Base - Systematica - Blockforce Capital

`BaseStatArb`

BaseStatArb()

Base Statistical Arbitrage class.

Ancestors

abc.ABC

Descendants

systematica.api.models.arbitrage_index.ArbitrageBaseIndex
systematica.api.models.arbitrage_index.ArbitrageClipIndex
systematica.api.models.arbitrage_index.ArbitrageCumulativeIndex
systematica.api.models.arbitrage_index.ArbitrageResetIndex
systematica.api.models.arbitrage_index.ArbitrageRollingZscoreIndex
systematica.api.models.meta_model.MetaModel
systematica.api.models.momentum.AverageMomentumFactorCV
systematica.api.models.momentum.RollingAverageMomentumFactor
systematica.api.models.ou_process.RollingOUProcess
systematica.api.models.range_breakout.RangeBreakout
systematica.api.models.range_breakout.RangeMeanReversion
systematica.api.models.volatility.RollingVolatilityFactor
systematica.api.models.volatility.VolatilityFactorCV
systematica.api.models.volume_profile.RollingVolumeProfileFactor
systematica.api.models.volume_profile.VolumeProfileFactorCV

Static methods

`is_valid`

is_valid(
    model_params: Dict[str, Any],
    signal_params: Dict[str, Any],
)

Validate model parameters. This method checks if the model parameters are valid for the statistical arbitrage model. It should be implemented in subclasses and decorated with staticmethod to allow calling it without an instance. If the model does not require validation, it can be implemented as a no-op method with the @staticmethod decorator. Examples: To implement this method, define it in the subclass and use the @staticmethod decorator like so:

>>> @staticmethod
>>> def is_valid(model_params: tp.Kwargs, signal_params: tp.Kwargs):
...     # Implement validation logic here
...     pass

Parameters:

Name	Type	Default	Description
`model_params`	`tp.Kwargs`	`--`	Model parameters.
`signal_params`	`tp.Kwargs`	`--`	Signal parameters.

`run_report`

run_report(
    data: vectorbtpro.data.base.Data,
    s1: str,
    s2: str,
    use_close: bool = True,
    freq: str = 'auto',
    use_rolling: bool = False,
    **model_params,
) ‑> systematica.api.base.BaseReportMixin

Analyzes model using rolling or cross-validation techniques. Parameters:

Name	Type	Default	Description
`data`	`vbt.Data`	`--`	Input data containing time series data.
`s1`	`str`	`--`	First symbol.
`s2`	`str`	`--`	Second symbol.
`use_close`	`bool`	`True`	Whether to use closing prices (`True`) or opening prices (`False`).
`freq`	`str`	`auto`	Frequency of the index used in `BaseReportCV`. If `auto`, try infer frequency from the index. Ignored in `BaseRollingReport`. Defaults to `auto`.
`use_rolling`	`bool`	`False`	Flag to use rolling method via `BaseRollingReport`. Note that both rolling and cv models can be passed. Fallbacks to `BaseReportCV` if model is not using `from_rolling` splitter without error message. Defaults to `False`.
`model_params`	`tp.Kwargs`	`--`	Parameters to pass to the model constructor.

Returns:

Type	Description
`BaseReportMixin`	An instance of `BaseRollingReport` or `BaseReportCV` depending on the model and parameters.

`get_report_metrics`

get_report_metrics(
    data: vectorbtpro.data.base.Data,
    s1: str,
    s2: str,
    signal_model: str,
    long_entries: float,
    long_exits: float,
    short_entries: float,
    short_exits: float,
    select_symbols: str | int | list[str | int] = None,
    use_close: bool = True,
    metrics: str | List[str] = 'sharpe_ratio',
    size: float | numpy.ndarray = 50,
    size_type: str | numpy.ndarray = 'valuepercent100',
    allow_partial: float | numpy.ndarray = None,
    fees: float | numpy.ndarray = None,
    fixed_fees: float | numpy.ndarray = None,
    slippage: float | numpy.ndarray = None,
    min_size: float | numpy.ndarray = None,
    max_size: float | numpy.ndarray = None,
    size_granularity: float | numpy.ndarray = None,
    sl_stop: float | numpy.ndarray = None,
    tsl_stop: float | numpy.ndarray = None,
    tp_stop: float | numpy.ndarray = None,
    accumulate: bool | str | numpy.ndarray = None,
    init_cash: float | numpy.ndarray = None,
    cash_sharing: bool = True,
    group_by: bool = True,
    call_seq: str | bool = 'auto',
    fill_pos_info: bool = False,
    log: bool | numpy.ndarray = None,
    to_numpy: bool = False,
    validate_metrics: bool = True,
    validate_model: bool = True,
    use_rolling: bool = False,
    freq: str = 'auto',
    portfolio_kwargs: Dict[str, Any] = None,
    **model_params,
) ‑> pandas.core.frame.DataFrame | numpy.ndarray

Run report: Analyzes model using rolling or cross-validation techniques. Parameters:

Name	Type	Default	Description
`data`	`vbt.Data`	`--`	Input data containing time series data.
`s1`	`str`	`--`	First symbol.
`s2`	`str`	`--`	Second symbol.
`signal_model`	`str`	`--`	Model used for generating signals.
`long_entries`	`float`	`--`	Long entry signals.
`long_exits`	`float`	`--`	Long exit signals.
`short_entries`	`float`	`--`	Short entry signals.
`short_exits`	`float`	`--`	Short exit signals.
`select_symbols`	`str`	`None`	Symbol name (e.g., `BTCUSDT` or `ETHUSDT`) or column index (e.g., `0` or `1`) to keep. If `None`, no filtering.
`use_close`	`bool, optional`	`--`	Whether to use ‘Close’ prices if `True` or ‘Open’ prices if `False. Default to` True`.
`metrics`	`str`	`sharpe_ratio`	Performance metrics to compute. Defaults to `sharpe_ratio`.
`size`	`float`	`50`	Size of each order. Defaults to `50`.
`size_type`	`str`	`valuepercent100`	Type of size. Defaults to `valuepercent100`.
`allow_partial`	`float`	`None`	Whether to allow partial fills. Defaults to `None`.
`fees`	`float`	`None`	Fees per order. Defaults to `None`.
`fixed_fees`	`float`	`None`	Fixed fees per order. Defaults to `None`.
`slippage`	`float`	`None`	Slippage per order. Defaults to `None`.
`min_size`	`float`	`None`	Minimum size of each order. Defaults to `None`.
`max_size`	`float`	`None`	Maximum size of each order. Defaults to `None`.
`size_granularity`	`float`	`None`	Granularity of size. Defaults to `None`.
`sl_stop`	`float`	`None`	Stop-loss level. Defaults to `None`.
`tsl_stop`	`float`	`None`	Trailing stop-loss level. Defaults to `None`.
`tp_stop`	`float`	`None`	Take-profit level. Defaults to `None`.
`accumulate`	`bool`	`None`	Whether to accumulate orders. Defaults to `None`.
`init_cash`	`float`	`None`	Initial cash. Defaults to `None`.
`cash_sharing`	`bool`	`True`	Whether to share cash between assets. Defaults to `True`.
`group_by`	`bool`	`True`	Whether to group by symbol. Defaults to `True`.
`call_seq`	`bool`	`auto`	Call sequence. Defaults to `auto`.
`fill_pos_info`	`bool`	`False`	Whether to fill position info. Defaults to `False`.
`log`	`bool`	`None`	Whether to log orders. Defaults to `None`.
`to_numpy`	`bool`	`False`	If `True`, returns a `np.ndarray`. Default is `False`, returning a `pd.DataFrame`.
`validate_metrics`	`bool`	`True`	Check if `metric` is valid in the registry. Defaults to `True`.
`validate_model`	`bool`	`True`	Check if model parameters are valid. Defaults to `True`.
`use_rolling`	`bool`	`False`	Flag to use rolling method via `BaseRollingReport`. Note that both rolling and cv models can be passed. Fallbacks to `BaseReportCV` if model is not using `from_rolling` splitter without error message. Defaults to `False`.
`freq`	`str`	`auto`	Frequency of the index used in `BaseReportCV`. If `auto`, try infer frequency from the index. Ignored in `BaseRollingReport`. Defaults to `auto`.
`portfolio_kwargs`	`tp.Kwargs`	`None`	Additional arguments for portfolio simulation.
`model_params`	`tp.Kwargs`	`--`	Parameters to pass to the model constructor.

