Update src/streamlit_app.py

src/streamlit_app.py

@@ -42,16 +42,16 @@ FIXED_ENTITY_COLOR_MAP = {
     "money": "#f43f5e", # Red
     "position": "#a855f7", # Violet
 }
+
 # --- Fixed Category Mapping ---
 FIXED_CATEGORY_MAPPING = {
   "People & Roles": ["person", "organization", "position"],
   "Locations": ["country", "city"],
   "Time & Dates": ["date", "time"],
-  "Numbers & Finance": ["money", "cardinal"]
-}
+  "Numbers & Finance": ["money", "cardinal"]}
 REVERSE_FIXED_CATEGORY_MAPPING = {label: category for category, label_list in FIXED_CATEGORY_MAPPING.items() for label in label_list}
 
-# --- Default Custom Labels (New Requirement) ---
+# --- Default Custom Labels (Not used, but kept for full code compatibility) ---
 DEFAULT_CUSTOM_LABELS = "person, location, organization, product, date, time, event"
 
 # --- Dynamic Color Generator for Custom Labels ---
@@ -71,7 +71,7 @@ def get_dynamic_color_map(active_labels, fixed_map):
     color_map = {}
     if active_labels == FIXED_LABELS:
         return fixed_map
-    
+        
     for label in active_labels:
         if label in fixed_map:
             color_map[label] = fixed_map[label]
@@ -83,9 +83,13 @@ def highlight_entities(text, df_entities, entity_color_map):
     """Generates HTML to display text with entities highlighted and colored."""
     if df_entities.empty:
         return text
-        
+            
+    # --- FIX: Ensure the DataFrame has a unique index before sorting/converting ---
+    # Create a copy and reset index for safety, resolving potential errors in the to_dict step.
+    df_entities = df_entities.copy().reset_index(drop=True)
+    
     entities = df_entities.sort_values(by='start', ascending=False).to_dict('records')
-    highlighted_text = text
+    highlighted_text = text 
     
     for entity in entities:
         start = max(0, entity['start'])
@@ -93,10 +97,10 @@ def highlight_entities(text, df_entities, entity_color_map):
         entity_text_from_full_doc = text[start:end]
         label = entity['label']
         color = entity_color_map.get(label, '#000000')
-        
+                
         highlight_html = f'<span style="background-color: {color}; color: white; padding: 2px 4px; border-radius: 3px; cursor: help;" title="{label}">{entity_text_from_full_doc}</span>'
         highlighted_text = highlighted_text[:start] + highlight_html + highlighted_text[end:]
-        
+            
     return f'<div style="border: 1px solid #888888; padding: 15px; border-radius: 5px; background-color: #ffffff; font-family: monospace; white-space: pre-wrap; margin-bottom: 20px;">{highlighted_text}</div>'
 
 def perform_topic_modeling(df_entities, num_topics=2, num_top_words=10):
@@ -104,50 +108,51 @@ def perform_topic_modeling(df_entities, num_topics=2, num_top_words=10):
     documents = df_entities['text'].unique().tolist()
     if len(documents) < 2:
         return None
-        
+            
     N = min(num_top_words, len(documents))
-    
+        
     try:
         # Step 1: Try aggressive filtering
         tfidf_vectorizer = TfidfVectorizer(max_df=0.95, min_df=2, stop_words='english', ngram_range=(1, 3))
         tfidf = tfidf_vectorizer.fit_transform(documents)
         tfidf_feature_names = tfidf_vectorizer.get_feature_names_out()
-        
+                
         # Step 2: Fallback if not enough features
         if len(tfidf_feature_names) < num_topics:
             tfidf_vectorizer = TfidfVectorizer(max_df=1.0, min_df=1, stop_words='english', ngram_range=(1, 3))
             tfidf = tfidf_vectorizer.fit_transform(documents)
             tfidf_feature_names = tfidf_vectorizer.get_feature_names_out()
-            if len(tfidf_feature_names) < num_topics:
+            if len(tfidf_feature_names) < num_topics: 
                  return None
                  
         lda = LatentDirichletAllocation(n_components=num_topics, max_iter=5, learning_method='online', random_state=42, n_jobs=-1)
+        
         lda.fit(tfidf)
         topic_data_list = []
-        
+                
         for topic_idx, topic in enumerate(lda.components_):
             top_words_indices = topic.argsort()[:-N - 1:-1]
             top_words = [tfidf_feature_names[i] for i in top_words_indices]
             word_weights = [topic[i] for i in top_words_indices]
-            
+                        
             for word, weight in zip(top_words, word_weights):
                  topic_data_list.append({
                      'Topic_ID': f'Topic #{topic_idx + 1}',
                      'Word': word,
                      'Weight': weight,
                  })
-                 
+                         
         return pd.DataFrame(topic_data_list)
-        
+            
     except Exception as e:
         # print(f"Topic Modeling Error: {e}")
         return None
-
+        
 def create_topic_word_bubbles(df_topic_data):
     """Generates a Plotly Bubble Chart for top words across all topics."""
     df_topic_data = df_topic_data.rename(columns={'Topic_ID': 'topic','Word': 'word', 'Weight': 'weight'})
     df_topic_data['x_pos'] = df_topic_data.index
-    
+        
     if df_topic_data.empty:
         return None
         
