Update app.py

app.py

@@ -1,5 +1,5 @@
-import os
 import gradio as gr
+import pandas as pd
 import nltk
 import numpy as np
 import tflearn
@@ -11,8 +11,8 @@ from nltk.stem.lancaster import LancasterStemmer
 from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
 import googlemaps
 import folium
-import pandas as pd
-import torch
+import os
+import base64
 
 # Disable GPU usage for TensorFlow
 os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
@@ -62,7 +62,6 @@ def chatbot(message, history):
         results = model.predict([bag_of_words(message, words)])
         results_index = np.argmax(results)
         tag = labels[results_index]
-
         # Match tag with intent and choose a random response
         for tg in data["intents"]:
             if tg['tag'] == tag:
@@ -73,11 +72,9 @@ def chatbot(message, history):
             response = "I'm sorry, I didn't understand that. Could you please rephrase?"
     except Exception as e:
         response = f"An error occurred: {str(e)}"
-    
     # Convert the new message and response to the 'messages' format
     history.append({"role": "user", "content": message})
     history.append({"role": "assistant", "content": response})
-    
     return history, history
 
 # Sentiment Analysis using Hugging Face model
@@ -88,9 +85,9 @@ def analyze_sentiment(user_input):
     inputs = tokenizer_sentiment(user_input, return_tensors="pt")
     with torch.no_grad():
         outputs = model_sentiment(**inputs)
-    predicted_class = torch.argmax(outputs.logits, dim=1).item()
-    sentiment = ["Negative", "Neutral", "Positive"][predicted_class]  # Assuming 3 classes
-    return f"Predicted Sentiment: {sentiment}"
+        predicted_class = torch.argmax(outputs.logits, dim=1).item()
+        sentiment = ["Negative", "Neutral", "Positive"][predicted_class]
+        return f"Predicted Sentiment: {sentiment}"
 
 # Emotion Detection using Hugging Face model
 tokenizer_emotion = AutoTokenizer.from_pretrained("j-hartmann/emotion-english-distilroberta-base")
@@ -173,10 +170,9 @@ def generate_suggestions(emotion):
             {"Title": "Relaxation Video", "Subject": "Video", "Link": '<a href="https://youtu.be/m1vaUGtyo-A" target="_blank">Watch Video</a>'}
         ]
     }
-
     return suggestions.get(emotion, [])
 
-# Gradio interface
+# Define the Gradio interface
 def gradio_app(message, location, health_query, submit_button, history, state):
     if submit_button:
         # Chatbot interaction
@@ -197,14 +193,49 @@ def gradio_app(message, location, health_query, submit_button, history, state):
         # Create a DataFrame for displaying suggestions
         suggestions_df = pd.DataFrame(suggestions)
         
-        return history, sentiment_response, emotion_response, route_info, map_html, gr.DataFrame(suggestions_df, headers=["Title", "Subject", "Link"]), state
+        # Add emoticons based on emotion
+        emoticon = {
+            'joy': '😊',
+            'anger': '😡',
+            'fear': '😨',
+            'sadness': '😢',
+            'surprise': '😲'
+        }
+        
+        # Add info graphics based on emotion
+        info_graphics = {
+            'joy': 'joy.png',
+            'anger': 'anger.png',
+            'fear': 'fear.png',
+            'sadness': 'sadness.png',
+            'surprise': 'surprise.png'
+        }
+        
+        # Convert image to base64 for embedding in HTML
+        if info_graphics.get(emotion_response.split(': ')[1]):
+            with open(info_graphics[emotion_response.split(': ')[1]], "rb") as image_file:
+                encoded_string = base64.b64encode(image_file.read()).decode()
+            info_graphic_html = f'<img src="data:image/png;base64,{encoded_string}" alt="{emotion_response.split(": ")[1]}">'
+        else:
+            info_graphic_html = ''
+        
+        return (
+            history,
+            sentiment_response,
+            f"{emotion_response} {emoticon.get(emotion_response.split(': ')[1], '')}",
+            route_info,
+            map_html,
+            gr.DataFrame(suggestions_df, headers=["Title", "Subject", "Link"]),
+            info_graphic_html,
+            state
+        )
     else:
-        return history, "", "", "", "", gr.DataFrame([], headers=["Title", "Subject", "Link"]), state
+        return history, "", "", "", "", gr.DataFrame([], headers=["Title", "Subject", "Link"]), "", state
 
