Add FastAPI backend for energy trading system

Implements FastAPI backend with ML model support for energy trading,
including price prediction models and RL-based battery trading policy.
Features dashboard, trading, backtest, and settings API routes with
WebSocket support for real-time updates.

backend/app/ml/utils/__init__.py

@@ -0,0 +1,3 @@
+from app.ml.utils import time_based_split, MLConfig
+
+__all__ = ["time_based_split", "MLConfig"]

backend/app/ml/utils/config.py

@@ -0,0 +1,16 @@
+from dataclasses import dataclass
+from typing import List, Dict, Any
+
+
+@dataclass
+class MLConfig:
+    enable_gpu: bool = False
+    n_jobs: int = 4
+    verbose: bool = True
+
+    @classmethod
+    def from_dict(cls, config_dict: Dict[str, Any]) -> "MLConfig":
+        return cls(**{k: v for k, v in config_dict.items() if k in cls.__annotations__})
+
+
+__all__ = ["MLConfig"]

backend/app/ml/utils/data_split.py

@@ -0,0 +1,25 @@
+from typing import Tuple
+import pandas as pd
+from datetime import datetime
+
+
+def time_based_split(
+    df: pd.DataFrame,
+    timestamp_col: str = "timestamp",
+    train_pct: float = 0.70,
+    val_pct: float = 0.85,
+) -> Tuple[pd.DataFrame, pd.DataFrame, pd.DataFrame]:
+    df_sorted = df.sort_values(timestamp_col)
+
+    n_total = len(df_sorted)
+    n_train = int(n_total * train_pct)
+    n_val = int(n_total * val_pct)
+
+    train = df_sorted.iloc[:n_train]
+    val = df_sorted.iloc[n_train:n_val]
+    test = df_sorted.iloc[n_val:]
+
+    return train, val, test
+
+
+__all__ = ["time_based_split"]

backend/app/ml/utils/evaluation.py

@@ -0,0 +1,4 @@
+from app.ml.utils.data_split import time_based_split
+from app.ml.utils.config import MLConfig
+
+__all__ = ["time_based_split", "MLConfig"]