ResidualAutocorrelation
Autocorrelation of the residuals against the number of lags.
A good forecast leaves residuals that look like noise: each error carries no information about the next. Autocorrelation measures exactly that, so a bar above the confidence band means the model left structure behind — neighbouring periods are wrong in the same direction, which a tuned model would have learned. Lags rising and falling smoothly usually mean a missed trend or seasonality, while a single spike means a specific lag that was never modelled.
The residuals are the backtest's, every forecast step in date order: the windows of the origins tile the end of the series, so they follow one another.
Parameters
- max_lag : integer, default=
20 - Number of lags to plot the autocorrelation for.
Methods
compute_forecasts(self, forecasts: Dict[str, Any]) -> List[DashAI.back.core.artifacts.Artifact]
ResidualAutocorrelationBuild the residual autocorrelation bar chart.
Returns
- List[Artifact]
- A single bar figure with a confidence band around zero.
compute(self, y_true, y_pred, class_names: Optional[List[str]] = None) -> List[DashAI.back.core.artifacts.Artifact]
ForecastingReportA forecasting report has no rows to draw: see compute_forecasts.
get_credential(self, name: str)
ConfigObjectResolve a registered credential component by name.
Parameters
- name : str
- Credential component class name (e.g. "HuggingFaceCredential").
Returns
- BaseCredential
- An instance of the requested credential component.
get_metadata(cls) -> Dict[str, Any]
BaseReportGet metadata values for the current report.
Returns
- Dict[str, Any]
- UI metadata, including whether the report needs a model that outputs class probabilities.
get_schema(cls) -> dict
ConfigObjectGenerates the component related Json Schema.
Returns
- dict
- Dictionary representing the Json Schema of the component.
validate_and_transform(self, raw_data: dict) -> dict
ConfigObjectIt takes the data given by the user to initialize the model and returns it with all the objects that the model needs to work.
Parameters
- raw_data : dict
- A dictionary with the data provided by the user to initialize the model.
Returns
- dict
- A validated dictionary with the necessary objects.