Base

systematica.signals.base

Variables

• SIGNAL_MAPPER: Mapping of signal keys to human-readable names.

• VALID_SIGNALS: Get valid signal keys to human-readable names.

no_signals_found_nb

no_signals_found_nb(
    model_output: numpy.ndarray,
) ‑> systematica.signals.base.Signals

Create a Signals object with no signals found.

Parameters:

Name	Type	Default	Description
model_output	tp.Array	--	A 2d array representing model predictions for two assets.

Returns:

Type	Description
Signals	A Signals object with all entries and exits set to False.

Thresholds

Thresholds(
    long_entries: float,
    long_exits: float,
    short_entries: float,
    short_exits: float,
)

Named tuple to represent signal thresholds.

Ancestors

• builtins.tuple

Instance variables

• long_entries: float: Long entry signals.

• long_exits: float: Long exit signals.

• short_entries: float: Short entry signals.

• short_exits: float: Short exit signals.

Signals

Signals(
    long_entries: numpy.ndarray | pandas.core.series.Series | pandas.core.frame.DataFrame = nan,
    long_exits: numpy.ndarray | pandas.core.series.Series | pandas.core.frame.DataFrame = nan,
    short_entries: numpy.ndarray | pandas.core.series.Series | pandas.core.frame.DataFrame = nan,
    short_exits: numpy.ndarray | pandas.core.series.Series | pandas.core.frame.DataFrame = nan,
)

Named tuple to represent trading signals.

Ancestors

• builtins.tuple

Instance variables

• long_entries: numpy.ndarray | pandas.core.series.Series | pandas.core.frame.DataFrame: Array or DataFrame indicating long entry signals.

• long_exits: numpy.ndarray | pandas.core.series.Series | pandas.core.frame.DataFrame: Array or DataFrame indicating long exit signals.

• short_entries: numpy.ndarray | pandas.core.series.Series | pandas.core.frame.DataFrame: Array or DataFrame indicating short entry signals.

• short_exits: numpy.ndarray | pandas.core.series.Series | pandas.core.frame.DataFrame: Array or DataFrame indicating short exit signals.

• ndim: int: Get the number of dimensions of the signals.

• has_latest_signal: Signals: Check if the latest row in any of the entry or exit signals has a True value.

Methods

get_latest_signals

get_latest_signals(
    self,
    data: vectorbtpro.data.base.Data,
) ‑> Dict[str, str]

Get the names of the signals where the latest row contains a True value.

Initially checks if latest row in any of the entry or exit signals has any True values. Then maps signal names and symbols.

Convert signals to pandas.DataFrame object automatically.

Returns:

Type	Description
Dict[str, str]	Dict of symbols and mapped names if latest row has a True value. Empty dict otherwise.

to_frame

to_frame(
    self,
    data: pandas.core.frame.DataFrame | vectorbtpro.data.base.Data,
    clean: bool = False,
) ‑> systematica.signals.base.Signals

Convert signals to pandas DataFrame objects.

Parameters:

Name	Type	Default	Description
data	pd.DataFrame	--	or vbt.Data Market data used to structure the output signals.
clean	bool	False	Whether to clean the signals before converting.

Raises:

Type	Description
ValueError	If signal cleaning fails due to Numba-related errors.

Returns:

Type	Description
Signals	Converted signals wrapped as DataFrame objects.

asframe

asframe(
    self,
    data: pandas.core.frame.DataFrame | vectorbtpro.data.base.Data,
    clean: bool = False,
    level_names: List[str] = None,
) ‑> pandas.core.frame.DataFrame

Convert Signals object to a pandas DataFrame.

Parameters:

Name	Type	Default	Description
data	pd.DataFrame	--	or vbt.Data Market data used to structure the output signals.
clean	bool	False	Whether to clean the signals before converting.
level_names	tp.List[str, str], default None“	--	Names for the levels in the resulting hierarchical index. if None defaults to ['signals', 'symbol']. Defaults to None

Returns:

Type	Description
pd.DataFrame	pandas DataFrame objects.

clean_signals

clean_signals(
    self,
) ‑> systematica.signals.base.Signals

Clean raw signals using pre-defined cleaning functions.

Returns:

Type	Description
Signals	Cleaned signals with noise reduction.

fshift

fshift(
    self,
    n: int = 1,
) ‑> systematica.signals.base.Signals

Shift forward by n positions.

Numba equivalent to pd.Series(arr).shift(n).

Parameters:

Name	Type	Default	Description
n	int, optional	--	Number of steps. Defaults to 1.

Returns:

Type	Description
Signals	Cleaned signals with noise reduction.

plot

plot(
    self,
    df_or_data: pandas.core.series.Series | pandas.core.frame.DataFrame | vectorbtpro.data.base.Data,
    symbol: str | List[str],
    clean: bool = False,
    start: str | pandas._libs.tslibs.timestamps.Timestamp = None,
    end: str | pandas._libs.tslibs.timestamps.Timestamp = None,
    fig: vectorbtpro.utils.figure.FigureWidget = None,
    **plot_kwargs,
) ‑> vectorbtpro.utils.figure.FigureWidget

Plot trading signals over the provided market data.

Parameters:

Name	Type	Default	Description
df_or_data	tp.SeriesFrame	--	or vbt.Data Market data to use for plotting.
symbol	str	--	or list of str Symbol(s) to plot.
clean	bool	False	Whether to clean signals before plotting.
start	str	None	The start date. Defaults to None.
end	str	None	The end date. Defaults to None.
fig	vbt.FigureWidget	None	Figure widget to update with new plots.
plot_kwargs	tp.Kwargs	--	Additional keyword arguments for the plot function.

Raises:

Type	Description
ValueError	If signal cleaning fails due to Numba-related errors.

Returns:

Type	Description
vbt.FigureWidget	A figure widget containing the plotted signals.

select_symbols

select_symbols(
    self,
    symbols: str | int | list[str | int],
) ‑> systematica.signals.base.Signals

Select specified symbol(s) unchanged and set all other columns to False.

Parameters:

Name	Type	Default	Description
symbols	str, int, or list[str | int]	--	The symbol name(s) (e.g., BTCUSDT or ETHUSDT) or column index(es) (e.g., 0 or 1) to keep unchanged. All other columns will be set to False.

Raises:

Type	Description
ValueError	If any symbol name is invalid or any index is out of bounds.

Returns:

Type	Description
Signals	New Signals instance with only the specified symbol(s) retained, others set to False.