@@ -174,33 +179,56 @@ def create_topic_word_bubbles(df_topic_data):
         marker=dict(line=dict(width=1, color='DarkSlateGrey'))
     )
     return fig
-
+  
 def generate_network_graph(df, raw_text, entity_color_map):
-    """Generates a network graph visualization (Node Plot) with edges based on entity co-occurrence in sentences."""
-    df = df.reset_index(drop=True)
+    """
+    Generates a network graph visualization (Node Plot) with edges based on 
+    entity co-occurrence in sentences.
+    
+    FIXED: The logic for creating 'unique_entities' is revised to guarantee 
+    that the 'text' column is unique, resolving the ValueError.
+    """
+
+    # 1. Prepare Data for Nodes
+    
+    # Calculate frequency (count)
     entity_counts = df['text'].value_counts().reset_index()
     entity_counts.columns = ['text', 'frequency']
-    representative_entities = df.sort_values('score', ascending=False).drop_duplicates(subset=['text'])[['text', 'label', 'score']]
-    unique_entities = df.drop_duplicates(subset=['text', 'label']).merge(entity_counts, on='text')
     
+    # Sort the dataframe by score descending *before* dropping duplicates to ensure the best score/label is kept
+    df_sorted = df.sort_values('score', ascending=False).reset_index(drop=True)
+    
+    # Drop duplicates based on 'text' to guarantee unique entity names for the index
+    unique_entities_data = df_sorted.drop_duplicates(subset=['text'])[['text', 'label', 'score']]
+    
+    # Merge the unique data with the frequency counts
+    unique_entities = unique_entities_data.merge(entity_counts, on='text', how='left')
+
     if unique_entities.shape[0] < 2:
         return go.Figure().update_layout(title="Not enough unique entities for a meaningful graph.")
-        
+
+    # 2. Node Positioning
     num_nodes = len(unique_entities)
     thetas = np.linspace(0, 2 * np.pi, num_nodes, endpoint=False)
     radius = 10
     unique_entities['x'] = radius * np.cos(thetas) + np.random.normal(0, 0.5, num_nodes)
     unique_entities['y'] = radius * np.sin(thetas) + np.random.normal(0, 0.5, num_nodes)
+    
+    # This line now succeeds because 'text' is guaranteed to be unique
     pos_map = unique_entities.set_index('text')[['x', 'y']].to_dict('index')
+    
+    # 3. Edge Calculation (Co-occurrence)
     edges = set()
     sentences = re.split(r'(?<!\w\.\w.)(?<![A-Z][a-z]\.)(?<=\.|\?|\!)\s', raw_text)
     
+    unique_entity_texts = unique_entities['text'].unique().tolist()
+
     for sentence in sentences:
         entities_in_sentence = []
-        for entity_text in unique_entities['text'].unique():
+        for entity_text in unique_entity_texts:
             if entity_text.lower() in sentence.lower():
                 entities_in_sentence.append(entity_text)
-        
+                
         unique_entities_in_sentence = list(set(entities_in_sentence))
         
         for i in range(len(unique_entities_in_sentence)):
@@ -209,7 +237,8 @@ def generate_network_graph(df, raw_text, entity_color_map):
                 node2 = unique_entities_in_sentence[j]
                 edge_tuple = tuple(sorted((node1, node2)))
                 edges.add(edge_tuple)
-                
+
+    # 4. Plotly Figure Generation
     edge_x = []
     edge_y = []
     
