Update app.py

app.py

@@ -168,6 +168,7 @@ sdg_colors = {
     "SDG16_Peace, Justice and Strong Institutions": "#00689D"
 }
 
+# Function to plot SDG dominant bar graphs using Plotly
 # Function to plot SDG dominant bar graphs using Plotly
 def plot_sdg(df, title, pred_column, icons_folder='assets/icons/'):
     """
@@ -218,9 +219,9 @@ def plot_sdg(df, title, pred_column, icons_folder='assets/icons/'):
             title=None,
             tickfont=dict(size=12)
         ),
-        margin=dict(l=20, r=150, t=30, b=20),  # Increased right margin for icon
+        margin=dict(l=20, r=30, t=100, b=20),  # Increased right margin for icon
         height=600,
-        width=600,  # Increased width to accommodate the icon
+        width=800, 
         showlegend=False,
         template="simple_white",
         xaxis=dict(
@@ -249,7 +250,7 @@ def plot_sdg(df, title, pred_column, icons_folder='assets/icons/'):
                 dict(
                     source='data:image/png;base64,' + encoded_image,
                     xref="paper", yref="paper",
-                    x=0.5, y=1.05,  # Positioning: slightly to the right and top
+                    x=0.4, y=1.2,  # Positioning: slightly to the right and top
                     sizex=0.2, sizey=0.2,  # Size of the icon
                     xanchor="left",
                     yanchor="top",
@@ -263,7 +264,7 @@ def plot_sdg(df, title, pred_column, icons_folder='assets/icons/'):
 
 def save_figure_as_jpeg(fig, filename):
     """Saves the Plotly figure as a high-resolution JPEG."""
-    pio.write_image(fig, filename, format='jpeg', width=1000, height=600, scale=5)
+    pio.write_image(fig, filename, format='jpeg', width=900, height=600, scale=6)
 
 # Generate reports (page and sentence levels)
 def generate_page_report(df_pages, report_file_name):
@@ -471,12 +472,12 @@ def df_to_csv_bytes(df):
         raise RuntimeError(f"Error during CSV conversion: {e}")
 
 def launch_interface():
-    with gr.Blocks(title="SDG Document Analysis App", css=custom_css) as demo:
+    with gr.Blocks(css=custom_css) as demo:
 
         # Title as a visible heading at the top of the page with an icon
         gr.Markdown(
             """
-            # 🌍 SDG Document Analysis App  
+            # 🌍 SDG Document Analysis App - CPU  
             Analyze documents to map Sustainable Development Goals (SDGs) at both page and sentence levels.
             """
         )
@@ -490,7 +491,7 @@ def launch_interface():
         # Extraction mode selection with explanatory text
         gr.Markdown(
             """
-            ### 📋 PDF Text Extraction Mode  
+            ## PDF Text Extraction Mode  
             Choose whether to analyze all pages or a specific range of pages. If you want to exclude certain pages from the analysis, select "Range of Pages" and specify the start and end pages.
             """
         )
@@ -518,61 +519,77 @@ def launch_interface():
             outputs=[start_page, end_page]
         )
 
-        # Tabs for page-level and sentence-level analysis
+        # Main Tabs for Page-Level and Sentence-Level Analysis
+        gr.Markdown("## SDG Analysis Type")
+        
         with gr.Tab("📄 Page-Level Analysis"):
             gr.Markdown(
                 """
-                ### 📄 Page-Level SDG Analysis  
+                ### Page-Level SDG Analysis  
                 This section conducts Sustainable Development Goals (SDG) mapping 
                 of documents using the [sdgBERT model](https://huggingface.co/sadickam/sdgBERT). 
                 It provides **high-level SDG mapping** of documents at the page level.
                 """
             )
-            with gr.Row():
-                with gr.Column():
+            # Nested Tabs for Primary and Secondary SDGs
+            with gr.Tabs():
+                with gr.TabItem("📊 Primary SDGs"):
                     primary_page_plot = gr.Plot(label="📊 Primary SDGs [Page-Level]")
-                with gr.Column():
+
+                    with gr.Row():
+                        page_csv = gr.File(label="📊 Download Page Predictions CSV")
+                        page_docx = gr.File(label="📄 Download Page Report DOCX")
+                        page_jpeg1 = gr.File(label="🖼️ Download Primary SDGs JPEG")
+
+                with gr.TabItem("📈 Secondary SDGs"):
                     secondary_page_plot = gr.Plot(label="📈 Secondary SDGs [Page-Level]")
 
