Update src/streamlit_app.py

src/streamlit_app.py

@@ -39,23 +39,23 @@ except ImportError:
 # Set HF_HOME environment variable to a writable path
 os.environ['HF_HOME'] = '/tmp'
 
-# --- Color Map for Highlighting and Network Graph Nodes ---
+# --- Color Map for Highlighting and Network Graph Nodes (Monochrome Palette) ---
 entity_color_map = {
-    "person": "#10b981",
-    "username": "#3b82f6",
-    "hashtag": "#4ade80",
-    "mention" : "#f97316",
-    "organization": "#f59e0b",
-    "community": "#8b5cf6",
-    "position": "#ec4899",
-    "location": "#06b6d4",
-    "event": "#f43f5e",
-    "product": "#a855f7",
-    "platform": "#eab308",
-    "date": "#6366f1",
-    "media_type": "#14b8a6",
-    "url": "#60a5fa",
-    "nationality_religion": "#fb7185"
+    "person": "#444444",         # Dark Gray
+    "username": "#666666",       # Medium-Dark Gray
+    "hashtag": "#888888",        # Medium Gray
+    "mention" : "#aaaaaa",       # Medium-Light Gray
+    "organization": "#333333",   # Very Dark Gray
+    "community": "#bbbbbb",      # Light Gray
+    "position": "#555555",       # Slightly Dark Gray
+    "location": "#777777",       # Neutral Gray
+    "event": "#999999",          # Silver
+    "product": "#cccccc",        # Light Gray/Silver
+    "platform": "#222222",       # Black-ish
+    "date": "#dddddd",           # Very Light Gray
+    "media_type": "#333333",     # Very Dark Gray
+    "url": "#666666",            # Medium-Dark Gray
+    "nationality_religion": "#aaaaaa" # Medium-Light Gray
 }
 
 # --- Label Definitions and Category Mapping (Used by the App and PPTX) ---
@@ -96,6 +96,7 @@ def highlight_entities(text, df_entities):
         end = entity['end']
         label = entity['label']
         entity_text = entity['text']
+        # Use monochrome map
         color = entity_color_map.get(label, '#000000')
 
         # Create a span with background color and tooltip
@@ -103,8 +104,8 @@ def highlight_entities(text, df_entities):
         # Replace the original text segment with the highlighted HTML
         highlighted_text = highlighted_text[:start] + highlight_html + highlighted_text[end:]
 
-    # Use a div to mimic the Streamlit input box style for the report
-    return f'<div style="border: 1px solid #FF69B4; padding: 15px; border-radius: 5px; background-color: #FFFAF0; font-family: monospace; white-space: pre-wrap; margin-bottom: 20px;">{highlighted_text}</div>'
+    # Use a div to mimic the Streamlit input box style for the report - now in monochrome
+    return f'<div style="border: 1px solid #AAAAAA; 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):
     """
@@ -162,7 +163,7 @@ def create_topic_word_bubbles(df_topic_data):
         hover_name='word',
         size_max=80,
         title='Topic Word Weights (Bubble Chart)',
-        color_discrete_sequence=px.colors.qualitative.Bold,
+        color_discrete_sequence=px.colors.sequential.Greys, # Using grayscale palette
         labels={
             'x_pos': 'Entity/Word Index',
             'weight': 'Word Weight',
@@ -176,8 +177,8 @@ def create_topic_word_bubbles(df_topic_data):
         xaxis={'tickangle': -45, 'showgrid': False},
         yaxis={'showgrid': True},
         showlegend=True,
-        plot_bgcolor='#FFF0F5',
-        paper_bgcolor='#FFF0F5',
+        plot_bgcolor='#f9f9f9', # Neutral background
+        paper_bgcolor='#f9f9f9', # Neutral background
         height=600,
         margin=dict(t=50, b=100, l=50, r=10),
     )
@@ -253,7 +254,7 @@ def generate_network_graph(df, raw_text):
         showlegend=False,
         marker=dict(
             size=unique_entities['frequency'] * 5 + 10,
-            color=[entity_color_map.get(label, '#cccccc') for label in unique_entities['label']], # 'label' is safe here (local to list comprehension)
+            color=[entity_color_map.get(label, '#cccccc') for label in unique_entities['label']], # Use monochrome map
             line_width=1,
             line_color='black',
             opacity=0.9
@@ -325,13 +326,16 @@ def generate_pptx_report(df, text_input, elapsed_time, df_topic_data, reverse_ca
     # Layout 5: Title and Content (often good for charts)
     chart_layout = prs.slide_layouts[5]
 