Returns:

Type	Description
`pd.DataFrame \| tp.Array`	DataFrame or array containing portfolio performance metrics.

`run_analyzer`

run_analyzer(
    data: vectorbtpro.data.base.Data,
    s1: str,
    s2: str,
    signal_model: str,
    long_entries: float,
    long_exits: float,
    short_entries: float,
    short_exits: float,
    select_symbols: str | int | list[str | int] = None,
    use_close: bool = True,
    size: float | numpy.ndarray = 50,
    size_type: str | numpy.ndarray = 'valuepercent100',
    allow_partial: float | numpy.ndarray = None,
    fees: float | numpy.ndarray = None,
    fixed_fees: float | numpy.ndarray = None,
    slippage: float | numpy.ndarray = None,
    min_size: float | numpy.ndarray = None,
    max_size: float | numpy.ndarray = None,
    size_granularity: float | numpy.ndarray = None,
    sl_stop: float | numpy.ndarray = None,
    tsl_stop: float | numpy.ndarray = None,
    tp_stop: float | numpy.ndarray = None,
    accumulate: bool | str | numpy.ndarray = None,
    init_cash: float | numpy.ndarray = None,
    cash_sharing: bool = True,
    group_by: bool = True,
    call_seq: str | bool = 'auto',
    fill_pos_info: bool = False,
    log: bool | numpy.ndarray = None,
    portfolio_kwargs: Dict[str, Any] = None,
    validate_model: bool = True,
    **model_params,
) ‑> systematica.portfolio.analyzers.base.PortfolioAnalyzer

Executes the portfolio analyzer.

Combines scoring, signal generation, and portfolio simulation into a single pipeline for streamlined backtesting.

Parameters:

Name	Type	Default	Description
`data`	`vbt.Data`	`--`	Input vbt.Data containing time series data.
`s1`	`str`	`--`	Symbol.
`s2`	`str`	`--`	Symbol.
`signal_model`	`str`	`--`	Model used for generating signals.
`long_entries`	`float`	`--`	Long entry signals.
`long_exits`	`float`	`--`	Long exit signals.
`short_entries`	`float`	`--`	Short entry signals.
`short_exits`	`float`	`--`	Short exit signals.
`select_symbols`	`str`	`None`	Symbol name (e.g., `BTCUSDT` or `ETHUSDT`) or column index (e.g., `0` or `1`) to keep. If `None`, no filtering.
`size`	`float`	`50`	Size of each order. Defaults to `50`.
`size_type`	`str`	`valuepercent100`	Type of size. Defaults to `valuepercent100`.
`allow_partial`	`float`	`None`	Whether to allow partial fills. Defaults to `None`.
`fees`	`float`	`None`	Fees per order. Defaults to `None`.
`fixed_fees`	`float`	`None`	Fixed fees per order. Defaults to `None`.
`slippage`	`float`	`None`	Slippage per order. Defaults to `None`.
`min_size`	`float`	`None`	Minimum size of each order. Defaults to `None`.
`max_size`	`float`	`None`	Maximum size of each order. Defaults to `None`.
`size_granularity`	`float`	`None`	Granularity of size. Defaults to `None`.
`sl_stop`	`float`	`None`	Stop-loss level. Defaults to `None`.
`tsl_stop`	`float`	`None`	Trailing stop-loss level. Defaults to `None`.
`tp_stop`	`float`	`None`	Take-profit level. Defaults to `None`.
`accumulate`	`bool`	`None`	Whether to accumulate orders. Defaults to `None`.
`init_cash`	`float`	`None`	Initial cash. Defaults to `None`.
`cash_sharing`	`bool`	`True`	Whether to share cash between assets. Defaults to `True`.
`group_by`	`bool`	`True`	Whether to group by symbol. Defaults to `True`.
`call_seq`	`bool`	`auto`	Call sequence. Defaults to `auto`.
`fill_pos_info`	`bool`	`False`	Whether to fill position info. Defaults to `False`.
`log`	`bool`	`None`	Whether to log orders. Defaults to `None`.
`portfolio_kwargs`	`tp.Kwargs`	`None`	Additional arguments for portfolio simulation.
`to_numpy`	`bool`	`False`	If `True`, returns a `np.ndarray`. Default is `False`, returning a `pd.DataFrame`.
`validate_model`	`bool`	`True`	Check if model parameters are valid. Defaults to `True`.
`model_params`	`tp.Kwargs`	`--`	Additional parameters for `model_func`.

Returns:

Type	Description
`PortfolioAnalyzer`	An instance of `PortfolioAnalyzer` containing the results of the backtest.

`run_model`

run_model(
    cls,
    data: vectorbtpro.data.base.Data,
    s1: str,
    s2: str,
    use_close: bool = True,
    **model_params,
) ‑> pandas.core.frame.DataFrame

Run parameterized scores generation.

The method utilizes parameterization to run scores over various parameter combinations. The results can be merged and accessed as a single output object.

Parameters:

Name	Type	Default	Description
`data`	`vbt.Data`	`--`	Input vbt.Data containing time series data.
`s1`	`str`	`--`	First symbol.
`s2`	`str`	`--`	Second symbol.
`use_close`	`bool`	`True`	Use close price if `True`, otherwise use open price.
`model_params`	`tp.Kwargs`	`--`	Model arguments.

