Update app.py

app.py

@@ -169,17 +169,18 @@ sdg_colors = {
 }
 
 # 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/'):
+def plot_sdg(df, title, pred_column, analysis_level, sdg_type, icons_folder='assets/icons/'):
     """
-    Plots a horizontal bar graph of SDG predictions and superimposes the icon of the most frequent SDG.
-    
+    Plots a horizontal bar graph of SDG predictions and superimposes the icon of the most frequent SDG at the center.
+
     Args:
         df (pd.DataFrame): DataFrame containing SDG predictions.
         title (str): Title of the plot.
         pred_column (str): Column name to use for plotting (e.g., 'pred1').
+        analysis_level (str): Level of analysis ('pages' or 'sentences').
+        sdg_type (str): Type of SDG analysis ('primary' or 'secondary').
         icons_folder (str): Path to the folder containing SDG icons.
-    
+
     Returns:
         plotly.graph_objs._figure.Figure: The Plotly figure object.
     """
@@ -209,6 +210,9 @@ def plot_sdg(df, title, pred_column, icons_folder='assets/icons/'):
         textfont=dict(size=10)
     )
 
+    # Construct dynamic x-axis title
+    xaxis_title = f"Percentage of {analysis_level} aligned with {sdg_type.capitalize()} SDGs"
+
     # Adjust layout for better visibility
     fig.update_layout(
         title=dict(
@@ -219,14 +223,15 @@ def plot_sdg(df, title, pred_column, icons_folder='assets/icons/'):
             title=None,
             tickfont=dict(size=12)
         ),
-        margin=dict(l=20, r=30, t=100, b=20),  # Increased right margin for icon
+        xaxis=dict(
+            title=xaxis_title,            # Dynamic x-axis title
+            tickfont=dict(size=12)        # Reduce x-axis font size
+        ),
+        margin=dict(l=20, r=30, t=100, b=20),  # Adjusted margins
         height=600,
         #width=800, 
         showlegend=False,
         template="simple_white",
-        xaxis=dict(
-            tickfont=dict(size=12)  # Reduce x-axis font size
-        ),
     )
 
     # Identify the most frequent SDG
@@ -250,10 +255,10 @@ def plot_sdg(df, title, pred_column, icons_folder='assets/icons/'):
                 dict(
                     source='data:image/png;base64,' + encoded_image,
                     xref="paper", yref="paper",
-                    x=0.4, y=1.2,  # Positioning: slightly to the right and top
-                    sizex=0.2, sizey=0.2,  # Size of the icon
-                    xanchor="left",
-                    yanchor="top",
+                    x=0.3, y=1.2,  # Center of the plot
+                    sizex=0.2, sizey=0.2,  # Adjust size as needed
+                    xanchor="center",
+                    yanchor="middle",
                     layer="above"  # Ensure the icon is above other plot elements
                 )
             )
@@ -306,9 +311,9 @@ def generate_page_report(df_pages, report_file_name):
         first_sdg_plot_path = f"{sanitized_doc_name}_first_sdg_page.jpeg"
         second_sdg_plot_path = f"{sanitized_doc_name}_second_sdg_page.jpeg"
 
-        plot_sdg(df_doc, "Primary SDGs", 'pred1').write_image(
+        plot_sdg(df_doc, "Primary SDGs", 'pred1', analysis_level='pages', sdg_type='primary').write_image(
             first_sdg_plot_path, format='jpeg', scale=7, engine="kaleido")
-        plot_sdg(df_doc, "Secondary SDGs", 'pred2').write_image(
+        plot_sdg(df_doc, "Secondary SDGs", 'pred2', analysis_level='pages', sdg_type='secondary').write_image(
             second_sdg_plot_path, format='jpeg', scale=7, engine="kaleido")
 
