Update app.py

app.py

@@ -1,4 +1,7 @@
+import re
 import typing
+
+import plotly.graph_objects as go
 import streamlit as st
 from transformers import pipeline
 import yake
@@ -6,7 +9,6 @@ import yake
 MAX_TEXT_LENGTH = 1500
 CANDIDATE_TONES = ["alarmist", "objective", "defensive", "optimistic", "critical"]
 
-
 ARTICLE_A = """
 Global leaders achieved a historic breakthrough today, signing a comprehensive climate accord aimed at drastically slashing carbon emissions by 2030. Environmental advocates are celebrating the mandate, which forces heavy-polluting industries to finally take accountability for their ecological damage. While corporations warn of transition costs, scientists emphasize that failing to act now would result in catastrophic, irreversible damage to our planet's fragile ecosystems.
 """
@@ -39,7 +41,6 @@ def _load_nlp_models() -> typing.Dict[str, typing.Any]:
 
 def analyze_article(text: str) -> dict:
     models = _load_nlp_models()
-
     safe_text = text[:MAX_TEXT_LENGTH]
 
     sentiment_result = models["sentiment"](safe_text)[0]
@@ -47,56 +48,138 @@ def analyze_article(text: str) -> dict:
     keyword_results = models["keyword"].extract_keywords(safe_text)
 
     is_positive = sentiment_result["label"] == "POSITIVE"
-    sentiment_score = sentiment_result["score"] if is_positive else -sentiment_result["score"]
+    sentiment_score = (
+        sentiment_result["score"] if is_positive else -sentiment_result["score"]
+    )
+
+    tone_scores = {
+        label: score
+        for label, score in zip(tone_result["labels"], tone_result["scores"])
+    }
 
     extracted_keywords = [kw[0] for kw in keyword_results]
 
     return {
-        "sentiment_score": round(sentiment_score, 2),
+        "sentiment_score": sentiment_score,
         "primary_tone": tone_result["labels"][0],
+        "tone_scores": tone_scores,
         "keywords": extracted_keywords,
     }
 
 
+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": 18}},
+            gauge={
+                "axis": {"range": [-1, 1], "tickwidth": 1},
+                "bar": {"color": "black"},
+                "steps": [
+                    {"range": [-1, -0.3], "color": "lightpink"},
+                    {"range": [-0.3, 0.3], "color": "lightgray"},
+                    {"range": [0.3, 1], "color": "lightgreen"},
+                ],
+            },
+        )
+    )
+    fig.update_layout(height=250, margin=dict(l=20, r=20, t=40, b=20))
+    return fig
+
+
+def _create_tone_bar_chart(tone_scores: typing.Dict[str, float]) -> go.Figure:
+    labels = list(tone_scores.keys())
+    values = list(tone_scores.values())
+
+    fig = go.Figure(go.Bar(x=values, y=labels, orientation="h", marker_color="royalblue"))
+    fig.update_layout(
+        title="Emotional Tone Distribution",
+        xaxis_title="Confidence",
+        yaxis_title="Tone",
+        height=250,
+        margin=dict(l=20, r=20, t=40, b=20),
+        yaxis={"categoryorder": "total ascending"},
+    )
+    return fig
+
+
+def _highlight_keywords(text: str, keywords: typing.List[str]) -> str:
+    highlighted_text = text
+    for kw in keywords:
+        pattern = re.compile(rf"\b({re.escape(kw)})\b", re.IGNORECASE)
+        highlighted_text = pattern.sub(
+            r"<span style='background-color: #ffcc00; padding: 2px; border-radius: 3px;'>\1</span>",
+            highlighted_text,
+        )
+    return highlighted_text
+
+
 st.set_page_config(page_title="FrameVis MVP", layout="wide")
 st.title("FrameVis: Media Framing Analyzer")
-st.markdown("Compare how different news sources frame the same event using free, open-source NLP models.")
+st.markdown("Compare how different news sources frame the same event using NLP.")
 
-with st.spinner("Waking up NLP models (this takes a moment on startup)..."):
+with st.spinner("Waking up NLP models..."):
     _load_nlp_models()
 
-st.markdown("### The Event: 2026 Global Climate Summit Accord")
+st.markdown("### Input Articles")
+st.markdown("Paste custom articles below or use the default samples to see the analysis.")
 
 col1, col2 = st.columns(2)
 
 with col1:
-    st.subheader("Source A (The 'Eco-Urgency' Frame)")
-    st.info(ARTICLE_A)
-    should_analyze_a = st.button("Analyze Source A")
+    st.subheader("Source A")
+    user_article_a = st.text_area(
+        "Paste Article A Text:", value=ARTICLE_A.strip(), height=200
+    )
+    should_analyze_a = st.button("Analyze Source A", use_container_width=True)
 
 with col2:
-    st.subheader("Source B (The 'Economic-Cost' Frame)")
-    st.warning(ARTICLE_B)
-    should_analyze_b = st.button("Analyze Source B")
+    st.subheader("Source B")
+    user_article_b = st.text_area(
+        "Paste Article B Text:", value=ARTICLE_B.strip(), height=200
+    )
+    should_analyze_b = st.button("Analyze Source B", use_container_width=True)
 
 st.divider()
 
 if should_analyze_a or should_analyze_b:
-    st.markdown("### Analysis Results")
+    st.markdown("### Visual Analytics Results")
     res_col1, res_col2 = st.columns(2)
 
-    if should_analyze_a:
+    if should_analyze_a and user_article_a:
         with st.spinner("Analyzing Source A..."):
-            results_a = analyze_article(ARTICLE_A)
+            results_a = analyze_article(user_article_a)
             with res_col1:
-                st.metric("Sentiment Score (-1 to 1)", results_a["sentiment_score"])
-                st.write(f"**Primary Tone:** {results_a['primary_tone'].title()}")
-                st.write(f"**Loaded Keywords:** {', '.join(results_a['keywords'])}")
-
-    if should_analyze_b:
+                st.plotly_chart(
+                    _create_sentiment_gauge(results_a["sentiment_score"], "Sentiment"),
+                    use_container_width=True,
+                )
+                st.plotly_chart(
+                    _create_tone_bar_chart(results_a["tone_scores"]),
+                    use_container_width=True,
+                )
+                st.markdown("**Highlighted Text (Loaded Keywords):**")
+                annotated_text = _highlight_keywords(
+                    user_article_a, results_a["keywords"]
+                )
+                st.markdown(f"> {annotated_text}", unsafe_allow_html=True)
+
+    if should_analyze_b and user_article_b:
         with st.spinner("Analyzing Source B..."):
-            results_b = analyze_article(ARTICLE_B)
+            results_b = analyze_article(user_article_b)
             with res_col2:
-                st.metric("Sentiment Score (-1 to 1)", results_b["sentiment_score"])
-                st.write(f"**Primary Tone:** {results_b['primary_tone'].title()}")
-                st.write(f"**Loaded Keywords:** {', '.join(results_b['keywords'])}")
+                st.plotly_chart(
+                    _create_sentiment_gauge(results_b["sentiment_score"], "Sentiment"),
+                    use_container_width=True,
+                )
+                st.plotly_chart(
+                    _create_tone_bar_chart(results_b["tone_scores"]),
+                    use_container_width=True,
+                )
+                st.markdown("**Highlighted Text (Loaded Keywords):**")
+                annotated_text = _highlight_keywords(
+                    user_article_b, results_b["keywords"]
+                )
+                st.markdown(f"> {annotated_text}", unsafe_allow_html=True)