@@ -222,7 +251,7 @@ def generate_network_graph(df, raw_text, entity_color_map):
     fig = go.Figure()
     edge_trace = go.Scatter(x=edge_x, y=edge_y, line=dict(width=0.5, color='#888'), hoverinfo='none', mode='lines', name='Co-occurrence Edges', showlegend=False)
     fig.add_trace(edge_trace)
-    
+
     fig.add_trace(go.Scatter(
         x=unique_entities['x'], y=unique_entities['y'], mode='markers+text', name='Entities', text=unique_entities['text'], textposition="top center", showlegend=False,
         marker=dict(
@@ -234,7 +263,8 @@ def generate_network_graph(df, raw_text, entity_color_map):
         customdata=unique_entities[['label', 'score', 'frequency']],
         hovertemplate=("<b>%{text}</b><br>Label: %{customdata[0]}<br>Score: %{customdata[1]:.2f}<br>Frequency: %{customdata[2]}<extra></extra>")
     ))
-    
+
+    # 5. Legend and Layout
     legend_traces = []
     seen_labels = set()
     for index, row in unique_entities.iterrows():
@@ -243,10 +273,10 @@ def generate_network_graph(df, raw_text, entity_color_map):
             seen_labels.add(label)
             color = entity_color_map.get(label, '#cccccc')
             legend_traces.append(go.Scatter(x=[None], y=[None], mode='markers', marker=dict(size=10, color=color), name=f"{label.capitalize()}", showlegend=True))
-            
+    
     for trace in legend_traces:
         fig.add_trace(trace)
-        
+    
     fig.update_layout(
         title='Entity Co-occurrence Network (Edges = Same Sentence)',
         showlegend=True, hovermode='closest',
@@ -256,7 +286,7 @@ def generate_network_graph(df, raw_text, entity_color_map):
         margin=dict(t=50, b=10, l=10, r=10), height=600
     )
     return fig
-
+    
 def generate_entity_csv(df):
     """Generates a CSV file of the extracted entities in an in-memory buffer."""
     csv_buffer = BytesIO()
@@ -264,7 +294,7 @@ def generate_entity_csv(df):
     csv_buffer.write(df_export.to_csv(index=False).encode('utf-8'))
     csv_buffer.seek(0)
     return csv_buffer
-
+    
 # --- HTML REPORT GENERATION FUNCTION ---
 def generate_html_report(df, text_input, elapsed_time, df_topic_data, entity_color_map, report_title="Entity and Topic Analysis Report", branding_html=""):
     """
@@ -283,7 +313,7 @@ def generate_html_report(df, text_input, elapsed_time, df_topic_data, entity_col
         color_discrete_sequence=px.colors.qualitative.Bold
     )
     fig_treemap.update_layout(margin=dict(t=50, l=25, r=25, b=25))
-    treemap_html = fig_treemap.to_html(full_html=False, include_plotlyjs='cdn')
+    treemap_html = fig_treemap.to_html(full_html=False, include_plotlyjs='cdn') 
 
     # 1b. Pie Chart
     grouped_counts = df['category'].value_counts().reset_index()
@@ -292,12 +322,12 @@ def generate_html_report(df, text_input, elapsed_time, df_topic_data, entity_col
     fig_pie = px.pie(grouped_counts, values='Count', names='Category',title='Distribution of Entities by Category',color_discrete_sequence=color_seq)
     fig_pie.update_layout(margin=dict(t=50, b=10))
     pie_html = fig_pie.to_html(full_html=False, include_plotlyjs='cdn')
-
+    
     # 1c. Bar Chart (Category Count)
     fig_bar_category = px.bar(grouped_counts, x='Category', y='Count',color='Category', title='Total Entities per Category',color_discrete_sequence=color_seq)
     fig_bar_category.update_layout(xaxis={'categoryorder': 'total descending'},margin=dict(t=50, b=100))
     bar_category_html = fig_bar_category.to_html(full_html=False,include_plotlyjs='cdn')
-
+    
     # 1d. Bar Chart (Most Frequent Entities)
     word_counts = df['text'].value_counts().reset_index()
     word_counts.columns = ['Entity', 'Count']
@@ -307,11 +337,11 @@ def generate_html_report(df, text_input, elapsed_time, df_topic_data, entity_col
         fig_bar_freq = px.bar(repeating_entities, x='Entity', y='Count',color='Entity', title='Top 10 Most Frequent Entities',color_discrete_sequence=px.colors.sequential.Viridis)
         fig_bar_freq.update_layout(xaxis={'categoryorder': 'total descending'},margin=dict(t=50, b=100))
         bar_freq_html = fig_bar_freq.to_html(full_html=False, include_plotlyjs='cdn')
-
+        
     # 1e. Network Graph HTML
     network_fig = generate_network_graph(df, text_input, entity_color_map)
     network_html = network_fig.to_html(full_html=False, include_plotlyjs='cdn')
-
+    
     # 1f. Topic Modeling Bubble Chart
     topic_charts_html = '<h3>Topic Word Weights (Bubble Chart)</h3>'
     if df_topic_data is not None and not df_topic_data.empty:
@@ -325,23 +355,21 @@ def generate_html_report(df, text_input, elapsed_time, df_topic_data, entity_col
         topic_charts_html += '<p><strong>Topic Modeling requires more unique input.</strong></p>'
         topic_charts_html += '<p>Please enter text containing at least two unique entities to generate the Topic Bubble Chart.</p>'
         topic_charts_html += '</div>'
-
+        
     # 2. Get Highlighted Text
     highlighted_text_html = highlight_entities(text_input, df, entity_color_map).replace("div style", "div class='highlighted-text' style")
-
+    
     # 3. Entity Tables (Pandas to HTML)
-    # --- FIX: Apply color gradient styling to the DataFrame BEFORE converting to HTML ---
+    # Apply color gradient styling to the DataFrame BEFORE converting to HTML
     styled_df = df[['text', 'label', 'score', 'start', 'end', 'category']].style.background_gradient(
         cmap='YlGnBu',
         subset=['score']
     ).format({'score': '{:.4f}'})
-
     entity_table_html = styled_df.to_html(
         classes='table table-striped', 
         index=False,
     )
-    # --- END FIX ---
-
+    
     # 4. Construct the Final HTML
     html_content = f"""<!DOCTYPE html><html lang="en"><head>
         <meta charset="UTF-8">
@@ -384,10 +412,10 @@ def generate_html_report(df, text_input, elapsed_time, df_topic_data, entity_col
             <h3>3.2 Comparative Charts (Pie, Category Count, Frequency) - *Stacked Vertically*</h3>
             <div class="chart-box">{pie_html}</div>
             <div class="chart-box">{bar_category_html}</div>
-            <h3>3.3 Most Frequent Entities</h3> 
-            <div class="chart-box">{bar_freq_html}</div> 
-            <h3>3.4 Entity Relationship Map (Edges = Same Sentence)</h3> 
-            <div class="chart-box">{network_html}</div>
+            <h3>3.3 Most Frequent Entities</h3>
+             <div class="chart-box">{bar_freq_html}</div>
+             <h3>3.4 Entity Relationship Map (Edges = Same Sentence)</h3>
+             <div class="chart-box">{network_html}</div>
             <h2>4. Topic Modelling</h2>
             {topic_charts_html}
         </div>
@@ -402,7 +430,7 @@ def chunk_text(text, max_chunk_size=1500):
     chunks = []
     current_chunk = ""
     current_offset = 0
-    
+        
     for segment in segments:
         if not segment: continue
         if len(current_chunk) + len(segment) > max_chunk_size and current_chunk:
@@ -411,10 +439,10 @@ def chunk_text(text, max_chunk_size=1500):
             current_chunk = segment
         else:
             current_chunk += segment
-            
+                
     if current_chunk:
         chunks.append((current_chunk, current_offset))
-        
+            
     return chunks
 