Returns:

Type	Description
`pd.DataFrame`	Scores for each parameter combination.

`run_signals`

run_signals(
    cls,
    data: vectorbtpro.data.base.Data,
    s1: str,
    s2: str,
    signal_model: str,
    long_entries: float,
    long_exits: float,
    short_entries: float,
    short_exits: float,
    select_symbols: str | int = None,
    use_close: bool = True,
    validate_model: bool = True,
    **model_params,
) ‑> pandas.core.frame.DataFrame

Run parametrized signals generation.

The method utilizes parameterization to run signal generation over various parameter combinations. The results can be merged and accessed as a single output object.

Parameters:

Name	Type	Default	Description
`data`	`vbt.Data`	`--`	Input vbt.Data containing time series data.
`s1`	`str`	`--`	Symbol.
`s2`	`str`	`--`	Symbol.
`signal_model`	`str`	`--`	Model or parameter for generating trading signals.
`long_entries`	`float`	`--`	Long entry signals.
`long_exits`	`float`	`--`	Long exit signals.
`short_entries`	`float`	`--`	Short entry signals.
`short_exits`	`float`	`--`	Short exit signals.
`select_symbols`	`str`	`None`	Symbol name (e.g., `BTCUSDT` or `ETHUSDT`) or column index (e.g., `0` or `1`) to keep. If `None`, no filtering.
`use_close`	`bool`	`True`	Use close price if `True`, otherwise use open price.
`validate_model`	`bool`	`True`	Validate model parameters. Defaults to `True`.
`model_params`	`tp.Kwargs`	`--`	Model arguments.

Returns:

Type	Description
`pd.DataFrame`	Signals for each parameter combination.

`run_pipeline`

run_pipeline(
    cls,
    data: vectorbtpro.data.base.Data,
    s1: str,
    s2: str,
    signal_model: str,
    long_entries: float,
    long_exits: float,
    short_entries: float,
    short_exits: float,
    select_symbols: str | int | list[str | int] = None,
    metrics: str | List[str] = None,
    use_rolling: bool = False,
    metric_registry_kwargs: Dict[str, Any] = None,
    use_close: bool = True,
    size: float | numpy.ndarray = 50,
    size_type: str | numpy.ndarray = 'valuepercent100',
    allow_partial: float | numpy.ndarray = None,
    fees: float | numpy.ndarray = None,
    fixed_fees: float | numpy.ndarray = None,
    slippage: float | numpy.ndarray = None,
    min_size: float | numpy.ndarray = None,
    max_size: float | numpy.ndarray = None,
    size_granularity: float | numpy.ndarray = None,
    sl_stop: float | numpy.ndarray = None,
    tsl_stop: float | numpy.ndarray = None,
    tp_stop: float | numpy.ndarray = None,
    accumulate: bool | str | numpy.ndarray = None,
    init_cash: float | numpy.ndarray = None,
    cash_sharing: bool = True,
    group_by: bool = True,
    call_seq: str | bool = 'auto',
    fill_pos_info: bool = False,
    log: bool | numpy.ndarray = None,
    portfolio_kwargs: Dict[str, Any] = None,
    to_numpy: bool = False,
    validate_metrics: bool = True,
    validate_model: bool = True,
    **model_params,
) ‑> vectorbtpro.portfolio.base.Portfolio | collections.OrderedDict | pandas.core.frame.DataFrame | numpy.ndarray

Executes the portfolio pipeline. Method is parametrizable.

Combines scoring, signal generation, and portfolio simulation into a single pipeline for streamlined backtesting.

Parameters:

Name	Type	Default	Description
`data`	`vbt.Data`	`--`	Input vbt.Data containing time series data.
`s1`	`str`	`--`	First symbol.
`s2`	`str`	`--`	Second symbol.
`signal_model`	`str`	`--`	Model used for generating signals.
`long_entries`	`float`	`--`	Long entry signals.
`long_exits`	`float`	`--`	Long exit signals.
`short_entries`	`float`	`--`	Short entry signals.
`short_exits`	`float`	`--`	Short exit signals.
`select_symbols`	`str`	`None`	Symbol name (e.g., `BTCUSDT` or `ETHUSDT`) or column index (e.g., `0` or `1`) to keep. If `None`, no filtering.
`metrics`	`str`	`sharpe_ratio`	Performance metrics to compute. Defaults to `sharpe_ratio`.
`use_rolling`	`bool`	`False`	Flag to use rolling method via `BaseRollingReport`. Note that both rolling and cv models can be passed. Fallbacks to `BaseReportCV` if model is not using `from_rolling` splitter without error message. Defaults to `False`.
`metric_registry_kwargs`	`tp.Kwargs`	`None`	Parameters for metric registry. If `None`, uses default parameters based on the model type. This is used to specify parameters such as `window` or `minp` for rolling metrics. If using cross-validation, this should be set to `None` as it is not applicable. If using rolling metrics, this should be set to a dictionary with parameters for the metric registry. For example, `{"window": 20}`. Defaults to `None`.
`use_close`	`bool, optional`	`--`	Whether to use ‘Close’ prices if `True` or ‘Open’ prices if `False. Default to` True`.
`size`	`float`	`50`	Size of each order. Defaults to `50`.
`size_type`	`str`	`valuepercent100`	Type of size. Defaults to `valuepercent100`.
`allow_partial`	`float`	`None`	Whether to allow partial fills. Defaults to `None`.
`fees`	`float`	`None`	Fees per order. Defaults to `None`.
`fixed_fees`	`float`	`None`	Fixed fees per order. Defaults to `None`.
`slippage`	`float`	`None`	Slippage per order. Defaults to `None`.
`min_size`	`float`	`None`	Minimum size of each order. Defaults to `None`.
`max_size`	`float`	`None`	Maximum size of each order. Defaults to `None`.
`size_granularity`	`float`	`None`	Granularity of size. Defaults to `None`.
`sl_stop`	`float`	`None`	Stop-loss level. Defaults to `None`.
`tsl_stop`	`float`	`None`	Trailing stop-loss level. Defaults to `None`.
`tp_stop`	`float`	`None`	Take-profit level. Defaults to `None`.
`accumulate`	`bool`	`None`	Whether to accumulate orders. Defaults to `None`.
`init_cash`	`float`	`None`	Initial cash. Defaults to `None`.
`cash_sharing`	`bool`	`True`	Whether to share cash between assets. Defaults to `True`.
`group_by`	`bool`	`True`	Whether to group by symbol. Defaults to `True`.
`call_seq`	`bool`	`auto`	Call sequence. Defaults to `auto`.
`fill_pos_info`	`bool`	`False`	Whether to fill position info. Defaults to `False`.
`log`	`bool`	`None`	Whether to log orders. Defaults to `None`.
`portfolio_kwargs`	`tp.Kwargs`	`None`	Additional keyword arguments for the portfolio simulation.
`to_numpy`	`bool`	`False`	If `True`, returns a `np.ndarray`. Default is `False`, returning a `pd.DataFrame`.
`validate_metrics`	`bool`	`True`	Check if `metric` is valid in the registry. Defaults to `True`.
`validate_model`	`bool`	`True`	Check if model parameters are valid. Defaults to `True`.
`model_params`	`tp.Kwargs`	`--`	Additional parameters for `model_func`.