-    # 1. Title Slide
+    # 1. Title Slide (Layout 0)
     title_slide_layout = prs.slide_layouts[0]
     slide = prs.slides.add_slide(title_slide_layout)
-    title = slide.shapes.title
-    subtitle = slide.placeholders[1]
-    title.text = "NER & Topic Analysis Report"
-    subtitle.text = f"Source Text Analysis\nGenerated: {time.strftime('%Y-%m-%d %H:%M:%S')}\nProcessing Time: {elapsed_time:.2f} seconds"
+    slide.shapes.title.text = "NER & Topic Analysis Report"
+
+    # FIX: Add safety check for placeholder index 1 (subtitle)
+    if len(slide.placeholders) > 1:
+        subtitle = slide.placeholders[1]
+        subtitle.text = f"Source Text Analysis\nGenerated: {time.strftime('%Y-%m-%d %H:%M:%S')}\nProcessing Time: {elapsed_time:.2f} seconds"
+    # End FIX
 
     # 2. Source Text Slide
     slide = prs.slides.add_slide(chart_layout)
@@ -382,13 +386,6 @@ def generate_pptx_report(df, text_input, elapsed_time, df_topic_data, reverse_ca
         cell.fill.solid()
         # Optional: Add simple styling to header
 
-    # Fill in the data
-    for i in range(rows):
-        for j in range(cols):
-            cell = table.cell(i+1, j)
-            cell.text = str(grouped_entity_table.iloc[i, j])
-            # Optional: Style data cells
-
     # 4. Treemap Slide (Visualization)
     fig_treemap = px.treemap(
         df,
@@ -396,7 +393,7 @@ def generate_pptx_report(df, text_input, elapsed_time, df_topic_data, reverse_ca
         values='score',
         color='category',
         title="Entity Distribution by Category and Label",
-        color_discrete_sequence=px.colors.qualitative.Dark24
+        color_discrete_sequence=px.colors.sequential.Greys # Monochrome palette
     )
     fig_treemap.update_layout(margin=dict(t=50, l=25, r=25, b=25))
     treemap_image = fig_to_image_buffer(fig_treemap)
@@ -409,7 +406,9 @@ def generate_pptx_report(df, text_input, elapsed_time, df_topic_data, reverse_ca
         # Placeholder if image conversion failed (e.g., Kaleido issue)
         slide = prs.slides.add_slide(chart_layout)
         slide.shapes.title.text = "Entity Distribution Treemap (Chart Failed)"
-        slide.placeholders[1].text = "Chart generation failed. Check app logs for Kaleido errors."
+        # FIX: Safety check for placeholder index 1
+        if len(slide.placeholders) > 1:
+            slide.placeholders[1].text = "Chart generation failed. Check app logs for Kaleido errors."
 