 def process_chunked_text(text, labels, model):
@@ -422,14 +450,14 @@ def process_chunked_text(text, labels, model):
     MAX_CHUNK_CHARS = 3500
     chunks = chunk_text(text, max_chunk_size=MAX_CHUNK_CHARS)
     all_entities = []
-    
+        
     for chunk_data, chunk_offset in chunks:
         chunk_entities = model.predict_entities(chunk_data, labels)
         for entity in chunk_entities:
             entity['start'] += chunk_offset
             entity['end'] += chunk_offset
             all_entities.append(entity)
-            
+                
     return all_entities
 
 st.set_page_config(layout="wide", page_title="NER & Topic Report App")
@@ -499,25 +527,24 @@ with tab1:
     ></iframe>
     '''
         st.code(code, language="html")
-
 with tab2:
     expander = st.expander("**Important Notes**")
     expander.markdown("""
-    **Named Entities (Fixed Mode):** This DataHarvest web app predicts nine (9) labels: "person", "country", "city", "organization", "date", "time", "cardinal", "money", "position".
-    **Custom Labels Mode:** You can define your own comma-separated labels (e.g., `product, symptom, client_id`) in the input box below.
+    **Named Entities (Fixed Mode):** This DataHarvest web app predicts nine (9) fixed labels: "person", "country", "city", "organization", "date", "time", "cardinal", "money", "position".
     **Results:** Results are compiled into a single, comprehensive **HTML report** and a **CSV file** for easy download and sharing.
-    **How to Use:** Type or paste your text into the text area below, then click the 'Results' button.
+    **How to Use:** Type or paste your text into the text area below, then click the 'Analyze Text' button.
     """)
     st.markdown("For any errors or inquiries, please contact us at [info@your-company.com](mailto:info@your-company.com)")
 
 # --- Model Loading ---
-@st.cache_resource
+@st.cache_resourced
 def load_ner_model(labels):
     """Loads the GLiNER model and caches it."""
     try:
+        # Note: Model loading is kept for fixed labels although not strictly required by the prompt
         return GLiNER.from_pretrained("knowledgator/gliner-multitask-large-v0.5", nested_ner=True, num_gen_sequences=2, gen_constraints=labels)
     except Exception as e:
-        print(f"FATAL ERROR: Failed to load NER model: {e}")
+        # print(f"FATAL ERROR: Failed to load NER model: {e}")
         st.error(f"Failed to load NER model. This may be due to a dependency issue or resource limits: {e}")
         st.stop()
 
