Update app.py

app.py

@@ -1,83 +1,125 @@
 import gradio as gr
 import pandas as pd
 import numpy as np
+import time
+import random
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.ensemble import RandomForestClassifier
-from sklearn.utils import Bunch
+from sklearn.svm import SVC
+from sklearn.naive_bayes import MultinomialNB
 
-# 1. SETUP & DATA LOADING (Based on your notebook logic)
-def load_message_data():
-    # In a real Space, you'd upload your 'messages_emojis.csv' to the repo
-    try:
-        df = pd.read_csv('messages_emojis.csv').dropna(subset=['content'])
-    except:
-        # Fallback dummy data for demonstration if file is missing
-        data = {
-            'content': ["I love this!", "That is so scary", "Hahaha so funny", "I agree", "I am sad"],
-            'emoji': ["❤️", "😮", "😂", "👍", "😢"]
-        }
-        df = pd.DataFrame(data)
-    
-    sent_map = {'❤️':'Pos', '👍':'Pos', '😂':'Pos', '💯':'Pos', '😢':'Neg', '😭':'Neg', '😮':'Neu'}
-    intent_map = {'❤️':'Emotion', '👍':'Agreement', '😂':'Emotion', '😮':'Surprise'}
-    
-    get_sent = lambda x: sent_map.get(x, 'Neutral')
-    get_intent = lambda x: intent_map.get(x, 'Other')
+# 1. SETUP DATA AND MAPPINGS (From your Notebook)
+SENT_MAP = {'❤️':'Pos', '👍':'Pos', '😂':'Pos', '💯':'Pos', '😢':'Neg', '😭':'Neg', '😮':'Neu'}
+INTENT_MAP = {'❤️':'Emotion', '👍':'Agreement', '😂':'Emotion', '😮':'Surprise'}
 
-    return Bunch(
-        data=df['content'].values,
-        target_emoji=df['emoji'].values,
-        target_sentiment=df['emoji'].apply(get_sent).values,
-        target_intent=df['emoji'].apply(get_intent).values
-    )
+def get_sent(emoji): return SENT_MAP.get(emoji, 'Neutral')
+def get_intent(emoji): return INTENT_MAP.get(emoji, 'Other')
+
+# Mock Data for training (As the CSV isn't provided, we use a small seed set)
+# In your Space, you can replace this by loading your actual CSV
+data = {
+    'content': ["I love this!", "That is so sad", "Wow really?", "I agree with you", "LMAO", "I am angry"],
+    'emoji': ["❤️", "😢", "😮", "👍", "😂", "😢"]
+}
+df = pd.DataFrame(data)
+df['sentiment'] = df['emoji'].apply(get_sent)
+df['intent'] = df['emoji'].apply(get_intent)
+
+# 2. TRAIN MODELS
+tfidf = TfidfVectorizer(max_features=1000)
+X = tfidf.fit_transform(df['content'])
+
+# Emoji Models
+model_rf_emoji = RandomForestClassifier().fit(X, df['emoji'])
+model_svm_emoji = SVC(probability=True).fit(X, df['emoji'])
+model_nb_emoji = MultinomialNB().fit(X, df['emoji'])
 
-# 2. MODEL TRAINING
-dataset = load_message_data()
-tfidf = TfidfVectorizer(max_features=1000, stop_words='english')
-X = tfidf.fit_transform(dataset.data)
+# Sentiment & Intent Models (Using Random Forest as base)
+model_sent = RandomForestClassifier().fit(X, df['sentiment'])
+model_intent = RandomForestClassifier().fit(X, df['intent'])
 
-clf_emoji = RandomForestClassifier().fit(X, dataset.target_emoji)
-clf_sent = RandomForestClassifier().fit(X, dataset.target_sentiment)
-clf_intent = RandomForestClassifier().fit(X, dataset.target_intent)
+# 3. HELPER FUNCTIONS
+def get_avatar(name):
+    return f"https://api.dicebear.com/7.x/avataaars/svg?seed={name}"
 
-# 3. CHAT LOGIC
 def predict_all(text):
     vec = tfidf.transform([text])
-    emoji = clf_emoji.predict(vec)[0]
-    sentiment = clf_sent.predict(vec)[0]
-    intent = clf_intent.predict(vec)[0]
-    return emoji, sentiment, intent
+    return {
+        "Random Forest": model_rf_emoji.predict(vec)[0],
+        "SVM": model_svm_emoji.predict(vec)[0],
+        "Naive Bayes": model_nb_emoji.predict(vec)[0],
+        "Sentiment": model_sent.predict(vec)[0],
+        "Intent": model_intent.predict(vec)[0]
+    }
 
