Update app.py

app.py

@@ -18,6 +18,7 @@ from sklearn.tree import DecisionTreeClassifier
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.naive_bayes import GaussianNB
 from sklearn.metrics import accuracy_score
+import logging
 
 # Suppress TensorFlow warnings
 os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
@@ -49,14 +50,17 @@ model_sentiment = AutoModelForSequenceClassification.from_pretrained("cardiffnlp
 tokenizer_emotion = AutoTokenizer.from_pretrained("j-hartmann/emotion-english-distilroberta-base")
 model_emotion = AutoModelForSequenceClassification.from_pretrained("j-hartmann/emotion-english-distilroberta-base")
 
+# Initialize emotion pipeline once
+emotion_pipeline = pipeline("text-classification", model=model_emotion, tokenizer=tokenizer_emotion)
+
 # Google Maps API Client
 gmaps = googlemaps.Client(key=os.getenv("GOOGLE_API_KEY"))
 
 # Load the disease dataset
 df_train = pd.read_csv("Training.csv")  # Change the file path as necessary
-df_test = pd.read_csv("Testing.csv")  # Change the file path as necessary
+df_test = pd.read_csv("Testing.csv")    # Change the file path as necessary
 
-# Encode diseases
+# Encode diseases dictionary (optional, currently unused directly)
 disease_dict = {
     'Fungal infection': 0, 'Allergy': 1, 'GERD': 2, 'Chronic cholestasis': 3, 'Drug Reaction': 4,
     'Peptic ulcer disease': 5, 'AIDS': 6, 'Diabetes ': 7, 'Gastroenteritis': 8, 'Bronchial Asthma': 9,
@@ -70,18 +74,22 @@ disease_dict = {
     'Psoriasis': 39, 'Impetigo': 40
 }
 
-# Function to prepare data
-def prepare_data(df):
-    """Prepares data for training/testing."""
+# Label encoder for consistent train/test encoding
+label_encoder = LabelEncoder()
+
+def prepare_data(df, is_train=True):
+    """Prepares data for training/testing with consistent label encoding."""
     X = df.iloc[:, :-1]  # Features
     y = df.iloc[:, -1]   # Target
-    label_encoder = LabelEncoder()
-    y_encoded = label_encoder.fit_transform(y)
-    return X, y_encoded, label_encoder
+    if is_train:
+        y_encoded = label_encoder.fit_transform(y)
+    else:
+        y_encoded = label_encoder.transform(y)
+    return X, y_encoded
 
-# Preparing training and testing data
-X_train, y_train, label_encoder_train = prepare_data(df_train)
-X_test, y_test, label_encoder_test = prepare_data(df_test)
+# Preparing training and testing data with the same label encoder
+X_train, y_train = prepare_data(df_train, is_train=True)
+X_test, y_test = prepare_data(df_test, is_train=False)
 
 # Define the models
 models = {
@@ -93,12 +101,13 @@ models = {
 # Train and evaluate models
 trained_models = {}
 for model_name, model_obj in models.items():
-    model_obj.fit(X_train, y_train)  # Fit the model
-    y_pred = model_obj.predict(X_test)  # Make predictions
-    acc = accuracy_score(y_test, y_pred)  # Calculate accuracy
+    model_obj.fit(X_train, y_train)
+    y_pred = model_obj.predict(X_test)
+    acc = accuracy_score(y_test, y_pred)
     trained_models[model_name] = {'model': model_obj, 'accuracy': acc}
 
-# Helper Functions for Chatbot
+# --- Helper Functions for Chatbot ---
+
 def bag_of_words(s, words):
     """Convert user input to bag-of-words vector."""
     bag = [0] * len(words)
@@ -136,9 +145,8 @@ def analyze_sentiment(user_input):
     return f"Sentiment: {sentiment_map[sentiment_class]}"
 
 def detect_emotion(user_input):
-    """Detect emotions based on input."""
-    pipe = pipeline("text-classification", model=model_emotion, tokenizer=tokenizer_emotion)
-    result = pipe(user_input)
+    """Detect emotions based on input using cached pipeline."""
+    result = emotion_pipeline(user_input)
     emotion = result[0]["label"].lower().strip()
     emotion_map = {
         "joy": "Joy 😊",
@@ -184,13 +192,15 @@ def generate_suggestions(emotion):
         ],
     }
 
-    # Create a markdown string for clickable suggestions in a table format
-    formatted_suggestions = ["### Suggestions"]
-    formatted_suggestions.append(f"Since you’re feeling {emotion}, you might find these links particularly helpful. Don’t hesitate to explore:")
-    formatted_suggestions.append("| Title | Link |")
-    formatted_suggestions.append("|-------|------|")  # Table headers
+    formatted_suggestions = [
+        "### Suggestions",
+        f"Since you’re feeling {emotion}, you might find these links particularly helpful. Don’t hesitate to explore:",
+        "| Title | Link |",
+        "|-------|------|"
+    ]
     formatted_suggestions += [
-        f"| {title} | [{link}]({link}) |" for title, link in suggestions.get(emotion_key, [("No specific suggestions available.", "#")])
+        f"| {title} | [{link}]({link}) |"
+        for title, link in suggestions.get(emotion_key, [("No specific suggestions available.", "#")])
     ]
 