 
     # 5. Entity Count Bar Chart Slide (Visualization)
@@ -421,7 +420,7 @@ def generate_pptx_report(df, text_input, elapsed_time, df_topic_data, reverse_ca
         y='Count',
         color='Category',
         title='Total Entities per Category',
-        color_discrete_sequence=px.colors.qualitative.Pastel
+        color_discrete_sequence=px.colors.sequential.Greys # Monochrome palette
     )
     fig_bar_category.update_layout(xaxis={'categoryorder': 'total descending'})
     bar_category_image = fig_to_image_buffer(fig_bar_category)
@@ -433,7 +432,9 @@ def generate_pptx_report(df, text_input, elapsed_time, df_topic_data, reverse_ca
     else:
         slide = prs.slides.add_slide(chart_layout)
         slide.shapes.title.text = "Total Entities per Category (Chart Failed)"
-        slide.placeholders[1].text = "Chart generation failed. Check app logs for Kaleido errors."
+        # FIX: Safety check for placeholder index 1
+        if len(slide.placeholders) > 1:
+            slide.placeholders[1].text = "Chart generation failed. Check app logs for Kaleido errors."
 
 
     # 6. Topic Modeling Bubble Chart Slide
@@ -449,13 +450,17 @@ def generate_pptx_report(df, text_input, elapsed_time, df_topic_data, reverse_ca
         else:
             slide = prs.slides.add_slide(chart_layout)
             slide.shapes.title.text = "Topic Word Weights (Chart Failed)"
-            slide.placeholders[1].text = "Chart generation failed. Check app logs for Kaleido errors."
+            # FIX: Safety check for placeholder index 1
+            if len(slide.placeholders) > 1:
+                slide.placeholders[1].text = "Chart generation failed. Check app logs for Kaleido errors."
 
     else:
         # Placeholder slide if topic modeling is not available
         slide = prs.slides.add_slide(chart_layout)
         slide.shapes.title.text = "Topic Modeling Results"
-        slide.placeholders[1].text = "Topic Modeling requires more unique input (at least two unique entities)."
+        # FIX: Safety check for placeholder index 1
+        if len(slide.placeholders) > 1:
+            slide.placeholders[1].text = "Topic Modeling requires more unique input (at least two unique entities)."
 
     # Save the presentation to an in-memory buffer
     pptx_buffer = BytesIO()
@@ -490,8 +495,8 @@ def generate_html_report(df, text_input, elapsed_time, df_topic_data):
         path=[px.Constant("All Entities"), 'category', 'label', 'text'],
         values='score',
         color='category',
-        title="Entity Distribution by Category and Label",
-        color_discrete_sequence=px.colors.qualitative.Dark24
+        
+        color_discrete_sequence=px.colors.sequential.Greys # Monochrome palette
     )
     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')
@@ -499,12 +504,12 @@ def generate_html_report(df, text_input, elapsed_time, df_topic_data):
     # 1b. Pie Chart
     grouped_counts = df['category'].value_counts().reset_index()
     grouped_counts.columns = ['Category', 'Count']
-    fig_pie = px.pie(grouped_counts, values='Count', names='Category',title='Distribution of Entities by Category',color_discrete_sequence=px.colors.sequential.RdBu)
+    fig_pie = px.pie(grouped_counts, values='Count', names='Category',title='Distribution of Entities by Category',color_discrete_sequence=px.colors.sequential.Greys) # Monochrome palette
     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=px.colors.qualitative.Pastel)
+    fig_bar_category = px.bar(grouped_counts, x='Category', y='Count',color='Category', title='Total Entities per Category',color_discrete_sequence=px.colors.sequential.Greys) # Monochrome palette
     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')
 
@@ -515,7 +520,7 @@ def generate_html_report(df, text_input, elapsed_time, df_topic_data):
     bar_freq_html = '<p>No entities appear more than once in the text for visualization.</p>'
 
     if not repeating_entities.empty:
-        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.Plasma)
+        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.Greys) # Monochrome palette
         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')
 
@@ -524,7 +529,7 @@ def generate_html_report(df, text_input, elapsed_time, df_topic_data):
     network_html = network_fig.to_html(full_html=False, include_plotlyjs='cdn')
 
