class ThresholdAD ( _NonTrainableUnivariateDetector ): """Detector that detects anomaly based on user-given threshold. detect_func ( s, ** detect_func_params ) _fitted_detect_func_params = ) else : return self. """ def _init_ ( self, detect_func : Callable, detect_func_params : Optional ] = None, fit_func : Optional = None, fit_func_params : Optional ] = None, ) -> None : self. fit_func_params: dict, optional Parameters of `fit_func`. The first input argument must be a pandas Series, optional input argument may be accepted through parameter `fit_func_params`, and the output must be a dict that can be used by `detect_func` as parameters. fit_func: function, optional A function training parameters of `detect_func` with univariate time series. detect_func_params: dict, optional Parameters of `detect_func`. The first input argument must be a pandas Series, optional input argument may be accepted through parameter `detect_func_params` and the output of `fit_func`, and the output must be a binary pandas Series with the same index as input. Parameters - detect_func: function A function detecting anomalies from univariate time series. Class CustomizedDetector1D ( _TrainableUnivariateDetector ): """Univariate detector derived from a user-given function and parameters.
0 kommentar(er)