         # Add plots to the Word document
@@ -358,9 +363,9 @@ def generate_sentence_report(df_sentences, report_file_name):
         first_sdg_plot_path = f"{sanitized_doc_name}_first_sdg_sentence.jpeg"
         second_sdg_plot_path = f"{sanitized_doc_name}_second_sdg_sentence.jpeg"
 
-        plot_sdg(df_doc, "Primary SDGs", 'pred1').write_image(
+        plot_sdg(df_doc, "Primary SDGs", 'pred1', analysis_level='sentences', sdg_type='primary').write_image(
             first_sdg_plot_path, format='jpeg', scale=7, engine="kaleido")
-        plot_sdg(df_doc, "Secondary SDGs", 'pred2').write_image(
+        plot_sdg(df_doc, "Secondary SDGs", 'pred2', analysis_level='sentences', sdg_type='secondary').write_image(
             second_sdg_plot_path, format='jpeg', scale=7, engine="kaleido")
 
         # Add plots to the Word document
@@ -521,9 +526,10 @@ def launch_interface():
             outputs=[start_page, end_page]
         )
 
-        # Main Tabs for Page-Level and Sentence-Level Analysis
+        # SDG Analysis Type Section
         gr.Markdown("## SDG Analysis Type")
-        
+
+        # Main Tabs for Page-Level and Sentence-Level Analysis
         with gr.Tab("📄 Page-Level Analysis"):
             gr.Markdown(
                 """
@@ -546,10 +552,10 @@ def launch_interface():
                         gr.Markdown(
                             "When the analysis is done, the Primary SDGs bar graph on the left will show "+
                             "the percentage of pages that strongly align with each SDG. The icon for the most frequent "+
-                            "SDG will be highlighted above the graph. Download the Page Predictions CVS for further details.",
-                            label = "Note", container=True
+                            "SDG will be highlighted above the graph. Download the Page Predictions CSV for further details.",
+                            label="Note", container=True
                         )
-                        
+                    
                     gr.Markdown("##### Download Results")    
                     with gr.Row():
                         page_csv = gr.File(label="📊 Download Page Predictions CSV")
@@ -562,8 +568,8 @@ def launch_interface():
                         gr.Markdown(
                             "When the analysis is done, the Secondary SDGs bar graph on the left will show "+
                             "SDGs that are not the primary focus of the pages analysed. These SDGs are second to the "+
-                            "Primary SDGs. Download the Sentence Predictions CVS for further details",
-                            label = "Note", container=True
+                            "Primary SDGs. Download the Page Predictions CSV for further details.",
+                            label="Note", container=True
                         )
                     
                     gr.Markdown("##### Download Results") 
@@ -594,10 +600,10 @@ def launch_interface():
                         gr.Markdown(
                             "When the analysis is done, the Primary SDGs bar graph on the left will show "+
                             "the percentage of sentences that strongly align with each SDG. The icon for the most frequent "+
-                            "SDG will be highlighted above the graph. Download the Sentence Predictions CVS for further details.",
-                            label = "Note", container=True
+                            "SDG will be highlighted above the graph. Download the Sentence Predictions CSV for further details.",
+                            label="Note", container=True
                         )
-                        
+                    
                     gr.Markdown("##### Download Results")  
                     with gr.Row():
                         sentence_csv = gr.File(label="📊 Download Sentence Predictions CSV")
@@ -610,10 +616,10 @@ def launch_interface():
                         gr.Markdown(
                             "When the analysis is done, the Secondary SDGs bar graph on the left will show "+
                             "SDGs that are not the primary focus of the sentences analysed. These SDGs are second to the "+
-                            "Primary SDGs. Download the Sentence Predictions CVS for further details",
-                            label = "Note", container=True
+                            "Primary SDGs. Download the Sentence Predictions CSV for further details.",
+                            label="Note", container=True
                         )
-                        
+                    
                     gr.Markdown("##### Download Results")  
                     with gr.Row():
                         sentence_csv_secondary = gr.File(label="📊 Download Sentence Predictions CSV")
@@ -662,10 +668,18 @@ def launch_interface():
 