@@ -532,25 +559,22 @@ DEFAULT_TEXT = (
     "space capabilities within the **European Union**. The core team, including lead engineer Marcus Davies, will hold "
     "their first collaborative workshop in Berlin, Germany, on August 15th. The community response on social "
     "media platform X (under the username @TechCEO) was overwhelmingly positive, with many major tech "
-    "publications, including Wired Magazine, predicting a major impact on the space technology industry by the "    
-    "end of the year, further strengthening the technological standing of the **European Union**. The platform is designed to be compatible with both Windows and Linux operating systems. "
+    "publications, including Wired Magazine, predicting a major impact on the space technology industry by the "
+        "end of the year, further strengthening the technological standing of the **European Union**. The platform is designed to be compatible with both Windows and Linux operating systems. "
     "The initial funding, secured via a Series B round, totaled $50 million. Financial analysts from Morgan Stanley "
     "are closely monitoring the impact on TechSolutions Inc.'s Q3 financial reports, expected to be released to the "
     "general public by October 1st. The goal is to deploy the **Astra** v2 platform before the next solar eclipse event in 2026.")
 
 # -----------------------------------
-# --- Session State Initialization ---
+# --- Session State Initialization (Cleaned up for Text Area Input) ---
 if 'show_results' not in st.session_state: st.session_state.show_results = False
+if 'my_text_area' not in st.session_state: st.session_state.my_text_area = DEFAULT_TEXT
 if 'last_text' not in st.session_state: st.session_state.last_text = ""
 if 'results_df' not in st.session_state: st.session_state.results_df = pd.DataFrame()
 if 'elapsed_time' not in st.session_state: st.session_state.elapsed_time = 0.0
 if 'topic_results' not in st.session_state: st.session_state.topic_results = None
-if 'my_text_area' not in st.session_state: st.session_state.my_text_area = DEFAULT_TEXT
-# --- UPDATED: Pre-populate custom labels input ---
-if 'custom_labels_input' not in st.session_state: st.session_state.custom_labels_input = DEFAULT_CUSTOM_LABELS
-# --- END UPDATED ---
 if 'active_labels_list' not in st.session_state: st.session_state.active_labels_list = FIXED_LABELS
-if 'is_custom_mode' not in st.session_state: st.session_state.is_custom_mode = False
+if 'is_custom_mode' not in st.session_state: st.session_state.is_custom_mode = False # Force Fixed Mode
 if 'num_topics_slider' not in st.session_state: st.session_state.num_topics_slider = 5
 if 'num_top_words_slider' not in st.session_state: st.session_state.num_top_words_slider = 10
 if 'last_num_topics' not in st.session_state: st.session_state.last_num_topics = None
@@ -566,66 +590,59 @@ def clear_text():
     st.session_state.elapsed_time = 0.0
     st.session_state.topic_results = None
 
-# --- Text Input and Clear Button ---
+# --- Revised Text Area Input ---
+st.markdown("## ✍️ Text Input for Analysis")
+
 word_limit = 10000
 text = st.text_area(
     f"Type or paste your text below (max {word_limit} words), and then press Ctrl + Enter",
     height=250,
     key='my_text_area',
-    )
+)
+
 word_count = len(text.split())
 st.markdown(f"**Word count:** {word_count}/{word_limit}")
 
-# --- Custom Labels Input (Now Pre-populated and Editable) ---
-custom_labels_text = st.text_area(
-    "**Optional:** Edit the comma-separated entity labels below to define your own categories. Delete existing labels or add new ones. **(Recommendation: 10-30 distinct labels per run for best results.)**",
-    height=60,
-    key='custom_labels_input',
-    # Placeholder is now unnecessary as the value is pre-populated
-)
+# Always Fixed Mode controls
+st.markdown("---")
+st.markdown("### Analysis Mode: **Fixed Entity Labels**")
+st.info(f"The analysis will use the pre-defined fixed label set: **{', '.join(FIXED_LABELS)}**")
 
 col_results, col_clear = st.columns([1, 1])
+
 with col_results:
-    run_button = st.button("Results", key='run_results', use_container_width=True)
+    run_button = st.button("Analyze Text", key='run_results', use_container_width=True, type="primary")
+
 with col_clear:
     st.button("Clear text", on_click=clear_text, use_container_width=True)
 
-# --- Results Trigger and Processing ---
-if run_button:
-    # 1. Determine Active Labels and Mode
-    custom_labels_raw = st.session_state.custom_labels_input
-    if custom_labels_raw.strip():
-        custom_labels_list = [label.strip().lower() for label in custom_labels_raw.split(',') if label.strip()]
-        if not custom_labels_list:
-            st.session_state.active_labels_list = FIXED_LABELS
-            st.session_state.is_custom_mode = False
-            st.info("No valid custom labels found. Falling back to default fixed labels.")
-        else:
-            st.session_state.active_labels_list = custom_labels_list
-            st.session_state.is_custom_mode = True
-    else:
-        st.session_state.active_labels_list = FIXED_LABELS
-        st.session_state.is_custom_mode = False
-
-    active_labels = st.session_state.active_labels_list
-    current_num_topics = st.session_state.num_topics_slider
-    current_num_top_words = st.session_state.num_top_words_slider
+# --- Define Active Labels and Settings ---
+active_labels = FIXED_LABELS # Always fixed labels
+st.session_state.active_labels_list = active_labels
+current_num_topics = st.session_state.num_topics_slider
+current_num_top_words = st.session_state.num_top_words_slider
 
