Update app.py

app.py

@@ -287,35 +287,55 @@ def fDistancePlot(text2Party):
         plt.tight_layout()
     return safe_plot(plot_func)
 
-# --- Updated DispersionPlot without passing 'ax' ---
 def DispersionPlot(textParty):
     """Generates the word dispersion plot."""
     buf = None # Initialize buffer
     try:
         word_tokens_party = word_tokenize(textParty)
+        print(f"Debug DispersionPlot: Total tokens: {len(word_tokens_party)}") # Debug print
         if not word_tokens_party:
             print("Warning: No tokens found for dispersion plot.")
             return None
 
         moby = Text(word_tokens_party)
         fdistance = FreqDist(word_tokens_party)
-        # Get top 5 words, handle potential IndexError if less than 5 unique words
-        common_words = fdistance.most_common(6)
-        if len(common_words) < 5:
-            word_Lst = [word for word, _ in common_words]
+        print(f"Debug DispersionPlot: FreqDist sample: {list(fdistance.most_common(10))}") # Debug print
+
+        # --- Improved word selection logic ---
+        # Get common words, excluding very short words which might be punctuation/non-informative
+        # or words that dispersion_plot might have trouble with.
+        common_words_raw = fdistance.most_common(15) # Check a few more common words
+        # Filter: length > 2, isalpha (to avoid punctuation), not just digits
+        common_words_filtered = [(word, freq) for word, freq in common_words_raw if len(word) > 2 and word.isalpha() and not word.isdigit()]
+        print(f"Debug DispersionPlot: Filtered common words: {common_words_filtered}") # Debug print
+
+        # Select top 5 from filtered list
+        if len(common_words_filtered) < 5:
+            word_Lst = [word for word, _ in common_words_filtered]
         else:
-            word_Lst = [common_words[x][0] for x in range(5)]
-
-        if not word_Lst:
-            print("Warning: No common words found for dispersion plot.")
-            return None
-
-        # --- Manage figure explicitly without passing 'ax' ---
-        fig = plt.figure(figsize=(10, 5)) # Create figure explicitly
-        plt.title('Dispersion Plot')
-        # Call dispersion_plot without 'ax' argument
-        moby.dispersion_plot(word_Lst)
-        plt.tight_layout()
+            word_Lst = [common_words_filtered[x][0] for x in range(5)]
+
+        # Final check: Ensure words are present in the Text object (moby)
+        # This is crucial for dispersion_plot
+        final_word_list = [word for word in word_Lst if word in moby] # Check membership in the Text object
+        print(f"Debug DispersionPlot: Final word list for plot: {final_word_list}") # Debug print
+
+        if not final_word_list:
+            print("Warning: No suitable words found for dispersion plot after filtering and checking membership.")
+            # Create a simple plot indicating no data
+            fig, ax = plt.subplots(figsize=(8, 3))
+            ax.text(0.5, 0.5, "No suitable words found for dispersion plot", ha='center', va='center', transform=ax.transAxes)
+            ax.set_xlim(0, 1)
+            ax.set_ylim(0, 1)
+            ax.axis('off') # Hide axes for the message
+            fig.suptitle('Dispersion Plot')
+        else:
+            # --- Manage figure explicitly without passing 'ax' ---
+            fig = plt.figure(figsize=(10, 5)) # Create figure explicitly
+            plt.title('Dispersion Plot')
+            # Call dispersion_plot with the verified word list
+            moby.dispersion_plot(final_word_list)
+            plt.tight_layout()
 
         buf = BytesIO()
         # Handle potential apply_aspect error for dispersion plot
@@ -340,9 +360,11 @@ def DispersionPlot(textParty):
             buf.close() # Ensure buffer is closed on error
         traceback.print_exc()
         plt.close('all') # Aggressive close on error
+        # Optionally return a placeholder image or None
         return None # Return None on error
 
-# --- Updated word_cloud_generator with robust figure handling ---
+
+
 def word_cloud_generator(parsed_text_name, text_Party):
     """Generates the word cloud image."""
     buf = None # Initialize buffer
@@ -362,14 +384,14 @@ def word_cloud_generator(parsed_text_name, text_Party):
         elif 'aap' in filename_lower:
             mask_path = 'aapMain2.jpg'
 
-        # Generate word cloud
+
         if text_Party.strip() == "":
              raise ValueError("Text for word cloud is empty")
 
         # Generate word cloud object
         if mask_path and os.path.exists(mask_path):
             orgImg = Image.open(mask_path)
-            # Ensure mask is in the right format (e.g., uint8)
+
             if orgImg.mode != 'RGB':
                 orgImg = orgImg.convert('RGB')
             mask = np.array(orgImg)
@@ -505,7 +527,6 @@ with gr.Blocks(title='Manifesto Analysis') as demo:
                     dispersion_output = gr.Image(label='Dispersion Plot', interactive=False, height=400) # Adjust height as needed
 
     # --- Link Button Click to Function and Outputs ---
-    # Ensure the order of outputs matches the function return order
     submit_btn.click(
         fn=analysis,
         inputs=[file_input, search_input],
@@ -534,6 +555,6 @@ with gr.Blocks(title='Manifesto Analysis') as demo:
         fn=analysis # Run analysis on example click
     )
 
-# Launch the app
+
 if __name__ == "__main__":
     demo.launch(debug=True, share=False, show_error=True)