Base

`BaseComposer`

BaseComposer(
    model_name: str,
    signal_params=_Nothing.NOTHING,
    portfolio_params: Dict[str, Any] = _Nothing.NOTHING,
    model_params: Dict[str, Any] = _Nothing.NOTHING,
)

Compose portfolio(s). This abstract base class provides a framework for creating portfolio composers that can run models with varying parameters. Method generated by attrs for class BaseComposer.

Descendants

systematica.portfolio.composers.ColumnStackComposer
systematica.portfolio.composers.Composer
systematica.portfolio.composers.SignalComposer

Class variables

model_name: str: Name of the model to use. Should match to a model in systematica.api.models.
portfolio_params: Dict[str, Any]: Additional keyword arguments for portfolio simulation.
model_params: Dict[str, Any]: A dictionary of optional keyword arguments needed to compute the model.

Methods

`run`

run(
    self,
    data: vectorbtpro.data.base.Data,
    s1: str,
    s2: str,
    portfolio_kwargs: Dict[str, Any],
    **kwargs,
) ‑> systematica.portfolio.analyzer.PortfolioAnalyzer

Run the portfolio composer with the specified data. Parameters:

Name	Type	Default	Description
`data`	`vbt.Data`	`--`	Vector BT data object containing the input data.
`s1`	`str`	`--`	First symbol or identifier for the data.
`s2`	`str`	`--`	Second symbol or identifier for the data.
`portfolio_kwargs`	`tp.Kwargs`	`--`	Keyword arguments for portfolio configuration.
`kwargs`	`tp.Kwargs`	`--`	Additional keyword arguments passed to the model.

Returns:

Type	Description
`PortfolioAnalyzer`	Portfolio analyzer instance containing the results of the composition.

`BaseFrontier`

BaseFrontier(
    alpha: float = 0.05,
    a_sim: int = 100,
    beta: float = None,
    b_sim: int = None,
    kappa: float = 0.3,
    model: str = 'Classic',
    rm: str = 'MV',
    kelly: str = None,
    rf: float = 0.0,
    hist: bool = True,
    solver: str = 'CLARABEL',
    constraints: List[Dict[str, str]] = None,
    asset_classes: dict = _Nothing.NOTHING,
    config: Dict[str, Any] = _Nothing.NOTHING,
)

Base class for portfolio objects with all properties needed to calculate optimal portfolios. Risk Measures:

MV: Standard Deviation.
KT: Square Root of Kurtosis.
MAD: Mean Absolute Deviation.
GMD: Gini Mean Difference.
MSV: Semi Standard Deviation.
SKT: Square Root of Semi Kurtosis.
FLPM: First Lower Partial Moment (Omega Ratio).
SLPM: Second Lower Partial Moment (Sortino Ratio).
CVaR: Conditional Value at Risk.
TG: Tail Gini.
EVaR: Entropic Value at Risk.
RLVaR: Relativistic Value at Risk.
WR: Worst Realization (Minimax).
RG: Range of returns.
CVRG: CVaR range of returns.
TGRG: Tail Gini range of returns.
EVRG: EVaR range of returns.
RVRG: RLVaR range of returns. I recommend only use this function with MOSEK solver.
MDD: Maximum Drawdown of uncompounded cumulative returns (Calmar Ratio).
ADD: Average Drawdown of uncompounded cumulative returns.
CDaR: Conditional Drawdown at Risk of uncompounded cumulative returns.
EDaR: Entropic Drawdown at Risk of uncompounded cumulative returns.
RLDaR: Relativistic Drawdown at Risk of uncompounded cumulative returns.
UCI: Ulcer Index of uncompounded cumulative returns.

Method generated by attrs for class BaseFrontier.

Ancestors

abc.ABC
riskfolio.src.Portfolio.Portfolio

Descendants

systematica.portfolio.frontiers.FrontierAssetStats
systematica.portfolio.frontiers.FrontierBLFactorsStats
systematica.portfolio.frontiers.FrontierBLStats
systematica.portfolio.frontiers.FrontierFactorsStats
systematica.portfolio.frontiers.FrontierWCStats

Class variables

alpha: float: Significance level of VaR, CVaR, EVaR, RLVaR, DaR, CDaR, EDaR, RLDaR and Tail Gini of losses. The default is 0.05.
a_sim: int: Number of CVaRs used to approximate Tail Gini of losses. The default is 100.
beta: float: Significance level of CVaR and Tail Gini of gains. If None it duplicates alpha value. The default is None.
b_sim: int: Number of CVaRs used to approximate Tail Gini of gains. If None it duplicates a_sim value. The default is None.
model: str: Methodology used to estimate input parameters. The default is Classic.
rm: str: The risk measure used to optimize the portfolio. The default is MV. Possible values are displayed above.
kelly: str: Method used to calculate mean return. Possible values are: None for arithmetic mean return, “approx” for approximate mean logarithmic return using first and second moment and “exact” for mean logarithmic return. The default is None.
rf: float: Risk free rate. The default is 0.0.
hist: bool: Indicate what kind of returns are used to calculate risk measures that depends on scenarios (All except MV risk measure). The default is True. If model = BL, True means historical covariance and returns and False Black Litterman covariance and historical returns. If model = FM, True means historical covariance and returns and False Risk Factor model for covariance and returns. If model = BL_FM, True means historical covariance and returns, False Black Litterman with Risk Factor model for covariance and Risk Factor model for returns, and 2 Risk Factor model for covariance and returns.
solver: str: Solver available for CVXPY that supports power cone programming. Used to calculate RLVaR and RLDaR. The default value is CLARABEL.
constraints: List[Dict[str, str]]: Risk contribution constraints. Defaults to None.
asset_classes: dict: Asset classes.
config: Dict[str, Any]: Riskfolio-lib configuration. Overwrite other required parameters if referenced.

