
 st.markdown("""
 <style>
-    .block-container { padding-top: 2rem; padding-bottom: 2rem; }
-    [data-testid="stMetric"] { background-color: #f8fafc; border: 1px solid #e2e8f0; border-radius: 8px; padding: 15px; box-shadow: 0 1px 2px 0 rgba(0,0,0,0.05); }
-    [data-testid="stMetricValue"] > div { white-space: normal !important; word-wrap: break-word !important; line-height: 1.2 !important; font-size: 1.6rem !important; }
+    #MainMenu {visibility: hidden;}
+    footer {visibility: hidden;}
+    header {visibility: hidden;}
+    
+    .block-container {
+        padding-top: 2rem;
+        padding-bottom: 2rem;
+    }
+    
+    [data-testid="stMetric"] {
+        background-color: #f8fafc;
+        border: 1px solid #e2e8f0;
+        border-radius: 8px;
+        padding: 15px;
+        box-shadow: 0 1px 2px 0 rgba(0, 0, 0, 0.05);
+    }
+
+    [data-testid="stMetricValue"] > div {
+        white-space: normal !important;
+        word-wrap: break-word !important;
+        line-height: 1.2 !important;
+        font-size: 1.6rem !important; 
+    }
 </style>
 """, unsafe_allow_html=True)
 
-if not HF_TOKEN:
-    st.error("Hugging Face Token Missing.")
-    st.stop()
+# STATE MANAGEMENT
+if "results_a" not in st.session_state:
+    st.session_state.results_a = None
+if "results_b" not in st.session_state:
+    st.session_state.results_b = None
+if "nli_result" not in st.session_state:
+    st.session_state.nli_result = None
 
 st.title("FrameVis")
 st.markdown("##### Media bias and framing effects across global news sources.")
@@ -212,25 +277,37 @@ st.divider()
 input_method = st.radio("Input Method", ["Paste Text", "Paste URL"], horizontal=True, index=0)
 
 col1, col2 = st.columns(2)
+
 with col1:
-    if input_method == "Paste Text": user_article_a = st.text_area("Data Source A", value=ARTICLE_A.strip(), height=220)
-    else: 
+    if input_method == "Paste Text":
+        user_article_a = st.text_area("Data Source A", value=ARTICLE_A.strip(), height=220)
+    else:
         url_a = st.text_input("Source A URL", value=URL_A)
-        with st.spinner("Scraping Source A."): user_article_a = fetch_article_text(url_a) if url_a else ""
+        user_article_a = fetch_article_text(url_a) if url_a else ""
+
 with col2:
-    if input_method == "Paste Text": user_article_b = st.text_area("Data Source B", value=ARTICLE_B.strip(), height=220)
-    else: 
+    if input_method == "Paste Text":
+        user_article_b = st.text_area("Data Source B", value=ARTICLE_B.strip(), height=220)
+    else:
         url_b = st.text_input("Source B URL", value=URL_B)
-        with st.spinner("Scraping Source B."): user_article_b = fetch_article_text(url_b) if url_b else ""
+        user_article_b = fetch_article_text(url_b) if url_b else ""
 
+st.write("")
+
+# Execution button
 if st.button("Analyze and Compare Sources", use_container_width=True, type="primary"):
+    
     text_a_clean = user_article_a.strip() if user_article_a else ""
     text_b_clean = user_article_b.strip() if user_article_b else ""
 
-    if not text_a_clean or not text_b_clean: st.warning("Please provide text/URLs for both sources.")
-    elif text_a_clean.startswith("Error") or text_b_clean.startswith("Error"): st.error("Scraping failed. Try pasting text directly.")
+    if not text_a_clean or not text_b_clean:
+        st.warning("Please provide text or a valid URL for both Source A and Source B before analyzing.")
+    
+    elif text_a_clean.startswith("Error:") or text_b_clean.startswith("Error:"):
+        st.error("One of the URLs could not be scraped. Please copy and paste the text directly.")
+    
     else:
-        with st.spinner("Running deep semantic analysis."):
+        with st.spinner("Analyzing framing semantics for both sources."):
             with concurrent.futures.ThreadPoolExecutor() as executor:
                 future_a = executor.submit(analyze_article, text_a_clean)
                 future_b = executor.submit(analyze_article, text_b_clean)
@@ -240,43 +317,55 @@ if st.button("Analyze and Compare Sources", use_container_width=True, type="prim
                 st.session_state.results_b = future_b.result()
                 st.session_state.nli_result = future_nli.result()
 
-if "results_a" in st.session_state and st.session_state.results_a:
+# Analysis Display
+if st.session_state.results_a and st.session_state.results_b:
     st.divider()
     st.markdown("### Framing Analytics & Comparison")
     
