Source code for skfolio.optimization.convex._maximum_diversification

"""Maximum Diversification Optimization estimator."""

# Copyright (c) 2023
# Author: Hugo Delatte <delatte.hugo@gmail.com>
# License: BSD 3 clause

import numpy as np
import numpy.typing as npt

import skfolio.typing as skt
from skfolio.measures import RiskMeasure
from skfolio.optimization.convex._base import ObjectiveFunction
from skfolio.optimization.convex._mean_risk import MeanRisk
from skfolio.prior import BasePrior


[docs] class MaximumDiversification(MeanRisk): r"""Maximum Diversification Optimization estimator. Maximizes the diversification ratio which is the ratio of the weighted volatilities over the total volatility. It is a special case of the :class:`~skfolio.optimization.MeanRisk` estimator where the expected return from the objective function is replaced by the weighted volatilities. Parameters ---------- prior_estimator : BasePrior, optional :ref:`Prior estimator <prior>`. The prior estimator is used to estimate the :class:`~skfolio.prior.PriorModel` containing the estimation of assets expected returns, covariance matrix, returns and Cholesky decomposition of the covariance. The default (`None`) is to use :class:`~skfolio.prior.EmpiricalPrior`. min_weights : float | dict[str, float] | array-like of shape (n_assets, ) | None, default=0.0 Minimum assets weights (weights lower bounds). If a float is provided, it is applied to each asset. `None` is equivalent to `-np.Inf` (no lower bound). If a dictionary is provided, its (key/value) pair must be the (asset name/asset minium weight) and the input `X` of the `fit` method must be a DataFrame with the assets names in columns. When using a dictionary, assets values that are not provided are assigned a minimum weight of `0.0`. The default value is `0.0` (no short selling). Example: * `min_weights = 0` --> long only portfolio (no short selling). * `min_weights = None` --> no lower bound (same as `-np.Inf`). * `min_weights = -2` --> each weight must be above -200%. * `min_weights = {"SX5E": 0, "SPX": -2}` * `min_weights = [0, -2]` max_weights : float | dict[str, float] | array-like of shape (n_assets, ) | None, default=1.0 Maximum assets weights (weights upper bounds). If a float is provided, it is applied to each asset. `None` is equivalent to `+np.Inf` (no upper bound). If a dictionary is provided, its (key/value) pair must be the (asset name/asset maximum weight) and the input `X` of the `fit` method must be a DataFrame with the assets names in columns. When using a dictionary, assets values that are not provided are assigned a minimum weight of `1.0`. The default value is `1.0` (each asset is below 100%). Example: * `max_weights = 0` --> no long position (short only portfolio). * `max_weights = None` --> no upper bound. * `max_weights = 2` --> each weight must be below 200%. * `max_weights = {"SX5E": 1, "SPX": 2}` * `max_weights = [1, 2]` budget : float | None, default=1.0 Investment budget. It is the sum of long positions and short positions (sum of all weights). `None` means no budget constraints. The default value is `1.0` (fully invested portfolio). Examples: * `budget = 1` --> fully invested portfolio. * `budget = 0` --> market neutral portfolio. * `budget = None` --> no constraints on the sum of weights. min_budget : float, optional Minimum budget. It is the lower bound of the sum of long and short positions (sum of all weights). If provided, you must set `budget=None`. The default (`None`) means no minimum budget constraint. max_budget : float, optional Maximum budget. It is the upper bound of the sum of long and short positions (sum of all weights). If provided, you must set `budget=None`. The default (`None`) means no maximum budget constraint. max_short : float, optional Maximum short position. The short position is defined as the sum of negative weights (in absolute term). The default (`None`) means no maximum short position. max_long : float, optional Maximum long position. The long position is defined as the sum of positive weights. The default (`None`) means no maximum long position. transaction_costs : float | dict[str, float] | array-like of shape (n_assets, ), default=0.0 Transaction costs of the assets. It is used to add linear transaction costs to the optimization problem: .. math:: total\_cost = \sum_{i=1}^{N} c_{i} \times |w_{i} - w\_prev_{i}| with :math:`c_{i}` the transaction cost of asset i, :math:`w_{i}` its weight and :math:`w\_prev_{i}` its previous weight (defined in `previous_weights`). The float :math:`total\_cost` is impacting the portfolio expected return in the optimization: .. math:: expected\_return = \mu^{T} \cdot w - total\_cost with :math:`\mu` the vector af assets' expected returns and :math:`w` the vector of assets weights. If a float is provided, it is applied to each asset. If a dictionary is provided, its (key/value) pair must be the (asset name/asset cost) and the input `X` of the `fit` method must be a DataFrame with the assets names in columns. The default value is `0.0`. .. warning:: Based on the above formula, the periodicity of the transaction costs needs to be homogenous to the periodicity of :math:`\mu`. For example, if the input `X` is composed of **daily** returns, the `transaction_costs` need to be expressed as **daily** costs. (See :ref:`sphx_glr_auto_examples_1_mean_risk_plot_6_transaction_costs.py`) management_fees : float | dict[str, float] | array-like of shape (n_assets, ), default=0.0 Management fees of the assets. It is used to add linear management fees to the optimization problem: .. math:: total\_fee = \sum_{i=1}^{N} f_{i} \times w_{i} with :math:`f_{i}` the management fee of asset i and :math:`w_{i}` its weight. The float :math:`total\_fee` is impacting the portfolio expected return in the optimization: .. math:: expected\_return = \mu^{T} \cdot w - total\_fee with :math:`\mu` the vector af assets expected returns and :math:`w` the vector of assets weights. If a float is provided, it is applied to each asset. If a dictionary is provided, its (key/value) pair must be the (asset name/asset fee) and the input `X` of the `fit` method must be a DataFrame with the assets names in columns. The default value is `0.0`. .. warning:: Based on the above formula, the periodicity of the management fees needs to be homogenous to the periodicity of :math:`\mu`. For example, if the input `X` is composed of **daily** returns, the `management_fees` need to be expressed in **daily** fees. .. note:: Another approach is to directly impact the management fees to the input `X` in order to express the returns net of fees. However, when estimating the :math:`\mu` parameter using for example Shrinkage estimators, this approach would mix a deterministic value with an uncertain one leading to unwanted bias in the management fees. previous_weights : float | dict[str, float] | array-like of shape (n_assets, ), optional Previous weights of the assets. Previous weights are used to compute the portfolio cost and the portfolio turnover. If a float is provided, it is applied to each asset. If a dictionary is provided, its (key/value) pair must be the (asset name/asset previous weight) and the input `X` of the `fit` method must be a DataFrame with the assets names in columns. The default (`None`) means no previous weights. l1_coef : float, default=0.0 L1 regularization coefficient. It is used to penalize the objective function by the L1 norm: .. math:: l1\_coef \times \Vert w \Vert_{1} = l1\_coef \times \sum_{i=1}^{N} |w_{i}| Increasing this coefficient will reduce the number of non-zero weights (cardinality). It tends to increase robustness (out-of-sample stability) but reduces diversification. The default value is `0.0`. l2_coef : float, default=0.0 L2 regularization coefficient. It is used to penalize the objective function by the L2 norm: .. math:: l2\_coef \times \Vert w \Vert_{2}^{2} = l2\_coef \times \sum_{i=1}^{N} w_{i}^2 It tends to increase robustness (out-of-sample stability). The default value is `0.0`. linear_constraints : array-like of shape (n_constraints,), optional Linear constraints. The linear constraints must match any of following patterns: * "2.5 * ref1 + 0.10 * ref2 + 0.0013 <= 2.5 * ref3" * "ref1 >= 2.9 * ref2" * "ref1 == ref2" * "ref1 >= ref1" With "ref1", "ref2" ... the assets names or the groups