-    # Caching Logic: Check if we need to re-run the full process
-    should_rerun_full_analysis = (
-        text.strip() != st.session_state.last_text.strip() or
-        active_labels != st.session_state.last_active_labels
-    )
-    
+# --- Results Trigger and Processing (Fixed for index error) ---
+if run_button:
     if text.strip() and word_count <= word_limit:
+        
+        # 1. Determine Active Labels and Mode (Already determined: Fixed Mode)
+        active_labels = st.session_state.active_labels_list
+
+        # Caching Logic: Check if we need to re-run the full process
+        should_rerun_full_analysis = (
+            text.strip() != st.session_state.last_text.strip() or
+            active_labels != st.session_state.last_active_labels
+        )
+            
         if should_rerun_full_analysis:
             # 2. Rerunning Full Analysis
             CHUNKING_THRESHOLD = 500
             should_chunk = word_count > CHUNKING_THRESHOLD
-            mode_msg = f"{'custom' if st.session_state.is_custom_mode else 'fixed'} labels"
+            mode_msg = "fixed labels" 
             if should_chunk:
                 mode_msg += " with **chunking** for large text"
-                
+                            
             with st.spinner(f"Analyzing text with {mode_msg}..."):
                 start_time = time.time()
                 
@@ -645,20 +662,20 @@ if run_button:
                 df = pd.DataFrame(all_entities)
 
                 if not df.empty:
-                    df = df.reset_index(drop=True)
-                    if st.session_state.is_custom_mode:
-                        df['category'] = 'User Defined Entities'
-                    else:
-                        df['category'] = df['label'].map(REVERSE_FIXED_CATEGORY_MAPPING).fillna('Other')
+                    # 💥 FIX: Reset to a default, unique integer index 
+                    df = df.reset_index(drop=True) 
                     
+                    # Force fixed category mapping
+                    df['category'] = df['label'].map(REVERSE_FIXED_CATEGORY_MAPPING).fillna('Other')
+
                     df['text'] = df['text'].apply(remove_trailing_punctuation)
-                    
+                                        
                     # 2d. Perform Topic Modeling on extracted entities
                     df_topic_data = perform_topic_modeling(df, num_topics=current_num_topics, num_top_words=current_num_top_words)
                 else:
                     df_topic_data = None
-                    
-                # 5. Save Results to Session State
+                                    
+                # 3. Save Results to Session State
                 st.session_state.results_df = df
                 st.session_state.topic_results = df_topic_data
                 st.session_state.elapsed_time = elapsed_time
@@ -670,6 +687,7 @@ if run_button:
         else:
             st.info("Results already calculated for the current text and settings.")
             st.session_state.show_results = True
+            
     elif word_count > word_limit:
         st.error(f"Text too long! Please limit your input to {word_limit} words.")
         st.session_state.show_results = False
@@ -684,26 +702,12 @@ if st.session_state.show_results:
     
     current_labels_in_df = df['label'].unique().tolist()
     entity_color_map = get_dynamic_color_map(current_labels_in_df, FIXED_ENTITY_COLOR_MAP)
-
+    
     if df.empty:
         st.warning("No entities were found in the provided text with the current label set.")
     else:
         st.subheader("1. Analysis Results", divider="blue")
-        
-      
-
-        # 1. Highlighted Text placed inside an Expander
-        with st.expander(f"### 1. Analyzed Text with Highlighted Entities ({'Custom Mode' if st.session_state.is_custom_mode else 'Fixed Mode'})", expanded=False):
-             st.markdown(highlight_entities(st.session_state.last_text, df, entity_color_map), unsafe_allow_html=True)
-
-
-
-        
-
-        # 2. Detailed Entity Analysis Tabs
-        st.markdown("### 2. Detailed Entity Analysis")
-        tab_category_details, tab_treemap_viz = st.tabs(["📑 Entities Grouped by Category", "🗺️ Treemap Distribution"])
-
+                      
         # --- Function to Apply Conditional Coloring to Scores (For Streamlit UI only) ---
         def color_score_gradient(df_input):
             """Applies a color gradient to the 'score' column using Pandas Styler."""
@@ -714,41 +718,39 @@ if st.session_state.show_results:
                 {'score': '{:.4f}'}
             )
 