Returns:

Type	Description
`vbt.PF \| OrderedDict \| pd.DataFrame \| tp.Array`	Backtested portfolio or requested metrics.

`run_optuna_study`

run_optuna_study(
    data: vectorbtpro.data.base.Data,
    s1: str,
    s2: str,
    signal_model: str,
    long_entries: float,
    long_exits: float,
    short_entries: float,
    short_exits: float,
    *,
    select_symbols: str | int | list[str | int] = None,
    use_close: bool = True,
    metrics: str | List[str] = 'sharpe_ratio',
    metric_registry_kwargs: Dict[str, Any] = None,
    pruner: optuna.pruners._base.BasePruner = None,
    sampler: optuna.samplers._base.BaseSampler = None,
    direction: str | List[str] = 'maximize',
    create_study_kwargs: Dict[str, Any] = None,
    n_trials: int = 100,
    n_completed_trials: int = None,
    n_jobs: int = -1,
    gc_after_trial: bool = False,
    optimize_kwargs: Dict[str, Any] = None,
    verbose: bool = True,
    tracker: ~BaseTracker = None,
    cross_validate: bool = False,
    reduce_func: Callable = None,
    use_rolling: bool = False,
    size: float | numpy.ndarray = 50,
    size_type: str | numpy.ndarray = 'valuepercent100',
    allow_partial: float | numpy.ndarray = None,
    fees: float | numpy.ndarray = None,
    fixed_fees: float | numpy.ndarray = None,
    slippage: float | numpy.ndarray = None,
    min_size: float | numpy.ndarray = None,
    max_size: float | numpy.ndarray = None,
    size_granularity: float | numpy.ndarray = None,
    sl_stop: float | numpy.ndarray = None,
    tsl_stop: float | numpy.ndarray = None,
    tp_stop: float | numpy.ndarray = None,
    accumulate: bool | str | numpy.ndarray = None,
    init_cash: float | numpy.ndarray = None,
    cash_sharing: bool = True,
    group_by: bool = True,
    call_seq: str | bool = 'auto',
    fill_pos_info: bool = False,
    log: bool | numpy.ndarray = None,
    portfolio_kwargs: Dict[str, Any] = None,
    freq: str = None,
    **model_params,
) ‑> optuna.study.study.Study

Run hyperparameter optimization using optuna for a signal-based trading strategy.

Optuna is used for hyperparameter tuning and efficiently finds the best parameters.
The study prunes trials with poor results to accelerate the search process.

References:

Parameters:

Name	Type	Default	Description
`data`	`vbt.Data`	`--`	Market data used for generating trading signals and backtesting.
`s1`	`str`	`--`	First symbol.
`s2`	`str`	`--`	Second symbol.
`signal_model`	`str`	`--`	The signal generation model that determines entry and exit points.
`long_entries`	`float`	`--`	Long entry signals.
`long_exits`	`float`	`--`	Long exit signals.
`short_entries`	`float`	`--`	Short entry signals.
`short_exits`	`float`	`--`	Short exit signals.
`select_symbols`	`str`	`None`	Symbol name (e.g., `BTCUSDT` or `ETHUSDT`) or column index (e.g., `0` or `1`) to keep. If `None`, no filtering.
`use_close`	`bool, optional`	`--`	Whether to use ‘Close’ prices if `True` or ‘Open’ prices if `False. Default to` True`.
`metrics`	`str`	`sharpe_ratio`	Performance metrics to compute. Defaults to `sharpe_ratio`.
`metric_registry_kwargs`	`tp.Kwargs`	`None`	Parameters for metric registry. If `None`, uses default parameters based on the model type. This is used to specify parameters such as `window` or `minp` for rolling metrics. If using cross-validation, this should be set to `None` as it is not applicable. If using rolling metrics, this should be set to a dictionary with parameters for the metric registry. For example, `{"window": 20}`. Defaults to `None`.
`pruner`	`optuna.pruners.BasePruner`	`None`	Optuna Pruner. If `None`, defaults to Asynchronous Successive Halving Algorithm. Defaults to `None`.
`sampler`	`optuna.samplers.BaseSampler`	`--`	Optuna Sampler. If `None`, defaults to TPE (Tree-structured Parzen Estimator) algorithm. Defaults to `None`.
`direction`	`str`	`maximize`	Optimization objective, either `minimize` or `maximize`, default is `maximize`.
`create_study_kwargs`	`tp.Kwargs`	`None`	Additional arguments for `optuna.create_study`, default is `None`.
`n_trials`	`int`	`100`	The number of trials for the optimization. This is the maximum number of trials that will be run. If `n_completed_trials` is set, the optimization will stop when the number of completed trials reaches this value. If `n_completed_trials` is not set, the optimization will run for `n_trials` trials. If `n_trials` is set to `None`, it will run indefinitely until `n_completed_trials` is reached. If `n_trials` is set to `0`, it will not run any trials. If `n_trials` is set to a negative value, it will run indefinitely until `n_completed_trials` is reached. Defaults to `100`.
`n_completed_trials`	`int`	`None`	The number of successfully completed trials before stopping the optimization. If `None`, it will run for `n_trials` trials. TO be effective, the number of trials should be higher than the number of completed trials. default is `None`.
`n_jobs`	`int`	`-1`	Number of parallel jobs for optimization (`-1` for using all available `CPUs` cores), default is `-1`.
`gc_after_trial`	`bool`	`False`	Flag to determine whether to automatically run garbage collection after each trial. Set to `True` to run the garbage collection, `False` otherwise. It runs a full collection by internally calling `gc.collect`. If you see an increase in memory consumption over several trials, try setting this flag to `True`. Defaults to `False`.
`optimize_kwargs`	`dict`	`None`	Additional arguments for `study.optimize`, default is `None`.
`verbose`	`bool`	`True`	Whether to print Optuna logs during the optimization process. If True, prints logs to the console. Default is `True`.
`tracker`	`BaseTracker`	`None`	Tracker instance for logging and monitoring the optimization process. If `None`, no tracking is performed. If you want to use a tracker, you can pass an instance of a tracker class that inherits from `BaseTracker`. For example, you can use `NeptuneTracker`. This tracker will log the optimization process and metrics to the tracker service. Default to None.
`cross_validate`	`bool`	`False`	If `True`, uses cross-validation analytics through `run_report`, wrapping `BaseReportCV` instead of `_apply_pipeline`. If `False`, uses data history as a whole. This is useful for optimizing the model using cross-validation. Defaults to `False`.
`reduce_func`	`tp.Callable`	`None`	Function to reduce the results of the cross-validation. This function should take a 2D array of shape (n_trials, n_metrics) and return a 1D array of shape (n_metrics). This is used to reduce the results of the cross-validation to a single value for each metric. If `None`, defaults to `vbt.nb.nanmedian_nb`, which computes the median of the cross-validation results while ignoring NaN values. Defaults to None.
`use_rolling`	`bool`	`False`	Flag to use rolling method via `BaseRollingReport`. Note that both rolling and cv models can be passed. Fallbacks to `BaseReportCV` if model is not using “from_rolling” splitter without error message. Defaults to `False`.
`size`	`float`	`50`	Size of each order. Defaults to `50`.
`size_type`	`str`	`valuepercent100`	Type of size. Defaults to `valuepercent100`.
`allow_partial`	`float`	`None`	Whether to allow partial fills. Defaults to `None`.
`fees`	`float`	`None`	Fees per order. Defaults to `None`.
`fixed_fees`	`float`	`None`	Fixed fees per order. Defaults to `None`.
`slippage`	`float`	`None`	Slippage per order. Defaults to `None`.
`min_size`	`float`	`None`	Minimum size of each order. Defaults to `None`.
`max_size`	`float`	`None`	Maximum size of each order. Defaults to `None`.
`size_granularity`	`float`	`None`	Granularity of size. Defaults to `None`.
`sl_stop`	`float`	`None`	Stop-loss level. Defaults to `None`.
`tsl_stop`	`float`	`None`	Trailing stop-loss level. Defaults to `None`.
`tp_stop`	`float`	`None`	Take-profit level. Defaults to `None`.
`accumulate`	`bool`	`None`	Whether to accumulate orders. Defaults to `None`.
`init_cash`	`float`	`None`	Initial cash. Defaults to `None`.
`cash_sharing`	`bool`	`True`	Whether to share cash between assets. Defaults to `True`.
`group_by`	`bool`	`True`	Whether to group by symbol. Defaults to `True`.
`call_seq`	`bool`	`auto`	Call sequence. Defaults to `auto`.
`fill_pos_info`	`bool`	`False`	Whether to fill position info. Defaults to `False`.
`log`	`bool`	`None`	Whether to log orders. Defaults to `None`.
`portfolio_kwargs`	`tp.Kwargs`	`None`	Additional keyword arguments for the portfolio simulation.
`freq`	`str`	`None`	Frequency of the data. Used when `cross_validate` is `True`. Defaults to `None`.
`model_params`	`tp.Kwargs`	`--`	Additional model parameters to optimize.