names provided in the parameter `groups`. Assets names can be referenced without the need of `groups` if the input `X` of the `fit` method is a DataFrame with these assets names in columns. Examples: * "SPX >= 0.10" --> SPX weight must be greater than 10% (note that you can also use `min_weights`) * "SX5E + TLT >= 0.2" --> the sum of SX5E and TLT weights must be greater than 20% * "US == 0.7" --> the sum of all US weights must be equal to 70% * "Equity == 3 * Bond" --> the sum of all Equity weights must be equal to 3 times the sum of all Bond weights. * "2*SPX + 3*Europe <= Bond + 0.05" --> mixing assets and group constraints groups : dict[str, list[str]] or array-like of shape (n_groups, n_assets), optional The assets groups referenced in `linear_constraints`. If a dictionary is provided, its (key/value) pair must be the (asset name/asset groups) and the input `X` of the `fit` method must be a DataFrame with the assets names in columns. Examples: * groups = {"SX5E": ["Equity", "Europe"], "SPX": ["Equity", "US"], "TLT": ["Bond", "US"]} * groups = [["Equity", "Equity", "Bond"], ["Europe", "US", "US"]] left_inequality : array-like of shape (n_constraints, n_assets), optional Left inequality matrix :math:`A` of the linear constraint :math:`A \cdot w \leq b`. right_inequality : array-like of shape (n_constraints, ), optional Right inequality vector :math:`b` of the linear constraint :math:`A \cdot w \leq b`. risk_free_rate : float, default=0.0 Risk-free interest rate. The default value is `0.0`. max_tracking_error : float, optional Upper bound constraint on the tracking error. The tracking error is defined as the RMSE (root-mean-square error) of the portfolio returns compared to a target returns. If `max_tracking_error` is provided, the target returns `y` must be provided in the `fit` method. max_turnover : float, optional Upper bound constraint of the turnover. The turnover is defined as the absolute difference between the portfolio weights and the `previous_weights`. Note that another way to control for turnover is by using the `transaction_costs` parameter. min_return : float | array-like of shape (n_optimization), optional Lower bound constraint on the expected return. min_return : float | array-like of shape (n_optimization), optional Lower bound constraint on the expected return. add_objective : Callable[[cp.Variable], cp.Expression], optional Add a custom objective to the existing objective expression. It is a function that must take as argument the weights `w` and returns a CVXPY expression. add_constraints : Callable[[cp.Variable], cp.Expression|list[cp.Expression]], optional Add a custom constraint or a list of constraints to the existing constraints. It is a function that must take as argument the weights `w` and returns a CVPXY expression or a list of CVPXY expressions. solver : str, default="CLARABEL" The solver to use. The default is "CLARABEL" which is written in Rust and has better numerical stability and performance than ECOS and SCS. Cvxpy will replace its default solver "ECOS" by "CLARABEL" in future releases. For more details about available solvers, check the CVXPY documentation: https://www.cvxpy.org/tutorial/advanced/index.html#choosing-a-solver solver_params : dict, optional Solver parameters. For example, `solver_params=dict(verbose=True)`. The default (`None`) is use `{"tol_gap_abs": 1e-9, "tol_gap_rel": 1e-9}` for the solver "CLARABEL" and the CVXPY default otherwise. For more details about solver arguments, check the CVXPY documentation: https://www.cvxpy.org/tutorial/advanced/index.html#setting-solver-options scale_objective : float, optional Scale each objective element by this value. It can be used to increase the optimization accuracies in specific cases. The default (`None`) is set depending on the problem. scale_constraints : float, optional Scale each constraint element by this value. It can be used to increase the optimization accuracies in specific cases. The default (`None`) is set depending on the problem. save_problem : bool, default=False If this is set to True, the CVXPY Problem is saved in `problem_`. The default is `False`. raise_on_failure : bool, default=True