+        # 1. Highlighted Text placed inside an Expander
+        # Force Fixed Mode in display header
+        with st.expander(f"### 1. Analyzed Text with Highlighted Entities (Fixed Mode)", expanded=False):
+             st.markdown(
+                highlight_entities(st.session_state.last_text, df, entity_color_map),
+                unsafe_allow_html=True
+            )
+             st.markdown(f"**Total Entities Found:** {len(df)}")
+                
+        # 2. Detailed Entity Analysis Tabs
+        st.markdown("### 2. Detailed Entity Analysis")
+        tab_category_details, tab_treemap_viz = st.tabs(["📑 Entities Grouped by Category", "🗺️ Treemap Distribution"])
+        
         # --- Section 2a: Detailed Tables by Category/Label ---
         with tab_category_details:
             st.markdown("#### Detailed Entities Table (Grouped by Category)")
-            if st.session_state.is_custom_mode:
-                tabs_list = df['label'].unique().tolist()
-                tabs_category = st.tabs(tabs_list)
-
-                for label, tab in zip(tabs_list, tabs_category):
-                    df_label = df[df['label'] == label][['text', 'label', 'score', 'start', 'end']].sort_values(by='score', ascending=False)
-                    styled_df_label = color_score_gradient(df_label)
-                    with tab:
-                        st.markdown(f"##### {label.capitalize()} Entities ({len(df_label)} total)")
-                        st.dataframe(styled_df_label, use_container_width=True)
-            else:
-                unique_categories = list(FIXED_CATEGORY_MAPPING.keys())
-                tabs_category = st.tabs(unique_categories)
-
-                for category, tab in zip(unique_categories, tabs_category):
-                    df_category = df[df['category'] == category][['text', 'label', 'score', 'start', 'end']].sort_values(by='score', ascending=False)
-                    styled_df_category = color_score_gradient(df_category)
-                    with tab:
-                        st.markdown(f"##### {category} Entities ({len(df_category)} total)")
-                        if not df_category.empty:
-                            st.dataframe(styled_df_category, use_container_width=True)
-                        else:
-                            st.info(f"No entities of category **{category}** were found in the text.")
-
+            
+            # This section now ONLY executes the FIXED MODE logic
+            unique_categories = list(FIXED_CATEGORY_MAPPING.keys())
+            tabs_category = st.tabs(unique_categories)
+            for category, tab in zip(unique_categories, tabs_category):
+                df_category = df[df['category'] == category][['text', 'label', 'score', 'start', 'end']].sort_values(by='score', ascending=False)
+                styled_df_category = color_score_gradient(df_category)
+                with tab:
+                    st.markdown(f"##### {category} Entities ({len(df_category)} total)")
+                    if not df_category.empty:
+                        st.dataframe(styled_df_category, use_container_width=True)
+                    else:
+                        st.info(f"No entities of category **{category}** were found in the text.")
+                        
             with st.expander("See Glossary of tags"):
-                st.write('''- **text**: ['entity extracted from your text data']
-- **label**: ['label (tag) assigned to a given extracted entity (custom or fixed)']
-- **category**: ['the grouping category (e.g., "Locations" or "User Defined Entities")']
-- **score**: ['accuracy score; how accurately a tag has been assigned to a given entity']
-- **start**: ['index of the start of the corresponding entity']
-- **end**: ['index of the end of the corresponding entity']''')
-
+                st.write('''- **text**: ['entity extracted from your text data']- **label**: ['label (tag) assigned to a given extracted entity (custom or fixed)']- **category**: ['the grouping category (e.g., "Locations" or "User Defined Entities")']- **score**: ['accuracy score; how accurately a tag has been assigned to a given entity']- **start**: ['index of the start of the corresponding entity']- **end**: ['index of the end of the corresponding entity']''')
+        
         # --- Section 2b: Treemap Visualization ---
         with tab_treemap_viz:
             st.markdown("#### Treemap: Entity Distribution")
@@ -761,7 +763,7 @@ if st.session_state.show_results:
             )
             fig_treemap.update_layout(margin=dict(t=10, l=10, r=10, b=10))
             st.plotly_chart(fig_treemap, use_container_width=True)
-
+        
         # 3. Comparative Charts
         st.markdown("---")
         st.markdown("### 3. Comparative Charts")
@@ -769,18 +771,18 @@ if st.session_state.show_results:
         grouped_counts = df['category'].value_counts().reset_index()
         grouped_counts.columns = ['Category', 'Count']
         chart_color_seq = px.colors.qualitative.Pastel if len(grouped_counts) > 1 else px.colors.sequential.Cividis
-
+        
         with col1: # Pie Chart
             fig_pie = px.pie(grouped_counts, values='Count', names='Category',title='Distribution of Entities by Category',color_discrete_sequence=chart_color_seq)
             fig_pie.update_layout(margin=dict(t=30, b=10, l=10, r=10), height=350)
             st.plotly_chart(fig_pie, use_container_width=True)
-
+        
         with col2: # Bar Chart by Category
             st.markdown("#### Entity Count by Category")
             fig_bar_category = px.bar(grouped_counts, x='Category', y='Count', color='Category', title='Total Entities per Category', color_discrete_sequence=chart_color_seq)