Returns:

Type	Description
`optuna.Study`	The Optuna study object containing optimization results.

Methods

`get_signals`

get_signals(
    self,
    model_output: numpy.ndarray,
    signal_model: str,
    long_entries: float,
    long_exits: float,
    short_entries: float,
    short_exits: float,
    select_symbols: str | int | list[str | int] = None,
) ‑> systematica.signals.base.Signals

Generate trading signals based on scores. Parameters:

Name	Type	Default	Description
`model_output`	`tp.Array`	`--`	Model output used for signal generation.
`signal_model`	`str`	`--`	Signal model used for generating signals.
`long_entries`	`float`	`--`	Long entry signals.
`long_exits`	`float`	`--`	Long exit signals.
`short_entries`	`float`	`--`	Short entry signals.
`short_exits`	`float`	`--`	Short exit signals.
`select_symbols`	`str`	`None`	Symbol name (e.g., `BTCUSDT` or `ETHUSDT`) or column index (e.g., `0` or `1`) to keep. If `None`, no filtering.

Returns:

Type	Description
`Signals`	Generated signals.

`BaseReportMixin`

BaseReportMixin()

Report mixin used in both rolling and cross-validated versions.

Ancestors

abc.ABC

Descendants

systematica.api.base.BaseReportCV
systematica.api.base.BaseRollingReport

Instance variables

all_metrics: List[str]: Get all available metrics
price_data: Retrieves price data for the specified symbols.
non_tunable_metrics: List[str]: Retrieves all non-tunable metrics from registry

Methods

`get_annualized_return`

get_annualized_return(
    self,
) ‑> pandas.core.frame.DataFrame

Computes the rolling (annualized) returns. Returns:

Type	Description
`pd.DataFrame`	DataFrame containing rolling annualized returns.

`get_portfolio_metric`

get_portfolio_metric(
    self,
    **kwargs,
) ‑> pandas.core.frame.DataFrame | numpy.ndarray

Computes portfolio performance metrics for different test sets. Parameters:

Name	Type	Default	Description
`kwargs`	`tp.Kwargs`	`--`	Additional arguments to run the pipeline.

Returns:

Type	Description
`pd.DataFrame \| tp.Array`	DataFrame or array containing portfolio performance metrics.

`get_model_output`

get_model_output(
    self,
    to_numpy: bool = False,
) ‑> numpy.ndarray | pandas.core.series.Series | pandas.core.frame.DataFrame

Computes the model output. Parameters:

Name	Type	Default	Description
`to_numpy`	`bool`	`False`	If `True`, converts output to a `np.array`. Default is `False`, returning a `pd.DataFrame`.

Returns:

Type	Description
`np.ndarray or pd.DataFrame`	Model output data.

`set_labels`

set_labels(
    self,
    group_by: bool,
    metrics: str | List[str],
) ‑> List[str]

Generate column labels for the output DataFrame. Parameters:

Name	Type	Default	Description
`group_by`	`bool`	`--`	Whether to group results by symbol.
`metrics`	`str`	`--`	List of metrics to compute.

Returns:

Type	Description
`List`	List of column names.

`plot_annualized_return`

plot_annualized_return(
    self,
    fig: vectorbtpro.utils.figure.FigureWidget = None,
    **layout_kwargs,
) ‑> vectorbtpro.utils.figure.FigureWidget

Plots total returns over time. Parameters:

Name	Type	Default	Description
`fig`	`vbt.FigureWidget`	`None`	Existing figure to update.
`layout_kwargs`	`tp.Kwargs`	`--`	Additional layout arguments for the plot.

Returns:

Type	Description
`vbt.FigureWidget`	Figure with the plotted total returns.

`plot_model_output`

plot_model_output(
    self,
    fig: vectorbtpro.utils.figure.FigureWidget = None,
    **layout_kwargs,
) ‑> vectorbtpro.utils.figure.FigureWidget

Plots model output over time. Parameters:

Name	Type	Default	Description
`fig`	`vbt.FigureWidget`	`None`	Existing figure to update.
`layout_kwargs`	`tp.Kwargs`	`--`	Additional layout arguments for the plot.

