Download backend/optimizer_agent.py from PROSTLE/AarthiAI: direct link, hf CLI and curl.
- Browser
- Download file 3.13 kB
-
https://huggingface.co/spaces/PROSTLE/AarthiAI/resolve/main/backend/optimizer_agent.py
- Command line
-
hf download hf://spaces/PROSTLE/AarthiAI/backend/optimizer_agent.py
-
curl -L -o optimizer_agent.py https://huggingface.co/spaces/PROSTLE/AarthiAI/resolve/main/backend/optimizer_agent.py
3.13 kB
| import os | |
| import json | |
| from feedback_engine import FeedbackEngine | |
| from dynamic_params import DynamicParams, KEYS | |
| from llm_analysis import _init_gemini | |
| # Re-using SDK logic from llm_analysis | |
| GEMINI_AVAILABLE = False | |
| try: | |
| from google import genai as _genai_sdk | |
| GEMINI_AVAILABLE = True | |
| except ImportError: | |
| pass | |
| class OptimizerAgent: | |
| def __init__(self): | |
| self.api_key = os.getenv("GEMINI_API_KEY") | |
| self.client = None | |
| self.model = "gemini-2.0-flash" | |
| if GEMINI_AVAILABLE and self.api_key: | |
| try: | |
| self.client = _genai_sdk.Client(api_key=self.api_key) | |
| except Exception as e: | |
| print(f"[Optimizer] Init error: {e}") | |
| def run_optimization(self): | |
| """ | |
| Analyze recent performance and update dynamic parameters. | |
| Returns a summary of changes. | |
| """ | |
| if not self.client: | |
| return {"status": "error", "message": "LLM client unavailable"} | |
| # 1. Gather Data | |
| report = FeedbackEngine.get_accuracy_report(days=7) | |
| params = DynamicParams.get_all() | |
| if not report: | |
| return {"status": "skipped", "reason": "Not enough accuracy data to optimize"} | |
| # 2. Build Optimization Prompt | |
| prompt = f""" | |
| You are an AI ML Optimizer for a stock trading bot. | |
| Current Performance Report (last 7 days): | |
| {json.dumps(report, indent=2)} | |
| Current Dynamic Parameters: | |
| {json.dumps(params, indent=2)} | |
| Based on the directional accuracy and average moves, suggest improvements to the parameters. | |
| - If Accuracy is < 50%, consider increasing BUY_THRESHOLD. | |
| - If a certain model (e.g., XGB) is performing significantly better than LSTM, adjust weights. | |
| - If Stop Losses (ATR_MULTIPLIER_SL) are hitting too often in volatile markets, adjust them. | |
| Respond ONLY with a JSON object of key-value pairs representing ONLY the parameters you want to change: | |
| {{ | |
| "PARAMETER_KEY": <new_value> | |
| }} | |
| """ | |
| try: | |
| # 3. Get LLM Recommendations | |
| response = self.client.models.generate_content( | |
| model=self.model, | |
| contents=prompt | |
| ) | |
| text = response.text.strip() | |
| if "```" in text: | |
| text = text.split("```")[1] | |
| if text.startswith("json"): | |
| text = text[4:] | |
| text = text.strip() | |
| updates = json.loads(text) | |
| # 4. Apply Updates | |
| applied = {} | |
| for key, val in updates.items(): | |
| if key in params: | |
| DynamicParams.update(key, val) | |
| applied[key] = val | |
| return { | |
| "status": "success", | |
| "updates_applied": applied, | |
| "report_summary": report | |
| } | |
| except Exception as e: | |
| print(f"[Optimizer] Optimization error: {e}") | |
| return {"status": "error", "message": str(e)} | |