Upload 4 files

README.md

@@ -0,0 +1,95 @@
+---
+title: PPO Mood Chatbot
+emoji: 🧠
+colorFrom: blue
+colorTo: green
+sdk: gradio
+sdk_version: 5.25.2
+app_file: app.py
+pinned: true
+---
+
+# 🧠 Mood Support Chatbot with PPO & GPT-3.5
+
+This project is an AI-powered mental health support chatbot that infers a user's emotional state from natural language input and provides personalized wellness suggestions. It combines:
+
+- **GPT-3.5** for mood detection from conversation
+- **PPO (Proximal Policy Optimization)** for reinforcement-learned action selection
+- **Gradio** for an interactive web interface
+- **Hugging Face Spaces** for free public hosting
+
+---
+
+## 🌟 Features
+- **Multi-turn Conversation Context**: Mood detection takes the recent chat history into account
+- **Visual Mood Tracking**: A mood trend chart tracks how the user's state evolves
+- **Personalized Suggestion Memory**: Keeps count of which strategies are offered per session
+- **Custom PPO Policy**: Trained in a simulated environment with an expanded action space of 8 wellness suggestions
+- **Deployment Ready**: Packaged and hosted on Hugging Face Spaces with OpenAI key stored securely
+
+---
+
+## 🧩 Action Space
+The agent selects from the following actions:
+
+- meditation 🧘
+- talk_therapy 💬
+- journal_prompt 📝
+- breathing_ex 💨
+- video 🎥
+- nature_walk 🌿
+- soothing_music 🎶
+- gratitude_exercise 🙏
+
+---
+
+## 🛠 Training
+The PPO agent was trained using `stable-baselines3` in a custom Gymnasium environment. The reward is based on simulated mood improvements, and training ends when the mood exceeds a threshold (e.g., 0.95).
+
+**Training script includes:**
+- SimulatedUser with mood boost logic
+- MoodSupportEnv with gym-style `reset()` and `step()`
+- PPO training loop with model save + zip
+
+---
+
+## 🧪 How to Test
+Use emotional prompts like:
+
+- "I'm so tired and I can't stop overthinking."
+- "I'm feeling hopeful but a bit nervous."
+- "I don't feel like doing anything."
+
+Or test edge cases like:
+
+- Extremely long emotional rants
+- Repeated vague responses ("I don't know")
+- Rapid mood swings over turns
+
+---
+
+## 🚀 Deployment on Hugging Face Spaces
+This project runs on Hugging Face using:
+- `app.py`: Main chatbot logic and UI
+- `ppo_mental_health_model_expanded.zip`: Trained PPO model
+- `requirements.txt`: Dependency list
+- `OPENAI_API_KEY`: Set as a Hugging Face Secret
+
+---
+
+## 🧠 Future Enhancements
+- Mood-aware GPT text responses
+- Feedback buttons (👍/👎) to improve the agent
+- Session export or user login
+- Local transformer fallback (offline mode)
+- Mood milestone alerts ("You've improved by 40%!")
+
+---
+
+## 👤 Author
+Built and maintained by Chirasmayee B and Pallavi Bichupriya.
+
+---
+
+## 📄 License
+MIT License