If this is set to True, an error is raised when the optimization fail otherwise it passes with a warning. portfolio_params : dict, optional Portfolio parameters passed to the portfolio evaluated by the `predict` and `score` methods. If not provided, the `name`, `transaction_costs`, `management_fees`, `previous_weights` and `risk_free_rate` are copied from the optimization model and passed to the portfolio. Attributes ---------- weights_ : ndarray of shape (n_assets,) or (n_optimizations, n_assets) Weights of the assets. problem_values_ : dict[str, float] | list[dict[str, float]] of size n_optimizations Expression values retrieved from the CVXPY problem. prior_estimator_ : BasePrior Fitted `prior_estimator`. problem_: cvxpy.Problem CVXPY problem used for the optimization. Only when `save_problem` is set to `True`. n_features_in_ : int Number of assets seen during `fit`. feature_names_in_ : ndarray of shape (`n_features_in_`,) Names of assets seen during `fit`. Defined only when `X` has assets names that are all strings. """ def __init__( self, prior_estimator: BasePrior | None = None, min_weights: skt.MultiInput | None = 0.0, max_weights: skt.MultiInput | None = 1.0, budget: float | None = 1.0, min_budget: float | None = None, max_budget: float | None = None, max_short: float | None = None, max_long: float | None = None, transaction_costs: skt.MultiInput = 0.0, management_fees: skt.MultiInput = 0.0, previous_weights: skt.MultiInput | None = None, groups: skt.Groups | None = None, linear_constraints: skt.LinearConstraints | None = None, left_inequality: skt.Inequality | None = None, right_inequality: skt.Inequality | None = None, l1_coef: float = 0.0, l2_coef: float = 0.0, risk_free_rate: float = 0.0, min_return: skt.Target | None = None, max_tracking_error: skt.Target | None = None, max_turnover: skt.Target | None = None, solver: str = "CLARABEL", solver_params: dict | None = None, scale_objective: float | None = None, scale_constraints: float | None = None, save_problem: bool = False, raise_on_failure: bool = True, add_objective: skt.ExpressionFunction | None = None, add_constraints: skt.ExpressionFunction | None = None, portfolio_params: dict | None = None, ): super().__init__( objective_function=ObjectiveFunction.MAXIMIZE_RATIO, risk_measure=RiskMeasure.VARIANCE, prior_estimator=prior_estimator, min_weights=min_weights, max_weights=max_weights, budget=budget, min_budget=min_budget, max_budget=max_budget, max_short=max_short, max_long=max_long, transaction_costs=transaction_costs, management_fees=management_fees, previous_weights=previous_weights, groups=groups, linear_constraints=linear_constraints, left_inequality=left_inequality, right_inequality=right_inequality, l1_coef=l1_coef, l2_coef=l2_coef, risk_free_rate=risk_free_rate, min_return=min_return, max_tracking_error=max_tracking_error, max_turnover=max_turnover, solver=solver, solver_params=solver_params, scale_objective=scale_objective, scale_constraints=scale_constraints, save_problem=save_problem, raise_on_failure=raise_on_failure, add_objective=add_objective, add_constraints=add_constraints, portfolio_params=portfolio_params, )
[docs] def fit( self, X: npt.ArrayLike, y: npt.ArrayLike | None = None, **fit_params ) -> "MaximumDiversification": """Fit the Maximum Diversification Optimization estimator. Parameters ---------- X : array-like of shape (n_observations, n_assets) Price returns of the assets. y : array-like of shape (n_observations, n_targets), optional Price returns of factors or a target benchmark. The default is `None`. **fit_params : dict Parameters to pass to the underlying estimators. Only available if `enable_metadata_routing=True`, which can be set by using ``sklearn.set_config(enable_metadata_routing=True)``. See :ref:`Metadata Routing User Guide <metadata_routing>` for more details. Returns ------- self : MaximumDiversification Fitted estimator. """ self._check_feature_names(X, reset=True) def func(w, obj): """weighted volatilities""" covariance = obj.prior_estimator_.prior_model_.covariance return np.sqrt(np.diag(covariance)) @ w self.overwrite_expected_return = func super().fit(X, y, **fit_params) return self