Returns:

Type	Description
`vbt.FigureWidget`	Figure with the plotted model output.

`plot_portfolio_metric`

plot_portfolio_metric(
    self,
    signal_model: str,
    long_entries: float,
    long_exits: float,
    short_entries: float,
    short_exits: float,
    select_symbols: str | int | list[str | int] = None,
    metrics: str | List[str] = 'sharpe_ratio',
    size: float | numpy.ndarray = 50,
    size_type: str | numpy.ndarray = 'valuepercent100',
    allow_partial: float | numpy.ndarray = None,
    fees: float | numpy.ndarray = None,
    fixed_fees: float | numpy.ndarray = None,
    slippage: float | numpy.ndarray = None,
    min_size: float | numpy.ndarray = None,
    max_size: float | numpy.ndarray = None,
    size_granularity: float | numpy.ndarray = None,
    sl_stop: float | numpy.ndarray = None,
    tsl_stop: float | numpy.ndarray = None,
    tp_stop: float | numpy.ndarray = None,
    accumulate: bool | str | numpy.ndarray = None,
    init_cash: float | numpy.ndarray = None,
    cash_sharing: bool = True,
    group_by: bool = True,
    call_seq: str | bool = 'auto',
    fill_pos_info: bool = False,
    log: bool | numpy.ndarray = None,
    fig: vectorbtpro.utils.figure.FigureWidget = None,
    layout_kwargs: Dict[str, Any] = None,
    **portfolio_kwargs,
) ‑> vectorbtpro.utils.figure.FigureWidget

Plot portfolio performance metrics over time. Parameters:

Name	Type	Default	Description
`signal_model`	`str`	`--`	Model used for generating signals.
`long_entries`	`float`	`--`	Long entry signals.
`long_exits`	`float`	`--`	Long exit signals.
`short_entries`	`float`	`--`	Short entry signals.
`short_exits`	`float`	`--`	Short exit signals.
`select_symbols`	`str`	`None`	Symbol name (e.g., `BTCUSDT` or `ETHUSDT`) or column index (e.g., `0` or `1`) to keep. If `None`, no filtering.
`metrics`	`str`	`sharpe_ratio`	Performance metrics to compute. Defaults to `sharpe_ratio`.
`size`	`float`	`50`	Size of each order. Defaults to `50`.
`size_type`	`str`	`valuepercent100`	Type of size. Defaults to `valuepercent100`.
`allow_partial`	`float`	`None`	Whether to allow partial fills. Defaults to `None`.
`fees`	`float`	`None`	Fees per order. Defaults to `None`.
`fixed_fees`	`float`	`None`	Fixed fees per order. Defaults to `None`.
`slippage`	`float`	`None`	Slippage per order. Defaults to `None`.
`min_size`	`float`	`None`	Minimum size of each order. Defaults to `None`.
`max_size`	`float`	`None`	Maximum size of each order. Defaults to `None`.
`size_granularity`	`float`	`None`	Granularity of size. Defaults to `None`.
`sl_stop`	`float`	`None`	Stop-loss level. Defaults to `None`.
`tsl_stop`	`float`	`None`	Trailing stop-loss level. Defaults to `None`.
`tp_stop`	`float`	`None`	Take-profit level. Defaults to `None`.
`accumulate`	`bool`	`None`	Whether to accumulate orders. Defaults to `None`.
`init_cash`	`float`	`None`	Initial cash. Defaults to `None`.
`cash_sharing`	`bool`	`True`	Whether to share cash between assets. Defaults to `True`.
`group_by`	`bool`	`True`	Whether to group by symbol. Defaults to `True`.
`call_seq`	`bool`	`auto`	Call sequence. Defaults to `auto`.
`fill_pos_info`	`bool`	`False`	Whether to fill position info. Defaults to `False`.
`log`	`bool`	`None`	Whether to log orders. Defaults to `None`.
`fig`	`vbt.FigureWidget`	`None`	Existing figure to update. If `None`, a new figure is created. Defaults to `None`.
`layout_kwargs`	`dict`	`None`	Additional layout arguments for the plot. If `None`, uses default layout settings. Defaults to `None`.
`portfolio_kwargs`	`tp.Kwargs`	`--`	Additional arguments for portfolio simulation.

Returns:

Type	Description
`vbt.FigureWidget`	Figure with the plotted portfolio performance metrics.

`BaseReportCV`

BaseReportCV(
    data: vectorbtpro.data.base.Data,
    s1: str,
    s2: str,
    model: ~BaseStatArb,
    use_close: bool = True,
    freq: str = 'auto',
)

Analyzes a statistical arbitrage model using cross-validation. Method generated by attrs for class BaseReportCV.

Ancestors

systematica.api.base.BaseReportMixin
abc.ABC

Descendants

systematica.api.reports.arbitrage_index.ArbitrageIndexReport
systematica.api.reports.meta_model.MetaModelCVReport
systematica.api.reports.momentum.AverageMomentumFactorCVReport
systematica.api.reports.momentum.MomentumFactorCVReport
systematica.api.reports.ou_process.OUProcessCVReport
systematica.api.reports.range_breakout.RangeBreakoutReport
systematica.api.reports.volatility.VolatilityFactorCVReport
systematica.api.reports.volume_profile.VolumeProfileFactorCVReport

Instance variables

splitter: systematica.utils.custom_splitter.CustomSplitter: Split arrays or matrices into specified train and test subsets.
splits: pandas.core.frame.DataFrame: Retrieves data splits based on the cross-validation splitter.
index_test: pandas.core.indexes.base.Index: Computes and returns the test set index of the dataset. The test set index is derived from the end bounds values returned by the splitter.
all_metrics: List[str]: Get available cross-validation metrics.
data: vectorbtpro.data.base.Data: Input data containing time series data.
freq: str: Set frequency. Default is auto, which infers frequency from the data index.
model: ~BaseStatArb: Model to analyse.
s1: str: Symbol.
s2: str: Symbol.
use_close: bool: Price close or open. Default is True, using close prices.

Methods

`check`

check(
    self,
    attribute: Type,
    value: Any,
)

Validates CV model. Parameters:

Name	Type	Default	Description
`attribute`	`tp.Type`	`--`	The attribute being validated.
`value`	`tp.Any`	`--`	The model instance.

Raises:

Type	Description
`AttributeError`	If the model does not use `splitter` as a parameter.

`price_reset_stacked_by_set`

price_reset_stacked_by_set(
    self,
) ‑> pandas.core.frame.DataFrame

Resets the price data stacked by set and attaches bounds to the index. This method uses the splitter to reset the price data, stacking it by set and attaching bounds to the index. Returns:

Type	Description
`pd.DataFrame`	The reset price data stacked by set with bounds attached to the index.

