Open Lopa10ko opened 4 weeks ago
The integration test fails quite often, passing NaN-containing inputs between nodes.
In examples/simple/time_series_forecasting/api_forecasting.py::run_ts_forecasting_example pass initial_assumption to a Fedot instance like so:
examples/simple/time_series_forecasting/api_forecasting.py::run_ts_forecasting_example
initial_assumption
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 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().load('<path_to_troubled_pipeline_dir>')) ...
possibly related to issues with ETSModel #1285
[!NOTE] One is welcomed to provide new troubled pipelines for this issue (If managed to save Pipeline obj before facing some kind of error).
Pipeline
Current Behavior
The integration test fails quite often, passing NaN-containing inputs between nodes.
Troubled pipelines
Steps to reproduce
In
examples/simple/time_series_forecasting/api_forecasting.py::run_ts_forecasting_example
passinitial_assumption
to a Fedot instance like so:Context
possibly related to issues with ETSModel #1285