-            with gr.Row():
-                page_csv = gr.File(label="📊 Download Page Predictions CSV")
-                page_docx = gr.File(label="📄 Download Page Report DOCX")
-                page_jpeg1 = gr.File(label="🖼️ Download Primary SDGs JPEG")
-                page_jpeg2 = gr.File(label="🖼️ Download Secondary SDGs JPEG")
+                    with gr.Row():
+                        page_csv_secondary = gr.File(label="📊 Download Page Predictions CSV")
+                        page_report_file_secondary = gr.File(label="📄 Download Page Report DOCX")
+                        secondary_page_jpeg = gr.File(label="🖼️ Download Secondary SDGs JPEG")
 
-            page_button = gr.Button("🏃‍♂️ Run Page-Level Analysis")
-            reset_page_button = gr.Button("🔄 Reset Page-Level Analysis")
+            with gr.Row():
+                page_button = gr.Button("🏃‍♂️ Run Page-Level Analysis")
+                reset_page_button = gr.Button("🔄 Reset Page-Level Analysis", elem_classes="reset-button")
 
         with gr.Tab("✍️ Sentence-Level Analysis"):
             gr.Markdown(
                 """
-                ### ✍️ Sentence-Level SDG Analysis  
+                ### Sentence-Level SDG Analysis  
                 This section conducts Sustainable Development Goals (SDG) mapping 
                 using the [sdgBERT model](https://huggingface.co/sadickam/sdgBERT). 
-                It provides **detailed SDG mapping** at the sentence level. **Note that 
-                all sentences under 70 characters are excluded from the analysis.**
+                It provides **detailed SDG mapping** at the sentence level.
                 """
             )
-            with gr.Row():
-                with gr.Column():
+            # Nested Tabs for Primary and Secondary SDGs
+            with gr.Tabs():
+                with gr.TabItem("📊 Primary SDGs"):
                     primary_sentence_plot = gr.Plot(label="📊 Primary SDGs [Sentence-Level]")
-                with gr.Column():
+
+                    with gr.Row():
+                        sentence_csv = gr.File(label="📊 Download Sentence Predictions CSV")
+                        sentence_docx = gr.File(label="📄 Download Sentence Report DOCX")
+                        sentence_jpeg1 = gr.File(label="🖼️ Download Primary SDGs JPEG")
+
+                with gr.TabItem("📈 Secondary SDGs"):
                     secondary_sentence_plot = gr.Plot(label="📈 Secondary SDGs [Sentence-Level]")
 
-            with gr.Row():
-                sentence_csv = gr.File(label="📊 Download Sentence Predictions CSV")
-                sentence_docx = gr.File(label="📄 Download Sentence Report DOCX")
-                sentence_jpeg1 = gr.File(label="🖼️ Download Primary SDGs JPEG")
-                sentence_jpeg2 = gr.File(label="🖼️ Download Secondary SDGs JPEG")
+                    with gr.Row():
+                        sentence_csv_secondary = gr.File(label="📊 Download Sentence Predictions CSV")
+                        sentence_report_file_secondary = gr.File(label="📄 Download Sentence Report DOCX")
+                        secondary_sentence_jpeg = gr.File(label="🖼️ Download Secondary SDGs JPEG")
 
-            sentence_button = gr.Button("🏃‍♂️ Run Sentence-Level Analysis")
-            reset_sentence_button = gr.Button("🔄 Reset Sentence-Level Analysis")
+            with gr.Row():
+                sentence_button = gr.Button("🏃‍♂️ Run Sentence-Level Analysis")
+                reset_sentence_button = gr.Button("🔄 Reset Sentence-Level Analysis", elem_classes="reset-button")
 
         # Function to process page-level analysis
         @spaces.GPU
         def process_pages(file, extraction_mode, start_page, end_page):
             if not file:
-                return None, None, None, None, None, None
+                # Return None for each output component
+                return [None, None, None, None, None, None, None, None]
 
             try:
                 if hasattr(file, 'name'):
@@ -607,6 +624,7 @@ def launch_interface():
                 # Predict SDGs at page level
                 df_page_predictions = predict_pages(page_df)
 