`model_reset_stacked_by_set`

model_reset_stacked_by_set(
    self,
) ‑> pandas.core.frame.DataFrame

Resets the model output stacked by set and attaches bounds to the index. This method uses the splitter to reset the model output, stacking it by set and attaching bounds to the index. Returns:

Type	Description
`pd.DataFrame`	The reset model output stacked by set with bounds attached to the index.

`get_annualized_return`

get_annualized_return(
    self,
) ‑> pandas.core.series.Series

Computes the annualized returns for the test set. Returns:

Type	Description
`pd.Series`	Series containing the annualized returns for the test set.

`get_portfolio_metric`

get_portfolio_metric(
    self,
    signal_model: str,
    long_entries: float,
    long_exits: float,
    short_entries: float,
    short_exits: float,
    select_symbols: str | int | list[str | int] = None,
    metrics: str | List[str] = 'sharpe_ratio',
    size: float | numpy.ndarray = 50,
    size_type: str | numpy.ndarray = 'valuepercent100',
    allow_partial: float | numpy.ndarray = None,
    fees: float | numpy.ndarray = None,
    fixed_fees: float | numpy.ndarray = None,
    slippage: float | numpy.ndarray = None,
    min_size: float | numpy.ndarray = None,
    max_size: float | numpy.ndarray = None,
    size_granularity: float | numpy.ndarray = None,
    sl_stop: float | numpy.ndarray = None,
    tsl_stop: float | numpy.ndarray = None,
    tp_stop: float | numpy.ndarray = None,
    accumulate: bool | str | numpy.ndarray = None,
    init_cash: float | numpy.ndarray = None,
    cash_sharing: bool = True,
    group_by: bool = True,
    call_seq: str | bool = 'auto',
    fill_pos_info: bool = False,
    log: bool | numpy.ndarray = None,
    to_numpy: bool = False,
    validate_metrics: bool = True,
    validate_model: bool = True,
    **portfolio_kwargs,
) ‑> pandas.core.frame.DataFrame | numpy.ndarray

Computes portfolio performance metrics for different test sets. Parameters:

Name	Type	Default	Description
`signal_model`	`str`	`--`	Model used for generating signals.
`long_entries`	`float`	`--`	Long entry signals.
`long_exits`	`float`	`--`	Long exit signals.
`short_entries`	`float`	`--`	Short entry signals.
`short_exits`	`float`	`--`	Short exit signals.
`select_symbols`	`str`	`None`	Symbol name (e.g., `BTCUSDT` or `ETHUSDT`) or column index (e.g., `0` or `1`) to keep. If `None`, no filtering.
`metrics`	`str`	`sharpe_ratio`	Performance metrics to compute. Defaults to `sharpe_ratio`.
`size`	`float`	`50`	Size of each order. Defaults to `50`.
`size_type`	`str`	`valuepercent100`	Type of size. Defaults to `valuepercent100`.
`allow_partial`	`float`	`None`	Whether to allow partial fills. Defaults to `None`.
`fees`	`float`	`None`	Fees per order. Defaults to `None`.
`fixed_fees`	`float`	`None`	Fixed fees per order. Defaults to `None`.
`slippage`	`float`	`None`	Slippage per order. Defaults to `None`.
`min_size`	`float`	`None`	Minimum size of each order. Defaults to `None`.
`max_size`	`float`	`None`	Maximum size of each order. Defaults to `None`.
`size_granularity`	`float`	`None`	Granularity of size. Defaults to `None`.
`sl_stop`	`float`	`None`	Stop-loss level. Defaults to `None`.
`tsl_stop`	`float`	`None`	Trailing stop-loss level. Defaults to `None`.
`tp_stop`	`float`	`None`	Take-profit level. Defaults to `None`.
`accumulate`	`bool`	`None`	Whether to accumulate orders. Defaults to `None`.
`init_cash`	`float`	`None`	Initial cash. Defaults to `None`.
`cash_sharing`	`bool`	`True`	Whether to share cash between assets. Defaults to `True`.
`group_by`	`bool`	`True`	Whether to group by symbol. Defaults to `True`.
`call_seq`	`bool`	`auto`	Call sequence. Defaults to `auto`.
`fill_pos_info`	`bool`	`False`	Whether to fill position info. Defaults to `False`.
`log`	`bool`	`None`	Whether to log orders. Defaults to `None`.
`to_numpy`	`bool`	`False`	If `True`, returns a `np.ndarray`. Default is `False`, returning a `pd.DataFrame`.
`validate_metrics`	`bool`	`True`	Check if `metric` is valid in the registry. Defaults to `True`.
`validate_model`	`bool`	`True`	Check if model parameters are valid. Defaults to `True`.
`portfolio_kwargs`	`tp.Kwargs`	`--`	Additional arguments for portfolio simulation.

Returns:

Type	Description
`pd.DataFrame \| tp.Array`	Portfolio performance metrics.

`BaseRollingReport`

BaseRollingReport(
    data: vectorbtpro.data.base.Data,
    s1: str,
    s2: str,
    model: ~BaseStatArb,
    use_close: bool = True,
    freq: str = 'auto',
)

Analyzes a statistical arbitrage model using rolling metrics. Method generated by attrs for class BaseRollingReport.

Ancestors

systematica.api.base.BaseReportMixin
abc.ABC

Descendants

systematica.api.reports.meta_model.RollingMetaModelReport
systematica.api.reports.momentum.RollingAverageMomentumFactorReport
systematica.api.reports.momentum.RollingMomentumFactorReport
systematica.api.reports.ou_process.RollingOUProcessReport
systematica.api.reports.volatility.RollingVolatilityFactorReport
systematica.api.reports.volume_profile.RollingVolumeProfileFactorReport

Instance variables

window: int: Window size.
minp: None | int: Minimum number of observations required.
all_metrics: List[str]: Get available rolling metrics.
data: vectorbtpro.data.base.Data: Input data containing time series data.
freq: str: Set frequency.
model: ~BaseStatArb: Model to analyse.
s1: str: Symbol.
s2: str: Symbol.
use_close: bool: Price close or open.

Methods

`check`

check(
    self,
    attribute: Type,
    value: Any,
)

Validates that the model has the necessary parameters for the strategy. Specifically, the model must have either:

Both window and minp attributes, or
Both train_window and splitter (set to *_rolling).

Parameters:

Name	Type	Default	Description
`attribute`	`tp.Type`	`--`	The attribute being validated.
`value`	`tp.Any`	`--`	The value being set (not used in this validator).

Raises:

Type	Description
`ValueError`	If the model does not have either `window` and `minp` or `train_window` and `splitter=="*_rolling"`).

