Create app.py

app.py

@@ -0,0 +1,83 @@
+import gradio as gr
+import pandas as pd
+import numpy as np
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.utils import Bunch
+
+# 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')
+
+    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
+    )
+
+# 2. MODEL TRAINING
+dataset = load_message_data()
+tfidf = TfidfVectorizer(max_features=1000, stop_words='english')
+X = tfidf.fit_transform(dataset.data)
+
+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. 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
+
+def chat_response(message, history):
+    emoji, sentiment, intent = 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"}}
+    ]
+    
+    # We yield them one by one to simulate typing
+    full_history = []
+    for resp in responses:
+        full_history.append(resp)
+        
+    return f"**Group Chat Analysis:**\n\n**EmojiBot**: {emoji}\n\n**SentiBot**: I'm feeling a {sentiment} energy!\n\n**IntentBot**: Noted! Category: {intent}."
+
+# 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"
+
+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]
+)
+
+if __name__ == "__main__":
+    demo.launch()