Closed Lopa10ko closed 1 month ago
Passed integration test: https://github.com/aimclub/FEDOT/blob/0bdece11af60d6e9abc84a894ddd66ea960b5611/test/integration/real_applications/test_examples.py#L86-L88
Predictions on the metric evaluation process of a ETSModel end up being NaN-containing: https://github.com/aimclub/FEDOT/blob/0bdece11af60d6e9abc84a894ddd66ea960b5611/fedot/core/operations/evaluation/operation_implementations/models/ts_implementations/statsmodels.py#L276-L283
Maybe with a multiplicative trend these lines in statsmodels are raising some kind of exception (e.g. zero-devision) with a small enough endog values.
You can add the following code in api_forecasting.py:
def run_ts_forecasting_example(dataset='australia', horizon: int = 30, timeout: float = None, visualization=False, validation_blocks=2, with_tuning=True): train_data, test_data, label = get_ts_data(dataset, horizon, validation_blocks=validation_blocks) # init model for the time series forecasting pipeline = Pipeline().load('<PATH_TO_PIPELINE>') model = Fedot(problem='ts_forecasting', task_params=Task(TaskTypesEnum.ts_forecasting, TsForecastingParams(forecast_length=horizon)).task_params, timeout=timeout, n_jobs=-1, metric='mae', with_tuning=with_tuning. initial_assumption=pipeline) ...
Here is one of a troubled pipelines: 0_pipeline_saved.zip
similar to #1279
Expected Behavior
Passed integration test: https://github.com/aimclub/FEDOT/blob/0bdece11af60d6e9abc84a894ddd66ea960b5611/test/integration/real_applications/test_examples.py#L86-L88
Current Behavior
Predictions on the metric evaluation process of a ETSModel end up being NaN-containing: https://github.com/aimclub/FEDOT/blob/0bdece11af60d6e9abc84a894ddd66ea960b5611/fedot/core/operations/evaluation/operation_implementations/models/ts_implementations/statsmodels.py#L276-L283
Possible Solution
Maybe with a multiplicative trend these lines in statsmodels are raising some kind of exception (e.g. zero-devision) with a small enough endog values.
Steps to Reproduce
You can add the following code in api_forecasting.py:
Here is one of a troubled pipelines: 0_pipeline_saved.zip