`get_portfolio_metric`

get_portfolio_metric(
    self,
    signal_model: str,
    long_entries: float,
    long_exits: float,
    short_entries: float,
    short_exits: float,
    select_symbols: str | int | list[str | int] = None,
    metrics: str | List[str] = 'sharpe_ratio',
    size: float | numpy.ndarray = 50,
    size_type: str | numpy.ndarray = 'valuepercent100',
    allow_partial: float | numpy.ndarray = None,
    fees: float | numpy.ndarray = None,
    fixed_fees: float | numpy.ndarray = None,
    slippage: float | numpy.ndarray = None,
    min_size: float | numpy.ndarray = None,
    max_size: float | numpy.ndarray = None,
    size_granularity: float | numpy.ndarray = None,
    sl_stop: float | numpy.ndarray = None,
    tsl_stop: float | numpy.ndarray = None,
    tp_stop: float | numpy.ndarray = None,
    accumulate: bool | str | numpy.ndarray = None,
    init_cash: float | numpy.ndarray = None,
    cash_sharing: bool = True,
    group_by: bool = True,
    call_seq: str | bool = 'auto',
    fill_pos_info: bool = False,
    log: bool | numpy.ndarray = None,
    to_numpy: bool = False,
    validate_metrics: bool = True,
    validate_model: bool = True,
    **portfolio_kwargs,
) ‑> pandas.core.frame.DataFrame | numpy.ndarray

Computes portfolio performance metrics on a rolling basis. Parameters:

Name	Type	Default	Description
`signal_model`	`str`	`--`	Model used for generating signals.
`long_entries`	`float`	`--`	Long entry signals.
`long_exits`	`float`	`--`	Long exit signals.
`short_entries`	`float`	`--`	Short entry signals.
`short_exits`	`float`	`--`	Short exit signals.
`select_symbols`	`str`	`None`	Symbol name (e.g., `BTCUSDT` or `ETHUSDT`) or column index (e.g., `0` or `1`) to keep. If `None`, no filtering.
`metrics`	`str`	`sharpe_ratio`	Performance metrics to compute. Defaults to `sharpe_ratio`.
`size`	`float`	`50`	Size of each order. Defaults to `50`.
`size_type`	`str`	`valuepercent100`	Type of size. Defaults to `valuepercent100`.
`allow_partial`	`float`	`None`	Whether to allow partial fills. Defaults to `None`.
`fees`	`float`	`None`	Fees per order. Defaults to `None`.
`fixed_fees`	`float`	`None`	Fixed fees per order. Defaults to `None`.
`slippage`	`float`	`None`	Slippage per order. Defaults to `None`.
`min_size`	`float`	`None`	Minimum size of each order. Defaults to `None`.
`max_size`	`float`	`None`	Maximum size of each order. Defaults to `None`.
`size_granularity`	`float`	`None`	Granularity of size. Defaults to `None`.
`sl_stop`	`float`	`None`	Stop-loss level. Defaults to `None`.
`tsl_stop`	`float`	`None`	Trailing stop-loss level. Defaults to `None`.
`tp_stop`	`float`	`None`	Take-profit level. Defaults to `None`.
`accumulate`	`bool`	`None`	Whether to accumulate orders. Defaults to `None`.
`init_cash`	`float`	`None`	Initial cash. Defaults to `None`.
`cash_sharing`	`bool`	`True`	Whether to share cash between assets. Defaults to `True`.
`group_by`	`bool`	`True`	Whether to group by symbol. Defaults to `True`.
`call_seq`	`bool`	`auto`	Call sequence. Defaults to `auto`.
`fill_pos_info`	`bool`	`False`	Whether to fill position info. Defaults to `False`.
`log`	`bool`	`None`	Whether to log orders. Defaults to `None`.
`to_numpy`	`bool`	`False`	If `True`, returns a `np.ndarray`. Default is `False`, returning a `pd.DataFrame`.
`validate_metrics`	`bool`	`True`	Check if `metric` is valid in the registry. Defaults to `True`.
`validate_model`	`bool`	`True`	Check if model parameters are valid. Defaults to `True`.
`portfolio_kwargs`	`tp.Kwargs`	`--`	Additional arguments for portfolio simulation.

Returns:

Type	Description
`pd.DataFrame \| tp.Array`	DataFrame or array containing portfolio performance metrics.

`BaseSignal`

BaseSignal()

Abstract base class for signal generation.

Ancestors

abc.ABC

Descendants

systematica.api.signals.cross_spread.CrossSpread
systematica.api.signals.crossover.Crossover
systematica.api.signals.crossover.Crossover1d
systematica.api.signals.spread.Spread
systematica.api.signals.twin_spread.TwinSpread

Static methods

`run`

run(
    *arg,
    **kwargs,
)

Run the signal generation process. Parameters:

Name	Type	Default	Description
`arg`	`tuple`	`--`	Positional arguments.
`kwargs`	`tp.Kwargs`	`--`	Keyword arguments.

Overview

Analytics

Models

Reports

Signal Models

Signals

​BaseStatArb

​Ancestors

​Descendants

​Static methods

​is_valid

​run_report

​get_report_metrics

​run_analyzer

​run_model

​run_signals

​run_pipeline

​run_optuna_study

​Methods

​get_signals

​BaseReportMixin

​Ancestors

​Descendants

​Instance variables

​Methods

​get_annualized_return

​get_portfolio_metric

​get_model_output

​set_labels

​plot_annualized_return

​plot_model_output

​plot_portfolio_metric

​BaseReportCV

​Ancestors

​Descendants

​Instance variables

​Methods

​check

​price_reset_stacked_by_set

​model_reset_stacked_by_set

​get_annualized_return

​get_portfolio_metric

​BaseRollingReport

​Ancestors

​Descendants

​Instance variables

​Methods

​check

​get_portfolio_metric

​BaseSignal

​Ancestors

​Descendants

​Static methods

​run

`BaseStatArb`

Ancestors

Descendants

Static methods

`is_valid`

`run_report`

`get_report_metrics`

`run_analyzer`

`run_model`

`run_signals`

`run_pipeline`

`run_optuna_study`

Methods

`get_signals`

`BaseReportMixin`

Ancestors

Descendants

Instance variables

Methods

`get_annualized_return`

`get_portfolio_metric`

`get_model_output`

`set_labels`

`plot_annualized_return`

`plot_model_output`

`plot_portfolio_metric`

`BaseReportCV`

Ancestors

Descendants

Instance variables

Methods

`check`

`price_reset_stacked_by_set`

`model_reset_stacked_by_set`

`get_annualized_return`

`get_portfolio_metric`

`BaseRollingReport`

Ancestors

Descendants

Instance variables

Methods

`check`

`get_portfolio_metric`

`BaseSignal`

Ancestors

Descendants

Static methods

`run`