Trouble in `api.main.Fedot.fit()` with features of `np.ndarray` type

[aPovidlo]

I tried to make experiment in Fedot for the task of time series forecasting with Sea level dataset. There is ValueError in fit() if you want use np.ndarray array as features.

Code example:

from fedot.api.main import Fedot
from fedot.core.repository.tasks import TsForecastingParams

df = pd.read_csv('ts_sea_level.csv')
timeseries_df['Date'] = pd.to_datetime(timeseries_df['Date'])
train_array = np.array(df['Level'])

auto_model = Fedot(
    problem='ts_forecasting',
    task_params=TsForecastingParams(forecast_length=250),
    timeout=5
)

pipeline = auto_model.fit(features=train_array)

Error message: ValueError: Please specify the "features" as path to as path to csv file/Numpy array/Pandas DataFrame/FEDOT InputData/dict for multimodal data, Exception: only integers, slices (:), ellipsis (...), numpy.newaxis (None) and integer or boolean arrays are valid indices