+    # Display Contradictions
     nli_result = st.session_state.nli_result
     if nli_result:
-        rel = nli_result["relationship"].upper()
-        if rel == "CONTRADICTION": st.error(f"**NARRATIVE CONTRADICTION** (Confidence: {nli_result['confidence']:.2f}) - Disputing facts.")
-        elif rel == "ENTAILMENT": st.success(f"**NARRATIVE ALIGNMENT** (Confidence: {nli_result['confidence']:.2f}) - Agreeing on premises.")
-        else: st.info("**NEUTRAL RELATIONSHIP** - Discussing without direct contradiction.")
+        if nli_result["relationship"].upper() == "CONTRADICTION":
+            st.error(f"**NARRATIVE CONTRADICTION** (Confidence: {nli_result['confidence']:.2f}) - These sources are disputing each other's facts.")
+        elif nli_result["relationship"].upper() == "ENTAILMENT":
+            st.success(f"**NARRATIVE ALIGNMENT** (Confidence: {nli_result['confidence']:.2f}) - These sources agree on the core premise.")
+        else:
+            st.info(f"**NEUTRAL RELATIONSHIP** - These sources are discussing the topic without direct contradiction or alignment.")
             
     st.plotly_chart(_create_comparison_radar_chart(st.session_state.results_a, st.session_state.results_b), use_container_width=True)
 
     res_col1, res_col2 = st.columns(2)
 
+    # Render Column A
     with res_col1:
         r_a = st.session_state.results_a
         st.markdown("#### Source A Breakdown")
-        m1, m2 = st.columns(2); m3, m4 = st.columns(2)
-        m1.metric("Subjectivity", f"{r_a['subjectivity_score']:.2f}", help="0 is objective, 1 is highly opinionated.")
-        m2.metric("Primary Emotion", str(r_a['primary_tone']).title())
-        m3.metric("Framing Lens", str(r_a['primary_theme']).title())
-        m4.metric("Reading Ease", f"{r_a['reading_ease']:.1f}", help="0-30 is college graduate level, 60-70 is 8th grade.")
+        m1, m2 = st.columns(2)
+        m3, m4 = st.columns(2)
+        m1.metric("Subjectivity", f"{r_a['subjectivity_score']:.2f}")
+        m2.metric("Primary Emotion", r_a['primary_tone'].title())
+        m3.metric("Framing Lens", r_a['primary_theme'].title())
+        m4.metric("Reading Ease", f"{r_a['reading_ease']:.1f}")
 
         st.plotly_chart(_create_sentiment_gauge(r_a["sentiment_score"], "Sentiment Bias"), use_container_width=True, key="gauge_a")
+
         st.markdown("**Key Framing Language:**")
-        st.markdown(f"<div style='background-color: #f8fafc; padding: 1rem; border-radius: 8px; border: 1px solid #e2e8f0;'>{_highlight_framing_words(user_article_a)}</div>", unsafe_allow_html=True)
+        annotated_text = _highlight_framing_words(user_article_a)
+        st.markdown(f"<div style='background-color: #f8fafc; padding: 1rem; border-radius: 8px; border: 1px solid #e2e8f0;'>{annotated_text}</div>", unsafe_allow_html=True)
 
+    # Render Column B
     with res_col2:
         r_b = st.session_state.results_b
         st.markdown("#### Source B Breakdown")
-        m1, m2 = st.columns(2); m3, m4 = st.columns(2)
-        m1.metric("Subjectivity", f"{r_b['subjectivity_score']:.2f}", help="0 is objective, 1 is highly opinionated.")
-        m2.metric("Primary Emotion", str(r_b['primary_tone']).title())
-        m3.metric("Framing Lens", str(r_b['primary_theme']).title())
-        m4.metric("Reading Ease", f"{r_b['reading_ease']:.1f}", help="0-30 is college graduate level, 60-70 is 8th grade.")
+        m1, m2 = st.columns(2)
+        m3, m4 = st.columns(2)
+        m1.metric("Subjectivity", f"{r_b['subjectivity_score']:.2f}")
+        m2.metric("Primary Emotion", r_b['primary_tone'].title())
+        m3.metric("Framing Lens", r_b['primary_theme'].title())
+        m4.metric("Reading Ease", f"{r_b['reading_ease']:.1f}")
 
         st.plotly_chart(_create_sentiment_gauge(r_b["sentiment_score"], "Sentiment Bias"), use_container_width=True, key="gauge_b")
+
         st.markdown("**Key Framing Language:**")
-        st.markdown(f"<div style='background-color: #f8fafc; padding: 1rem; border-radius: 8px; border: 1px solid #e2e8f0;'>{_highlight_framing_words(user_article_b)}</div>", unsafe_allow_html=True)
+        annotated_text = _highlight_framing_words(user_article_b)
+        st.markdown(f"<div style='background-color: #f8fafc; padding: 1rem; border-radius: 8px; border: 1px solid #e2e8f0;'>{annotated_text}</div>", unsafe_allow_html=True)