added training xgboost code

app.py

@@ -48,6 +48,16 @@ tokenizer_model_name = "nlptown/bert-base-multilingual-uncased-sentiment"
 mental_classifier_model_path = "mental_health_model.pkl"
 mental_classifier = MentalHealthClassifier(data_path, mental_classifier_model_path)
 
+if not os.path.exists(mental_classifier_model_path):
+    mental_classifier.initialize_tokenizer(tokenizer_model_name)
+    X, y = mental_classifier.preprocess_data()
+    y_test, y_pred = mental_classifier.train_model(X, y)
+    mental_classifier.save_model()
+else:
+    mental_classifier.load_model()
+    mental_classifier.initialize_tokenizer(tokenizer_model_name)  # Ensure tokenizer is initialized if loading model from pickle
+    X, y = mental_classifier.preprocess_data()  # Preprocess data again if needed
+    mental_classifier.model.fit(X, y)  # Fit the loaded model to the data
 
 # Function to display Q-table
 def display_q_table(q_values, states, actions):
@@ -82,10 +92,10 @@ def speech_recognition_callback():
 
 
 def remove_html_tags(text):
-    clean_text = re.sub("<.*?>", "", text)
+    # clean_text = re.sub("<.*?>", "", text)
+    clean_text = re.sub(r'<.*?>|- |"|\\n', '', text)
     return clean_text
 
-
 # Initialize memory
 if "entered_text" not in st.session_state:
     st.session_state.entered_text = []
@@ -254,7 +264,7 @@ if user_message:
 
             llm_model = LLLResponseGenerator()
             temperature = 0.5
-            max_length = 128
+            max_length = 128 * 4
 
             # Collect all messages exchanged so far into a single text string
             all_messages = "\n".join(
@@ -271,6 +281,7 @@ if user_message:
                 Response;
                 """
             context = f"You are a mental health supporting non-medical assistant. Provide some advice and ask a relevant question back to the user. {all_messages}"
+            # context = f"You are a Mindful Media Mentor, dedicated to providing compassionate support and guidance to users facing mental health challenges. Your goal is to foster a safe and understanding environment where users feel heard and supported. Draw from your expertise to offer practical advice and resources, and encourage users to explore their feelings and experiences openly. Your responses should aim to empower users to take positive steps towards their well-being. {all_messages}"
 
             llm_response = llm_model.llm_inference(
                 model_type="huggingface",