Instance variables

kappa: float: Deformation parameter of RLVaR and RLDaR for losses, must be between 0 and 1. The default is 0.30.
freq: Infer the frequency of the returns index.
ann_factor: Calculate the annualization factor based on the frequency.
x_axis: str: Generate the label for the x-axis based on the risk measure.
y_axis: str: Generate the label for the y-axis based on the Kelly criterion.
z_axis: str: Generate the label for the z-axis.

Methods

`init`

init(
    self,
    market_returns: pandas.core.frame.DataFrame,
)

Initialize the portfolio object with market returns. Parameters:

Name	Type	Default	Description
`market_returns`	`pd.DataFrame`	`--`	DataFrame containing market returns data.

Raises:

Type	Description
`ValueError`	If the cleaned market returns still contain `NaN` values.

`fit`

fit(
    self,
    market_returns: pandas.core.frame.DataFrame,
) ‑> systematica.portfolio.base.BaseFrontier

Abstract method to fit the portfolio model. Parameters:

Name	Type	Default	Description
`market_returns`	`pd.DataFrame`	`--`	Market returns data.

Returns:

Type	Description
`BaseFrontier`	Fitted portfolio object.

`add_constraints`

add_constraints(
    self,
) ‑> systematica.portfolio.base.BaseFrontier

Add inequality constraints to the portfolio. Returns:

Type	Description
`BaseFrontier`	Portfolio object with added constraints.

`predict`

predict(
    self,
    points: int = 20,
) ‑> pandas.core.frame.DataFrame

Predict the efficient frontier. Parameters:

Name	Type	Default	Description
`points`	`int`	`20`	Number of points to calculate on the frontier, by default 20.

Returns:

Type	Description
`pd.DataFrame`	DataFrame containing the efficient frontier.

`get_portfolio`

get_portfolio(
    self,
    weights: pandas.core.series.Series,
) ‑> pandas.core.frame.DataFrame

Calculate the portfolio performance based on the given weights. Parameters:

Name	Type	Default	Description
`weights`	`pd.Series`	`--`	Portfolio weights.

Returns:

Type	Description
`pd.DataFrame`	Target portfolio.

`get_efficient_frontier`

get_efficient_frontier(
    self,
    points: int = 20,
) ‑> pandas.core.frame.DataFrame

Calculate the efficient frontier. Parameters:

Name	Type	Default	Description
`points`	`int`	`20`	Number of points to calculate on the frontier, by default 20.

Returns:

Type	Description
`pd.DataFrame`	Efficient frontier.

`plot_frontier`

plot_frontier(
    self,
    weights,
    display_frontier: bool = True,
    points: int = 20,
    portfolio_name: str = 'Target Portfolio',
    marker_color: str = 'red',
    marker_size: int = 20,
    make_figure_kwargs: Dict[str, Any] | None = None,
    fig: plotly.basedatatypes.BaseFigure = None,
    showscale: bool = True,
    **layout_kwargs,
) ‑> vectorbtpro.utils.figure.FigureWidget

Plot the efficient frontier. Parameters:

Name	Type	Default	Description
`weights`	`pd.Series`	`--`	Portfolio weights.
`display_frontier`	`bool`	`True`	Display frontier. Defaults to True.
`portfolio_name`	`str`	`Target...`	Portfolio name. Defaults to “Target Portfolio”.
`marker_color`	`str`	`red`	Color of the portfolio star shaped marker. Defaults to “red”.
`marker_size`	`int`	`20`	Size of the portfolio star shaped marker. Default to 20.
`make_figure_kwargs`	`tp.KwargsLike`	`None`	Additional figure arguments, by default None.
`fig`	`tp.BaseFigure`	`None`	Existing figure to update, by default None.
`showscale`	`bool`	`True`	Whether to show the scale, by default True.
`layout_kwargs`	`tp.Kwargs`	`--`	Additional layout arguments for the figure.

Returns:

Type	Description
`vbt.FigureWidget`	A Plotly FigureWidget containing the frontier plot.

Overview

Analyzers

Composers

Frontier

Messengers

Metrics

Sandbox

Schedulers

Trackers

Transformers

Trial Selectors

Tuners

`BaseComposer`

Descendants

Class variables

Methods

`run`

`BaseFrontier`

Ancestors

Descendants

Class variables

Instance variables

Methods

`init`

`fit`

`add_constraints`

`predict`

`get_portfolio`

`get_efficient_frontier`

`plot_frontier`

Overview

Analyzers

Composers

Frontier

Messengers

Metrics

Sandbox

Schedulers

Trackers

Transformers

Trial Selectors

Tuners

​BaseComposer

​Descendants

​Class variables

​Methods

​run

​BaseFrontier

​Ancestors

​Descendants

​Class variables

​Instance variables

​Methods

​init

​fit

​add_constraints

​predict

​get_portfolio

​get_efficient_frontier

​plot_frontier

`BaseComposer`

Descendants

Class variables

Methods

`run`

`BaseFrontier`

Ancestors

Descendants

Class variables

Instance variables

Methods

`init`

`fit`

`add_constraints`

`predict`

`get_portfolio`

`get_efficient_frontier`

`plot_frontier`