Since ConstantTemplate (the sklearn estimator for ConstantTimeseriesRegressor) only uses the input data X to determine the shape of the predictions, it isn't necessary for X to have specifically numeric dtypes without any nan or inf values, so it shouldn't check for this when calling check_X_y/check_array.
Since
ConstantTemplate(the sklearn estimator forConstantTimeseriesRegressor) only uses the input data X to determine the shape of the predictions, it isn't necessary for X to have specifically numeric dtypes without any nan or inf values, so it shouldn't check for this when callingcheck_X_y/check_array.