Update app.py

app.py

@@ -75,6 +75,8 @@ def process_ner(text: str, pipeline) -> dict:
 
     return {"text": text, "entities": entities}
 
+import os
+
 def generate_charts(ner_output_bin: dict) -> Tuple[go.Figure, np.ndarray]:
     entities_bin = [entity['entity'] for entity in ner_output_bin['entities']]
 
@@ -83,7 +85,6 @@ def generate_charts(ner_output_bin: dict) -> Tuple[go.Figure, np.ndarray]:
     bin_labels = list(entity_counts_bin.keys())
     bin_sizes = list(entity_counts_bin.values())
 
-
     bin_color_map = {
         "External": "#6ad5bc",
         "Internal": "#ee8bac"
@@ -91,7 +92,6 @@ def generate_charts(ner_output_bin: dict) -> Tuple[go.Figure, np.ndarray]:
 
     bin_colors = [bin_color_map.get(label, "#FFFFFF") for label in bin_labels]
     
-    
     # Create bar chart for binary classification
     fig2 = go.Figure(data=[go.Bar(x=bin_labels, y=bin_sizes, marker=dict(color=bin_colors))])
     fig2.update_layout(
@@ -103,14 +103,22 @@ def generate_charts(ner_output_bin: dict) -> Tuple[go.Figure, np.ndarray]:
     )
     
     # Generate word cloud
-    wordcloud_image = generate_wordcloud(ner_output_bin['entities'], bin_color_map, "dh3.img")
+    wordcloud_image = generate_wordcloud(ner_output_bin['entities'], bin_color_map, "dh3.png")
     
     return fig2, wordcloud_image
 
 def generate_wordcloud(entities: List[Dict], color_map: Dict[str, str], file_path: str) -> np.ndarray:
-
-    image_path = os.path.join(os.path.dirname(__file__), file_path)
+    # Construct the absolute path
+    base_path = os.path.dirname(os.path.abspath(__file__))
+    image_path = os.path.join(base_path, file_path)
     
+    # Debugging statement to print the image path
+    print(f"Image path: {image_path}")
+
+    # Check if the file exists
+    if not os.path.exists(image_path):
+        raise FileNotFoundError(f"Mask image file not found: {image_path}")
+
     mask_image = np.array(Image.open(image_path))
     
     token_texts = []
@@ -119,14 +127,12 @@ def generate_wordcloud(entities: List[Dict], color_map: Dict[str, str], file_pat
 
     for entity in entities:
         for token in entity['tokens']:
-            # Remove any leading non-alphanumeric characters
             cleaned_token = re.sub(r'^\W+', '', token)
             token_texts.append(cleaned_token)
             token_scores.append(entity['score'])
             token_types.append(entity['entity'])
             print(f"{cleaned_token} ({entity['entity']}): {entity['score']}")
 
-    # Create a dictionary for word cloud
     word_freq = {text: score for text, score in zip(token_texts, token_scores)}
 
     def color_func(word, font_size, position, orientation, random_state=None, **kwargs):
@@ -135,13 +141,11 @@ def generate_wordcloud(entities: List[Dict], color_map: Dict[str, str], file_pat
 
     wordcloud = WordCloud(width=800, height=400, background_color='#121212', mask=mask_image, color_func=color_func).generate_from_frequencies(word_freq)
 
-    # Convert to image array
     plt.figure(figsize=(10, 5))
     plt.imshow(wordcloud, interpolation='bilinear')
     plt.axis('off')
     plt.tight_layout(pad=0)
 
-    # Convert plt to numpy array
     plt_image = plt.gcf()
     plt_image.canvas.draw()
     image_array = np.frombuffer(plt_image.canvas.tostring_rgb(), dtype=np.uint8)