     # 1f. Topic Charts HTML
-    topic_charts_html = '<h3>Topic Word Weights (Bubble Chart)</h3>'
+    topic_charts_html = '<h3>Bubble size = word weight</h3>'
     if df_topic_data is not None and not df_topic_data.empty:
         bubble_figure = create_topic_word_bubbles(df_topic_data)
         if bubble_figure:
@@ -532,12 +537,13 @@ def generate_html_report(df, text_input, elapsed_time, df_topic_data):
         else:
             topic_charts_html += '<p style="color: red;">Error: Topic modeling data was available but visualization failed.</p>'
     else:
-        topic_charts_html += '<div class="chart-box" style="text-align: center; padding: 50px; background-color: #fff; border: 1px dashed #FF69B4;">'
+        topic_charts_html += '<div class="chart-box" style="text-align: center; padding: 50px; background-color: #fff; border: 1px dashed #AAAAAA;">'
         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
+    # The div style is now monochrome/neutral (border: #AAAAAA, background: #FFFFFF)
     highlighted_text_html = highlight_entities(text_input, df).replace("div style", "div class='highlighted-text' style")
 
     # 3. Entity Tables (Pandas to HTML)
@@ -547,23 +553,24 @@ def generate_html_report(df, text_input, elapsed_time, df_topic_data):
     )
 
