Merge branch #sadickam/document-SDG-App' into 'sadickam/document-SDG-App-cpu'

app.py

@@ -170,7 +170,7 @@ 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, x_axis_title=None, y_axis_title=None, icons_folder='assets/icons/'):
     """
     Plots a horizontal bar graph of SDG predictions and superimposes the icon of the most frequent SDG.
     
@@ -178,6 +178,8 @@ def plot_sdg(df, title, pred_column, icons_folder='assets/icons/'):
         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').
+        x_axis_title (str): Title for the x-axis.
+        y_axis_title (str): Title for the y-axis.
         icons_folder (str): Path to the folder containing SDG icons.
     
     Returns:
@@ -206,7 +208,7 @@ def plot_sdg(df, title, pred_column, icons_folder='assets/icons/'):
     fig.update_traces(
         texttemplate='%{x:.2f}%',
         textposition='auto',
-        textfont=dict(size=10)
+        textfont=dict(size=11)
     )
 
     # Adjust layout for better visibility
@@ -216,16 +218,17 @@ def plot_sdg(df, title, pred_column, icons_folder='assets/icons/'):
         ),
         yaxis=dict(
             automargin=True,
-            title=None,
-            tickfont=dict(size=12)
+            title=y_axis_title,
+            tickfont=dict(size=13)
         ),
-        margin=dict(l=20, r=30, t=100, b=20),  # Increased right margin for icon
+        margin=dict(l=20, r=100, t=30, b=20),  # Increased right margin for icon
         height=600,
-        #width=800, 
+        #width=800,
         showlegend=False,
         template="simple_white",
         xaxis=dict(
-            tickfont=dict(size=12)  # Reduce x-axis font size
+            title=x_axis_title,
+            tickfont=dict(size=13)  # Reduce x-axis font size
         ),
     )
 
@@ -250,7 +253,7 @@ def plot_sdg(df, title, pred_column, icons_folder='assets/icons/'):
                 dict(
                     source='data:image/png;base64,' + encoded_image,
                     xref="paper", yref="paper",
-                    x=0.4, y=1.2,  # Positioning: slightly to the right and top
+                    x=.98, y=1.0,  # Positioning: slightly to the right and top
                     sizex=0.2, sizey=0.2,  # Size of the icon
                     xanchor="left",
                     yanchor="top",
@@ -264,7 +267,7 @@ 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=1200, height=600, scale=6)
+    pio.write_image(fig, filename, format='jpeg', width=700, height=650, scale=7, engine="kaleido")
 
 # Generate reports (page and sentence levels)
 def generate_page_report(df_pages, report_file_name):
@@ -306,10 +309,17 @@ 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(
-            first_sdg_plot_path, format='jpeg', scale=7, engine="kaleido")
-        plot_sdg(df_doc, "Secondary SDGs", 'pred2').write_image(
-            second_sdg_plot_path, format='jpeg', scale=7, engine="kaleido")
+        plot_sdg(
+            df_doc, "", 'pred1',
+            x_axis_title="Percentage (%) of aligned pages",
+            y_axis_title="Primary SDGs"
+        ).write_image(first_sdg_plot_path, format='jpeg', scale=7, engine="kaleido")
+        
+        plot_sdg(
+            df_doc, "", 'pred2',
+            x_axis_title="Percentage (%) of aligned pages",
+            y_axis_title="Secondary SDGs"
+        ).write_image(second_sdg_plot_path, format='jpeg', scale=7, engine="kaleido")
 
         # Add plots to the Word document
         doc.add_picture(first_sdg_plot_path, width=Inches(6))
@@ -358,10 +368,17 @@ 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(
-            first_sdg_plot_path, format='jpeg', scale=7, engine="kaleido")
-        plot_sdg(df_doc, "Secondary SDGs", 'pred2').write_image(
-            second_sdg_plot_path, format='jpeg', scale=7, engine="kaleido")
+        plot_sdg(
+            df_doc, "", 'pred1',
+            x_axis_title="Percentage (%) of aligned sentences",
+            y_axis_title="Primary SDGs"
+        ).write_image(first_sdg_plot_path, format='jpeg', scale=7, engine="kaleido")
+
+        plot_sdg(
+            df_doc, "", 'pred2',
+            x_axis_title="Percentage (%) of aligned sentences",
+            y_axis_title="Secondary SDGs"
+        ).write_image(second_sdg_plot_path, format='jpeg', scale=7, engine="kaleido")
 
         # Add plots to the Word document
         doc.add_picture(first_sdg_plot_path, width=Inches(6))
@@ -546,7 +563,7 @@ 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.",
+                            "SDG will be highlighted on the graph. Download the Page Predictions CVS for further details.",
                             label = "Note", container=True
                         )
                         
@@ -594,7 +611,7 @@ 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.",
+                            "SDG will be highlighted on the graph. Download the Sentence Predictions CVS for further details.",
                             label = "Note", container=True
                         )
                         
@@ -662,10 +679,16 @@ def launch_interface():
 
                 # Generate plots with icon overlay
                 first_plot = plot_sdg(
-                    df_page_predictions, "📊 Primary SDGs", 'pred1'
+                    df_page_predictions, "",
+                    'pred1',
+                    x_axis_title="Percentage (%) of aligned pages",
+                    y_axis_title="Primary SDGs"
                 )
                 second_plot = plot_sdg(
-                    df_page_predictions, "📈 Secondary SDGs", 'pred2'
+                    df_page_predictions, "",
+                    'pred2',
+                    x_axis_title="Percentage (%) of aligned pages",
+                    y_axis_title="Secondary SDGs"
                 )
 
                 # Define output file names
@@ -740,10 +763,16 @@ def launch_interface():
 
                 # Generate plots with icon overlay
                 first_plot = plot_sdg(
-                    df_sentence_predictions, "📊 Primary SDGs", 'pred1'
+                    df_sentence_predictions, "",
+                    'pred1',
+                    x_axis_title="Percentage (%) of aligned sentences",
+                    y_axis_title="Primary SDGs"
                 )
                 second_plot = plot_sdg(
-                    df_sentence_predictions, "📈 Secondary SDGs", 'pred2'
+                    df_sentence_predictions, "",
+                    'pred2',
+                    x_axis_title="Percentage (%) of aligned sentences",
+                    y_axis_title="Secondary SDGs"
                 )
 
                 # Define output file names