Update app.py

app.py

@@ -20,12 +20,9 @@ import seaborn as sns
 
 warnings.filterwarnings('ignore', category=FutureWarning, module='huggingface_hub.file_download')
 
-# Download necessary NLTK data
-nltk.download('vader_lexicon', quiet=True)
-nltk.download('punkt', quiet=True)
-nltk.download('averaged_perceptron_tagger', quiet=True)
-nltk.download('maxent_ne_chunker', quiet=True)
-nltk.download('words', quiet=True)
+# Download necessary NLTK data (lazy loading)
+nltk.download('vader_lexicon', quiet=True, raise_on_error=True)
+nltk.data.path.append('/nltk_data')  # Specify the path where NLTK data should be stored
 
 # Initialize Example Dataset (For Emotion Prediction)
 data = {
@@ -148,17 +145,7 @@ def evolve_emotions():
     best_individual = tools.selBest(population, k=1)[0]
     emotion_values = best_individual[:len(emotions)]
     intensities = best_individual[len(emotions):]
-
-    for i, (emotion, data) in enumerate(emotions.items()):
-        data['percentage'] = emotion_values[i]
-        data['intensity'] = intensities[i]
-
-    # Normalize percentages
-    total = sum(e['percentage'] for e in emotions.values())
-    for e in emotions:
-        emotions[e]['percentage'] = (emotions[e]['percentage'] / total) * 100
-
-def predict_emotion(context):
+    def predict_emotion(context):
     load_models()
     inputs = emotion_prediction_tokenizer(context, return_tensors="pt", truncation=True, max_length=512)
     with torch.no_grad():
@@ -174,6 +161,22 @@ def sentiment_analysis(text):
     return sentiment_scores
 
 def extract_entities(text):
+    # Lazy load the necessary NLTK data
+    try:
+        nltk.data.find('tokenizers/punkt')
+    except LookupError:
+        nltk.download('punkt', quiet=True, raise_on_error=True)
+
+    try:
+        nltk.data.find('taggers/averaged_perceptron_tagger')
+    except LookupError:
+        nltk.download('averaged_perceptron_tagger', quiet=True, raise_on_error=True)
+
+    try:
+        nltk.data.find('chunkers/maxent_ne_chunker')
+    except LookupError:
+        nltk.download('maxent_ne_chunker', quiet=True, raise_on_error=True)
+
     chunked = ne_chunk(pos_tag(word_tokenize(text)))
     entities = []
     for chunk in chunked:
@@ -266,68 +269,23 @@ def interactive_interface(input_text):
     if len(conversation_history) > max_history_length:
         conversation_history.pop(0)
 
+    # Save conversation history to a file
+    save_historical_data(conversation_history)
+
     # Return the expected outputs in the correct order
     return (
         gr.Textbox(value=predicted_emotion, label="Predicted Emotion"),
         gr.Textbox(value=str(sentiment_scores), label="Sentiment Scores"),
         gr.Textbox(value=str(entities), label="Extracted Entities"),
         gr.Textbox(value=str(text_complexity), label="Text Complexity"),
-        gr.Textbox(value=ai_emotion, label="AI Emotion"),
-        gr.Textbox(value=f"{ai_emotion_percentage:.2f}%", label="AI Emotion Percentage"),
-        gr.Textbox(value=f"{ai_emotion_intensity:.2f}", label="AI Emotion Intensity"),
-        gr.Image(value=emotion_visualization, label="Emotion Visualization"),
-        gr.Textbox(value=response, label="AI Response")
+        gr.Textbox(value=response, label="AI Response"),
+        gr.Image(value=emotion_visualization, label="Emotion Visualization")
     )
 
-# 443 additional features
-additional_features = {}
-for i in range(443):
-    additional_features[f'feature_{i+1}'] = 0
-
-def feature_transformations():
-    global additional_features
-    for feature in additional_features:
-        additional_features[feature] += random.uniform(-1, 1)
-
-def visualize_emotions():
-    emotions_df = pd.DataFrame([(e, d['percentage'], d['intensity']) for e, d in emotions.items()],
-                               columns=['emotion', 'percentage', 'intensity'])
-
-    plt.figure(figsize=(12, 6))
-    sns.barplot(x='emotion', y='percentage', data=emotions_df)
-    plt.title('Emotion Percentages')
-    plt.xlabel('Emotion')
-    plt.ylabel('Percentage')
-    plt.xticks(rotation=90)
-    plt.savefig('emotion_percentages.png')
-
-    plt.figure(figsize=(12, 6))
-    sns.barplot(x='emotion', y='intensity', data=emotions_df)
-    plt.title('Emotion Intensities')
-    plt.xlabel('Emotion')
-    plt.ylabel('Intensity')
-    plt.xticks(rotation=90)
-    plt.savefig('emotion_intensities.png')
-
-    return 'emotion_percentages.png', 'emotion_intensities.png'
-
 # Create the Gradio interface
-iface = gr.Interface(
-    fn=interactive_interface,
-    inputs=gr.Textbox(label="Input Text"),
-    outputs=[
-        gr.Textbox(label="Predicted Emotion"),
-        gr.Textbox(label="Sentiment Scores"),
-        gr.Textbox(label="Extracted Entities"),
-        gr.Textbox(label="Text Complexity"),
-        gr.Textbox(label="AI Emotion"),
-        gr.Textbox(label="AI Emotion Percentage"),
-        gr.Textbox(label="AI Emotion Intensity"),
-        gr.Image(label="Emotion Visualization"),
-        gr.Textbox(label="AI Response")
-    ],
-    title="Emotional AI Assistant",
-    description="An AI assistant that can analyze the emotional content of text and generate responses based on its emotional state.",
-)
+iface = gr.Interface(fn=interactive_interface, inputs="text", outputs=[
+    "text", "text", "text", "text", "text", "image"
+], title="Emotion-Aware AI Assistant")
 
-iface.launch()
+# Launch the interface
+iface.launch()