     # 4. Construct the Final HTML
+    # Updated CSS to remove all color/pink references
     html_content = f"""<!DOCTYPE html><html lang="en"><head>
     <meta charset="UTF-8">
     <meta name="viewport" content="width=device-width, initial-scale=1.0">
     <title>Entity and Topic Analysis Report</title>
     <script src="https://cdn.plot.ly/plotly-latest.min.js"></script>
     <style>
-        body {{ font-family: 'Inter', sans-serif; margin: 0; padding: 20px; background-color: #f4f4f9; color: #333; }}
+        body {{ font-family: 'Inter', sans-serif; margin: 0; padding: 20px; background-color: #f4f4f4; color: #333; }}
         .container {{ max-width: 1200px; margin: 0 auto; background-color: #ffffff; padding: 30px; border-radius: 12px; box-shadow: 0 4px 12px rgba(0,0,0,0.1); }}
-        h1 {{ color: #FF69B4; border-bottom: 3px solid #FF69B4; padding-bottom: 10px; margin-top: 0; }}
-        h2 {{ color: #007bff; margin-top: 30px; border-bottom: 1px solid #ddd; padding-bottom: 5px; }}
+        h1 {{ color: #333333; border-bottom: 3px solid #666666; padding-bottom: 10px; margin-top: 0; }}
+        h2 {{ color: #555555; margin-top: 30px; border-bottom: 1px solid #ddd; padding-bottom: 5px; }}
         h3 {{ color: #555; margin-top: 20px; }}
-        .metadata {{ background-color: #FFE4E1; padding: 15px; border-radius: 8px; margin-bottom: 20px; font-size: 0.9em; }}
+        .metadata {{ background-color: #eeeeee; padding: 15px; border-radius: 8px; margin-bottom: 20px; font-size: 0.9em; }}
         .chart-box {{ background-color: #f9f9f9; padding: 15px; border-radius: 8px; box-shadow: 0 2px 4px rgba(0,0,0,0.05); min-width: 0; margin-bottom: 20px; }}
         table {{ width: 100%; border-collapse: collapse; margin-top: 15px; }}
         table th, table td {{ border: 1px solid #ddd; padding: 8px; text-align: left; }}
         table th {{ background-color: #f0f0f0; }}
-        .highlighted-text {{ border: 1px solid #FF69B4; padding: 15px; border-radius: 5px; background-color: #FFFAF0; font-family: monospace; white-space: pre-wrap; margin-bottom: 20px; }}
+        .highlighted-text {{ border: 1px solid #AAAAAA; padding: 15px; border-radius: 5px; background-color: #FFFFFF; font-family: monospace; white-space: pre-wrap; margin-bottom: 20px; }}
     </style></head><body>
     <div class="container">
         <h1>Entity and Topic Analysis Report</h1>
@@ -581,13 +588,13 @@ def generate_html_report(df, text_input, elapsed_time, df_topic_data):
         <h2>3. Data Visualizations</h2>
         <h3>3.1 Entity Distribution Treemap</h3>
         <div class="chart-box">{treemap_html}</div>
-        <h3>3.2 Comparative Charts (Pie, Category Count, Frequency) - *Stacked Vertically*</h3>
+        <h3>3.2 Comparative Charts</h3>
         <div class="chart-box">{pie_html}</div>
         <div class="chart-box">{bar_category_html}</div>
         <div class="chart-box">{bar_freq_html}</div>
-        <h3>3.3 Entity Co-occurrence Network (Edges = Same Sentence)</h3>
+        <h3>3.3 Entity Relationship Map</h3>
         <div class="chart-box">{network_html}</div>
-        <h2>4. Topic Modeling (LDA on Entities)</h2>
+        <h2>4. Topic Modelling</h2>
         {topic_charts_html}
     </div></body></html>
     """
@@ -601,21 +608,21 @@ st.markdown(
     <style>
     /* Overall app container - NO SIDEBAR */
     .main {
-        background-color: #FFF0F5; /* Blanched Almond/Light Pink */
+        background-color: #F8F8F8; /* Near White/Lightest Gray */
         color: #333333; /* Dark grey text for contrast */
     }
     .stApp {
-        background-color: #FFF0F5;
+        background-color: #F8F8F8;
     }
     /* Text Area background and text color (input fields) */
     .stTextArea textarea {
-        background-color: #FFFAF0; /* Floral White/Near white for input fields */
+        background-color: #FFFFFF; /* Pure White for input fields */
         color: #000000; /* Black text for input */
-        border: 1px solid #FF69B4; /* Deep Pink border */
+        border: 1px solid #AAAAAA; /* Gray border */
     }
     /* Button styling */
     .stButton > button {
-        background-color: #FF69B4; /* Deep Pink for the button */
+        background-color: #666666; /* Medium Gray for the button */
         color: #FFFFFF; /* White text for contrast */
         border: none;
         padding: 10px 20px;
@@ -623,21 +630,23 @@ st.markdown(
         transition: background-color 0.3s;
     }
     .stButton > button:hover {
-        background-color: #E05C9E; /* Slightly darker pink on hover */
+        background-color: #444444; /* Darker Gray on hover */
     }
     /* Expander header and content background */
     .streamlit-expanderHeader, .streamlit-expanderContent {
-        background-color: #FFE4E1; /* Misty Rose/Lighter Pink */
+        background-color: #EEEEEE; /* Very Light Gray */
         color: #333333;
     }
     </style>
     """,
     unsafe_allow_html=True)
-st.subheader("NER and Topic Analysis Report Generator", divider="rainbow")
+st.subheader("NER and Topic Analysis Report Generator", divider="gray") # Divider is now gray
 st.link_button("by nlpblogs", "https://nlpblogs.com", type="secondary")
 expander = st.expander("**Important notes**")
 expander.write(f"""**Named Entities:** This app predicts fifteen (15) labels: {', '.join(entity_color_map.keys())}.
-""")
+**Dependencies:** Note that **PPTX** and **image export** require the Python libraries `python-pptx`, `plotly`, and `kaleido`. If charts in the PPTX are blank, please check your environment's $\text{kaleido}$ installation/permissions.
+**Results:** Results are compiled into a single, comprehensive **HTML report**, a **PowerPoint (.pptx) file**, and a **CSV file** for easy download and sharing.
+**How to Use:** Type or paste your text into the text area below, then press Ctrl + Enter. Click the 'Results' button to extract entities and generate the report.""")
 st.markdown("For any errors or inquiries, please contact us at [info@nlpblogs.com](mailto:info@nlpblogs.com)")
 
 # --- Comet ML Setup (Placeholder/Conditional) ---