+                # Generate plots with icon overlay
                 first_plot = plot_sdg(
                     df_page_predictions, "📊 Primary SDGs", 'pred1'
                 )
@@ -615,31 +633,41 @@ def launch_interface():
                 )
 
                 # Define output file names
-                page_csv_file = f"{sanitized_file_name}_page_predictions.csv"
-                page_report_file = f"{sanitized_file_name}_page_report.docx"
+                page_csv_file = f"{sanitized_file_name}_page_predictions_primary.csv"
+                page_report_file = f"{sanitized_file_name}_page_report_primary.docx"
                 primary_page_jpeg = f"{sanitized_file_name}_primary_page.jpeg"
+
+                page_csv_file_secondary = f"{sanitized_file_name}_page_predictions_secondary.csv"
+                page_report_file_secondary = f"{sanitized_file_name}_page_report_secondary.docx"
                 secondary_page_jpeg = f"{sanitized_file_name}_secondary_page.jpeg"
 
+                # Save CSV and reports
                 df_page_predictions.to_csv(page_csv_file, index=False)
-                page_report = generate_page_report(df_page_predictions, page_report_file)
+                page_report_primary = generate_page_report(df_page_predictions, page_report_file)
+
+                df_page_predictions.to_csv(page_csv_file_secondary, index=False)
+                page_report_secondary = generate_page_report(df_page_predictions, page_report_file_secondary)
 
                 # Save figures as JPEG
                 save_figure_as_jpeg(first_plot, primary_page_jpeg)
                 save_figure_as_jpeg(second_plot, secondary_page_jpeg)
 
                 return (
-                    first_plot, second_plot, page_csv_file, page_report_file, 
-                    primary_page_jpeg, secondary_page_jpeg)
+                    first_plot, second_plot,
+                    page_csv_file, page_report_file, primary_page_jpeg,
+                    page_csv_file_secondary, page_report_file_secondary, secondary_page_jpeg
+                )
 
             except Exception as e:
                 print(f"Error: {e}")
-                return None, None, None, None, None, None
+                return [None, None, None, None, None, None, None, None]
 
         # Function to process sentence-level analysis
         @spaces.GPU
         def process_sentences(file, extraction_mode, start_page, end_page):
             if not file:
-                return None, None, None, None, None, None
+                # Return None for each output component
+                return [None, None, None, None, None, None, None, None]
 
             try:
                 if hasattr(file, 'name'):
@@ -674,6 +702,7 @@ def launch_interface():
                 # Predict SDGs at sentence level
                 df_sentence_predictions = predict_sentences(sentence_df)
 
+                # Generate plots with icon overlay
                 first_plot = plot_sdg(
                     df_sentence_predictions, "📊 Primary SDGs", 'pred1'
                 )
@@ -682,59 +711,100 @@ def launch_interface():
                 )
 
                 # Define output file names
-                sentence_csv_file = f"{sanitized_file_name}_sentence_predictions.csv"
-                sentence_report_file = f"{sanitized_file_name}_sentence_report.docx"
+                sentence_csv_file = f"{sanitized_file_name}_sentence_predictions_primary.csv"
+                sentence_report_file = f"{sanitized_file_name}_sentence_report_primary.docx"
                 primary_sentence_jpeg = f"{sanitized_file_name}_primary_sentence.jpeg"
+
+                sentence_csv_file_secondary = f"{sanitized_file_name}_sentence_predictions_secondary.csv"
+                sentence_report_file_secondary = f"{sanitized_file_name}_sentence_report_secondary.docx"
                 secondary_sentence_jpeg = f"{sanitized_file_name}_secondary_sentence.jpeg"
 
+                # Save CSV and reports
                 df_sentence_predictions.to_csv(sentence_csv_file, index=False)
-                sentence_report = generate_sentence_report(df_sentence_predictions, sentence_report_file)
+                sentence_report_primary = generate_sentence_report(df_sentence_predictions, sentence_report_file)
+
+                df_sentence_predictions.to_csv(sentence_csv_file_secondary, index=False)
+                sentence_report_secondary = generate_sentence_report(df_sentence_predictions, sentence_report_file_secondary)
 