                 # Generate plots with icon overlay
                 first_plot = plot_sdg(
-                    df_page_predictions, "📊 Primary SDGs", 'pred1'
+                    df_page_predictions, 
+                    "📊 Primary SDGs", 
+                    'pred1',
+                    analysis_level='pages',      # Specify analysis level
+                    sdg_type='primary'           # Specify SDG type
                 )
                 second_plot = plot_sdg(
-                    df_page_predictions, "📈 Secondary SDGs", 'pred2'
+                    df_page_predictions, 
+                    "📈 Secondary SDGs", 
+                    'pred2',
+                    analysis_level='pages',      # Specify analysis level
+                    sdg_type='secondary'         # Specify SDG type
                 )
 
                 # Define output file names
@@ -689,9 +703,14 @@ def launch_interface():
                 save_figure_as_jpeg(second_plot, secondary_page_jpeg)
 
                 return (
-                    first_plot, second_plot,
-                    page_csv_file, page_report_file, primary_page_jpeg,
-                    page_csv_file_secondary, page_report_file_secondary, 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:
@@ -740,10 +759,18 @@ def launch_interface():
 
                 # Generate plots with icon overlay
                 first_plot = plot_sdg(
-                    df_sentence_predictions, "📊 Primary SDGs", 'pred1'
+                    df_sentence_predictions, 
+                    "📊 Primary SDGs", 
+                    'pred1',
+                    analysis_level='sentences',    # Specify analysis level
+                    sdg_type='primary'             # Specify SDG type
                 )
                 second_plot = plot_sdg(
-                    df_sentence_predictions, "📈 Secondary SDGs", 'pred2'
+                    df_sentence_predictions, 
+                    "📈 Secondary SDGs", 
+                    'pred2',
+                    analysis_level='sentences',    # Specify analysis level
+                    sdg_type='secondary'           # Specify SDG type
                 )
 
                 # Define output file names
@@ -767,9 +794,14 @@ def launch_interface():
                 save_figure_as_jpeg(second_plot, secondary_sentence_jpeg)
 
                 return (
-                    first_plot, second_plot,
-                    sentence_csv_file, sentence_report_file, primary_sentence_jpeg,
-                    sentence_csv_file_secondary, sentence_report_file_secondary, 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:
@@ -778,10 +810,10 @@ def launch_interface():
 
         # Reset functions to clear the outputs
         def reset_page_outputs():
-            return [None, None, None, None, None, None, None, None]
+            return [None] * 8
 
         def reset_sentence_outputs():
-            return [None, None, None, None, None, None, None, None]
+            return [None] * 8
 
         # Button actions for Page-Level Analysis
         page_button.click(
@@ -793,7 +825,7 @@ def launch_interface():
                 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
+                page_csv_file_secondary,     # 📊 Download Page Predictions CSV
                 page_report_file_secondary,  # 📄 Download Page Report DOCX
                 secondary_page_jpeg          # 🖼️ Download Secondary SDGs JPEG
             ]
@@ -807,7 +839,7 @@ def launch_interface():
                 page_csv,
                 page_docx,
                 page_jpeg1,
-                page_csv_secondary,
+                page_csv_file_secondary,
                 page_report_file_secondary,
                 secondary_page_jpeg
             ]
@@ -823,7 +855,7 @@ def launch_interface():
                 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
+                sentence_csv_file_secondary,     # 📊 Download Sentence Predictions CSV
                 sentence_report_file_secondary,  # 📄 Download Sentence Report DOCX
                 secondary_sentence_jpeg          # 🖼️ Download Secondary SDGs JPEG
             ]
@@ -837,7 +869,7 @@ def launch_interface():
                 sentence_csv,
                 sentence_docx,
                 sentence_jpeg1,
-                sentence_csv_secondary,
+                sentence_csv_file_secondary,
                 sentence_report_file_secondary,
                 secondary_sentence_jpeg
             ]