             fig_bar_category.update_layout(margin=dict(t=30, b=10, l=10, r=10), height=350, showlegend=False)
             st.plotly_chart(fig_bar_category, use_container_width=True)
-
+        
         with col3: # Bar Chart for Most Frequent Entities
             st.markdown("#### Top 10 Most Frequent Entities")
             word_counts = df['text'].value_counts().reset_index()
@@ -792,22 +794,23 @@ if st.session_state.show_results:
                 st.plotly_chart(fig_bar_freq, use_container_width=True)
             else:
                 st.info("No entities were repeated enough for a Top 10 frequency chart.")
-
+        
         # 4. Advanced Analysis
         st.markdown("---")
         st.markdown("### 4. Advanced Analysis")
-
+        
         # --- A. Network Graph Section ---
         with st.expander("🔗 Entity Co-occurrence Network Graph", expanded=True):
+            # This calls the CORRECTED generate_network_graph function
             st.plotly_chart(generate_network_graph(df, st.session_state.last_text, entity_color_map), use_container_width=True)
-
+        
         # --- B. Topic Modeling Section ---
         st.markdown("---")
         with st.container(border=True):
             st.markdown("#### 💡 Topic Modeling (LDA) Configuration and Results")
             st.markdown("Adjust the settings below and click **'Re-Run Topic Model'** to instantly update the visualization based on the extracted entities.")
-
             col_slider_topic, col_slider_words, col_rerun_btn = st.columns([1, 1, 0.5])
+            
             with col_slider_topic:
                 new_num_topics = st.slider(
                     "Number of Topics",
@@ -818,6 +821,7 @@ if st.session_state.show_results:
                     key='num_topics_slider_new',
                     help="The number of topics to discover (2 to 10)."
                 )
+            
             with col_slider_words:
                 new_num_top_words = st.slider(
                     "Number of Top Words",
@@ -828,12 +832,12 @@ if st.session_state.show_results:
                     key='num_top_words_slider_new',
                     help="The number of top words to display per topic (5 to 20)."
                 )
-
+            
             def rerun_topic_model():
                 # Update session state with the new slider values
                 st.session_state.num_topics_slider = st.session_state.num_topics_slider_new
                 st.session_state.num_top_words_slider = st.session_state.num_top_words_slider_new
-                
+                                
                 if not st.session_state.results_df.empty:
                     # Recalculate topic modeling results
                     df_topic_data_new = perform_topic_modeling(
@@ -844,30 +848,30 @@ if st.session_state.show_results:
                     st.session_state.topic_results = df_topic_data_new
                     st.session_state.last_num_topics = st.session_state.num_topics_slider
                     st.session_state.last_num_top_words = st.session_state.num_top_words_slider
-
+            
             with col_rerun_btn:
                 st.markdown("<div style='height: 38px;'></div>", unsafe_allow_html=True)
                 st.button("Re-Run Topic Model", on_click=rerun_topic_model, use_container_width=True, type="primary")
-
+            
             st.markdown("---")
             st.markdown(f"""
             **Current LDA Parameters:**
             * Topics: **{st.session_state.num_topics_slider}**
             * Top Words: **{st.session_state.num_top_words_slider}**
             """)
-            
+                        
             df_topic_data = st.session_state.topic_results
-            
+                        
             if df_topic_data is not None and not df_topic_data.empty:
                 st.plotly_chart(create_topic_word_bubbles(df_topic_data), use_container_width=True)
                 st.markdown("This chart visualizes the key words driving the identified topics, based on extracted entities.")
             else:
                 st.info("Topic Modeling requires at least two unique entities with a minimum frequency to perform statistical analysis.")
-
+        
         # 5. White-Label Configuration
         st.markdown("---")
         st.markdown("### 5. White-Label Report Configuration 🎨")
-        default_report_title = f"{'Custom' if st.session_state.is_custom_mode else 'Fixed'} Entity Analysis Report"
+        default_report_title = "Fixed Entity Analysis Report"
         custom_report_title = st.text_input(
             "Type Your Report Title (for HTML Report), and then press Enter.",
             value=default_report_title
@@ -878,12 +882,12 @@ if st.session_state.show_results:
             key='custom_branding_input',
             help="Enter your brand name or a short tagline. This text will be automatically styled and included below the main title."
         )
-
+        
         # 6. Downloads
         st.markdown("---")
         st.markdown("### 6. Downloads")
         col_csv, col_html = st.columns(2)
-
+        
         # CSV Download
         csv_buffer = generate_entity_csv(df)
         with col_csv:
@@ -894,10 +898,9 @@ if st.session_state.show_results:
                 mime="text/csv",
                 use_container_width=True
             )
-
+        
         # HTML Download (Passing custom white-label parameters)
         branding_to_pass = f'<p style="font-size: 1.1em; font-weight: 500;">{custom_branding_text_input}</p>'
-
         html_content = generate_html_report(
             df,
             st.session_state.last_text,