Working covariance matrix based on historical data.

run.py

@@ -57,7 +57,7 @@
 
 print()
 optimizer = MPCMaximumUtility(portfolio, simulator.return_tensor, gamma=1)
-optimizer.solve()
+# optimizer.solve()
 
 
 print("OK!")

src/abacus/optimizer/optimizer.py

@@ -95,6 +95,8 @@ def _set_ampl_data(self):
 
 class MPCMaximumUtility(OptimizationModel):
 
+    # TODO: Follow Boyd et al (https://doi.org/10.1007/s10479-018-2947-3) for transaction costs and risk aversion.
+
     _model_specification = OptimizationSpecifications.MPC_MAXIMIZE_UTILITY
 
     def __init__(self, portfolio: Portfolio, return_tensor: torch.Tensor, gamma: float):

src/abacus/simulator/simulator.py

@@ -5,6 +5,7 @@
 
 from src.abacus.utils.instrument import Instrument
 from src.abacus.utils.exceptions import ParameterError
+from src.abacus.utils.enumerations import DataTypes
 from src.abacus.simulator.model_selector import ModelSelector
 from src.abacus.config import VINE_COPULA_FAMILIES, VINE_COPULA_NUMBER_OF_THREADS
 
@@ -22,6 +23,21 @@ def __init__(self, instruments: list[Instrument]):
         self._return_tensor = None
         self._price_tensor = None
 
+    @property
+    def covariance_matrix(self, data_type: DataTypes=DataTypes.LOG_RETURNS) -> torch.Tensor:
+        # TODO: Add explanation of stacking here.
+        # TODO: Ensure working under odd data length inputs.
+        # TODO: Add input for price through enum.
+        # TODO: Consider making static.
+        # TODO: Consider check for symmetric and positive semi definiteness.
+        if data_type == DataTypes.LOG_RETURNS:
+            instrument_data = [instrument.log_returns_tensor for instrument in self._instruments]
+        elif data_type == DataTypes.ART_RETURNS:
+            instrument_data = [instrument.art_returns_tensor for instrument in self._instruments]
+        else:
+            raise NotImplementedError(f"Data type {data_type} not supported to build covariance matrix.")
+        return torch.cov(torch.stack(instrument_data))
+
     @property
     def return_tensor(self) -> torch.Tensor:
         self._check_calibration()

src/abacus/utils/enumerations.py

@@ -1,7 +1,12 @@
 # -*- coding: utf-8 -*-
-from enum import Enum
+from enum import Enum, auto
 
 
 class OptimizationSpecifications(Enum):
     SP_MAXIMIZE_UTILITY = "sp_maximize_utility.mod"
     MPC_MAXIMIZE_UTILITY = "mpc_maximize_utility.mod"
+
+class DataTypes(Enum):
+    LOG_RETURNS = auto(),
+    ART_RETURNS = auto(),
+    PRICES = auto(),