 # Gradio UI components
 message_input = gr.Textbox(lines=1, label="Message", placeholder="Type your message here...")
 location_input = gr.Textbox(value="Honolulu, HI", label="Current Location", placeholder="Enter your current location...")
-health_query_input = gr.Textbox(value="doctor", label="Health Professional Query (e.g., doctor, health professional, well-being professional", placeholder="Search for health professionals...")
+health_query_input = gr.Textbox(value="doctor", label="Health Professional Query (e.g., doctor, health professional, well-being professional)", placeholder="Search for health professionals...")
 submit_button = gr.Button("Submit")
 
 # Updated chat history component with 'messages' type
@@ -216,6 +247,7 @@ emotion_output = gr.Textbox(label="Emotion Detection Result")
 route_info_output = gr.Textbox(label="Health Professionals Information")
 map_output = gr.HTML(label="Map with Health Professionals")
 suggestions_output = gr.DataFrame(label="Well-Being Suggestions", headers=["Title", "Subject", "Link"])
+info_graphic_output = gr.HTML(label="Info Graphic")
 
 # Custom CSS for styling
 custom_css = """
@@ -225,11 +257,9 @@ body {
     color: #333;
     font-family: Arial, sans-serif;
 }
-
 h1, h2, h3, h4, h5, h6 {
     color: #0056b3;
 }
-
 .gradio-app {
     max-width: 800px;
     margin: 0 auto;
@@ -238,11 +268,9 @@ h1, h2, h3, h4, h5, h6 {
     border-radius: 10px;
     box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);
 }
-
 .gradio-input, .gradio-output {
     margin-bottom: 15px;
 }
-
 .gradio-button {
     background-color: #0056b3;
     color: #fff;
@@ -251,43 +279,41 @@ h1, h2, h3, h4, h5, h6 {
     border-radius: 5px;
     cursor: pointer;
 }
-
 .gradio-button:hover {
     background-color: #004080;
 }
-
 .gradio-dataframe {
     border: 1px solid #ddd;
     border-radius: 5px;
     overflow: hidden;
 }
-
 .gradio-dataframe th, .gradio-dataframe td {
     padding: 10px;
     text-align: left;
 }
-
 .gradio-dataframe th {
     background-color: #0056b3;
     color: #fff;
 }
-
 .gradio-dataframe a {
     color: #0056b3;
     text-decoration: none;
 }
-
 .gradio-dataframe a:hover {
     text-decoration: underline;
 }
+.info-graphic img {
+    max-width: 100%;
+    height: auto;
+}
 </style>
 """
 
 # Create Gradio interface
-iface = gr.Interface(
-    fn=gradio_app, 
-    inputs=[message_input, location_input, health_query_input, submit_button, gr.State()],
-    outputs=[chat_history, sentiment_output, emotion_output, route_info_output, map_output, suggestions_output, gr.State()],
+demo = gr.Interface(
+    fn=gradio_app,
+    inputs=[message_input, location_input, health_query_input, submit_button, gr.State(), gr.State()],
+    outputs=[chat_history, sentiment_output, emotion_output, route_info_output, map_output, suggestions_output, info_graphic_output, gr.State()],
     allow_flagging="never",
     live=False,
     title="Well-Being App: Support, Sentiment, Emotion Detection & Health Professional Search",
@@ -295,4 +321,5 @@ iface = gr.Interface(
 )
 
 # Launch the Gradio interface
-iface.launch()
+if __name__ == "__main__":
+    demo.launch()