                 # Save figures as JPEG
                 save_figure_as_jpeg(first_plot, primary_sentence_jpeg)
                 save_figure_as_jpeg(second_plot, secondary_sentence_jpeg)
 
                 return (
-                    first_plot, second_plot, sentence_csv_file, sentence_report_file, 
-                    primary_sentence_jpeg, secondary_sentence_jpeg)
+                    first_plot, second_plot,
+                    sentence_csv_file, sentence_report_file, primary_sentence_jpeg,
+                    sentence_csv_file_secondary, sentence_report_file_secondary, secondary_sentence_jpeg
+                )
 
             except Exception as e:
                 print(f"Error: {e}")
-                return None, None, None, None, None, None
+                return [None, None, None, None, None, None, None, None]
 
         # Reset functions to clear the outputs
         def reset_page_outputs():
-            return None, None, None, None, None, None
+            return [None, None, None, None, None, None, None, None]
 
         def reset_sentence_outputs():
-            return None, None, None, None, None, None
+            return [None, None, None, None, None, None, None, None]
 
-        # Button actions for each tab
+        # Button actions for Page-Level Analysis
         page_button.click(
             process_pages,
             inputs=[file_input, extraction_mode, start_page, end_page],
-            outputs=[primary_page_plot, secondary_page_plot, page_csv, page_docx,
-                    page_jpeg1, page_jpeg2]
+            outputs=[
+                primary_page_plot,           # 📊 Primary SDGs [Page-Level]
+                secondary_page_plot,         # 📈 Secondary SDGs [Page-Level]
+                page_csv,                    # 📊 Download Page Predictions CSV
+                page_docx,                   # 📄 Download Page Report DOCX
+                page_jpeg1,                  # 🖼️ Download Primary SDGs JPEG
+                page_csv_secondary,          # 📊 Download Page Predictions CSV (Secondary)
+                page_report_file_secondary,  # 📄 Download Page Report DOCX (Secondary)
+                secondary_page_jpeg          # 🖼️ Download Secondary SDGs JPEG
+            ]
+        )
+
+        reset_page_button.click(
+            reset_page_outputs,
+            outputs=[
+                primary_page_plot,
+                secondary_page_plot,
+                page_csv,
+                page_docx,
+                page_jpeg1,
+                page_csv_secondary,
+                page_report_file_secondary,
+                secondary_page_jpeg
+            ]
         )
 
+        # Button actions for Sentence-Level Analysis
         sentence_button.click(
             process_sentences,
             inputs=[file_input, extraction_mode, start_page, end_page],
-            outputs=[primary_sentence_plot, secondary_sentence_plot, sentence_csv, sentence_docx,
-                    sentence_jpeg1, sentence_jpeg2]
-        )
-
-        # Reset button actions to clear outputs
-        reset_page_button.click(
-            reset_page_outputs,
-            outputs=[primary_page_plot, secondary_page_plot, page_csv, page_docx,
-                    page_jpeg1, page_jpeg2]
+            outputs=[
+                primary_sentence_plot,           # 📊 Primary SDGs [Sentence-Level]
+                secondary_sentence_plot,         # 📈 Secondary SDGs [Sentence-Level]
+                sentence_csv,                    # 📊 Download Sentence Predictions CSV
+                sentence_docx,                   # 📄 Download Sentence Report DOCX
+                sentence_jpeg1,                  # 🖼️ Download Primary SDGs JPEG
+                sentence_csv_secondary,          # 📊 Download Sentence Predictions CSV (Secondary)
+                sentence_report_file_secondary,  # 📄 Download Sentence Report DOCX (Secondary)
+                secondary_sentence_jpeg          # 🖼️ Download Secondary SDGs JPEG
+            ]
         )
 
         reset_sentence_button.click(
             reset_sentence_outputs,
-            outputs=[primary_sentence_plot, secondary_sentence_plot, sentence_csv, sentence_docx,
-                    sentence_jpeg1, sentence_jpeg2]
+            outputs=[
+                primary_sentence_plot,
+                secondary_sentence_plot,
+                sentence_csv,
+                sentence_docx,
+                sentence_jpeg1,
+                sentence_csv_secondary,
+                sentence_report_file_secondary,
+                secondary_sentence_jpeg
+            ]
         )
 
     demo.queue().launch()