Update app.py

app.py

@@ -1,18 +1,14 @@
 # imports
 import re
-import typing
 import plotly.graph_objects as go
 import streamlit as st
-from textblob import TextBlob
 import json
 import google.generativeai as genai
-import os
 import concurrent.futures
 import textstat
 import trafilatura
 import requests
 from bs4 import BeautifulSoup
-import nltk
 
 # constants
 MAX_WORDS = 400
@@ -36,17 +32,6 @@ def _truncate_to_words(text: str, limit: int) -> str:
     words = text.split()
     return " ".join(words[:limit])
 
-@st.cache_resource
-def _initialize_app():
-    """Downloads lightweight NLTK data needed for highlighting."""
-    try:
-        nltk.data.find('tokenizers/punkt')
-    except LookupError:
-        nltk.download('punkt')
-        nltk.download('punkt_tab')
-
-_initialize_app()
-
 def analyze_article(text: str) -> dict:
     """Analyzes framing using an LLM API and calculates readability."""
     safe_text = _truncate_to_words(text, MAX_WORDS)
@@ -61,6 +46,7 @@ def analyze_article(text: str) -> dict:
     "primary_theme": Choose ONE from: ["economic consequences", "moral and ethical fairness", "legal and bureaucratic", "public safety and health"].
     "tone_scores": A dictionary scoring THESE EXACT 6 EMOTIONS from 0.0 to 1.0: {{"anger": 0.0, "fear": 0.0, "joy": 0.0, "sadness": 0.0, "surprise": 0.0, "trust": 0.0}}.
     "framing_words": A list of the 5 to 8 most emotionally charged, biased, or subjective words used in the text (e.g., ["draconian", "slammed", "titans", "catastrophic"]).
+    "subjectivity_score": A float between 0.0 (completely objective/factual) and 1.0 (highly opinionated/subjective).
     
     Text to analyze:
     "{safe_text}"
@@ -74,7 +60,6 @@ def analyze_article(text: str) -> dict:
     )
     llm_data = json.loads(response.text)
 
-    subjectivity_score = TextBlob(safe_text).sentiment.subjectivity
     raw_reading_ease = textstat.flesch_reading_ease(safe_text)
     
     tones = llm_data.get("tone_scores", {})
@@ -93,7 +78,7 @@ def analyze_article(text: str) -> dict:
         "primary_theme": llm_data.get("primary_theme", "unclear"),
         "tone_scores": standard_tones, 
         "framing_words": llm_data.get("framing_words", []),
-        "subjectivity_score": subjectivity_score,
+        "subjectivity_score": llm_data.get("subjectivity_score", 0.0), 
         "reading_ease": max(0.0, min(100.0, raw_reading_ease)),
     }
 
@@ -249,24 +234,40 @@ st.markdown("""
     footer {visibility: hidden;}
     header {visibility: hidden;}
     
+    /* Clean up the main container */
     .block-container {
         padding-top: 2rem;
         padding-bottom: 2rem;
+        max-width: 1200px;
     }
     
+    /* Commercial-grade metric cards */
     [data-testid="stMetric"] {
-        background-color: #f8fafc;
+        background-color: #ffffff;
         border: 1px solid #e2e8f0;
-        border-radius: 8px;
-        padding: 15px;
-        box-shadow: 0 1px 2px 0 rgba(0, 0, 0, 0.05);
+        border-radius: 12px;
+        padding: 20px;
+        box-shadow: 0 4px 6px -1px rgba(0, 0, 0, 0.05), 0 2px 4px -1px rgba(0, 0, 0, 0.03);
+        transition: transform 0.2s ease-in-out;
+    }
+    
+    [data-testid="stMetric"]:hover {
+        transform: translateY(-2px);
+        box-shadow: 0 10px 15px -3px rgba(0, 0, 0, 0.1), 0 4px 6px -2px 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; 
+        color: #0f172a;
+        font-weight: 700 !important;
+        font-size: 1.8rem !important; 
+    }
+    
+    [data-testid="stMetricLabel"] > div {
+        color: #64748b;
+        font-weight: 500;
+        text-transform: uppercase;
+        letter-spacing: 0.05em;
+        font-size: 0.85rem;
     }
 </style>
 """, unsafe_allow_html=True)
@@ -283,28 +284,30 @@ st.title("FrameVis")
 st.markdown("##### Media bias and framing effects across global news sources.")
 st.divider()
 
-input_method = st.radio("Input Method", ["Paste Text", "Paste URL"], horizontal=True, index=0)
+with st.container(border=True):
+    st.markdown("#### Configure Data Sources")
+    input_method = st.radio("Input Method", ["Paste Text", "Paste URL"], horizontal=True, index=0)
 
-col1, col2 = st.columns(2)
+    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:
-        url_a = st.text_input("Source A URL", value=URL_A)
-        user_article_a = fetch_article_text(url_a) if url_a else ""
+    with col1:
+        if input_method == "Paste Text":
+            user_article_a = st.text_area("Data Source A", value=ARTICLE_A.strip(), height=180)
+        else:
+            url_a = st.text_input("Source A URL", value=URL_A)
+            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:
-        url_b = st.text_input("Source B URL", value=URL_B)
-        user_article_b = fetch_article_text(url_b) if url_b else ""
+    with col2:
+        if input_method == "Paste Text":
+            user_article_b = st.text_area("Data Source B", value=ARTICLE_B.strip(), height=180)
+        else:
+            url_b = st.text_input("Source B URL", value=URL_B)
+            user_article_b = fetch_article_text(url_b) if url_b else ""
 
-st.write("")
+    st.write("")
+    execute_analysis = st.button("Analyze and Compare Sources", use_container_width=True, type="primary")
 
-# Execution button
-if st.button("Analyze and Compare Sources", use_container_width=True, type="primary"):
+if execute_analysis:
     
     text_a_clean = user_article_a.strip() if user_article_a else ""
     text_b_clean = user_article_b.strip() if user_article_b else ""