app.py

@@ -0,0 +1,109 @@
+import gradio as gr
+import numpy as np
+import openai
+import os
+import zipfile
+from stable_baselines3 import PPO
+import matplotlib.pyplot as plt
+import io
+import base64
+
+# Load OpenAI API key from environment
+openai.api_key = os.getenv("OPENAI_API_KEY")
+
+# Unzip PPO model only if not already extracted
+if not os.path.exists("ppo_mental_health_model_expanded"):
+    with zipfile.ZipFile("ppo_mental_health_model_expanded.zip", "r") as zip_ref:
+        zip_ref.extractall(".")
+
+# Load PPO model
+ppo_model = PPO.load("ppo_mental_health_model_expanded")
+
+# PPO environment-related mappings
+ACTIONS = ['meditation', 'talk_therapy', 'journal_prompt', 'breathing_ex', 'video', 'nature_walk', 'soothing_music', 'gratitude_exercise']
+INDEX_TO_ACTION = {i: a for i, a in enumerate(ACTIONS)}
+suggestion_map = {
+    'meditation': "Would you like to try a short meditation exercise? 🧘",
+    'talk_therapy': "Talking to someone might help. Want to explore talk therapy?",
+    'journal_prompt': "Journaling might help you express your thoughts. 📝",
+    'breathing_ex': "Try a calming breathing exercise. Inhale deeply... 💨",
+    'video': "Here’s a calming video that might lift your mood. 🎥",
+    'nature_walk': "How about a short walk in nature? A little fresh air might help. 🌿",
+    'soothing_music': "Listening to soothing music might help you relax. 🎶",
+    'gratitude_exercise': "Let's try a quick gratitude exercise. Name one thing you're thankful for. 🙏"
+}
+
+# Mood scoring
+mood_score_map = {
+    'positive': 0.8, 'negative': 0.3,
+    'joy': 0.9, 'love': 0.8, 'surprise': 0.6, 'neutral': 0.5,
+    'sadness': 0.3, 'fear': 0.2, 'anger': 0.2, 'anxiety': 0.3,
+    'disgust': 0.2, 'guilt': 0.2, 'hope': 0.7, 'calm': 0.75
+}
+
+# Session state
+chat_history = []
+mood_scores = []
+suggestion_memory = {action: 0 for action in ACTIONS}
+
+# Mood inference using OpenAI (with context)
+def get_mood_from_openai(user_input, history):
+    chat_context = "\n".join([f"User: {msg}" for msg in history[-3:]])
+    prompt = f"""You are a mental health assistant. Analyze the user's emotional state from their recent conversation and return one mood word from:
+["joy", "sadness", "anger", "fear", "anxiety", "guilt", "neutral", "love", "surprise", "disgust", "hope", "calm", "positive", "negative"].
+Conversation:
+{chat_context}
+User: {user_input}
+Mood:"""
+    response = openai.chat.completions.create(
+        model="gpt-3.5-turbo",
+        messages=[{"role": "user", "content": prompt}],
+        temperature=0.2,
+        max_tokens=5,
+        timeout=20
+    )
+    return response.choices[0].message.content.strip().lower()
+
+# Mood trend plot
+def plot_mood_trend():
+    fig, ax = plt.subplots()
+    ax.plot(range(1, len(mood_scores)+1), mood_scores, marker='o')
+    ax.set_title("Mood Score Over Time")
+    ax.set_xlabel("Turn")
+    ax.set_ylabel("Mood Score")
+    ax.set_ylim(0, 1)
+    filepath = "mood_trend.png"
+    plt.savefig(filepath)
+    plt.close(fig)
+    return filepath
+
+# Chatbot response with tracking
+def chatbot_response(user_input, history=None):
+    try:
+        chat_history.append(user_input)
+        mood_label = get_mood_from_openai(user_input, chat_history)
+        mood_score = mood_score_map.get(mood_label, 0.4)
+        mood_scores.append(mood_score)
+
+        obs = np.array([mood_score], dtype=np.float32).reshape(1, -1)
+        action, _ = ppo_model.predict(obs)
+        suggestion = INDEX_TO_ACTION[int(action)]
+        suggestion_memory[suggestion] += 1
+        response = suggestion_map[suggestion]
+
+        chat_output = f"🤖 I sense you might be feeling *{mood_label}*. {response}"
+        return chat_output, plot_mood_trend()
+
+    except Exception as e:
+        import traceback
+        traceback.print_exc()
+        return f"❌ Error: {str(e)}", None
+
+# Launch Gradio interface
+gr.Interface(
+    fn=chatbot_response,
+    inputs=gr.Textbox(lines=2, placeholder="How are you feeling today?"),
+    outputs=[gr.Textbox(label="Chatbot Response"), gr.Image(label="Mood Trend")],
+    title="Mental Health Support Bot",
+    description="This chatbot tracks mood over time, remembers your context, and suggests helpful wellness strategies."
+).launch()

ppo_mental_health_model_expanded.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01c3ca64a9811778df1754325b4fde3b9b43588faf676ec366ff7e05d88627bd
+size 142140

requirements.txt

@@ -0,0 +1,5 @@
+openai
+gradio
+stable-baselines3
+numpy
+gymnasium