+# 4. CHAT LOGIC
 def chat_response(message, history):
-    emoji, sentiment, intent = predict_all(message)
+    preds = predict_all(message)
     
-    # The models "responding" as people in a group chat
-    responses = [
-        {"role": "assistant", "content": f"I react to that with: {emoji}", "metadata": {"title": "EmojiBot"}},
-        {"role": "assistant", "content": f"I sense a {sentiment} vibe from you.", "metadata": {"title": "SentiBot"}},
-        {"role": "assistant", "content": f"Your intent seems to be {intent}.", "metadata": {"title": "IntentBot"}}
+    # User's message with reactions
+    # We format reactions as a small row at the bottom
+    reactions_html = f"""
+    <div style='display: flex; gap: 5px; margin-top: 8px; font-size: 0.8em;'>
+        <span title='RF: {preds["Random Forest"]} | SVM: {preds["SVM"]} | NB: {preds["Naive Bayes"]}' 
+              style='background: #f0f2f5; padding: 2px 8px; border-radius: 12px; cursor: help;'>
+            {preds["Random Forest"]} {preds["SVM"]} {preds["Naive Bayes"]}
+        </span>
+    </div>
+    """
+    history.append({"role": "user", "content": message + reactions_html})
+    yield history
+
+    # Simulate group chat replies
+    bots = [
+        {"name": "The Forester (RF)", "avatar": get_avatar("Forester")},
+        {"name": "The Maverick (SVM)", "avatar": get_avatar("Maverick")},
+        {"name": "The Sage (NB)", "avatar": get_avatar("Sage")}
     ]
     
-    # We yield them one by one to simulate typing
-    full_history = []
-    for resp in responses:
-        full_history.append(resp)
+    random.shuffle(bots)
+    
+    for bot in bots:
+        # Random delay for typing simulation
+        time.sleep(random.uniform(0.5, 1.5))
         
-    return f"**Group Chat Analysis:**\n\n**EmojiBot**: {emoji}\n\n**SentiBot**: I'm feeling a {sentiment} energy!\n\n**IntentBot**: Noted! Category: {intent}."
+        bot_msg = f"**Sentiment:** {preds['Sentiment']}  \n**Intent:** {preds['Intent']}"
+        history.append({
+            "role": "assistant", 
+            "content": bot_msg, 
+            "metadata": {"title": bot["name"]},
+            "avatar": bot["avatar"]
+        })
+        yield history
+
+# 5. UI CONSTRUCTION
+custom_css = """
+.gradio-container { background-color: #e5ddd5; } /* WhatsApp Background */
+.message-row { font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif; }
+"""
 
-# 4. UI CUSTOMIZATION (Messenger Style)
-# Dicebear Avatars
-user_avatar = "https://api.dicebear.com/7.x/avataaars/svg?seed=User"
-bot_avatar = "https://api.dicebear.com/7.x/bottts/svg?seed=ModelGroup"
+with gr.Blocks(css=custom_css) as demo:
+    gr.Markdown("# 📱 Multi-Model Emoji Group Chat")
+    gr.Markdown("Type a message to see how different models react and respond based on sentiment and intent.")
+    
+    chatbot = gr.Chatbot(
+        bubble_full_width=False,
+        show_label=False,
+        type="messages",
+        avatar_images=(None, "https://api.dicebear.com/7.x/avataaars/svg?seed=User")
+    )
+    
+    with gr.Row():
+        txt = gr.Textbox(
+            show_label=False,
+            placeholder="Type a message...",
+            scale=4
+        )
+        submit_btn = gr.Button("Send", variant="primary")
 
-demo = gr.ChatInterface(
-    fn=chat_response,
-    title="Model Group Chat",
-    description="Type a message to see how the models react and respond!",
-    examples=["I'm so happy today!", "This is very confusing", "I totally agree with you"],
-    theme="soft",
-    avatar_images=[user_avatar, bot_avatar]
-)
+    # Hooking up logic
+    txt.submit(chat_response, [txt, chatbot], [chatbot])
+    submit_btn.click(chat_response, [txt, chatbot], [chatbot])
+    txt.submit(lambda: "", None, [txt]) # Clear textbox
+    submit_btn.click(lambda: "", None, [txt])
 
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()