I really struggle to run sktime.TBATS algo on a timeseries I have in a Py dataframe
df_to_process_tbats = engineered_df_to_process[
engineered_df_to_process.Pack == product].reset_index(
drop=True)
forecaster_tbats = TBATS()
result = pd.DataFrame(df_to_process_tbats ["Qty"])
forecaster_tbats.fit(result)
The dataframe looks like
Date Pack Qty
0 2019-12-15 name 0
1 2019-12-16 name 0
2 2019-12-17 name 0
3 2019-12-18 name 0
4 2019-12-19 name 0
.. ... ... ...
755 2022-01-08 name 0
Error: TypeError: y must be in an sktime compatible format, of scitype Series, Panel or Hierarchical, for instance a pandas.DataFrame with sktime compatible time indices, or with MultiIndex and last(-1) level an sktime compatible time index. See the forecasting tutorial examples/01_forecasting.ipynb, or the data format tutorial examples/AA_datatypes_and_datasets.ipynb,If you think y is already in an sktime supported input format, run sktime.datatypes.check_raise(y, mtype) to diagnose the error, where mtype is the string of the type specification you want for y. Possible mtype specification strings are as follows. "For Hierarchical scitype: ['pd_multiindex_hier'].
I tried already using to_convert(), using apply(np.array) - without any success
Can anyone please help me ?