     return "\n".join(formatted_suggestions)
@@ -200,7 +210,7 @@ def get_health_professionals_and_map(location, query):
     try:
         if not location or not query:
             return [], ""  # Return empty list if inputs are missing
-            
+
         geo_location = gmaps.geocode(location)
         if geo_location:
             lat, lng = geo_location[0]["geometry"]["location"].values()
@@ -214,9 +224,10 @@ def get_health_professionals_and_map(location, query):
                     popup=f"{place['name']}"
                 ).add_to(map_)
             return professionals, map_._repr_html_()
-        return [], ""  # Return empty list if no professionals found
+        return [], ""
     except Exception as e:
-        return [], ""  # Return empty list on exception
+        logging.error(f"Error fetching health professionals: {e}")
+        return [], ""
 
 # Main Application Logic for Chatbot
 def app_function_chatbot(user_input, location, query, history):
@@ -242,13 +253,15 @@ def predict_disease(symptoms):
     predictions = {}
     for model_name, info in trained_models.items():
         prediction = info['model'].predict([input_test])[0]
-        predicted_disease = label_encoder_train.inverse_transform([prediction])[0]
+        predicted_disease = label_encoder.inverse_transform([prediction])[0]
         predictions[model_name] = predicted_disease
 
     # Create a Markdown table for displaying predictions
-    markdown_output = ["### Predicted Diseases"]
-    markdown_output.append("| Model | Predicted Disease |")
-    markdown_output.append("|-------|------------------|")  # Table headers
+    markdown_output = [
+        "### Predicted Diseases",
+        "| Model | Predicted Disease |",
+        "|-------|------------------|"
+    ]
     for model_name, disease in predictions.items():
         markdown_output.append(f"| {model_name} | {disease} |")
 
@@ -275,15 +288,15 @@ welcome_message = """
         margin: 20px 0;
     }
     .info-graphic img {
-        width: 150px;  /* Adjust size as needed */
-        height: auto;  /* Keep aspect ratio */
-        margin: 0 10px;  /* Space between images */
+        width: 150px;
+        height: auto;
+        margin: 0 10px;
     }
     h1 {
-        text-align: center;  /* Center-align the main title */
-        font-size: 3em;  /* Increase title size */
-        color: #004d40;  /* Use your theme's color */
-        margin-bottom: 20px;  /* Space below the title */
+        text-align: center;
+        font-size: 3em;
+        color: #004d40;
+        margin-bottom: 20px;
     }
 </style>
 <div id="welcome-message">Welcome to the Well-Being Companion!</div>
@@ -325,27 +338,25 @@ with gr.Blocks(theme="shivi/calm_seafoam") as app:
             location = gr.Textbox(label="Please Enter Your Current Location", placeholder="E.g., Honolulu", max_lines=1)
             query = gr.Textbox(label="Search Health Professionals Nearby", placeholder="E.g., Health Professionals", max_lines=1)
 
-        with gr.Row():  # Align Submit and Clear buttons side by side
+        with gr.Row():
             submit_chatbot = gr.Button(value="Submit Your Message", variant="primary")
-            clear_chatbot = gr.Button(value="Clear", variant="secondary")  # Clear button
+            clear_chatbot = gr.Button(value="Clear", variant="secondary")
 
         chatbot = gr.Chatbot(label="Chat History", show_label=True)
         sentiment = gr.Textbox(label="Detected Sentiment", show_label=True)
         emotion = gr.Textbox(label="Detected Emotion", show_label=True)
 
-        # Apply styles and create the DataFrame
         professionals = gr.DataFrame(
-            label="Nearby Health Professionals",  # Use label parameter to set the title
+            label="Nearby Health Professionals",
             headers=["Name", "Address"],
-            value=[]  # Initialize with empty data
+            value=[]
         )
 
         suggestions_markdown = gr.Markdown(label="Suggestions")
         map_html = gr.HTML(label="Interactive Map")
 
-        # Functionality to clear the chat input
         def clear_input():
-            return "", []  # Clear both the user input and chat history
+            return "", []
 
         submit_chatbot.click(
             app_function_chatbot,
@@ -356,7 +367,7 @@ with gr.Blocks(theme="shivi/calm_seafoam") as app:
         clear_chatbot.click(
             clear_input,
             inputs=None,
-            outputs=[user_input, chatbot]  # Reset user input and chat history
+            outputs=[user_input, chatbot]
         )
 
     with gr.Tab("Disease Prediction"):
@@ -385,11 +396,11 @@ with gr.Blocks(theme="shivi/calm_seafoam") as app:
         disease_prediction_result = gr.Markdown(label="Predicted Diseases")
 
         submit_disease.click(
-            lambda symptom1, symptom2, symptom3, symptom4, symptom5: predict_disease(
-                [symptom1, symptom2, symptom3, symptom4, symptom5]),
+            lambda sym1, sym2, sym3, sym4, sym5: predict_disease([sym1, sym2, sym3, sym4, sym5]),
             inputs=[symptom1, symptom2, symptom3, symptom4, symptom5],
             outputs=disease_prediction_result
         )
 
 # Launch the Gradio application
-app.launch(share=True)
+if __name__ == "__main__":
+    app.launch(share=True)