run_from_signals
run_from_signals(
data: pandas.core.frame.DataFrame | vectorbtpro.data.base.Data,
signals: systematica.signals.base.Signals,
*,
metrics: str | List[str] = None,
metrics_kwargs: Dict[str, Any] = None,
use_rolling: bool = False,
to_numpy: bool = False,
**portfolio_config,
) ‑> vectorbtpro.portfolio.base.Portfolio | collections.OrderedDict | pandas.core.frame.DataFrame | numpy.ndarray
| Name | Type | Default | Description |
|---|---|---|---|
data | vbt.Data | -- | Historical market data. |
signals | Signals | -- | Generated trading signals. |
metrics | str | None | Metrics to evaluate the portfolio, by default None. |
use_rolling | bool | False | Use rolling metrics. See metrics config. Defauts to False. |
metrics_kwargs | tp.Kwargs | None | Additional arguments for metric config. Parameters such as window of minp for rolling metrics should be specificed. Defaults to None. |
validate_metrics | bool | True | Check if metric is valid in the config. Might slow-down code if set to True. Defaults to True. |
to_numpy | bool | False | If True, returns a numpy ndarray. Defaults to False, which means returns a pandas SeriesFrame. |
portfolio_config | tp.Kwargs | -- | Additional arguments for portfolio simulation. |
| Type | Description |
|---|---|
vbt.PF | OrderedDict | pd.DataFrame | tp.Array | Simulated portfolio or requested metrics. |
run_from_signals_nb
run_from_signals_nb(
open: numpy.ndarray,
high: numpy.ndarray,
low: numpy.ndarray,
close: numpy.ndarray,
signals: systematica.signals.base.Signals,
size: int = 50,
sl_stop: float = nan,
tsl_stop: float = nan,
tp_stop: float = nan,
) ‑> vectorbtpro.portfolio.enums.SimulationOutput
| Name | Type | Default | Description |
|---|---|---|---|
close | Array1d | -- | Array of closing prices. |
signals | Signals | -- | Generated trading signals. |
size | int | 50 | Size of each order, default is 50. |
sl_stop | float | np.nan | Stop-loss level, default is np.nan (no stop-loss). |
tsl_stop | float | np.nan | Trailing stop-loss level, default is np.nan (no trailing stop-loss). |
tp_stop | float | np.nan | Take-profit level, default is np.nan (no take-profit). |
| Type | Description |
|---|---|
SimulationOutput | Simulated portfolio. |
<Note> | |
The output of this function is an instance of the type SimulationOutput, | |
which can be used to construct a new Portfolio instance for analysis: | |
</Note> |
>>> pf = vbt.Portfolio(
... data.symbol_wrapper.regroup(group_by=True),
... sim_out,
... open=data.open,
... high=data.high,
... low=data.low,
... close=data.close,
... cash_sharing=True,
... init_cash=100
... )
>>> pf.total_return
# 0.19
run_from_optimize_func
run_from_optimize_func(
data: vectorbtpro.data.base.Data,
returns: numpy.ndarray,
signals: systematica.signals.base.Signals,
optimize_func: Callable,
*,
config: Dict[str, Any] = None,
) ‑> vectorbtpro.portfolio.pfopt.base.PortfolioOptimizer
| Name | Type | Default | Description |
|---|---|---|---|
data | vbt.Data | -- | Historical market data. |
returns | tp.Array | -- | Array of returns to be used for optimization. |
signals | Signals | -- | Generated trading signals. |
optimize_func | tp.Callable | -- | Custom optimization function that takes the returns and signals as input. This function should return a dictionary of optimized parameters or metrics. |
config | tp.Kwargs | None | Dictionary with optimization parameters. Defaults to None. |
| Type | Description |
|---|---|
vbt.PortfolioOptimizer | Configured portfolio optimizer instance ready for backtesting. |
>>> strategy = ...
>>> portfolio_optimizer = strategy.optimizer(
... ...,
... config={'obj': 'Sharpe', 'every': 'M'}
... )
>>> portfolio = portfolio_optimizer.simulate()